In the realm of energy research, a team from the School of Electrical Engineering at Wuhan University, led by Jin Ye, Lingmei Wang, Shujian Zhang, and Haihang Wu, has made significant strides in optimizing the scheduling of combined electricity-heat systems. Their work, published in the journal Applied Energy, addresses the growing challenge of integrating renewable energy sources into these systems while managing multiple uncertainties.
The researchers propose an intelligent scheduling method that leverages an improved Dual-Delay Deep Deterministic Policy Gradient (PVTD3) algorithm. This method introduces a penalty term for grid power purchase variations, aiming to optimize system performance. The study evaluates the algorithm under three typical scenarios with varying levels of renewable energy penetration: 10%, 20%, and 30%.
The results are promising. The PVTD3 algorithm reduces the system’s comprehensive cost by 6.93%, 12.68%, and 13.59% respectively compared to the traditional TD3 algorithm. It also decreases the average fluctuation amplitude of grid power purchases by 12.8%. In terms of energy storage management, the algorithm reduces the end-time state values of low-temperature thermal storage tanks by 7.67-17.67 units while keeping high-temperature tanks within the 3.59-4.25 safety operating range.
The practical applications for the energy sector are significant. The proposed algorithm not only improves economic efficiency and grid stability but also demonstrates superior sustainable scheduling capabilities in energy storage device management. This could be particularly beneficial for energy providers looking to integrate more renewable energy sources into their systems while maintaining stable and cost-effective operations.
The research, titled “Optimized scheduling of electricity-heat cooperative system considering wind energy consumption and peak shaving and valley filling,” was published in the journal Applied Energy, volume 333, in March 2023.
This article is based on research available at arXiv.