Aiming at the green job shop scheduling problem under the integration of processing resources and transportation resources, a multi-objective optimization model based on the integrated scheduling of machines and automated guided vehicle(AGV) is established by studying the comprehensive energy consumption in production workshop. An improved estimation of distribution algorithm (IEDA) is proposed to solve the problem. First, excellent individuals are generated as sample learning to construct the probability distribution model for improving the global search ability of IEDA. Then, inspired by the hormone regulation mechanism, a new speed cooling control method is designed in simulated annealing algorithm to improve the local search ability of IEDA. Finally, numerical experiments are conducted and the results show the feasibility and effectiveness of the proposed model and algorithm.