An Artificial Intelligence Approach for Reliability Analysis in Distribution Network

Abstract

Power distribution systems (PDS) have gained less attention in the past than in comparison with transmission and distribution. The rapid increase in the usage of intermittent renewable energy, ongoing changes in electrical power system structure and operational needs pose growing problems while ensuring adequate service reliability and retaining the quality of power. Power system reliability is a pertinent factor to consider while planning, designing, and operating distribution systems. According to customer failure statistics from major utilities, the maximum unavailability of electrical power to consumers is due to distribution system outages. Power suppliers are obligated to offer their customers uninterrupted electrical service at the least cost while maintaining a satisfactory level of service quality. The important metric for gauging the effect of distributed renewable energy on distribution networks is reliability analysis. Reliability analysis in distribution systems involves evaluating the performance and robustness of electrical distribution networks. An artificial intelligence approach is implemented in this paper to improve reliability analysis with dispersed generations in a distribution network. Deep belief neural networks (DBNNs) are a type of artificial neural network that can be used for various tasks, including analyzing complex data such as those found in power distribution systems. Layer-by-layer learning allows a deep belief network (DBN) to absorb feature specifics from huge amounts of data. This study introduces a deep belief neural network (DBNN) optimized with particle swarm optimization (PSO) for distribution network reliability analysis. A 16-bus system is taken for reliability analysis. The input data and output data are obtained from the reliability analysis code. The proposed model performance is assessed using mean square error, mean absolute error, root mean square error, and R squared error. The findings reveal that reliability analysis with this novel technique is more accurate. The reliability of power distribution networks may also be investigated using an optimized DBN model, which can then be used on a variety of grid configurations in distribution networks.