Peer Offloading in Mobile-Edge Computing With Worst Case Response Time Guarantees

Mobile edge computing (MEC) is a new paradigm that provides cloud services at the of networks. To achieve better performance with limited resources, peer offloading between cooperative servers (e.g. MEC- enabled base stations) has been proposed as an effective technique to handle bursty and spatially imbalanced arrival computation tasks. While various metrics policies have considered in literatures, worst-case response time, common Quality Service(QoS) requirement real-time applications, yet receives much less attention. fill gap, we formulate problem based on stochastic model propose two online algorithms for cases without prior knowledge task rate. Our goal maximize utility function time-average throughput under constraints energy consumption time. Both theoretical analysis numerical results show our are able produce close optimal performance.