Online Auction of QoE/Utility-balanced Resource Allocation in Mobile Edge Network

In mobile edge computing (MEC), edge servers are deployed near IoT devices such as smart phones and wearable devices. These IoT devices can offload their computation-demanding tasks to the edge servers for lower latency services. One fundamental problem is that how to allocate distributed computing resources to offloaded tasks. In this paper, we propose a general model for the MEC resource allocation, where edge servers sell their spare computing resources for processing offloaded tasks and obtain rewards. We construct a resource allocation framework, namely differentiated resources based continuous auction (DR-CA). DR-CA aims to achieve the tradeoff between system QoE and utility, jointly considering the MEC capabilities, bid differentiation, and individual rational, between edge servers and end devices. With the help of theoretical analysis, DR-CA is demonstrated to feature truthfulness, individual rational, budget-balanced and computational efficiency. Extensive simulation results also indicate that the proposed mechanism efficiently reduces waiting time under the premise of system utility, and outperforms several existing schemes.