MULTI-OBJECTIVE SCALE OPTIMIZATION OF POWER SYSTEM ENERGY STORAGE BASED ON EFCPPO ALGORITHM

Engineering notes

Engineering notes will be added by the Power for Solar editorial team.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为光伏效率、钙钛矿太阳能电池、储能技术、太阳能热利用、BIPV、并网技术等高价值论文补充中文说明。

Original abstract

With the increasing penetration rate of renewable energy and the growing complexity of multi-energy coupled systems, power system energy storage dispatch faces challenges in terms of economy, environmental protection, and multi-timescale collaborative optimization.To achieve multi-objective and efficient dispatch of energy storage devices in integrated energy systems, this paper proposes an intelligent decision-making framework based on an exploration fallback clip proximal policy optimization algorithm.The new method introduces an exploration fallback mechanism and a hierarchical reinforcement learning structure, and achieves collaborative updating of policy and value through a dual network, constructing a collaborative dispatch mechanism of upper-level macro-planning and lower-level execution.The research results show that the new algorithm exhibits superior performance in both weekday and holiday scenarios.Its peak daily load dispatch is reduced by approximately 200 kW/h-210 kW/h compared to traditional multi-objective optimization methods, with an average decrease in operating costs of 3.1%-5.6%and pollution costs of 3.8%-8.3%.Simultaneously, by coordinating load sharing among electric boilers, gas-fired boilers, and combined heat and power units during off-peak hours, the algorithm effectively reduces the system's total energy consumption and carbon emission intensity.Therefore, the new algorithm demonstrates significant advantages in improving the economic efficiency and environmental friendliness of power system energy storage dispatch.This provides a feasible solution for multi-energy coordinated dispatch under high-proportion renewable energy integration.

Links and sources

• PDF from original source

Comments