Energy consumption is a key performance metric in multi-access edge computing (MEC) system. Therefore, minimizing consumed energy cost is critically essential. The 5G networks deal with edge computing resources so tha...
详细信息
Energy consumption is a key performance metric in multi-access edge computing (MEC) system. Therefore, minimizing consumed energy cost is critically essential. The 5G networks deal with edge computing resources so that the operator would face with power supply limitation. Therefore, it may not be able to provide sufficient resources to ever-increasing user's requests. One way to compensate such limitation is to form horizontal edge federation (HEF) so that all participant can share the resource capacities as well as request workloads. Energy efficient and ultra-low latency HEF involves the setting of critical factor in each participant: offloading ratios. The decided offloading ratios must provide satisfactory service level to meet latency and physical resource types capacity constraints demanded by requests. Our proposed problem is an energy efficient operational cost (eOPEX) optimization problem. In this paper, we formulate it as a mixed integer linear program and demonstrate that the problem is NP-hard and proposed a federated multidimensional fractional knapsack based algorithm (FMFK) as our approach. The result shows that the horizontal edge federation based on the FMFK performs better and saves the more e-OPEX as well as serving more input requests compare with the non-federation approach. The experimental results show that our approach save about 40% of e-OPEX specially for high latency sensitive application requests in hotspot zone. It shows around 50% e-OPEX saving in the case of high computation unit cost compare with non-federation approach.
暂无评论