Active-reactive power collaborative optimization model of electrical interconnection system based on deep learning under the goal of “carbon neutrality”

Abstract

With the goal of carbon neutralization put forward, new energy units have gradually become the main power supply, and its volatility has brought great challenges to the control and optimization of the system, especially the distribution network. In order to solve the reactive power problem caused by the high proportion of renewable energy connected to the distribution network, a source network load storage centralized optimal dispatching model considering reactive power optimization and multi energy collaborative interaction is proposed. The model aims at the optimal operation cost, minimum network loss and minimum carbon emission of the multi energy system, and considers reactive power compensation, energy storage regulation and energy conversion, so as to realize the safe and low-carbon economic dispatching of the electrical interconnection system. The switching capacity of the discrete reactive power compensation device is linearized, and the model is transformed into a mixed integer second-order cone programming problem for solution. The simulation results show that the proposed method can effectively compensate the reactive power required by the wind turbine parallel network, coordinate the energy interaction between electricity and gas, and improve the stability and flexibility of the distribution network after large-scale renewable energy access, According to the charging and discharging power and charge state, and the automatic adjustment of the gears of on load voltage regulating transformer and compensation capacitor bank, this paper shows that the system has safe and stable operation performance.