Demand Side Control for Energy Saving in Renewable Energy Resources Using Deep Learning Optimization
Himanshu Shekhar, Chandra Bhushan Mahato, Sanjay Kumar Suman, Satyanand Singh, L. Bhagyalakshmi, Mahendra Prasad Sharma, B. Laxmi Kantha, T. Helan Vidhya, Siva Kumar Agraharam, A. Rajaram
Abstract
Convolutional neural networks a type of deep learning technology, are used for forecasting future power usage. The mean absolute error, mean square error, root mean square error, and mean constant percentage error are used to evaluate the performance of the models. These metrics are used to rank the models. Among the models tested, the CNN stack demonstrates the highest precision in estimating energy consumption and solar power output, with a mean absolute error of 0.015% points, a root mean square error of 0.23% points, and an average absolute percentage deviation of 1.71% points. However, for wind turbine (WT) energy generation, the recurrent neural network proves for most accurate model, achieving 0.070 as the median absolute percentage error is 2.65, Both the root of the mean square error and the average absolute error are 0.38. The training and validation data utilized in this study comprise the International Renewable Energy Agency’s data on solar power production, WT power generation, and the “ensue” dataset, which includes hourly power consumption information from the Pennsylvania, New Jersey, and Maryland interconnection.