Adaptive dynamic scheduling strategy in knowledgeable manufacturing based on improved Q-learning

Aiming at the uncertainty of the production environment in knowledgeable manufacturing system, a dynamic scheduling simulation system based on the multi-agent is built. To ensure that the machine agent can select the appropriate bid job based on the current system status, the improved Q-learning based on clustering-dynamic search (CDQ) algorithm is presented, which is used to guide the adaptive selection of dynamic scheduling strategy in the uncertain production environment, and the complexity analysis of the algorithm is given. The dynamic scheduling strategy adopts the method of the sequence clustering to reduce the dimension of system state and learns according to status different degree and the dynamic greed search strategy. Simulation experiments verify the adaptability and effectiveness of the dynamic scheduling strategy. ©, 2015, Northeast University. All right reserved.