Optimal Electricity Decomposition Method for New Energy Grid-Connected System based on Q-Learning Algorithm

Since the traditional contract power decomposition in the power trading market is difficult to meet the needs of new energy participating in the system operation, an optimal decomposition method of contract power based on the Q-learning algorithm under the uncertainty of new energy power is proposed. Considering the uncertainty of new energy power output, an optimization model to minimize the power purchase cost of the power grid is established. Given the uncertainty of the newly added electricity and the quotation in the market transaction, it is proposed to use the enhanced Q-learning algorithm to obtain the contract decomposition of electricity. According to the actual annual contract electricity data, the monthly optimal decomposition results of contract electricity are obtained, which verifies the economy and effectiveness of the optimal electricity decomposition method.