Software-Defined Networks in IoT Ecosystems for Renewable Energy Resource Management

Abstract

A novel approach toward modernizing energy infrastructures and improving operational performance in distribution of solar renewable energy in smart grid is through Software-Defined Networking (SDN) technology. In addition, the global solar radiation (GSR) plays a critical role in solar power system design in order to precisely identify where solar renewable energy systems should be installed. The hourly global sun radiation measurements using SDN are required in order to precisely calculate the amount of solar energy generated, amount of energy consumed and the amount of solar energy resources conserved. In order to solve the problem of smart grid energy distribution, this study utilized artificial neural network (ANN) algorithm to build a model that predicts, on a monthly basis, the average daily global sun irradiance on a horizontal region of ground base using meteorological data which include the earth's temperature, relative humidity, wind speed, rainfall and ambient air quality. In this paper, the authors discussed the issues in implementing SDN in the energy distribution, energy demand response, energy optimization, grid resilience and real-time monitoring. By using the proposed model, the results showed a good agreement between the measured and calculated levels of global solar irradiation, demonstrating the superiority of the ANN model over empirical models due to its small noise margin. For researchers, practitioners, and policymakers looking to fully leverage SDN for advancing solar renewable infrastructures within national grid system, this research paper offers insightful information through a thorough analysis of current developments and future trends.