This paper explores the optimization of supply chain networks for industrial plants in the manufacturing sector under vendor-managed inventory (VMI) policy. It puts more emphasis on the global coordination of multi-plant warehouses that are managed by vendors using the VMI policy that use Long Range Wide Area Network (LoRaWAN) technology, which aims to reduce the network’s total cost and enhance customer service. The problem was initially developed as a mixed-integer non-linear program (MINLP) model. To achieve better results, the modified firefly algorithm using exploration and exploitation was employed to solve the problem.  The simulation results indicated that the modified firefly algorithm has better results for optimizing supply chain networks when compared to the standard one. Additionally, the computational time was reduced using the proposed algorithm. Response surface methodology was applied to tune the parameters’ algorithms and trained to test the validity of the model.  A case study for pipes manufacturing integrated supply chain is used to demonstrate the efficiency of the model and the solutions obtained by firefly algorithm.