A DRL-based online real-time task scheduling method with ISSA strategy

In Industry 4.0, the focus of task scheduling is more on smart services such as robotic services under the paradigm of mobile edge computing, which are widely used to improve the efficiency of smart manufacturing. Existing scheduling research efforts on optimizing efficiency such as swarm algorithm, reinforcement learning, but with little real-time dynamic scheduling. Online learning and adaptation is a critical function when tackling real challenges in unpredictable and dynamically changing edge computing environments. Our goal is to propose algorithms that can meet the real-time dynamic task scheduling even reach the level of communication. We propose a Deep Reinforcement Learning (DRL)-based online real-time task scheduling method which has the new exploration and exploitation strategy using the improved sparrow search algorithm (ISSA). We replace the traditional strategy with a meta-heuristic algorithm, while introducing natural disturbances and modifying the population position update formula to converge to the optimal position. The algorithm has two layers. The first layer is scheduling generation layer, which is responsible for making decisions, and the second layer is scheduling policy update layer, which optimizes the strategy and finds the best set of hyperparameters. The experimental results show that the running time of the method to solve the problem can reach 0.0092 seconds, and the real-time performance reaches up to the millisecond communication level. At the same time other methods are compared, effectively reducing the running cost and meeting the requirements of production scheduling tasks.