Sequenced Quantization RNN Offloading for Dependency Task in Mobile Edge Computing

Mobile edge computing (MEC) allows terminals to send tasks to adjacent edge servers for calculation to reduce the burden on terminals and task completion time. With the widespread use of wireless devices (WDs) and the increasing complexity of applications, how to partially offload tasks to minimize task completion time has become a huge challenge. We propose a sequenced quantization based on recurrent neural network (SQ-RNN) algorithm that makes reasonable partial offload decisions for subtasks with dependencies. Specifically, the SQ-RNN algorithm first inputs the environment information into the RNN, and uses the RNN to generate a task offloading strategy. Then the algorithm quantifies the offloading strategy generated by the RNN into multiple binary offloading actions according to a certain method, and selects the action with the lowest computational delay from the multiple binary offloading actions as the offloading decision of the task. In addition, the algorithm also configs RNN with a fixed-size memory space to store the latest unloading strategy generated by RNN for further training of RNN. Experiments have proved that the SQ-RNN offloading algorithm described in our study generates better offloading decisions than those made by conventional offloading techniques.