Collaborative Caching in Edge Computing via Federated Learning and Deep Reinforcement Learning

Table 1

Comparison of existing papers addressing edge caching problems.

Reference	Optimization objective	Method	Disadvantages
[22]	Download latency	Hungarian algorithm	No quantitative benefits
[23]	Cache hit ratio	Greedy algorithm	High complexity
[24]	Cache hit ratio	Bidirectional recurrent neural networks	Privacy security
[25]	Energy consumption	Branch and bound algorithm	Privacy security
[26]	Estimating content popularity	Federated -means scheme	High complexity
[27]	Minimize traffic cost	Federated learning	Lower model accuracy
[29]	User response latency	Heuristic algorithm	Homogeneous user demand distribution
[30]	The cost of the video provider	Branch and bound algorithm	High time consuming