人工情感Q学习的互联电网自动发电控制算法
Artificial emotionnal Q-learning for automatic generation control of interconnected power grids

对互联电网中自动发电控制AGC中控制策略进行改进, 设计了人工智能中的人工心理学和人工智能中的 机器学习结合的控制策略.分别对Q学习算法和Q(λ)学习算法进行改进,设计了具有人工情感的智能体.提出了人 工情感Q学习算法和人工情感Q(λ)学习算法. 且将人工情感分别作用于Q学习算法和Q(λ)学习算法中的输出动作、 学习率和奖励函数. 最后在IEEE标准两区域和南方电网四区域的互联电网Simulink模型中进行数值仿真. 绘制并统 计了控制性能指标、区域控制误差和频率偏差的值.从仿真结果看,所提人工情感Q学习算法和人工情感Q(λ)学习 算法控制效果优于原有Q学习算法、 Q(λ)学习算法、 R(λ)算法、 Sarsa算法、 Sarsa(λ)算法和PID控制算法, 该数值仿 真结果验证了所提算法的可行性和有效性.
Arti?cial psychology and machine learning are combined in the automatic generation control strategy of interconnected power grids. An agent obtaining arti?cial emotion is designed, and the Q-learning and Q(λ)-learning algo- rithms are improved by arti?cial emotion. The novel arti?cial emotional Q-learning and arti?cial emotional Q(λ)-learning algorithms are proposed. The arti?cial emotion is respectively applied to the selection of output action, learning rate and reward function in Q-learning and Q(λ)-learning, and then simulated on the standard IEEE two-area model and the China Southern Power Grid four-area model. The control performance standard, area control error and frequency deviation are ?gured. Simulation results verify the feasibility and effectiveness of the proposed algorithms and their superiority to the Q-learning, Q(λ)-learning, R(λ), Sarsa, Sarsa(λ) and PID algorithms.