Optimal Scheduling Strategy of Wind–Solar–Thermal-Storage Power Energy Based on CGAN and Dynamic Line–Rated Power

Abstract

This paper introduces a new way to plan and manage the use of wind and solar power, along with traditional thermal power (TP) and batteries, to get the most environmental and economic benefits. It uses a special kind of artificial intelligence, called conditional generative adversarial networks (CGAN), to predict how much power wind and solar sources will produce. Subsequently, it takes into account the dynamic line–rated power (DLRP) in order to determine the dynamic transmission capacity of lines associated with wind and solar power generation. The primary objectives are to reduce the operating costs of TP plants, maximize the utilization of wind and solar energy, minimize power deviations in electricity transmission, and enhance revenue from electricity transmission. To solve this complex problem, the paper uses a smart method to simplify the model, making it possible to find solutions with CPLEX. Tests on a small network with six nodes show that this approach not only saves money but also makes better use of clean energy sources.