A renewable energy forecasting and control approach to secured edge-level efficiency in a distributed micro-grid

Abstract Energy forecasting using Renewable energy sources (RESs) is gradually gaining weight in the research field due to benefits it presents modern-day environment. Not only does renewable help mitigate greenhouse effect, also helps conserve for future use. Over years, several methods have been proposed, all of which were more concerned with accuracy prediction models little or no considerations operating This research, however, proposes uses Deep Neural Network (DNN) on mobile devices at edge network. ensures low latency and communication overhead operations since they are carried out network periphery. Nevertheless, cloud would be used as a support by providing permanent storage locally generated data platform offloading resource-intensive computations that exceed capabilities local well security them. Electrical topology was proposed allows seamless incorporation multiple RESs into distributed source (D-RES) Moreover, novel grid control algorithm model administer well-coordinated effective electrical designed. The simulated two DNN create trained dataset from solar power generation company Belgium (elis) experimented different number layers determine optimum architecture performing operations. performance each evaluated mean square error (MSE) r-square.