Intelligent Control and Smart Energy Management

Fuel cells are gradually becoming the competitive alternative to conventional internal combustion engines due to their high system efficiency and zero-local emission property. Nevertheless, the high manufacturing cost and the limited lifetime of fuel cell systems still remain the major barrier toward the massive promotion of fuel cell electric vehicles. To reduce the vehicle’s operating cost, reliable energy management strategies should be devised to coordinate the outputs of multiple energy sources in hybrid powertrain.

This chapter intends to present the development of predictive energy management strategy for fuel cell hybrid electric vehicles, especially focusing on the possibility of combining the driving predictive information with the real-time optimization framework. To this end, two driving prediction techniques are proposed, namely, a vehicle speed forecasting approach and a driving pattern recognition method. Thereafter, model predictive control is adopted for real-time decision-making with the assistance of the predicted information. Validation results indicate that the proposed control strategy outperforms the benchmark control strategies in terms of fuel economy and fuel cell durability, thereby verifying the control performance improvement imposed by driving prediction integration.

This chapter focuses on a hierarchical energy management strategy design methodology for total cost of ownership management at fleet level. A state of the art is presented of the different proposed learning-based energy management strategies and fleet energy management approaches. Digitalization, the new trend of monitoring the operation of each vehicle, and cloud computing new techniques, allowing to carry out heavier calculations on servers, have derived from new energy management strategy techniques and degrees of freedom. The fleet operation data acquisition allows to upgrade the management level from the local vehicle level to the fleet level. The fleet-level point of view facilitates the decisions when updating the energy management strategy and gives an additional degree of freedom of managing and optimizing the whole fleet. To exploit the new degrees of freedom, the fleet is reorganized, and the energy management strategy is updated throughout the bus lifetime. These decisions are made based on the planned total cost of ownership for each type of plug-in hybrid electric bus with determined battery chemistry. The most suitable decisions will be evaluated according to each type of bus, optimizing the total cost of ownership further. Improvements of the whole total cost of ownership in both fleets have been obtained, proving the need of EMS update and fleet reorganization.

Many stochastic optimal control problems have analytical solutions up to unknown numerical parameters. We demonstrate this fact with several examples from inventory theory, queuing theory, and risk theory. The paper reviews sufficient conditions for the existence of parametric optimal solutions to such problems in the stationary and nonstationary cases, for minimizing the average and discounted costs. The found parametric strategies are then substituted into the dynamic equations and the target functional of the primary optimal control problem. Thus, the original problem reduces to the problem of finite-dimensional stochastic programming concerning the unknown parameters. Since the optimal strategies are nonconvex, nonsmooth, or discontinuous functions of state variables and parameters, the corresponding stochastic programming problem may also be nonconvex, nonsmooth, or discontinuous. The paper proposes methods for calculating stochastic (quasi-)gradients (or their finite-difference analogs) of the objective function of the obtained stochastic programming problem and substantiates stochastic quasigradient methods for finding optimal parameter values. We illustrate the proposed solution approach by optimal inventory control and optimization of an energy accumulation system.

This chapter will review the challenges that the low-voltage electricity distribution network currently has to face in order to become a smart distribution grid that allows real-time management of the system and the devices connected to it. These challenges are of two types: on the one hand, we have technological challenges and, on the other hand, regulatory ones. Regarding the technological challenges, the chapter will focus on the study of how the low-voltage distribution system is currently structured and operated and the changes that the electricity companies have to introduce and are actually introducing into it in order to achieve a real-time operation that allows the massive, safe and efficient integration of new devices such as electric vehicles, distributed generation and storage systems, heat pumps and other flexible loads/generators. The chapter will then focus on the study of the existing regulatory framework (with special emphasis on European regulation), as it considers that the development of stable regulation which promotes new actors or business models such as aggregators or energy communities is key to achieving a low-carbon and efficient energy system. Different types of aggregation models will be reviewed, and the implications of these models within the complex network of roles within the current electricity system will be analysed.

This chapter aims to provide a general but comprehensive overview of the evolution of electrical railway power supply systems (ERPSS) for high-speed railway lines. To this end, the chapter starts describing the conventional transformer-based configurations and the most important approaches presented in literature to overcome their principal drawbacks. Then, it continues with the analysis of the converter-based configurations, typically restricted to low power rates but now extended to more power demanding applications, thanks to the outstanding development of electronic power converters. This latter section will analyze both AC and DC systems.

Maritime transportation has been, historically, a major factor in economic development and prosperity since it enables trade and contacts between nations. The amount of trade through maritime transport has increased drastically; for example, about 90% of the European Union’s external trade and one-third of its internal trade depend on maritime transport. Major ports, typically, incorporate multiple terminals serving containerships, railways, and other forms of hinterland transportation and require interterminal and intraterminal container transport. Many factors influence the productivity and efficiency of ports and hence their economic viability. Moreover, environmental concerns have been leading to stern regulation that requires ports to reduce, for example, greenhouse gas emissions. Therefore, port authorities need to balance economic and ecological objectives in order to ensure sustainable growth and to remain competitive. Once a containership moors at a container terminal, several quay cranes are assigned to the ship to load/unload the containers to/from the ship. Loading activities require the containers to have been previously made available at the quayside, while unloading ones require the containers to be removed from the quayside. The containers are transported between the quayside and the storage yard by a set of vehicles. This chapter addresses the intraterminal container transport scheduling problem by simultaneously scheduling the loading/unloading activities of quay cranes and the transport (between the quayside and the storage yard) activities of vehicles. In addition, the problem includes vehicles with adjustable travelling speed, a characteristic never considered in this context. For this problem, we propose bi-objective mixed-integer linear programming (MILP) models aiming at minimizing the makespan and the total energy consumption simultaneously. Computational experiments are conducted on benchmark instances that we also propose. The computational results show the effectiveness of the MILP models as well as the impact of considering vehicles with adjustable speed, which can reduce the makespan by up to 16.2% and the total energy consumption by up to 2.5%. Finally, we also show that handling unloading and loading activities simultaneously rather than sequentially (the usual practice rule) can improve the makespan by up to 34.5% and the total energy consumption by up to 18.3%.

Battery packs of electric vehicles are prone to capacity, thermal, and aging imbalances in their cells, which limit power delivery to the vehicle. To promote a more sustainable transportation, a solution to this problem is necessary. In this chapter, a hybrid battery management system (HBMS), capable of simultaneously equalizing battery state of charge and temperature while enabling hybridization with supercapacitors, is investigated. A model-free reinforcement learning is used to control the HBMS, where the control policy is obtained through direct interaction with the system’s model. The approach of this work exploits the soft actor-critic algorithm to handle continuous control actions and feedback states and deep neural networks as function approximators. The validation of the proposed control method is performed through numerical simulations, making use of numerically efficient models of the energy storage and power converters developed in Modelica language.

Due to the low-cost entry to space in recent years, the risk for on-board distributed collaborative autonomous formation control development has dramatically decreased. It is now feasible to have a distributed network of satellites autonomously coordinating their actions, which shifts the burden of space missions from a single monolithic operational structure into a distributed network of satellites. In this chapter, we consider the case of multiple satellites converging to a planar circular formation around a target satellite. The satellites are able to communicate over a connected graph which contains potentially noisy and disturbed links, demonstrating concepts of robustness and resilience. We illustrate these results in the case of a ten-satellite formation reaching an energy and fuel-efficient orbit about a desired target point and prove that such methods are robust.

Vertical transportation in buildings (elevators, vertical conveyors, escalators, etc.) moves more than one billion people worldwide every day, accounting for a significant portion of the energy consumption of an average building. This work discusses the operation of an energy management system in a hybrid energy storage system for an elevator in a commercial building. Besides energy support in case of mains failure, the storage units are also coordinated to attain an efficient management of the power flows in the full system, allowing for the implementation of a peak-shaving grid power strategy. The design procedure of such a storage system needs to take into account the effects in key performance parameters of the intended varying operating conditions. Among these key performance parameters, the system efficiency plays a vital role, namely, the power losses, the thermal performance, the reliability of the system, or even exploitation costs.

Keeping this in mind, the main contribution of the work is the proposal of a systematic methodology for the selection of the optimal configuration of the power electronic conversion systems, in terms of energy efficiency performance, for the case of study of the storage system in an elevator previously defined. But in any case, the proposal is formulated as a general approach, valid for any system in which the general functionality is defined as a sequence of transient intervals, rather than based on a fixed steady-state operating point. The algorithm, intended for evaluating the performance of a given power conversion stage, includes a procedure for the power electronic topology selection and for the dynamic control parameters’ adjustment. The methodology is introduced and described in detail, and then it is applied to two different topologies for the power converter configuration. Additionally, it forms the basis of an optimal controller design.

One of the major benefits of the methodology is that it provides the same information obtained from the thorough computation of mission profiles of the power demanded by the system, defined for full operating periods, but using a simplified characteristic power profile. Therefore, by applying such simple profile-based strategy, an optimal configuration of the control parameters can be derived in cases where the complete power profiles are unknown. An additional advantage of this contribution is that this approach provides very accurate results with a reduced number of calculations. This last aspect opens the possibility to implement the resulting low computational burden algorithm in real-time control schemes.

The technological advancements in terms of vehicle on-board sensors and actuators, as well as for infrastructures, open an unprecedented scenario for the management of vehicular traffic. We focus on the problem of smoothing traffic by controlling a small number of autonomous vehicles immersed in the bulk traffic stream. Specifically, we aim at dissipating stop-and-go waves, which are ubiquitous and proven to increase fuel consumption tremendously and reduce. Our approach is holistic, as it is based on a large collaborative effort, which ranges from mathematical models for traffic and control all the way to building infrastructures capable of measuring energy efficiency and providing real-time data. Such an approach allows to clearly set and measure a metric for success in the form of a reduction of at least 10% of fuel consumption using 5% of autonomous vehicles immersed in bulk traffic. The chapter illustrates the overall approach and provides simulation results on a tuned microsimulator for the California I-210.

Excluding passive topology, hybrid energy storage system (HESS) requires energy management strategy (EMS) which is traditionally developed by mono-objective approach. Meanwhile, energy management of HESS can be considered as multi-objective problems. Recently, multi-objective EMS has been studied; however, there is a lack of a proper benchmark for performance evaluation and/or EMS tuning. This chapter proposes a methodology for multi-objective global optimal EMS generating a Pareto front benchmark. The optimization process is organized in the form of a hierarchical structure, whereas the optimal solutions are obtained by using dynamic programming (DP) algorithm. Filtering strategy is used as an example of a rule-based strategy for performance evaluation using the generated benchmark. Numerical validations are carried out based on a real electric vehicle (EV) platform of our laboratory. The results confirm the advantages of the proposed approach for multi-objective benchmarking the real-time EMS performance by comparing to the generated Pareto front. Representative solutions in accordance with the typical weighting factor values are also reported to demonstrate the advanced EMS behaviors with different priorities given to the considered objectives. The proposed EMS can therefore be insightful to design and/or to tune the real-time strategies.

Automatic control of electric vehicles (EVs) is challenging due to the presence of system parameter uncertainty and large variations of resistant load. On the other hand, human drivers, without any knowledge of vehicle dynamic model and control, can properly deal with these challenges, thanks to the experiences acquired via training and practice. As a consequence, human expertise-based intelligent controllers are of interest for EVs, in which fuzzy logic controller (FLC) is a promising candidate considering its model-free essence with soft-computing techniques offering flexibility and robustness to the control system. This chapter proposes an FLC for speed control of AC electrical motors including induction motor (IM) and interior permanent magnet (IPM) synchronous motor in EV applications. The FLC membership functions and rules are designed with value normalization that allows the developed controller able to be flexible when applied to a wide range of speed control applications. The proposed FLC is numerically validated via an EV model with system parameters based on a practical off-road vehicle platform of our laboratory. Critical testing scenarios are employed including vehicle mass variations and rolling resistance force due to different load-carrying and road conditions. The results reveal that regardless of these uncertainty and load fluctuations, the speed error is kept within a bound of 2.5% comparing to the nominal speed of 40 km/h. The merit and flexibility of the proposed FLC have been discussed in comparison with the traditional PI controller and also with simulation on other platforms, i-MiEV of Mitsubishi in our lab. Moreover, thanks to its normalized design, the proposed FLC is not limited to the studied EVs, but can be applied to other e-mobility systems.