Service caching for meteorologicalc emergency decision-making in cloud-edge computing

The Intelligent Meteorological System (IMS) with cloud computing (CC) provides users with various meteorological services, but the long-distance communication of CC often brings high latency, which makes the IMS perform poorly in the series of real-time services for meteorological emergency decision-making. Considering the shortcomings of CC, edge computing is adopted to the IMS to process most service requests. In the IMS with cloud-edge computing, the commonly used contents of services is cached on edge servers (ESs) to reduce resource scheduling, thus avoiding high time costs. Due to the storage and computing resource limitations of ESs, the massive types of services and the changing service requests, how to determine the caching contents is still a challenge. In this paper, a service caching scheme based on deep reinforcement learning, named SCDR, is proposed. Specifically, a service caching framework for IMS with cloud-edge computing is designed. Then, the distributed distributional deep deterministic policy gradient (D4PG) is leveraged to realize the optimization of the service caching strategy with the highest service coverage rate and low processing latency. Besides, the performance of the generated caching strategy is evaluated through simulation experiments.