基于协同一致性迁移Q学习算法的虚拟发电部落AGC功率动态分配

Collaborative Consensus Transfer Q-learning Based Dynamic Generation Dispatch of Automatic Generation Control With Virtual Generation Tribe

为适应智能电网分散自治的发展趋势,文中在虚拟发电部落控制框架下,提出了一致性迁移Q学习的AGC功率动态分配方法。通过构建两层的功率分配模式,有效解决了机组规模较大导致的"维数灾难"问题。在每个部落与其相邻部落进行值函数矩阵的交互一致性计算后,部落领导者能自组织地协同各个部落的发电功率,从而达到"分散自治,集中协调"的效果。在引入迁移学习后,算法能有效地利用历史优化信息进行快速的功率动态分配优化,以满足AGC的控制时间尺度要求。广东电网模型仿真表明:与集中式分配算法相比,文中所提算法能有效解决复杂大规模电网AGC功率动态分配的分散式优化问题,在减少AGC机组调节费用的同时,可以提高区域电网的控制性能标准。

To adapt the trend in development of the smart grid from centralized to decentralized, this paper developed a decentralized collaborative consensus transfer Q-learning （CTQ） for dynamic generation dispatch of automatic generation control （AGC） under the control framework of the virtual generation tribe （VGT）. And a two-layer model for dynamic generation dispatch was constructed for solving the curse of dimensionality effectively caused by the large scale of the AGC units. Each VGT collaborated with its adjacent VGTs through exchanging the value-matrix function, then the generation command of each VGT can be calculated autonomously, so that the decentralized and autonomous AGC is achieved. Furthermore, the CTQ can be adopted for fast optimization of dynamic generation dispatch to meet the requirement of AGC control cycle after introducing the transfer learning, which can utilize the effective information of historical optimizing task. Simulations of Guangdong power grid prove that the proposed algorithm can effectively handle the decentralized optimization problem of dynamic generation dispatch for complex large-scale power grid compared with centralized algorithms. Moreover, the CTQ can enhance the AGC performance and reduce the regulation costs.