Boosting energy harvesting via deep learning-based renewable power generation prediction

The high-level variation of different energy generation resources makes the reliable power supply significantly challenging to end-users. These variations occur due to the intermittent nature of energy output and time-varying weather conditions. The recent literature focuses on the improvements in power generation and consumption forecasting, which is a demand of the current smart grids’ smooth operations with a balanced amount of energy generation and consumption for the connected customers. Inspired by the applications of load forecasting, therefore, in this work, we develop an efficient and effective hybrid model for power generation and consumption forecasting, thereby contributing to energy harvesting by providing valuable prediction data to the concerned renewable energy analysts. Herein, we integrate a convolutional neural network with an echo state network for robust renewable energy generation and consumption forecasting. The convolutional network is used to extract meaningful patterns from the historical data which is then forwarded to the echo state network for temporal features learning. The output spatiotemporal feature vector is then fed to fully connected layers for final forecasting. The proposed hybrid model is derived after extensive experiments over machine and deep learning models, where the results indicate that the proposed model substantially decreases the forecasting errors using RMSE, MSE, NRMSE, and MAE metrics, when compared to state-of-the-art models and acts as a paradigm towards energy equilibrium between production resources and consumers.