Multi-Constraint Optimal Path Finding for QoS-Enabled Smart Grids: A Combination Approach of Neural Network and Fuzzy System

Smart Grid (SG) is an intelligent managed network including various data networks. Due to using the two-way data and electricity flows in SG, relations among the network elements are in an efficient way. Path finding optimization is one of the important challenges in SG. In this paper, we propose a routing protocol, namely Neuro-Fuzzy Stable Optimization Multi-Constrained Routing (NFSOMCR), to investigate the optimal path between two nodes in the SG. For this purpose, seven parameters and one cost function are used to meet the important QoS requirements of SG. Depending on the different initializations applied on the parameters, some routes with their constraints are found out by Dijkstra routing algorithm that form the inputs of the Neuro-Fuzzy system. The output of this system is the optimized cost function as well as the optimal paths between two nodes. Experimental results show that the proposed method outperforms existing works in terms of power cost and throughput.