Optimal Scheduling of Biomass-Hybrid Microgrids with Energy Storage: An LSTM-PMOEVO Framework for Uncertain Environments

Abstract

The microgrid is a small-scale, independent power system that plays a crucial role in the transition to carbon-neutral energy systems. Combined heat and power (CHP) systems with energy storage reduce energy waste within microgrids, enhancing energy utilization efficiency. The key challenge for a microgrid integrated with a combined heat and power system is determining the optimal configuration and operation duration under different scenarios to meet users’ electricity and heat demands while minimizing both economic and environmental costs. Thus, this paper presents a bi-objective mathematical model to solve the optimal scheduling problem of the microgrid. The Long Short-Term Memory–Parallel Multi-Objective Energy Valley Optimizer (LSTM-PMOEVO) framework incorporates energy load prediction using LSTM and scheduling planning solved via PMOEVO. These strategies address the challenges posed by unpredictable energy load fluctuations and the complexity of solving such systems. Finally, a public dataset was utilized for the experiments to verify the performance of the proposed algorithm. Comparisons and discussions show that the proposed optimization strategies significantly improve the performance of PMOEVO, demonstrating marked advantages over six classical algorithms. In conclusion, the PMOEVO developed in this paper performs excellently in solving the Scheduling Problem of Biomass-Hybrid microgrids with energy storage considering uncertainty. The work presented in this paper provides a new solution framework for the microgrid-scheduling problem considering uncertainty. In future research, this solution framework will be further advanced for application in real-world scenarios.