Enhancing grid integration of renewable energy sources for micro grid stability using forecasting and optimal dispatch strategies

S. Senthil Kumar, C. Srinivasan and S. Balavignesh

Energy, 2025, vol. 322, issue C

Abstract: The intermittent nature of Renewable Energy Sources (RES) presents a major challenge to grid stability. Unlike conventional energy sources such as fossil fuels, RES generation is influenced by factors like weather conditions and time of day, leading to unpredictable fluctuations. This unpredictability can cause imbalances between supply and demand, potentially compromising grid stability and reliability. To address this issue, this research proposes a framework for the optimal management of microgrids, consisting of three key stages: forecasting, optimal dispatch, and management planning. The framework begins with power generation and load forecasts using the Extended Neural Basis Expansion Analysis (ExN-BEATS) model. The forecasting results serve as inputs for an optimization model that incorporates decision variables for generating units, energy storage system (ESS) charge/discharge plans, and power exchange. The optimization model aims to minimize operating costs while respecting technical and operational constraints. The Mutated Bald Eagle Optimization (MBEO) algorithm, inspired by the hunting behavior of eagles, is introduced to efficiently optimize the control of generators, ESS, and power exchange. The load forecasting analysis demonstrated that the ExN-BEATS model outperformed existing models, achieving an MAE of 5.3 kW, MAPE of 1.5 %, and RMSE of 6.9 kW, making it the most accurate for predicting load consumption. Furthermore, three load dispatch cases were analyzed, including the integration of EVs and ESS. The addition of ESS shifted the grid's peak load to off-peak hours, improving grid stability. In Cases 2 and 3, coordinated EV charging and discharging led to further cost reductions. To evaluate the optimization performance, Hypervolume (HV) was used as the primary metric, and the MBEO algorithm achieved the highest HV score of 0.9635, indicating superior trade-offs between objectives. Overall, the proposed framework, combining ExN-BEATS for forecasting and MBEO for optimal dispatch, demonstrates exceptional accuracy, efficiency, and cost-effectiveness in managing microgrid resources, highlighting the practical benefits of advanced forecasting and optimization techniques for real-world applications.

Keywords: Renewable energy sources; Optimization; Machine learning; Optimal dispatch; Microgrid (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225012149
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:322:y:2025:i:c:s0360544225012149

DOI: 10.1016/j.energy.2025.135572

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().