Automatic Generation Control for Distributed Multi-Region Interconnected Power System with Function Approximation

Solving the energy crisis and environmental pollution requires large-scale access to distributed popularization of electric vehicles. However, sources loads are characterized by randomness, intermittence difficulty in accurate prediction, which bring great challenges security, stability economic operation power system. Therefore, this paper explores an integrated system model that contains a large amount new combined cooling heating (CCHP) from perspective automatic generation control (AGC). Then, gradient Q(?,?) [GQ (?,?)] algorithm for multi-region interconnected is proposed solve it. The integrates unified mixed sampling parameter linear function approximation on basis Q(?) with characteristics interactive collaboration self-learning. GQ (?,?) avoids disadvantages action spaces required traditional reinforcement learning, so as obtain optimal cooperative control. Under such control, autonomy each region can be achieved, strong stochastic disturbance caused grid resolved. In paper, improved IEEE two-area load frequency (LFC) incorporating CCHP used simulation analysis. Results show compared other algorithms, has performance, fast convergence speed good robustness, connection energy.