Abstract: A novel ensemble learning（EL）method is proposed to achieve an optimal generation-consumption coordinated frequency control in an islanded microgrid.To solve the "dimension disaster"under the optimal generation-consumption coordinated frequency control,a large number of household consumers are aggregated as a load aggregator（LA）,which can be equivalent to a generator.The LA can continuously evaluate the minimal and maximal reserve capabilities according to the operation state of each thermostatically controlled load.The EL 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 transfer.Case studies are thoroughly carried out to verify the performance of EL for the generation-consumption coordinated frequency control in an islanded microgrid.