Review ArticleHybrid bio-Inspired computational intelligence techniques for solving power system optimization problems: A comprehensive survey
Graphical abstract
Introduction
Optimization of power system has been a topic of intense investigation for decades but for most of this period, the research effort has rarely shifted to computational Intelligence (CI)-based practices [1]. The trend has changed vividly over the last few decades and power system optimization using various CI techniques has now become an immense field of research. Furthermore, the bio-inspired CI is a biologically motivated computational approach and algorithm to solve complex real-world problems to which mathematical or traditional modelling can be impractical for some reasons in that the processes might be too complex for mathematical reasoning, it might comprise of some uncertainties during the process, or the nature of the process might only be stochastic [2]. CI mainly comprises of three types of principles such as: fuzzy logic, neural networks and evolutionary computation [3].
Earlier, extensive efforts have been done for the development of several conventional optimization techniques using fuzzy logic, neural networks and evolutionary computations. Traditional optimization techniques such as Newton-Raphson method, linear programming, quadratic programming, dynamic programming and interior point methods were used extensively for the purpose of solving power system optimization problem [4]. However, these methods generally suffer from insecure algorithmic complexity, convergence and sensitivity to the initial search point [5].
During the past few years, several works have been realized on hybrid optimization approaches. In many cases, best results are obtained with this kind of approaches, especially on real-life problems [6]. At the beginning, cooperation was mainly realized between several CI methods. However, nowadays, more and more cooperation schemes between general CI method and exact approaches have been proposed. These strategies usually give good results because they are able to exploit simultaneously the advantages of both types of methods [7]. For example, it may allow to give quality guarantees to identified solutions.
It is interesting to mention that many of these CI techniques have had their roots in pure science and engineering-based fields [8]. However, there is a good prospective to explore various hybrid CI methods for solving power system optimization problems as well as their associated theories for future enhancement [9].
Generally, hybrid CI techniques are two or more techniques that operate collectively and balance each other in order to make a gainful synergy from their integration. Hybrid CI techniques perform an important role in enhancing the capability of searching space. However, the purpose of hybridization is to associate the benefits of each technique and produce a hybrid technique, while concurrently trying to reduce any considerable drawback. Overall, the consequence of hybrid methods can typically produce some developments either in terms of accuracy or computation time. Hence, this paper reviews current progresses in the domain of different algorithms’ hybridization.
Nowadays, power system plays a vital part towards the progress of numerous sectors of any country. Most of the problems related to power system have non-convex and non-linear fitness functions along with powerful inequality and equality constraints and different kinds of decision variables (integer, discrete and continuous) [10]. As present power systems turn out to be more complex, proper operation, planning and systematic control of such systems using old-fashioned methods face growing complications. CI techniques can be effective substitutes because of the capability to avoid local optima in order to solve power system optimization problems. In this survey, authors have reviewed journal articles based on the performance hybrid techniques used to solve optimization problems related to power system.
Apparently, studies related to hybrid bio-inspired CI techniques in power system optimization has increased considerably from the year 2009 up to 2018. Overall, the number of journal articles shows a rising trend. Moreover, researchers used PSO, GA and DE methods while performing hybridization. In the year 2017, the number of other bio-inspired hybrid techniques becomes more (16 articles) which shows the emergence of hybrid bio-inspired CI techniques like FA, BA, ABC etc. for power system optimization.
Fig. 1 shows the number of the publications (includes hybrid bio-inspired CI techniques) per year in power system starting from the year 2009 until April, 2018. These statistics give the authors motivation to carry out detail literature survey in this domain.
The contribution of this survey is that it gives readers an overall outlook regarding the hybrid bio-inspired CI techniques for power system optimization by creating a classification framework in this regard. To date, hybrid bio-inspired CI techniques have been applied by the researchers in different power system optimization problems. This survey analyses the latest journal articles on the hybrid bio-inspired CI in power system optimization towards a dual objectives: (a) to emphasize the performance of this hybrid bio-inspired CI techniques to solve traditional power system optimization problems and (b) to develop a bibliographic basis for upcoming research developments.
The remaining segments are structured as follows: the second section presents the research methodology of this survey, section 3 introduces the suggested classification framework for the performance of hybrid bio-inspired CI techniques in power system optimization, section 4 analyses the studied journal articles from various perspectives, section 5 discusses the research gaps followed by the future research directions and lastly, section 6 concludes the overall survey. The lists of abbreviations used in this survey are given in the Appendix.
Section snippets
Scope of survey
This survey has been carried out based on three main scopes: focused field of survey, focused application and searching methodology. Each of these are discussed as follows:
Classification of hybrid bio-inspired CI techniques in power system optimization
A classification framework is proposed in this survey in order to provide a systematic review of the available literatures on the hybrid bio-inspired optimization techniques for power system optimization (see Fig. 3).
As Fig. 3 shows, all of the power system optimization problems can be classified into nine different domains. They are: economic dispatch, optimal power flow, load forecasting, unit commitment, control, generator maintenance scheduling, distribution feeder reconfiguration, voltage
Surveyed literatures
Total 180 suitable articles are identified and classified according to defined methodology.
Summary of surveyed literatures
Here, Fig. 8 illustrates the number of journal articles published related to power system optimization by hybrid bio-inspired CI techniques. It is clear that, most of the hybrid CI techniques were applied in economic dispatch, optimal power flow and load forecasting problems in power system
Finally, Fig. 9 shows a list of 21 journal titles which have published more than one articles in the subject of hybrid bio-inspired CI techniques applied to power systems (total 138 articles). Among these are
Future research directions
The newest edition in the modern search capability-based CI research is hyperheuristics optimization. The word ‘hyper-heuristics’ was first introduced in 2001 by Burke et al. [223]. Hyper-heuristics are largely concerned with intelligently choosing the right heuristic or algorithm in a certain condition [224]. The crucial feature of hyper-heuristics is that they work on a heuristics search space rather than directly on a search space of problem solutions [225]. Current research trends and
Conclusions
The shortage of energy capitals, growing cost of power generation, load shedding, rising demand of power supply and environmental concerns have amplified the concern to enhance the overall performance of power systems. Hybrid bio-inspired CI techniques have gained much attention among power system engineers as well as research communities for solving the complex power system optimization problems. With the aim of providing bibliographic basis for upcoming research developments, authors have
Acknowledgements
The authors would like to acknowledge the Institute of Postgraduate Studies (IPS), Universiti Sains Malaysia for the USM Global Fellowship (Ref. USM.IPS/USMGF/2/2016) and the Ministry of Higher Education Malaysia Fundamental Research Grant Scheme (Grant no. FRGS/1/2017/203.PELECT.6071371) for the financial support.
Imran Rahman received BSc. Engineering from Department of Electrical and Electronic Engineering, Islamic University of Technology (IUT), Bangladesh in the year 2011 and MSc. (research) from Department of Fundamental and Applied Sciences, Universiti Teknologi PETRONAS (UTP), Bandar Seri Iskandar, Malaysia in the year 2016. He is currently pursuing PhD. from School of Electrical and Electronic Engineering, Universiti Sains Malaysia (USM). His current field of research is Computational
References (229)
- et al.
Application of evolutionary computation for rule discovery in stock algorithmic trading: a literature review
Appl. Soft Comput.
(2015) - et al.
Particle swarm optimization: hybridization perspectives and experimental illustrations
Appl. Math. Comput.
(2011) - et al.
Hybrid human skin detection using neural network and k-means clustering technique
Appl. Soft Comput.
(2015) - et al.
A Q-learning-based multi-agent system for data classification
Appl. Soft Comput.
(2017) - et al.
Review of recent trends in optimization techniques for plug-in hybrid, and electric vehicle charging infrastructures
Renew. Sustain. Energy Rev.
(2016) - et al.
Memetic algorithms and memetic computing optimization: a literature review
Swarm Evol. Comput.
(2012) - et al.
A new reinforcement learning-based memetic particle swarm optimizer
Appl. Soft Comput.
(2016) - et al.
Hybrid weighted probabilistic neural network and biogeography based optimization for dynamic economic dispatch of integrated multiple-fuel and wind power plants
Int. J. Electr. Power Energy Syst.
(2016) Application of hybrid computational intelligence models in short-term bus load forecasting
Expert Syst. Appl.
(2016)- et al.
A novel hybrid approach for predicting wind farm power production based on wavelet transform, hybrid neural networks and imperialist competitive algorithm
Energy Convers. Manage.
(2016)
A hybrid model based on data preprocessing for electrical power forecasting
Int. J. Electr. Power Energy Syst.
A new hybrid model optimized by an intelligent optimization algorithm for wind speed forecasting
Energy Convers. Manage.
Electricity prices forecasting by a hybrid evolutionary-adaptive methodology
Energy Convers. Manage.
A hybrid annual power load forecasting model based on generalized regression neural network with fruit fly optimization algorithm
Knowl.-Based Syst.
A novel modified hybrid PSOGSA based on fuzzy logic for non-convex economic dispatch problem with valve-point effect
Int. J. Electr. Power Energy Syst.
A new fuzzy adaptive hybrid particle swarm optimization algorithm for non-linear, non-smooth and non-convex economic dispatch problem
Appl. Energy
A fuzzy adaptive chaotic ant swarm optimization for economic dispatch
Int. J. Electr. Power Energy Syst.
A hybrid FCASO-SQP method for solving the economic dispatch problems with valve-point effects
Energy
A novel hybrid particle swarm optimization for economic dispatch with valve-point loading effects
Energy Convers. Manage.
Optimal power flow under both normal and contingent operation conditions using the hybrid fuzzy particle swarm optimisation and Nelder-Mead algorithm (HFPSO-NM)
Appl. Soft Comput. J.
Optimal power flow by a fuzzy based hybrid particle swarm optimization approach
Electr. Power Syst. Res.
Novel hybrid fuzzy-Bees algorithm for optimal feeder multi-objective reconfiguration by considering multiple-distributed generation
Energy
A hybrid harmony search algorithm with differential evolution for day-ahead scheduling problem of a microgrid with consideration of power flow constraints
Appl. Energy
A novel hybrid particle swarm optimization and gravitational search algorithm for solving economic emission load dispatch problems with various practical constraints
Int. J. Electr. Power Energy Syst.
A novel hybrid optimizer for solving Economic Load Dispatch problem
Int. J. Electr. Power Energy Syst.
Performance assessment of PSO, de and hybrid PSO-DE algorithms when applied to the dispatch of generation and demand
Int. J. Electr. Power Energy Syst.
Maximum loadability limit of power system using hybrid differential evolution with particle swarm optimization
Int. J. Electr. Power Energy Syst.
Economic dispatch using hybrid grey wolf optimizer
Energy
The combined economic environmental dispatch using new hybrid metaheuristic
Energy
A new hybrid algorithm for optimal reactive power dispatch problem with discrete and continuous control variables
Appl. Soft Comput. J.
Application of imperialist competitive algorithm with its modified techniques for multi-objective optimal power flow problem: a comparative study
Inf. Sci.
A novel approach to multi-objective optimal power flow by a new hybrid optimization algorithm considering generator constraints and multi-fuel type
Energy
Hybrid: particle swarm optimization-genetic algorithm and particle swarm optimization-shuffled frog leaping algorithm for long-term generator maintenance scheduling
Int. J. Electr. Power Energy Syst.
Efficient hybrid optimization approach for emission constrained economic dispatch with nonsmooth cost curves
Int. J. Electr. Power Energy Syst.
A hybrid differential evolution algorithm based on particle swarm optimization for nonconvex economic dispatch problems
Appl. Soft Compu. J.
An effortless hybrid method to solve economic load dispatch problem in power systems
Energy Convers. Manage.
A hybrid GA-PS-SQP method to solve power system valve-point economic dispatch problems
Appl. Energ.
A hybrid artificial bee colony assisted differential evolution algorithm for optimal reactive power flow
Int. J. Electr. Power Energy Syst.
Hybrid differential evolution with biogeography-based optimization algorithm for solution of economic emission load dispatch problems
Expert Syst. Appl.
A hybrid genetic algorithm and bacterial foraging approach for dynamic economic dispatch problem
Int. J. Electr. Power Energy Syst.
A tabu search based hybrid optimization approach for a fuzzy modelled unit commitment problem
Electr. Power Syst. Res.
Generator maintenance scheduling in power systems using metaheuristic-based hybrid approaches
Electr. Power Syst. Res.
Maximum loadability of power systems using hybrid particle swarm optimization
Electr. Power Syst. Res.
Hybridizing exact methods and metaheuristics: a taxonomy
Eur. J. Oper. Res.
A holistic review on optimization strategies for combined economic emission dispatch problem
Renew. Sustain. Energy Rev.
A comprehensive study of practical economic dispatch problems by a new hybrid evolutionary algorithm
Appl. Soft Comput.
Hybrid PSO-SQP for economic dispatch with valve-point effect
Electr. Power Syst. Res.
Economic dispatch using particle swarm optimization with bacterial foraging effect
Int. J. Electr. Power Energy Syst.
Towards reactive power dispatch within a wind farm using hybrid PSO
Int. J. Electr. Power Energy Syst.
Hybrid bare-bones PSO for dynamic economic dispatch with valve-point effects
Appl. Soft Comput. J.
Cited by (49)
Optimal capacitor bank placement and sizing using particle swarm optimization for power loss minimization in distribution network
2024, Journal of Engineering Research (Kuwait)Emperor penguin optimizer: A comprehensive review based on state-of-the-art meta-heuristic algorithms
2023, Alexandria Engineering JournalA novel multi-objective framework for harmonic power market including plug-in electric vehicles as harmonic compensators using a new hybrid gray wolf-whale-differential evolution optimization
2022, Journal of Energy StorageCitation Excerpt :For instance, to solve the ORPD and defeat long computational time, the hybrid GWO-PSO has been presented in [70] for diminishing the power loss and the voltage deviation. A summary of the important hybrid bio-inspired computational intelligence techniques has been employed for power system optimization problems, such as economic dispatch, unit commitment, optimal power flow, load forecasting, etc. in [71]. In order to enhance the convergence characteristics of the WOA, The hybrid of the WOA and the sine cosine algorithm has been applied to improve the voltage profile and find the optimal allocation of the distributed generators and DSTATCOMs.
Differential evolution: A recent review based on state-of-the-art works
2022, Alexandria Engineering Journal
Imran Rahman received BSc. Engineering from Department of Electrical and Electronic Engineering, Islamic University of Technology (IUT), Bangladesh in the year 2011 and MSc. (research) from Department of Fundamental and Applied Sciences, Universiti Teknologi PETRONAS (UTP), Bandar Seri Iskandar, Malaysia in the year 2016. He is currently pursuing PhD. from School of Electrical and Electronic Engineering, Universiti Sains Malaysia (USM). His current field of research is Computational Intelligence. Imran Rahman is a recipient of USM Global Fellowship (USM.IPS/USMGF/2/2016). Google Scholar: https://scholar.google.com/citations?user=kEYajBIAAAAJ.
Junita Mohamad-Saleh received her B.Sc (in Computer Engineering) degree from the Case Western Reserve University, USA in 1994, the M.Sc. degree from the University of Sheffield, UK in 1996 and the Ph.D. degree from the University of Leeds, UK in 2002. She is currently an Associate Professor in the School of Electrical & Electronic Engineering, Universiti Sains Malaysia. Her research interests include computational intelligence, tomographic & medical imaging and soft computing. Google Scholar: https://scholar.google.com/citations?user=xdmhr5EAAAAJ.