Advances in Swarm Intelligence

The method of a physical swarm modeling, based on application of semi-Markov process theory to description of swarm unit cyclograms is worked out. It is shown, that ordinary semi-Markov processes with structural states are abstract analogue of units cyclograms. The method of gathering of ordinary semi-Markov processes into M-parallel process and further transformation of it into complex semi-Markov process with functional states is proposed. It is shown that functional states may be obtained as Cartesian product of sets of ordinary semi-Markov processes states. Operation of semi-Markov matrices Cartesian product is introduced. Method of evaluation of elements of complex semi-Markov matrix is worked out.

Consider the interaction of populations, in which there are exactly two species, one of which the predators eat the preys thereby affecting each other. In the study of this interaction Lotka-Volterra models have been used. Other non-classical methodologies as Petri nets and first order logic have been employed too. This paper proposes a formal modeling and verification analysis methodology, which consists in representing the interaction behavior by means of a modal logic formula. Then, using the concept of logic implication, and transforming this logical implication relation into a set of clauses, a modal resolution qualitative method for verification (satisfiability) as well as performance issues, for some queries is applied.

The article describes the approach to evaluation of the results of “competitions” arising from the access of intellectual agents to resources in distributed swarm systems. A mathematical model of “competitions” based on Petri-Markov nets was developed. Expressions for calculation of time and probabilistic characteristics of “competitions” are defined. Methods of simulation modelling of the process of “competition” and experimental determination of time parameters are proposed. The obtained results can be used for planning information processes of swarm distributed system.

The article presents a multi-species object-based model of a marine plankton community. The model was constructed using the synthesis of Lagrangian and Eulerian descriptions: we described the living components of an ecosystem by the individual-based approach and the non-living components (hydrochemical fields) – in a traditional way as concentrations in the nodes of a regular computational grid. A set of interacting objects simulated a plankton community. Each object modeled behavior of a group of identical plankters characterized by species, age, stage of development, biomass, abundance, and rates of physiological processes. Bioenergetic interaction between the objects and the environment was a source of population dynamics. We studied self-organization of plankton spatial distribution with no significant hydrophysical influences. Lloyd’s index of mean crowding, spectral and wavelet analyses were used to investigate patterns of simulated spatial variability. We compared spectra of simulated plankton patchiness with those estimated according to observation data collected by the Video Plankton Recorder (VPR).

During the past few decades, many Evolutionary Algorithms (EAs) together with the Constraint Handling Techniques (CHTs) have been developed to solve the constrained optimization problems (COPs). To obtain competitive performance, an effective CHT needs to be in conjunction with an efficient EA. In the previous paper, how the Differential Evolution influence the relationship between problems and penalty parameters was studied. In this paper, further study on how much can be improved through good evolutionary algorithms, or whether a good enough EA can make up the shortcoming of a simple CHT, and which factors are related will be the focus. Four different EAs are taken as an example, and Deb’s feasibility-based rule is taken as the CHT for its simplicity. Experimental results show that better performance in EAs is not necessarily the reason for the improved performance of constrained optimization evolutionary algorithms (COEAs), and the key point is to find the shortcoming of the CHT and improve the shortcoming in the corresponding revision of EA.

Social intelligence is an emerging property of a system composed of agents that consists of the ability of this system to conceive, design, implement and execute strategies to solve problems and thus achieve a collective state of the system that is concurrently satisfactory for all and each one of the agents that compose it. In order to make decisions when dealing with complex problems related to social systems and take advantage of social intelligence, cooperative games theory constitutes the standard theoretical framework. In the present work, an ontological framework for cooperative games modeling and simulation is presented.

Broadcasting is a popular and important way to information dissemination in vehicular ad-hoc networks (VANETs). But the weakness of broadcasting which is called broadcasting storm also reduces the performance of VANETs. In this paper, an adaptive game model for broadcasting in VANETs is proposed firstly. Then we optimize the proposed model adapting to the distance between two neighbor vehicles and use this optimizing game model to realize the probabilistic broadcasting. The simulation results show that the proposed adaptive game model can release the broadcasting storm, and make the performance better.

Population-based optimization algorithms adopt a regular network as topologies with one set of potential solutions, which may encounter the problem of premature convergence. In order to improve the performance of optimization techniques, this paper proposes a soft island model topology. The initial population is virtually separated into several subpopulations, and the connection between individuals from subpopulations is probabilistic. The workability of the proposed model was demonstrated through its implementation to the Particle Swarm Optimization and Differential Evolution algorithms and their modifications. Experiments were conducted on benchmark functions taken from the CEC’2017 competition. The best parameters for the new topology adaptation mechanism were found. Results verify the effectiveness of the population-based algorithms with the proposed model when compared with the same algorithms without the model. It was established that by applying this topology adaptation mechanism, the population-based algorithms are able to balance their exploitation and exploration abilities during the search process.

Swarm intelligence is well-known to enjoy fast convergence towards optimum. Recently, the Swarm Intelligence Based (SIB) method was proposed to deal with discrete optimization problems in mathematics and statistics. Whether it was the traditional framework or the augmented version, the initialization of the particles were always done randomly. In this work, we introduced a smart initialization procedure to improve the computational efficiency of the SIB method. We demonstrated the use of the SIB method, initialized by both the uniform pool (standard procedure) and the MCMC pool (smart initialization), on the search of optimal minimum energy designs, which were a new class of designs for computer experiments that considered uneven or functional gradients on the search domain. We compared two initialization approaches and showed that the SIB method with smart initialization could save much experimental resources and obtain better optimal solutions within equivalent number of iterations or time.

The article considers the possibility of applying an optimization algorithm based on the behavior of an ant colony to the problem of forming a multiversion fault-tolerant software package. The necessary modifications of the basic algorithm and a model of graph construction for the implementation of the ant algorithm for the chosen problem are proposed. The optimization takes into account such features as cost, reliability and evaluation of the successful implementation of each version with the specified characteristics. A certain combination of versions in each module affects the characteristics of the module, and each characteristic of the module affects the characteristics of the system, so it is important to choose the optimal structure for each module to ensure the required characteristics of the system as a whole. The program system that implements the proposed algorithm is considered. The simulation results obtained with the help of the proposed software tool are considered. The results confirm the applicability of the ant algorithms to the problem of forming a multiversion software package, and they show their effectiveness.

Proteins complexes accomplish biological functions such as transcription of DNA and translation of mRNA. Detecting protein complexes correctly and efficiently is becoming a challenging task. This paper presents a novel algorithm, core-attachment based on ant colony optimization (CA-ACO), which detects complexes in three stages. Firstly, initialize the similarity matrix. Secondly, complexes are predicted by clustering in the dynamic PPI networks. In the step, the clustering coefficient of every node is also computed. A node whose clustering coefficient is greater than the threshold is added to the core protein set. Then we mark every neighbor node of core proteins with unique core label during picking and dropping. Thirdly, filtering processes are carried out to obtain the final complex set. Experimental results show that CA-ACO algorithm had great superiority in precision, recall and f-measure compared with the state-of-the-art methods such as ClusterONE, DPClus, MCODE and so on.

Information-Centric Networking (ICN) aims to distribute and retrieve the content by name. In this paper, we review and approve the feasible Ant Colony Optimization (ACO)-inspired ICN routing solutions, i.e., applying ACO to solve ICN routing problem. At first, some significant challenges with respect to ICN routing are analyzed, such as explosive increasing of Forwarding Information Base (FIB), retrieval of closest content copy, uniform distribution of content and mobility support. Then, the solutions inspired by biology feature and behavior is reviewed. In addition, a general design thought of ACO-inspired solution is presented. Finally, the feasibility of ACO-inspired ICN routing solution is evaluated.

Particle swarm optimization (PSO) is a widely-adopted optimization algorithm which is based on particles’ fitness evaluations and their swarm intelligence. However, it is difficult to obtain the exact fitness evaluation value and is only able to compare particles in a pairwise manner in many real applications such as dose selection, tournament, crowdsourcing and recommendation. Such ordinal preferences from pairwise comparisons instead of exact fitness evaluations lead the traditional PSO to fail. This paper proposes a particle swarm optimization based on pairwise comparisons. Experiments show that the proposed method enables the traditional PSO to work well by using only ordinal preferences from pairwise comparisons.

Large biological molecules such as proteins associating to form multi-component complexes are attracting more and more research interests. The association reaction of the large biological molecules are closely related with associate rate and reaction intermediate states which are key to elucidate the reaction pathways as their kinetic and structural characteristics which shed lights on the reaction process and energy landscape. This paper proposes a novel method modelling the chemical reactions by using neural networks with the help of the predefined chemical reaction model, and then follows by using the typical particle swarm optimization algorithm to minimize the error between the output of neural networks and experimental data. Experiments are conducted to demonstrate the proposed method as a promising way dealing with this difficult task.

The ascending of quantity of CO₂ emissions is the main factor contributing the global warming which results in extremely abnormal weather and causes disaster damages. Due to intensive CO₂ pollutants produced by classic energy sources such as fossil fuels, practitioners and researchers pay increasing attentions on the renewable energy production such as wind power. Optimal wind turbine placement problem is to find the optimal number and placement location of wind turbines in a wind farm against the wake effect. The efficiency of wind power production does not necessarily grows with an increasing number of installed wind turbines. This paper presents a hyper-heuristic framework combining several lower-level heuristics with an artificial bee colony algorithm and a simulated annealing technique to construct an optimal wind turbine placement considering wake effect influence. Finally, we compare our approach with existing works in the literature. The experimental results show that our approach produces the wind power with a lower cost of energy.

The knapsack problem is one of the well known NP-Hard optimization problems. Because of its appearance as a sub-problem in many real world problems, it attracts the attention of many researchers on swarm intelligence and evolutionary computation community. In this paper, a new binary artificial bee colony called NB-ABC is proposed to solve the 0-1 knapsack problem. Instead of the search operators of the original ABC, new binary search operators are designed for the different phases of the ABC algorithm, namely the employed, the onlooker and the scout bee phases. Moreover, a novel hybrid repair operator called (HRO) is proposed to repair and improve the infeasible solutions. To assess the performance of the proposed algorithm, NB-ABC is compared with two other existing algorithms, namely GB-ABC and BABC-DE, for solving the 0-1 knapsack problem. Based on a set of 15 0-1 high dimensional knapsack problems classified in three categories. the experimental results in view of many criteria show the efficiency and the robustness of the proposed NB-ABC.

This paper proposes a new hybrid metaheuristic algorithm called teaching-learning artificial bee colony (TLABC) for function optimization. TLABC combines the exploitation of teaching learning based optimization (TLBO) with the exploration of artificial bee colony (ABC) effectively, by employing three hybrid search phases, namely teaching-based employed bee phase, learning-based onlooker bee phase, and generalized oppositional scout bee phase. The performance of TLABC is evaluated on 30 complex benchmark functions from CEC2014, and experimental results show that TLABC exhibits better results compared with previous TLBO and ABC algorithms.

The Artificial Bee Colony (ABC) algorithm is a new kind of intelligent optimization algorithm. Due to the advantages of few control parameters, computed conveniently and carried out easily, ABC algorithm has been applied to solve many practical optimization problems. But the algorithm also has some disadvantages, such as low precision, slow convergence, poor local search ability. In view of this, this article proposed an improved method based on adaptive neighborhood search and the improved algorithm is applied to the task assignment in Heterogeneous Multicore Architectures. In the experiments, although the numbers of iteration decreases from 1000 to 900, the quality of solution has been improved obviously, and the times of expenditure is reduced. Therefore, the improved ABC algorithm is better than the original ABC algorithm in optimization capability and search speed, which can improve the efficiency of heterogeneous multicore architectures.

Vehicle routing problem (VRP) is a classic combinatorial optimization problem and has many applications in industry. Solutions of VRP have significant impact on logistic cost. In most VRP models, the shortest distance is used as the objective function, which is not the case in many real-word applications. To this end, a VRP model with fixed and fuel cost is proposed. Genetic algorithm (GA) is a common approach for solving VRP. Due to the premature issue in GA, a tabu bee colony-based GA is employed to solve this model. The improved GA has three characteristics that differentiate from other similar algorithms: (1) The maximum preserved crossover is proposed, to protect the outstanding sub-path and avoid the phenomenon that two identical individuals cannot create new individuals; (2) The bee evolution mechanism is introduced. The optimal solution is selected as the queen-bee and a number of outstanding individuals are as the drones. The utilization of excellent individual characteristics is improved through the crossover of queen-bee and drones; (3) The tabu search is applied to optimize the queen-bee in each generation of bees and improve the quality of excellent individuals. Thus the population quality is improved. Extensive experiments were conducted. The experimental results show the rationality of the model and the validity of the proposed algorithm.

This study aims to generate the optimal trajectories for the biped walking up sloping surfaces after ensuring the minimum energy consumption by using genetic algorithm (GA) and motion/force control scheme. During optimization, the step length, the maximum height of swing foot and walking speed were optimized with the seven-link biped model. The impactless bipedal walking was investigated for walking on the ground level and slopes with different gradients, respectively. The results showed that the biped consumed more energy when the optimal walking speed increased for walking on the same slopes. There were no great differences in optimal step length when the biped changed the walking speed. The results showed that the proposed approach is able to generate optimal gaits for the biped simply by changing boundary conditions with GA.

Solving a multi-objective optimization problem results in a Pareto front approximation, and it differs from single-objective optimization, requiring specific search strategies. These strategies, mostly fitness assignment, are designed to find a set of non-dominated solutions, but different approaches use various schemes to achieve this goal. In many cases, cooperative algorithms such as island model-based algorithms outperform each particular algorithm included in this cooperation. However, we should note that there are some control parameters of the islands’ interaction and, in this paper, we investigate how they affect the performance of the cooperative algorithm. We consider the influence of a migration set size and its interval, the number of islands and two types of cooperation: homogeneous or heterogeneous. In this study, we use the real-valued evolutionary algorithms SPEA2, NSGA-II, and PICEA-g as islands in the cooperation. The performance of the presented algorithms is compared with the performance of other approaches on a set of benchmark multi-objective optimization problems.

Feature selection is a key step in classification task to prune out redundant or irrelevant information and improve the pattern recognition performance, but it is a challenging and complex combinatorial problem, especially in high dimensional feature selection. This paper proposes a self-adaptive strategy based differential evolution feature selection, abbreviated as SADEFS, in which the self-adaptive elimination and reproduction strategies are used to introduce superior features by considering their contributions in classification under historical records and to replace the poor performance features. The processes of the elimination and reproduction are self-adapted by leaning from their experiences to reduce search space and improve classification accuracy rate. Twelve high dimensional cancer micro-array benchmark datasets are introduced to verify the efficiency of SADEFS algorithm. The experiments indicate that SADEFS can achieve higher classification performance in comparison to the original DEFS algorithm.

Differential Evolution (DE) has been regarded as one of the excellent optimization algorithm in the science, computing and engineering field since its introduction by Storm and Price in 1995. Robustness, simplicity and easiness to implement are the key factors for DE’s success in optimization of engineering problems. However, DE experiences convergence and stagnation problems. This paper focuses on DE convergence speed improvement based on introduction of newly developed mutation schemes strategies with reference to DE/rand/1 on account and tuning of control parameters. Simulations are conducted using benchmark functions such as Rastrigin, Ackley and Sphere, Griewank and Schwefel function. The results are tabled in order to compare the improved DE with the traditional DE.

Translation control of an immersed tunnel element under the water current flow is a typical optimization problem, which always emphasizes on short duration and high translation security. Various optimization approaches have been proposed to address this issue in previous works, but most of them take only one objective into consideration. Thus, it is solved as a single objective optimization problem. However, the translation control of the immersed tunnel element usually involves two or more conflicting objectives in actual situation. It’s necessary to convert the translation control problem into a multi-objective optimization problem to obtain effective solutions. Therefore, a recently proposed multi-objective differential evolution algorithm is employed to solve the problem in the present work. The translation model of the immersed tunnel element is introduced with three sub-objectives. Results indicate that a multi-objective differential evolution algorithm can provide a set of non-dominated solutions for assisting decision makers to complete the translation of the immersed tunnel element according to different targets and changing environment.

Computing hierarchical routing networks in polygonal maps is significant to realize the efficient coordination of agents, robots and systems in general; and the fact of considering obstacles in the map, makes the computation of efficient networks a relevant need for cluttered environments. In this paper, we present an approach to compute the minimal-length hierarchical topologies in polygonal maps by Differential Evolution and Route Bundling Concepts. Our computational experiments in scenarios considering convex and non-convex configuration of polygonal maps show the feasibility of the proposed approach.

We propose an acceleration method for the fireworks algorithms which uses a convergence point for the population estimated from moving vectors between parent individuals and their sparks. To improve the accuracy of the estimated convergence point, we propose a new type of firework, the synthetic firework, to obtain the correct of the local/global optimum in its local area’s fitness landscape. The synthetic firework is calculated by the weighting moving vectors between a firework and each of its sparks. Then, they are used to estimate a convergence point which may replace the worst firework individual in the next generation. We design a controlled experiment for evaluating the proposed strategy and apply it to 20 CEC2013 benchmark functions of 2-dimensions (2-D), 10-D and 30-D with 30 trial runs each. The experimental results and the Wilcoxon signed-rank test confirm that the proposed method can significantly improve the performance of the canonical firework algorithm.

Grouping the sensor nodes into clusters is an approach to save energy in wireless sensor networks (WSNs). We proposed a new solution to improve the performance of clustering based on a novel swarm intelligence algorithm. Firstly, the objective function for clustering optimization is defined. Secondly, discrete fireworks algorithm for clustering (DFWA-C) in WSNs is designed to calculate the optimal number of clusters and to find the cluster-heads. At last, simulation is conducted using the DFWA-C and relevant algorithms respectively. Results show that the proposed algorithm could obtain the number of clusters which is close to the theoretical optimal value, and can effectively reduce energy consumption to prolong the lifetime of WSNs.

The p-median problem represents a widely applicable problem in different fields such as operational research and supply chain management. Numerous versions of the p-median problem are defined in literature and it has been shown that it belongs to the class of NP-hard problems. In this paper a recent swarm intelligence algorithm, the bare bones fireworks algorithm, which is the latest version of the fireworks algorithm is proposed for solving capacitated p-median problem. The proposed method is tested on benchmark datasets with different values for p. Performance of the proposed method was compared to other methods from literature and it exhibited competitive results with possibility for further improvements.

This paper proposes an improved bacterial forging optimization with differential tumble, perturbation, and cruising mechanisms, abbreviated as DPCBFO. In DPCBFO, the differential information between the population and the optimal individual is used to guide the tumble direction of the bacteria. The strategy of perturbation is employed to enhance the global search ability of the bacteria. While a new cruising mechanism is proposed in this study to improve the possibility of searching for the optimal by comparing the current position with the others obtained in the next chemotaxis steps. In addition, to reduce the computation complexity, the vectorized parallel evaluation is applied in the chemotaxis process. The performance of the proposed DPCBFO is evaluated on eight well-known benchmark functions. And the simulation results illustrate that the proposed DPCBFO achieves the superior performance on all functions.

Path planning is a very important problem in robotics, especially in the development of Automatic Guided Vehicles (AGVs). These problems are usually formulated as search problems, so many search algorithms with a high level of intelligence are evaluated to solve them. We propose a navigation algorithm based on bacterial swarming from a simplified model of bacterium that promises simple designs both at the system level and at the agent level. The most important feature of the algorithm is the inclusion of bacterial Quorum Sensing (QS), which reduces the convergence time, which is the major disadvantage of the scheme. The results in both simulation and real prototypes show not only stability but higher performance in convergence speed, showing that the strategy is feasible and valid for decentralized autonomous navigation.

The increasing scale and complex of software makes it difficult to ensure the correctness and consistency of the software, therefore, formal methods emerge and are gradually recognized by industry. Event-B and B method are two formal system languages based on set theory and predicate logic. By comparing the advantages and disadvantages of the Event-B and B method, combining with the case and rewriting requirements from the aspects of environment, function and properties, we use the Event-B to establish the abstract model of immune system and refine it step by step according to the refinement strategy until validating the model. The immune system is a typical large and high-complexity model involving many cytokines and immune responses. Taking immune system model as an example, this paper discusses how to apply the Event-B mothed to this systems from the perspective of the above functions.

This paper describes a large-scale data clustering algorithm which is a combination of Balanced Iterative Reducing and Clustering using Hierarchies Algorithm (BIRCH) and Artificial Immune Network Clustering Algorithm (aiNet). Compared with traditional clustering algorithms, aiNet can better adapt to non-convex datasets and does not require a given number of clusters. But it is not suitable for handling large-scale datasets for it needs a long time to evolve. Besides, the aiNet model is very sensitive to noise, which greatly restricts its application. Contrary to aiNet, BIRCH can better process large-scale datasets but cannot deal with non-convex datasets like traditional clustering algorithms, and requires the cluster number. By combining these two methods, a new large-scale data clustering algorithm is obtained which inherits the advantages and overcomes the disadvantages of BIRCH and aiNet simultaneously.

A novel Hydrologic cycle Optimization (HCO) is proposed by simulating the natural phenomena of the hydrologic cycle on the earth. Three operators are employed in the algorithm: flow, infiltration, evaporation and precipitation. Flow step simulates the water flowing to lower areas and makes the population converge to better areas. Infiltration step executes neighborhood search. Evaporation and precipitation step could keep diversity and escape from local optima. The proposed algorithm is verified on ten benchmark functions and applied to a real-world problem named Nurse Scheduling Problem (NSP) with several comparison algorithms. Experiment results show that HCO performs better on most benchmark functions and in NSP than the comparison algorithms. In Part I, the background and theory of HCO are introduced firstly. And then, experimental studies on benchmark and real world problems are given in Part II.

A novel Hydrologic Cycle Optimization (HCO) is proposed by simulating the natural phenomena of the hydrologic cycle on the earth. Three operators are employed in the algorithm: flow, infiltration, evaporation and precipitation. Flow step simulates the water flowing to lower areas and makes the population converge to better areas. Infiltration step executes neighborhood search. Evaporation and precipitation step could keep diversity and escape from local optima. The proposed algorithm is verified on ten benchmark functions and applied to a real-world problem named Nurse Scheduling Problem (NSP) with several comparison algorithms. Experiment results show that HCO performs better on most benchmark functions and in NSP than the other algorithms. In Part I, the background and theory of HCO are introduced firstly. And then, experimental studies on benchmark and real world problems are given in Part II.

Competition of swarms, every of which performs a conveyor cooperation of units, operated in physical time, is considered. Such sort of races objectively exists in economics, industry, defense, etc. It is shown, that natural approach to modeling of multiple relay-race with alternative routes is M-parallel semi-Markov process. Due to alternation there are multiple arks in the graph, represented the structure of semi-Markov process. Notion «the space of switches» is introduced. Formulae for calculation the number of routes in the space of switches, stochastic and time characteristics of wandering through M-parallel semi-Markov process are obtained. Conception of distributed forfeit, which depends on stages difference of swarm units, competed in pairs, is proposed. Dependence for evaluation of total forfeit of every participant is obtained. It is shown, that sum of forfeit may be used as optimization criterion in the game strategy optimization task.

Brain storm optimization (BSO) algorithm is a novel swarm intelligence algorithm. Inspired by differential evolution (DE) with multi-population based ensemble of mutation strategies (MPEDE), a new variant of BSO algorithm, called brain storm optimization with multi-population based ensemble of creating operations (MPEBSO), is proposed in this paper. There are three equally sized smaller indicator subpopulations and one much larger reward subpopulation. BSO algorithm is used to update individuals in every subpopulation. At first, each creating operation has one smaller indicator subpopulation, in which different mutation strategy is used to add noise instead of the Gaussian random strategy. After every certain number of generations, the larger reward subpopulation will be adaptively assigned to the best performing creating operation with more computational resources. The competitive performance of the proposed MPEBSO on CEC2005 benchmark functions is highlighted compared with DE, MPEDE, and other four variants of BSO.

Whale optimization algorithm (WOA) is a newly proposed search optimization technique which mimics the encircling prey and bubble-net attacking mechanisms of the whale. It has proven to be very competitive in comparison with other state-of-the-art metaheuristics. Nevertheless, the performance of WOA is limited by its monotonous search dynamics, i.e., only the encircling mechanism drives the search which mainly focus the exploration in the landscape. Thus, WOA lacks of the capacity of jumping out the of local optima. To address this problem, this paper propose a memetic whale optimization algorithm (MWOA) by incorporating a chaotic local search into WOA to enhance its exploitation ability. It is expected that MWOA can well balance the global exploration and local exploitation during the search process, thus achieving a better search performance. Forty eight benchmark functions are used to verify the efficiency of MWOA. Experimental results suggest that MWOA can perform better than its competitors in terms of the convergence speed and the solution accuracy.

The gravitational search algorithm (GSA) has proven to be a good optimization algorithm to solve various optimization problems. However, due to the lack of exploration capability, it often traps into local optima when dealing with complex problems. Hence its convergence speed will slow down. A clustering-based learning strategy (CLS) has been applied to GSA to alleviate this situation, which is called galactic gravitational search algorithm (GGSA). The CLS firstly divides the GSA into multiple clusters, and then it applies several learning strategies in each cluster and among clusters separately. By using this method, the main weakness of GSA that easily trapping into local optima can be effectively alleviated. The experimental results confirm the superior performance of GGSA in terms of solution quality and convergence in comparison with GSA and other algorithms.

Logistics distribution center are important logistics nodes and the choice of locations are critical management decisions. This study addresses a logistics distribution center location problem that aims at determining the location and allocation of the distribution centers. Considering the characteristic and complexity of problem, we propose an improved harmony search algorithm, in which we employ a novel way of improvising new harmony. The improved algorithm is compared with genetic algorithm, particle swarm optimization, generalized particle swarm optimization, and classical harmony search algorithm in solving a simulated distribution center location problem. Experiment results show that the improved algorithm can solve the logistics distribution center problem with more stable convergence speed and higher accuracy.

Fruit fly optimization algorithm (FOA) is a novel bio-inspired technique, which has attracted a lot of researchers’ attention. In order to improve the performance of FOA, a modified FOA is proposed which adopts the phase angle vector to encoded the fruit fly location and brings in the double sub-swarms mechanism. This new strategies can enhance the search ability of the fruit fly and helps find the better solution. Simulation experiments have been conducted on fifteen benchmark functions and the comparisons with the basic FOA show that θ-DFOA performs better in terms of solution accuracy and convergence speed. In addition, the proposed algorithm is used to optimization the PID controller, and the promising performance is achieved.

After studying the behavior of monarch butterflies in nature, Wang et al. proposed a new promising swarm intelligence algorithm, called monarch butterfly optimization (MBO), for addressing unconstrained optimization tasks. In the basic MBO algorithm, the fixed butterfly adjusting rate is used to carry out the butterfly adjusting operator. In this paper, the self-adaptive strategy is introduced to adjust the butterfly adjusting rate. In addition, the crossover operator that is generally used in evolutionary algorithms (EAs) is used to further improve the quality of butterfly individuals. The two optimization strategies, self-adaptive and crossover operator, are combined, and then self-adaptive crossover operator is proposed. After incorporating the above strategies into the basic MBO algorithm, a new version of MBO algorithm, called Self-adaptive Monarch Butterfly Optimization (SaMBO), is put forward. Also, few studies of constrained optimization has been done for MBO research. In this paper, in order to verify the performance of our proposed SaMBO algorithm, the proposed SaMBO algorithm is further benchmarked by 21 CEC 2017 constrained optimization problems. The experimental results indicate that the proposed SaMBO algorithm outperforms the basic MBO and other five state-of-the-art metaheuristic algorithms.

Chemical reaction system, dynamic operation can significantly increase the average rate of reaction, improve the time-average selectivity of complex reactions and enhance the molecular weight distribution of certain free-radical polymerization reactions, overcome the thermodynamic limitations of reversible reactions. It even can be used as integrated means of exothermic/endothermic reaction and catalytic reaction/catalyst regeneration, opens up new ways to strengthen and control the reaction process, reduce waste emissions, and increase economic and social benefits. Therefore, it has great significance to model, simulate and calculate the process of chemical reaction. In this paper, a cooperative firefly algorithm is proposed to solve the optimal dynamic model of chemical reaction. The characteristics of the proposed algorithm are analyzed in detailed and the simulation results of the algorithm are given. It provides a feasible solution to solve such problems and the simulation results also show the effectiveness of the proposed algorithm.

2-Chlorophenol is a kind of representative organic waste water. With the environmental pollution becoming increasingly serious, and the large amount of waste discharged and the increasing difficulty of treatment, the research on the kinetics of the oxidation of supercritical water of 2-chlorophenol has important significant. Aiming at the phenomenon that the Glowworm Swarm Optimization (GSO) algorithm has slow convergence, low precision and easy to get trapped into local optimum, this paper presents an improved version of the GSO based on the behavior of predator-prey and biological predator, and we call it dual population Glowworm Swarm Optimization (GSOPP). The algorithm accelerates the convergence speed by introducing strategies such as chase and escape and variation among populations, and can obtain a more accurate solution. Tested by three standard test functions, the results showed that the improved GSOPP algorithm had better performance than the basic GSO algorithm. Finally, the algorithm was applied to estimate the parameter estimation of the supercritical water oxidation kinetics of 2-chlorophenol, and satisfactory results were obtained.

As one of the most critical components in disaster relief operations, emergency transportation planning often involves huge amount of relief goods, complex hybrid transportation networks, and complex constraints. In this paper, we present a new emergency transportation planning model which combines rail and road transportation and supports transfer between the two modes. For solving the problem, we propose a novel hybrid algorithm that integrates two meta-heuristics, water wave optimization (WWO) and particle swarm optimization (PSO), whose operators are elaborately adapted to effectively balance the exploration and exploitation of the search space. Experimental results show that the performance of our method is better than a number of well-known heuristic algorithms on test instances.

To tackle with the urgent scenario of significant green house gas and air pollution emissions, it is pressing for modern power system operators to consider environmental issues in conventional economic based power system scheduling. Likewise, renewable generations and plug-in electric vehicles are both leading contributors in reducing the emission cost, however their integrations into the power grid remain to be a remarkable challenging issue. In this paper, a dual-objective economic/emission unit commitment problem is modelled considering the renewable generations and plug-in electric vehicles. A novel fast hybrid meta-heuristic algorithm is proposed combing a binary teaching-learning based optimization and the self-adaptive differential evolution for solving the proposed mix-integer problem. Numerical studies illustrate the competitive performance of the proposed method, and the economic and environmental cost have both been remarkably reduced.

A new hybrid algorithm, combining Particle Swarm Optimization (PSO) and Differential Evolution (DE), is presented in this paper. In the proposed algorithm, an alternative replication strategy is introduced to avoid the individuals falling into the suboptimal. There are two groups at the initial process. One is generated by the position updating method of PSO, and the other is produced by the mutation strategy of DE. Based on the alternative replication strategy, those two groups are updated. The poorer half of the population is selected and replaced by the better half. A new group is composed and conducted throughout the optimization process of DE to improve the population diversity. Additionally, the scaling factor is used to enhance the search ability. Numerous simulations on eight benchmark functions show the superior performance of the proposed algorithm.

The intermittency of wind remains the greatest challenge to its large scale adoption and sustainability of wind farms. Accurate wind power predictions therefore play a critical role for grid efficiency where wind energy is integrated. In this paper, we investigate two hybrid approaches based on the genetic algorithm (GA) and particle swarm optimisation (PSO). We use these techniques to optimise an Adaptive Neuro-Fuzzy Inference system (ANFIS) in order to perform one-hour ahead wind power prediction. The results show that the proposed techniques display statistically significant out-performance relative to the traditional backpropagation least-squares method. Furthermore, the hybrid techniques also display statistically significant out-performance when compared to the standard genetic algorithm.

Sparse reconstruction is an important method aiming at obtaining an approximation to an original signal from observed data. It can be deemed as a multiobjective optimization problem for the sparsity and the observational error terms, which are considered as two conflicting objectives in evolutionary algorithm. In this paper, a novel decomposition based multiobjective evolutionary algorithm is proposed to optimize the two objectives and reconstruct the original signal more exactly. In our algorithm, a sparse constraint specific differential evolution is designed to guarantee that the solution remains sparse in the next generation. In addition, a neighborhood-based local search approach is proposed to obtain better solutions and improve the speed of convergence. Therefore, a set of solutions is obtained efficiently and is able to closely approximate the original signal.

In order to efficiently manage the diversity and convergence in many-objective optimization, this paper proposes a novel multi-engine cooperation bacterial foraging algorithm (MCBFA) to enhance the selection pressure towards Pareto front. The main framework of MCBFA is to handle the convergence and diversity separately by evolving several search engines with different rules. In this algorithm, three engines are respectively endowed with three different evolution principles (i.e., Pareto-based, decomposition-based and indicator-based), and their archives are evolved according to comprehensive learning. In the foraging operations, each bacterium is evolved by reinforcement learning (RL). Specifically, each bacterium adaptively varies its own run-length unit and exchange information to dynamically balance exploration and exploitation during the search process. Empirical studies on DTLZ benchmarks show MCBFA exhibits promising performance on complex many-objective problems.

In order to efficiently reduce computational expense as well as manage the diversity and convergence in many-objective optimization, this paper proposes a novel multi-indicator bacterial foraging algorithm with Kriging model (K-MBFA) to guide the search process toward the Pareto front. In the proposed algorithm, a set of preferential individuals for the improved Kriging model are appropriately selected according to the different indicators. Specifically, the stochastic ranking technique is adopted to avoid the search biases of different indicators, which would lead the population to converge to local region of the Pareto front. With several test instances from DTLZ sets with 3, 5, 8 and 10 objectives, K-MBFA is verified to be significantly superior to other compared algorithms in terms of inverted generational distance (IGD).

In this paper, an improved bacterial foraging optimization algorithm (BFO), which is inspired by the foraging and chemotactic phenomenon of bacteria, named high dimensional multi-objective bacterial foraging optimization (HMBFO) is introduced for solving high dimensional multi-objective optimization (MO) problems. The high-dimension update strategy is presented in this paper to solve the problem that the global Pareto solutions can be hardly obtained by traditional MBFO in high-dimension MO problems. According to this strategy, the position of bacteria not only can be rapidly updated to the optimal solution, but also can enhance the searching precision and reduce chemotaxis dependency remarkably. Moreover, the penalty mechanism is considered for solving the inequality constraints MO problems, and three different performance metrics (Hypervolume, Convergence metric, Spacing metric) are introduced to evaluate the performances of algorithms. Compared with the other four evolutionary MO algorithms (MBFO, MOCLPSO, MOPSO, PESA2), the simulation result shows that in most cases, the proposed algorithm carries out better than the other existing algorithms, it has high efficiency, rapid speed of convergence and strong search capability of global Pareto solutions.

To solve the multimodal multi-objective optimization problems which may have two or more Pareto-optimal solutions with the same fitness value, a new multi-objective particle swarm optimizer with a self-organizing mechanism (SMPSO-MM) is proposed in this paper. First, the self-organizing map network is used to find the distribution structure of the population and build the neighborhood in the decision space. Second, the leaders are selected from the corresponding neighborhood. Meanwhile, the elite learning strategy is adopted to avoid premature convergence. Third, a non-dominated-sort method with special crowding distance is adopted to update the external archive. With the help of self-organizing mechanism, the solutions which are similar to each other can be mapped into the same neighborhood. In addition, the special crowding distance enables the algorithm to maintain multiple solutions in the decision space which may be very close in the objective space. SMPSO-MM is compared with other four multi-objective optimization algorithms. The experimental results show that the proposed algorithm is superior to the other four algorithms.

Evolutionary algorithms (EAs) based on decomposition have shown to be promising in solving many-objective optimization problems (MaOPs). First, the population (or objective space) is divided into K subpopulations (or subregions) by a group of uniform distribution reference vectors. Later, subpopulations are optimized simultaneously. In this paper, we propose a new decomposition based evolutionary algorithm with angle penalty selection strategy for MaOPs (MOEA-APS). In the environmental selection process, in order to prevent the solutions located around the boundary of the subregion from being simultaneously selected into the next generation which will affect negatively on the performance of the algorithm, a new angle similarity measure (AS) is calculated and used to punish the dense solutions. More precisely, after selecting a good solution x for a sub population, the solutions whose angle similarity with x exceeding $$\eta $$ or pareto dominated by x will be directly punished. Moreover, The threshold $$\eta $$ is not fixed, but decided by the distribution of the solutions around x. This mechanism allows to improve diversity of population. The experimental results on DTLZ benchmark test problems show that the results of the proposed algorithm are very competitive comparing with four other state-of-the-art EAs for MaOPs.

As a technology based on statistics and knowledge discovery, recommendation system can automatically provide appropriate recommendations to users, which is considered as a very effective tool for reducing information load. The accuracy and diversity of recommendation are important objectives of evaluating an algorithm. In order to improve the diversity of recommendation, a personalized recommendation algorithm Multi-Objective Evolutionary Algorithm with Probabilistic-spreading and Genetic Mutation Adaptation (MOEA-PGMA) based on Personalized Recommendation based on Multi-Objective Evolutionary Optimization (MOEA-ProbS) is proposed in this paper. Low-grade and unpurchased items are preprocessed before predicting the scores to avoid recommending low-grade items to users and improve recommendation accuracy. By introducing adaptive mutation, the better individuals will survive in the evolution with a smaller mutation rate, and worse individuals will eliminate. The experimental results show that MOEA-PMGA has a higher population search ability compared to MOEA-ProbS, and has improved the accuracy and diversity on the optimal solution set.

In recent years many real-world optimization problems have had to deal with growing dimensionality. Optimization problems with many hundreds or thousands of variables are called large-scale global optimization (LSGO) problems. Many well-known real-world LSGO problems are not separable and are complex for detailed analysis, thus they are viewed as the black-box optimization problems. The most advanced algorithms for LSGO are based on cooperative coevolution with problem decomposition using grouping methods, which form low-dimensional non-overlapping subcomponents of a high-dimensional objective vector. The standard random grouping can be applied to the wide range of separable and non-separable LSGO problems, but it does not use any feedback from the search process for creating more efficient variables combinations. Many learning-based dynamic grouping methods are able to identify interacting variables and to group them into the same subcomponent. At the same time, the majority of the proposed learning-based methods demonstrate greedy search and perform well only with separable problems. In this study, we proposed a new adaptive random grouping approach that create and adaptively change a probability distribution for assigning variables to subcomponents. The approach is able to form subcomponents of different size or can be used with predefined fix-sized subcomponents. The results of numerical experiments for benchmark problems are presented and discussed. The experiments show that the proposed approach outperforms the standard random grouping method.

Cooperative Co-evolution (CC) framework is an important method to tackle Large Scale Black-Box Optimization (LSBO) problem. One of the main step in CC is grouping for the decision variables, which affects the optimization performance. An ideal grouping result is that the relationship of decision variables in intra-group is stronger as possible and those in inter-groups is weaker as possible. Global Differential Grouping (GDG) is an efficient grouping method based on the idea of partial derivatives of multivariate functions, and it can automatically resolve the problem by maintaining the global information among variables. However, once the grouping result by GDG is determined, it will no longer be updated and will not be automatically adjusted with the evolution of the algorithm, which may affect the optimization performance of the algorithm. Therefore, based on GDG, a Dynamic Global Differential Grouping (DGDG) strategy is proposed for grouping the decision variables in this paper, which can update the grouping results with the evolution processing. DGDG works with Particle Swarm Optimization (PSO) algorithm in this paper, which is termed as CC-DGDG-PSO. The experimental results based on the LSBO benchmark functions from CEC’2010 show that DGDG algorithm can improve the performance of GDG.

Most of the optimization problems are dynamic in real world. When dealing with the dynamic optimization problems, the evolutionary algorithms always suffer from low accuracy and diversity loss. One of the main reasons of low accuracy is that the population cannot convergent to the optima in limit computational cost. And one of the main reasons of diversity loss is that some areas are searched repeatedly while leave the others unsearched deal to the unbalanced attraction from local optima. To cope with the deficiency, two strategies are proposed in this paper. One is called Searching Gbest, which searches for a better solution along each dimension of the best one in the population to accelerate the convergence, and the other is predicting convergence, which deletes the population if it has the trend of converge to the searched area to avoid the repeatedly search. The proposed methods are tested on PSO with multiple populations. The experiments on the Moving Peaks Benchmark show that the methods can improve optima tracking ability, avoid repeatedly search and save the computing resources effectively.

This paper proposes to optimise the steering linkage including an effect of McPherson strut front suspension. Usually, the suspension is exerted with an impact force due to uneven road, which dynamically changes to performance of a steering linkage. The present work proposes to study an effect of suspension to performance of steering mechanism with comparative study of steering mechanism with and without suspension system, which is included in optimization problem. The performance is minimised in both turning radius and steering error, that is called multi-objective optimisation problems. The model of McPherson strut front suspension is simplified model but it is sufficient accuracy. The results show that the suspension is an important effect on the optimisation design and the optimisation results show that the design concept leads to effective design of rack and pinion steering linkages satisfying both steering error and turning radius criteria.

Multi-scale quantum harmonic oscillator algorithm (MQHOA) is a novel global optimization algorithm inspired by wave function of quantum mechanics. In this paper, a MQHOA with individual stabilization strategy (IS-MQHOA) is proposed utilizing the individual steady criterion instead of the group statistics. The proposed strategy is more rigorous for the particles in the energy level stabilization process. A more efficient search takes place in the search space made by the particles and improves the exploration ability and the robustness of the algorithm. To verify its performance, numerical experiments are conducted to compare the proposed algorithm with the state-of-the-art SPSO2011 and QPSO. The experimental results show the superiority of the proposed approach on benchmark functions.