A neurofuzzy QoS-aware routing protocol for smart grids

Abstract

Smart Grid (SG), designed to integrate high-speed, reliable, and secure data communication networks to manage the complex power systems effectively and intelligently, uses two-way flows of electricity and information to create a widely distributed automated energy delivery network. One of the main challenges of SGs is routing optimization that the data transmission of power price must be equipped with Quality of Service (QoS) guarantee. Using artificial intelligence in routing schemes is appropriate to develop complex tasks such as path discovery. The proposed routing algorithm, namely neurofuzzy-based Optimization Multi-Constrained Routing (NFOMCR), has the novelty of being based on the introduction of artificial neural network and fuzzy logic. Other main challenge of SG is finding a feasible solution to a class of nonlinear inequalities defined on a graph. A neurofuzzy system is proposed to tackle this problem. Convergence of the neural network and the solution feasibility to the defined problem are both theoretically proven. The proposed neural network features a parallel computing mechanism and a distributed topology isomorphic to the corresponding graph. Thus, it is suitable for distributed real-time computation. Optimization of performance that concluded from minimizing the cost and error of this network is obviously achieved. Experimental results obtained by this routing protocol show the improvement of the performance achieved in this networks.