Correlated Equilibrium Q-Learning For Multi-Objective Reactive Power Optimization Considering Grid Side Carbon Emissions

In order to meet the development trend of smart grid, the correlated equilibrium Q-learning (CEQ) algorithm is proposed for multi-regional reactive power optimization. Meanwhile, in response to the national strategy of low carbon environmental protection, CO2 emission is considered as one of the control objectives in reactive power optimization. In this paper, CEQ algorithm is adopted to allocate the control variables rationally, through the correlated equilibrium game among areas and information communication and sharing to achieve multi-regional reactive power optimization, which solves the limited information-sharing mechanisms and curse of dimensionality problem effectively. Simulation of the IEEE 9-bus system indicates that through the combine of pre-learning and online learning CEQ algorithm solves the multi-regional collaborative reactive power optimization quickly and rationally.