Automatic Generation Control Strategy Based on Deep Forest

As the scale of power system continues to expand and energy situation changes dramatically, existing automatic generation control (AGC) strategy needs be optimized improved. The current grid AGC mainly adopts closed-loop PI control. By learning an excellent data set that incorporates characteristics DFT control, this paper proposes a real-time based on deep forest network. selects controller with better performance in each assessment period as for cycle deviation regulation studies. Simulation results show can achieve lower number actions outperform any learned strategies.