Optimized task distribution based on task requirements and time delay in edge computing environments

Abstract Edge computing is a new technology for completing real-time and complex tasks with low latency. However, due to limited storage, computing and communication capabilities of edge nodes, it is often necessary for multiple edge nodes to share a task’s related work load to decrease its overall execution time. To solve the problem, this paper proposes a task distribution method based on the analysis of task requirements and time delay in an edge computing environment. First, the related data is received by a proxy server to obtain the running states of edge nodes. Then, a task-based edge node selection algorithm is designed to select appropriate target edge nodes. It can meet task requirements by using a Bloom filter to filter malicious nodes. Finally, based on the above selected nodes, optimized target edge nodes are selected to achieve the minimum time delay. Based on the selected optimized target edge nodes, this paper proposes an algorithm to optimize task distribution for meeting task requirements and achieve the minimum delay in an edge computing environment. Because the method considers both task requirements and time delay, it can distribute tasks to target nodes at low cost. The experimental results show that the method is feasible and effective and outperforms two commonly-used methods