Application of PSO (particle swarm optimization) and GA (genetic algorithm) techniques on demand estimation of oil in Iran

doi:10.1016/j.energy.2010.07.043

Energy

Volume 35, Issue 12, December 2010, Pages 5223-5229

https://doi.org/10.1016/j.energy.2010.07.043 Get rights and content

Abstract

This paper presents application of PSO (Particle Swarm Optimization) and GA (Genetic Algorithm) techniques to estimate oil demand in Iran, based on socio-economic indicators. The models are developed in two forms (exponential and linear) and applied to forecast oil demand in Iran. PSO–DEM and GA–DEM (PSO and GA demand estimation models) are developed to estimate the future oil demand values based on population, GDP (gross domestic product), import and export data. Oil consumption in Iran from 1981 to 2005 is considered as the case of this study. The available data is partly used for finding the optimal, or near optimal values of the weighting parameters (1981–1999) and partly for testing the models (2000–2005). For the best results of GA, the average relative errors on testing data were 2.83% and 1.72% for GA–DEM_exponential and GA–DEM_linear, respectively. The corresponding values for PSO were 1.40% and 1.36% for PSO–DEM_exponential and PSO–DEM_linear, respectively. Oil demand in Iran is forecasted up to year 2030.

Introduction

The outlook of energy in Iran shows the importance of the need for systematic optimization of the energy use in Iran. Energy resources are limited and depleting [1]. Furthermore, Iran’s population is steadily increasing. The energy consumption in Iran is also rapidly increasing [2].

Iran, with population of more than 68 million [3], is one of the largest producers of crude oil in the world. In contrary to the public’s perception, Iran’s share of the market for high quality oil is as little as 2%. More specifically, while Iran has the fourth highest oil production rate, the oil produced in Iran is ranked 14th in terms of the quality [2].

Oil, natural gas, electric power, solar, wood, animal and plant waste are Iran’s primary energy sources [4].

Section snippets

Literature review

Several studies are presented to propose some models for energy demand policy management using different techniques. Unler developed PSO (Particle Swarm Optimization) energy demand models to estimate energy demand based on economic indicators in Turkey [5]. Canyurt and Ozturk presented Turkey’s fossil fuels demand estimation models by using the structure of the Turkish industry and economic conditions based on GA (Genetic Algorithm) [6]. Toksari developed Ant Colony energy demand estimation

GAs

The formulation of GAs was made about a decade after the first Evolutionary Strategies and Evolutionary Programming applications.

The theoretical basis of GAs lies in the concept of schema (plural schemata) [22]. Schemata represent solution templates where each location can be defined or left unspecified. The larger the number of uninstantiated location is, the greater the number of potential solutions that a schema represents. Schemata leading to higher fitness individuals are propagated

PSO

The PSO algorithm was first proposed by Eberhart and Kennedy [35], inspired by the natural flocking and swarming behavior of birds and insects. The concept of PSO gained in popularity due to its simplicity. Like other swarm-based techniques, PSO consists of a number of individuals refining their knowledge of the given search space. The individuals in a PSO have a position and a velocity and are denoted as particles. The PSO traditionally has no crossover between individuals, has no mutation and

Problem definition

Iran’s oil demand by using the structure of the Iran socio-economic conditions is the main objective of this study. GA and PSO demand estimation models (GA–DEM and PSO–DEM) are developed to estimate the future oil demand values based on population, GDP (gross domestic product), import and export figures.

The fitness function, F(x), takes the following form: $Min F (x) = \sum_{j = 1}^{m} {(E_{actual} - E_{predicted})}^{2}$ where E_actual and E_predicted are the actual and predicted oil demand, respectively, m is the number of

Results and discussions

The PSO algorithm was coded with MATLAB 2007 and for GA algorithm, toolbox of MATLAB 2007 was used. The convergence of the objective function and sensitivity analysis were examined for varying user-specified parameters of GA (population size, methods of selection, reproduction, crossover, mutation and generation) and PSO (particle size (n), inertia weight ( $ω$ ) and maximum iteration number (t)). Each user-specified parameter combination (for each algorithm) was tested 10 times.

It was found that

Conclusion

Energy consumption growth rate shows the importance of the need for systematic optimization of the energy consumption in Iran.

Artificial intelligence methods have been successfully used to estimate Iran’s oil demand based on the structure of the Iran socio-economic conditions. 25 Years’ data (1981–2005) has been used for developing two forms (linear and exponential) of the GA and PSO demand estimation models. Three scenarios are designed in order to estimate Iran’s oil demand during 2006–2030.

Acknowledgments

The authors are grateful for the support provided for the present work by the Islamic Azad University, Dezful Branch and Iran’s Ministry of Energy. The authors also highly appreciate the constructive comments of the reviewers.

References (42)

H. Houri Jafari et al.
The crisis of gasoline consumption in the Iran’s transportation sector
Energy Policy
(2008)
A.R. Karbassi et al.
Sustainability of energy production and use in Iran
Energy Policy
(2007)
F.A. Hessari
Sectoral energy consumption in Iran
Renewable and Sustainable Energy Reviews
(2005)
A. Unler
Improvement of energy demand forecasts using swarm intelligence: the case of Turkey with projections to 2025
Energy Policy
(2008)
O.E. Canyurt et al.
Application of genetic algorithm (GA) technique on demand estimation of fossil fuels in Turkey
Energy Policy
(2008)
A. Azadeh et al.
A simulated-based neural network algorithm for forecasting electrical energy consumption in Iran
Energy Policy
(2008)
A. Azadeh et al.
An integrated fuzzy regression algorithm for energy consumption estimation with non-stationary data: a case study of Iran
Energy
(2010)
M.H. Amjadi et al.
Estimation of electricity demand of Iran using two heuristic algorithms
Energy Conversion and Management
(2010)
M. Zhang et al.
Forecasting the transport energy demand based on PLSR method in China
Energy
(2009)
M. Nava et al.
The energy demand and the impact by fossil fuels use in the Mexico City Metropolitan Area, from 1988 to 2000
Energy
(2006)

H.A. Amarawickrama et al.

Electricity demand for Sri Lanka: a time series analysis

Energy

(2008)

H. Askari et al.

An oil demand and supply model incorporating monetary policy

Energy

(2010)

D. Cinar et al.

Development of future energy scenarios with intelligent algorithms: case of hydro in Turkey

Energy

(2010)

D. Akay et al.

Grey prediction with rolling mechanism for electricity demand forecasting of Turkey

Energy

(2007)

L. Ekonomou

Greek long-term energy consumption prediction using artificial neural networks

Energy

(2010)

M. Jovanovic et al.

An analytical method for the measurement of energy system sustainability in urban areas

Energy

(2010)

X. Tang et al.

Forecast of oil reserves and production in Daqing oilfield of China

Energy

(2010)

N. Amjady et al.

Short-term load forecasting of power systems by combination of wavelet transform and neuro-evolutionary algorithm

Energy

(2009)

S.Sp Pappas et al.

Electricity demand loads modeling using AutoRegressive Moving Average (ARMA) models

Energy

(2008)

G. Syswerda

Reproduction in generational and steady state genetic algorithm

D.E. Goldberg et al.

A comparison of selection schemes used in genetic algorithms

Cited by (198)

AI-based macro model learning for high cycle fatigue assessment of welded joints in large-span steel structures
2024, International Journal of Fatigue
Welded spherical joints are critical components in large-span bridges and spatial steel structures prone to high cycle fatigue (HCF) loadings. Challenges exist for assessing fatigue life of this joints in small data from physical experiments and no detailed fatigue classification in design codes. This paper investigates the fatigue resistance of welded spherical joints and the real-time pre-damage evolution under non-stationary HCF loadings by proposing AI-based macro model learning from fine FE models and fatigue tests. Firstly, the structural features of welded spherical joints about stress concentration and weld defects were analyzed and quantified, so modified S-N curve was built. Then, based on artificial intelligence (AI-based) learning, stress concentration factors (SCF) were obtained by an artificial neural network with particle swarm optimization and the modified fatigue resistance of welded spherical joints was derived by artificial bee colony algorithms. Finally, the macro linkage element was proposed as a user element subroutine (UEL), by which non-stationary fatigue pre-damage evolution based on the time-domain incremental analytical method was realized. The results not only indicated the damage value close to the ones derived by commonly used rain flow count methods, but also provided the pre-damage evolution curve for real-time monitoring.
Current status, future prediction and offset potential of fossil fuel CO<inf>2</inf> emissions in China
2023, Journal of Cleaner Production
Reducing carbon emissions and increasing carbon sinks are key strategies to effectively remove greenhouse gases from the atmosphere. Assessing the current carbon emission status and predicting future carbon emission scenarios could help formulate effective regional carbon emission reduction targets. However, it is necessary to enhance the carbon sink capacity of terrestrial ecosystems and improve forest management methods to promote greenhouse gas absorption. In this study, the spatiotemporal characteristics and dynamic evolution of fossil fuel CO₂ (FFCO₂) emissions in China from 2000 to 2019 were analyzed using the standard deviation ellipse, kernel density of emissions, and Theil index. A backpropagation (BP) neural network optimized with a genetic algorithm (GA) was used to predict FFCO₂ emission during 2020–2030. The biomass increment methodology was used to predict the potential carbon sinks generated by Chinese Certified Emission Reduction (CCER) carbon-sink forestry projects during 2020–2030. The results showed that China's FFCO₂ emissions exhibited a gradual increasing trend during 2000–2019, with an average annual growth rate of 6.29%. China's FFCO₂ emissions show a greater distribution on the southeastern coast than in the northwestern interior. The GA-BP prediction shows that China's FFCO₂ emissions will continue to fluctuate and increase between 2020 and 2030. The potential of carbon sinks will be 0.69 × 10⁸ Mg C generated by the CCER carbon-sink forestry projects during 2020–2030, which could offset 0.56% of FFCO₂ emissions. In the future, imbalances in regional development should be considered when formulating carbon-reduction strategies. Moreover, using carbon-sink of forestry projects of CCER to balance economic development including poverty eradication and environmental conservation should be considered. Specifically, establishing a methodology of projects for the management of natural forests' carbon-sink will be an important future strategy.
An oil imports dependence forecasting system based on fuzzy time series and multi-objective optimization algorithm: Case for China
2022, Knowledge-Based Systems
Oil production and consumption is of great importance for the sustainable development and management of energy and environment. The forecasting of oil imports dependence caused by the gap between production and consumption is particularly crucial in the strategic deployment of oil development. However, researches on oil import dependence forecasting are often limited by the small size of data samples and assumptions, and the previous single-objective optimization algorithms only focus on the improvement of forecasting accuracy but ignore the stability. Therefore, in order to overcome the shortcomings of researches, in this paper, a hybrid forecasting system for oil imports dependence forecasting based on fuzzy time series and multi-objective optimization algorithm is proposed considering the accuracy and stability simultaneously to achieve the balance and optimality and bridge the limitations of small sample forecasting. The proposed forecasting system is compared with other small sample forecasting models and the fuzzy times series model with traditional interval partition methods. The results show that the proposed system is superior to the traditional methods in all indicators for oil import dependence forecasting. Otherwise, the out of sample forecasting results provided in our research indicate that the oil import dependence will maintain an upward trend, but the rate of increase will slow down. The research results can not only provide the basis for the planning and control of oil import and safety, but also benefit the perceptions of oil price trend in the world energy market and the adjustment of energy market structure.
Prediction of transportation energy demand by novel hybrid meta-heuristic ANN
2022, Energy
Road automobiles are deemed one of the major resources of energy consumption throughout cities. To realize and design sustainable urban transport, it is essential to comprehend as well as evaluate interactions among a set of elements, which form transport impacts and behaviors. The goal of the current research was to propose a hybrid algorithm, Artificial Neural Network (ANN)-Genetic Algorithm (ANN-GA), ANN-Simulated Annealing (ANN-SA), and Particle Swarm Optimization (ANN-PSO) to better optimize the coefficients for predicting the energy demand based on the several predictor variables (1975–2019) i.e., GDP, year, vehicle-km, population, oil price, passenger-km, and ton-km in Turkey. Eleven combinations of all predictor variables were selected and then compared with real data. The outcomes exposed that the proposed ANN-PSO technique based on the GDP, population, ton-km outperforms the other two models. It is anticipated that this research can be useful for developing extremely productive and applicable planning regarding transportation energy policies.
An interval two-stage robust stochastic programming approach for steam power systems design and operation optimization under complex uncertainties
2022, Chemical Engineering Science
In this study, an interval two-stage robust stochastic programming approach is developed for the design and operation optimization of steam power systems under complex uncertainties by integrating interval-parameter programming and robust optimization into two-stage stochastic programming. The approach has the following advantages: (1) it extends the traditional two-stage stochastic programming method by enabling uncertainties presented as both probability distributions and discrete intervals to be effectively incorporated within the optimization framework, and could permit in-depth analyses of various policy scenarios when the promised policy targets are violated; (2) it could effectively reflect system risks generated by stochastic programming process, overcome the deficiency of uncontrollable risks in system and enhance the robustness of optimization, such that it is suitable for risk-aversion planners under high-variability conditions. One case of a refinery engineering project is provided for demonstrating the applicability and availability of the proposed approach. The numerical results provides ample decision-making space for decision makers to evaluate trade-offs between system economy and stability.
Research on equipment corrosion diagnosis method and prediction model driven by data
2022, Process Safety and Environmental Protection
With the rapid development of the oil refining industry, safety problems caused by equipment corrosion have become increasingly important, making equipment corrosion management a key factor to ensure process safety. Corrosion diagnosis, as the first step of equipment corrosion management, is of great significance in not only ensuring the proper corrosion supervision, but also realizing safety protection of equipment. This paper addresses the problems of incompleteness as well as the subjective factors of existing methods in equipment corrosion diagnosis. The proposed solution, based on data-driven corrosion diagnosis, suggests a more comprehensive view. Special focus in this paper is on evaluation and prediction of corrosion safety state, including the identification of corrosion mode and the prediction of corrosion type and degree. This paper brings together large amount of historical data of equipment corrosion detection and solves the problem of unbalanced original data by data wrangling and the application of Borderline-SMOTE algorithm. What’s more, a prediction model that is based on Random Forest (RF) algorithm is constructed, aiming at equipment corrosion mechanism, type and degree. The results show that the model, aiming at critical mechanism identification, performs ideally after evaluation and the accuracy of the results amount to 86%. As for the classification and prediction of corrosion state, the model can be further optimized by Particle Swarm Optimization (PSO) algorithm to reach a better accuracy (92%), which verifies generalization effect compared with traditional prediction models. In addition, this solution improves the functionality and practicability of corrosion diagnosis, which is beneficial to the investigation of hidden dangers. It also can serve as an instruction for equipment safety management to ensure the stable operation for an enterprise.

View all citing articles on Scopus

View full text

Application of PSO (particle swarm optimization) and GA (genetic algorithm) techniques on demand estimation of oil in Iran

Abstract

Introduction

Section snippets

Literature review

GAs

PSO

Problem definition

Results and discussions

Conclusion

Acknowledgments

Energy Policy

Energy Policy

Renewable and Sustainable Energy Reviews

Energy Policy

Energy Policy

Energy Policy

Energy

Energy Conversion and Management

Energy

Energy

Energy

Energy

Energy

Energy

Energy

Energy

Energy

Energy

Energy