To cope with the impact of different device computing capabilities and non-independent uniformly distributed data on federated learning performance. and to efficiently schedule terminal devices to complete model aggregation. a method of node selection based on deep reinforcement learning was proposed. It considered training quality and efficiency of heterogeneous terminal devices. https://www.roneverhart.com/Western-Digital-Ultrastar-DC-HC570-WUH722222ALE6L1-22TB-7-2K-RPM-SATA-6Gb-s-512e-SED-3-5in-Recertified-Hard-Drive/