Ensemble learning for optimal active power control of distributed energy resources and thermostatically controlled loads in an islanded microgrid

To achieve an effective coordination between the secondary control and the tertiary control of load frequency control (LFC), a new optimal active power control (OAPC) is constructed for real-timely changing the operating points of distributed energy resources (DERs) and thermostatically controlled loads (TCLs) in an islanded microgrid. A large number of TCLs are integrated as a load aggregator (LA) for participating the secondary control of LFC, which can enhance the dynamic response performance due to their much faster response speeds compared with that of distributed generators. Since OAPC is a nonsmooth and nonlinear optimization with a quite short implementation period, a novel model-free ensemble learning (EL) is proposed to rapidly obtain a high-quality optimal solution for it. EL based OAPC is composed of multiple sub-optimizers and a learning concentrator, where each sub-optimizer is responsible for providing the exploitation and exploration samples to the learning concentrator, while the reinforcement learning based concentrator is mainly used for knowledge learning and knowledge transfer. Case studies are thoroughly carried out to verify the performance of EL based OAPC in an islanded microgrid with 12 DERs and 900 TCLs.