MUET logo

Reinforcement Learning-Adaptive Hybrid Metaheuristic for Optimal Distributed Generation and Shunt Capacitor Placement with Embedded V2G Dispatch in Distribution Networks

Authors

  • Abdul Rehman Imtiaz

    Department of Electrical Engineering and Technology, Government College University, Faisalabad, 38000, Pakistan
    Author

  • Umer Ijaz

    Department of Electrical Engineering and Technology, Government College University, Faisalabad, 38000, Pakistan
    Author

  • Muhammad Farhan

    Department of Electrical Engineering and Technology, Government College University, Faisalabad, 38000, Pakistan
    Author

DOI:

https://doi.org/10.22581/0844

Keywords:

Adaptive Operator Selection , Distributed Generation Placement, Hybrid GOA-GWO, Multi-algorithm Benchmarking, Non-parametric Statistical Validation, Vehicle to Grid Integration

Abstract

This paper benchmarks six metaheuristics—including a reinforcement-learning- adaptive Grasshopper– Grey Wolf optimiser (RL-GOA-GWO) with Q-learning- based adaptive operator selection—and a four-layer multi-layer perceptron (MLP) surrogate for joint placement of distributed generation (DG) and shunt capacitor (SC)   banks   with   embedded   rule-based   vehicle-to-grid   (V2G)   dispatch.   A   six- objective weighted-sum formulation is evaluated on five systems (IEEE 33, 69, 123-bus   balanced   equivalent,   MV   Oberrhein   179,   Custom   567-bus)   under identical budgets (30 agents, 100 iterations, n=5 runs). The RL-adaptive advantage is topology-dependent: marginal on small radial feeders but producing a large effect on the rugged IEEE-123 landscape (mean improvement 6.8%, Cohen’s d= − 1.12, 95% confidence interval (CI) [−2.43,0.19]). Particle Swarm Optimization (PSO)   is   competitive   throughout,   consistent   with   No-Free-Lunch   theory. Friedman rank tests and Cohen’s d with 95% CIs provide exploratory validation; confirmatory studies with n≥25 are recommended.

Downloads

References

[1] M. Ahmadi Kamarposhti, R. Ghandour, M. Abdel-Atyet al., “Optimizing capacitor bank placement in distribution networks using a multi-objective particle swarm optimization approach for energy efficiency and cost reduction,” Scientific Reports, vol. 15, no. 1, p. 12332, 2025.

[2] A. S. Bouhouras, D. Kothona, P. A. Gkaidatziset al., “Distribution network energy loss reduction under EV charging schedule,” Int. J. Energy Res., vol. 46, no. 6, pp. 8256–8270, 2022.

[3] H. Byeon, W. Alghamdi, M. Evinet al., “A novel swarm intelligence-based approach for solving optimal power flow problems in modern power systems,” Results Control Optim., vol. 19, p. 100555, 2025.

[4] L. Da Costa, A. Fialho, M. Schoenaueret al., “Adaptive operator selection with dynamic multi-armed bandits,” in Proc. PPSN X, LNCS, vol. 5199, Springer, 2008, pp. 913–922, doi: 10.1007/978-3-540-87700-4_91.

[5] E. E. Che, K. R. Abeng, C. D. Iwehet al., “The impact of integrating variable renewable energy sources into grid-connected power systems: Challenges, mitigation strategies, and prospects,” Energies, vol. 18, no. 3, p. 689, 2025.

[6] A. Fialho, L. Da Costa, M. Schoenaueret al., “Analyzing bandit-based adaptive operator selection mechanisms,” in Proc. EA 2009, LNCS, vol. 5975, Springer, 2010, pp. 110–121, doi: 10.1007/978-3-642-14156-0_10.

[7] G. Gurumoorthi, S. Senthilkumar, G. Karthikeyanet al., “A hybrid deep learning approach to solve optimal power flow problem in hybrid renewable energy systems,” Scientific Reports, vol. 14, no. 1, p. 19377, 2024.

[8] T. Jayabarathi, T. Raghunathan, N. Mithulananthanet al., “Enhancement of distribution system performance with reconfiguration, distributed generation and capacitor bank deployment,” Heliyon, vol. 10, no. 7, 2024.

[9] Y. Jin, M. A. Acquah, M. Seoet al., “Optimal siting and sizing of EV charging station using stochastic power flow analysis for voltage stability,” IEEE Trans. Transp. Electrific., vol. 10, no. 1, pp. 777–794, 2023.

[10] S. S. Jodeiri-Seyedian, A. Fakour, R. Nourollahiet al., “Nodal pricing of renewable-oriented distribution network in the presence of EV charging stations: A hybrid robust/stochastic optimization,” J. Energy Storage, vol. 70, p. 107943, 2023.

[11] J. Kennedy and R. Eberhart, “Particle swarm optimization,” Proc. IEEE ICNN, vol. 4, 1995, pp. 1942–1948, doi: 10.1109/ICNN.1995.488968.

[12] Z. Kilwein, J. Jalving, M. Eydenberget al., “Optimization with neural network feasibility surrogates: Formulations and application to security-constrained optimal power flow,” Energies, vol. 16, no. 16, p. 5913, 2023.

[13] B. A. Kumar, B. Jyothi, A. R. Singh et al., “Hybrid genetic algorithm–simulated annealing based electric vehicle charging station placement for optimizing distribution network resilience,” Scientific Reports, vol. 14, no. 1, p. 7637, 2024.

[14] B. V. Kumar and A. Farhan, “Energy loss reduction by capacitor placement integrated with EVCS in distribution systems,” in Proc. IEEE ICEPES, 2024, pp. 1–6.

[15] B. V. Kumar and A. Farhan, “Optimal integration of EV charging stations and capacitors for net present value maximization in distribution network,” IEEE Latin Amer. Trans., vol. 23, no. 3, pp. 239–250, 2025.

[16] J. Meiers and G. Frey, “A case study of the use of smart EV charging for peak shaving in local area grids,” Energies, vol. 17, no. 1, 2024, doi: 10.3390/en17010047.

[17] M. Mersha, K. Lam, J. Wood et al., “Explainable artificial intelligence: A survey of needs, techniques, applications, and future direction,” Neurocomputing, vol. 599, p. 128111, 2024.

[18] S. Mirjalili and A. Lewis, “The whale optimization algorithm,” Adv. Eng. Softw., vol. 95, pp. 51–67, 2016.

[19] S. Mirjalili, S. M. Mirjalili, and A. Lewis, “Grey wolf optimizer,” Adv. Eng. Softw., vol. 69, pp. 46–61, 2014.

[20] S. Mohammadi, V. H. Bui, W. Su et al., “Surrogate modeling for solving OPF: A review,” Sustainability, vol. 16, no. 22, p. 9851, 2024.

[21] S. Panda, I. S. Samanta, B. Sahooet al., “Comprehensive framework for smart residential demand side management with electric vehicle integration and advanced optimization techniques,” Scientific Reports, vol. 15, no. 1, p. 9948, 2025.

[22] S. Sahay, S. Biswal, G. Shankar et al., “Optimized placement of distributed generators, capacitors, and EV charging stations in reconfigured radial distribution networks using enhanced artificial hummingbird algorithm,” Scientific Reports, vol. 15, p. 11144, 2025.

[23] S. Saremi, S. Mirjalili, and A. Lewis, “Grasshopper optimization algorithm: Theory and application,” Adv. Eng. Softw., vol. 105, pp. 30–47, 2017.

[24] A. Selim, S. Kamel, A. A. Mohamed et al., “Placement and sizing of distributed generations and shunt capacitors in radial distribution systems using hybrid optimization technique,” Electr.Power Compon.Syst., vol. 51, no. 5, pp. 421–437, 2023.

[25] H. Singh, S. Saxena, H. Sharma et al., “An integrative TLBO-driven hybrid grey wolf optimizer for the efficient resolution of multi-dimensional, nonlinear engineering problems,” Scientific Reports, vol. 15, no. 1, p. 11205, 2025.

[26] L. Thurner, A. Scheidler, F. Schäferet al., “pandapower—An open-source Python tool for convenient modeling, analysis, and optimization of electric power systems,” IEEE Trans. Power Syst., vol. 33, no. 6, pp. 6510–6521, 2018.

[27] S. Wang, Z. Li, and M. J. Golkar, “Optimum placement of distributed generation resources, capacitors and charging stations with a developed competitive algorithm,” Heliyon, vol. 10, no. 4, 2024.

[28] A. Zabihi and M. Parhamfar, “Decentralized energy solutions: The impact of smart grid-enabled EV charging stations,” Heliyon, 2025.

[29] Nawaz A., Wang H, Yang H et al. Farhan, “Risk-constrained probabilistic coordination in coupled transmission and distribution system”. Electric Power Systems Research,”228:110005, 2024.

[30] Nawaz A., Altamimi A., Javid Z, et al. Farhan, “ELLS–NSBA three-stage framework for optimal DG/SC placement and EV integration in distribution networks”. Scientific Reports,”16(1), 2026a.

Published

2026-10-01

Issue

Vol. 45 No. 4 (2026): October Issue

Section

Articles

License

Copyright (c) 2026 Mehran University Research Journal of Engineering and Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite

Reinforcement Learning-Adaptive Hybrid Metaheuristic for Optimal Distributed Generation and Shunt Capacitor Placement with Embedded V2G Dispatch in Distribution Networks. (2026). Mehran University Research Journal of Engineering and Technology, 45(4), 183-194. https://doi.org/10.22581/0844

Similar Articles

41-50 of 71

You may also start an advanced similarity search for this article.