Integrated Explainable Forecasting and Metaheuristic PI Optimization for LFC/AGC

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 16 | 02 | Page :
    By

    Neha Khurana,

  • Chetan Yadav,

  • Gopal Krishan,

  • Rajesh Kumar,

  1. Associate Professor, Department of University Institute of Engineering & Technology, Maharshi Dayanand University,Rohtak, Haryana, India
  2. Manager, Department of Electrical, Building Vertical, RITES Limited, Gurugram, Haryana, India
  3. Associate Professor, IIMT College of Engineering, Greater Noida, Uttar Pradesh, India
  4. Assistant Professor, Department of Artificial Intelligence & Data Science, Prestige Institute of Engineering Management & Research, Indore, Madhya Pradesh, India

Abstract

Since the last decade world has seen a paradigm shift towards alternate sources of energy, due to significant increase in population and ever-rising demand. However, the traditional systems were not designed to cope with these alternate sources and on the other hand these systems are posed with the challenges of efficiency and intermittency. So, it is inevitable that we need to design a system wherein forecasting data has to be studied followed by optimization of AGC for frequency regulation. The forecasting, however, could be more accurate if we consider net load forecast in case of renewable energy sources. The present work presents a framework for accurate net load forecasting backed with explainable ai and confirming which variables are playing a crucial role for prediction. For this real time dataset from NASA for temporal dataset , grid India for PSP and VRE dataset surrounding the region of  Bhiwani – Hisar – Jhajjar . To overcome the issues posed with the black box ensemble method , Explainability is employed. The explainability SHAP is used for analyzing deeply local and global feature contribution, while individual prediction is performed using  LIME based explanations. Then meta heuristic algorithms were analyzed using two area reheat thermal power systems and following algorithm were analyzed and compared ALA, PSO and GA. Considering the attributes peak frequency deviation , settling time, tie-line power fluctuations and integral error indices. From the results it is evident that when the settling time was considered PSO performed the best and had faster response, however improved damping of inter area oscillation is provided by ALA, and when we are looking for balance GA outperformed others.

Keywords: Net Load Forecasting, Explainable Artificial Intelligence, Renewable Energy Integration, Weather Informed Forecasting, SHAP Explainability, Indian Power Grid

How to cite this article:
Neha Khurana, Chetan Yadav, Gopal Krishan, Rajesh Kumar. Integrated Explainable Forecasting and Metaheuristic PI Optimization for LFC/AGC. Trends in Electrical Engineering. 2026; 16(02):-.
How to cite this URL:
Neha Khurana, Chetan Yadav, Gopal Krishan, Rajesh Kumar. Integrated Explainable Forecasting and Metaheuristic PI Optimization for LFC/AGC. Trends in Electrical Engineering. 2026; 16(02):-. Available from: https://journals.stmjournals.com/tee/article=2026/view=246108


References

  1. Nti IK, Teimeh M, Nyarko-Boateng O, Adekoya AF. Electricity load forecasting: a systematic review. Journal of Electrical Systems and Information Technology. 2020 Sep 9;7(1):13.
  2. Kuster C, Rezgui Y, Mourshed M. Electrical load forecasting models: A critical systematic review. Sustainable cities and society. 2017 Nov 1;35:257-70.
  3. Vanting NB, Ma Z, Jørgensen BN. A scoping review of deep neural networks for electric load forecasting. Energy Informatics. 2021 Sep 24;4(Suppl 2):49.
  4. Wang H, Zhang N, Du E, Yan J, Han S, Liu Y. A comprehensive review for wind, solar, and electrical load forecasting methods. Global Energy Interconnection. 2022 Feb 1;5(1):9-30.
  5. Alfares HK, Nazeeruddin M. Electric load forecasting: literature survey and classification of methods. International journal of systems science. 2002 Jan 1;33(1):23-34.
  6. Beichter M, Phipps K, Frysztacki MM, Mikut R, Hagenmeyer V, Ludwig N. Net load forecasting using different aggregation levels. Energy Informatics. 2022 Sep 1;5(Suppl 1):19.
  7. Babu VS, Sundar KS. Design of fractional order PID controller for AGC loop in a deregulated power system with RFB and IPFC units. J Eng Sci Technol. 2019 Apr;14(2):763-83.
  8. Dahiya P, Mukhija P, Saxena AR, Arya Y. Comparative performance investigation of optimal controller for AGC of electric power generating systems. automatika. 2016 Oct 1;57(4):902-21.
  9. Shayeghi H, Shayanfar HA, Jalili A. LFC design of a deregulated power system with TCPS using PSO. International Journal of Electrical and Electronics Engineering. 2009;3(10):632-40.
  10. Falehi AD. Optimal design of fuzzy-AGC based on PSO &  RCGA to improve dynamic stability of interconnected multi area power systems. International Journal of Automation and Computing. 2020 Aug;17(4):599-609.
  11. Farook S, Sangameswara P. Regular paper Feasible AGC Controllers to Optimize LFC Regulation in Deregulated Power System Using Evolutionary Hybrid Genetic Firefly Algorithm. J. Electrical Systems. 2012;8(4):459-71.
  12. Dash R, Reddy KJ, Mohapatra B, Bajaj M, Zaitsev I. An approach for load frequency control enhancement in two-area hydro-wind power systems using LSTM+ GA-PID controller with augmented lagrangian methods. Scientific Reports. 2025 Jan 8;15(1):1307.
  13. Khurana N, Yadav C, Krishan G, Kumar R. Explainable AI Framework for Net-Load Forecasting in Renewable-Rich Indian Grids. In2026 3rd International Conference on Advancements and Key Challenges in Green Energy and Computing (AKGEC) 2026 Feb 26 (pp. 1-6). IEEE.
Ahead of Print Subscription Review Article
Volume 16
02
Received 24/04/2026
Accepted 03/06/2026
Published 05/06/2026
Publication Time 42 Days
1

Login


My IP

PlumX Metrics