ESEC: A New Edge Server Selection Algorithm Under Multi-access Edge Computing

In multi-access edge computing, offloading tasks to edge nodes can effectively reduce the computing consumption of terminal devices. The traditional task offloading methods usually select edge node that are close to terminal equipment as offloading nodes and pay less attention to other edge nodes, which can easily lead to an imbalanced load on edge nodes and affect system performance. To deal with this problem, this paper proposes a new task-offloading node selection algorithm based on the edge density clustering algorithm (named ESEC), aiming to balance the load on edge nodes and reduce task completion latency. ESEC first divides edge nodes into multiple communities using the edge density clustering algorithm based on the topology structure of edge nodes, and then it takes into account multiple factors that affect task offloading latency and load, constructs a task latency risk graph, and selects the best edge node to offload the task according to the location of the node in the risk map. A large number of experiments have shown that compared with traditional methods, ESEC can not only effectively reduce the execution delay of tasks, but also reduce the maximum average load by about 10%.