Multi-agent reinforcement learning for distributed edge caching
There is an exponential increase in the network traffic worldwide due to the growth of social networks, multimedia sharing web services, streaming of video-on-demand (VoD) contents. However, the bandwidth isn’t growing at the same rate as the demand, resulting in a loss of Quality of Service (QoS) and Quality of Experience (QoE) for the users. Distributed edge caching provides an effective mechanism for mitigating the bandwidth requirements of the growing traffic demands by trading off bandwidth with storage. Storage owners (such as Ericsson) can leverage edge caching techniques to replicate the most popular content closer to the network edge rather than storing it in a central location to reduce the load at the core network, reduce performance bottlenecks, and provide differentiated services to end users of Content Providers (CPs).