Renewable energy (RE) sources, such as wind, geothermal, bioenergy, and solar, have gained interest in developed regions. The rapid expansion of the economies in the Middle East requires massive increases in electricity production capacity, and currently fossil fuel reserves meet most of the power station demand. There is a considerable measure of unpredictability surrounding the locations of the concerned regions where RE can be used to generate electricity. This makes forecasting difficult for the investor to estimate future electricity production that could be generated in each area over the course of a specific period. Energy production forecasting with complex time-series data is a challenge. However, artificial neural networks (ANNs) are well suited for handling nonlinearity effectively. This research aims to investigate the various ANN models capable of providing reliable predictions for sustainable sources of power such as wind and solar. In addition to the ANN models, a state-of-the-art ensemble learning approach is used to improve the accuracy of predictions further. The proposed strategies can forecast RE generation accurately over short and long time frames, relying on historical data for precise predictions. This work proposes a new hybrid ensemble framework that strategically combines multiple complementary machine learning (ML) models to improve RE forecasting accuracy. The ensemble learning (EL) methodology outperforms long short-term memory (LSTM), light gradient boosting machine (LightGBM), and sequenced-GRU in predicting wind power (MAE: 0.782, MAPE: 0.702, RMSE: 0.833) and solar power (MAE: 1.082, MAPE: 0.921, RMSE: 1.055). It achieved an impressive R² value of 0.9821, indicating its superior accuracy.

A formidable challenge that hinders the widespread adoption of renewable energy sources is the potential mismatch between their intermittent supply and the fluctuating demand. This necessitates proper coordination to moderate temporal net load variations while reducing costly curtailment of renewable energy production. By capturing the physical and security constraints of unbalanced distribution systems, this paper formulates a problem to manage various fleets of commercial- and residential-scale distributed energy resources. (DERs), i.e., photovoltaics (PVs), deferrable loads (DLs), electric vehicles (EVs), and thermostatically-controlled loads (TCLs). A multi-phase distribution system expanded on the relaxed power flow constraints is considered to account for network awareness. The proposed objective is to minimize hour-to-hour fluctuations of the net load variable, reduce solar energy curtailment, and prioritize preferred EV state of charge and indoor temperature. This objective, however, renders the convex relaxation inexact, wherein positive-semidefinite (PSD) matrices are higher than rank-1. To overcome this issue and therefore enhance the reliability of the solution, we propose to tighten the relaxation constraints via appending the trace of the power flow PSD matrices to the objective function. Multiple case studies on the IEEE 13-bus feeder demonstrate the effectiveness of the proposed problem to optimize the load profile and yield exact solutions.