GA−Reinforced Deep Neural Network for Net Electric Load Forecasting in Microgrids with Renewable Energy Resources for Scheduling Battery Energy Storage Systems

Abstract

The large−scale integration of wind power and PV cells into electric grids alleviates the problem of an energy crisis. However, this is also responsible for technical and management problems in the power grid, such as power fluctuation, scheduling difficulties, and reliability reduction. The microgrid concept has been proposed to locally control and manage a cluster of local distributed energy resources (DERs) and loads. If the net load power can be accurately predicted, it is possible to schedule/optimize the operation of battery energy storage systems (BESSs) through economic dispatch to cover intermittent renewables. However, the load curve of the microgrid is highly affected by various external factors, resulting in large fluctuations, which makes the prediction problematic. This paper predicts the net electric load of the microgrid using a deep neural network to realize a reliable power supply as well as reduce the cost of power generation. Considering that the backpropagation (BP) neural network has a good approximation effect as well as a strong adaptation ability, the load prediction model of the BP deep neural network is established. However, there are some defects in the BP neural network, such as the prediction effect, which is not precise enough and easily falls into a locally optimal solution. Hence, a genetic algorithm (GA)−reinforced deep neural network is introduced. By optimizing the weight and threshold of the BP network, the deficiency of the BP neural network algorithm is improved so that the prediction effect is realized and optimized. The results reveal that the error reduction in the mean square error (MSE) of the GA–BP neural network prediction is 2.0221, which is significantly smaller than the 30.3493 of the BP neural network prediction. Additionally, the error reduction is 93.3%. The error reductions of the root mean square error (RMSE) and mean absolute error (MAE) are 74.18% and 51.2%, respectively.

Deep Learning for Forecasting-Based Applications in Cyber–Physical Microgrids: Recent Advances and Future Directions

“…Finally, for more works related to the load forecasting, refs. [53][54][55][56][57][58][59][60][61][62][63][64][65][66][67][68][69][70] A dataset can be created to train the deep learning-based application (e.g., the ANN) to forecast the values of the loads. Then, based on Figure 4, the current values and the historical values of the desired inputs can be used to predict the future values of power consumption in a cyber-physical microgrid using the trained ANN.…”

Model Predictive Evolutionary Temperature Control via Neural-Network-Based Digital Twins

“…The subsequent component of the pipeline involves the utilization of genetic programming (GP) to generate control policies for the fans. GP is a variant of Genetic Algorithms (GA) developed by John R. Koza, where the solution is encoded in a tree structure instead of a string [40][41][42]. Similar to GA, GP draws inspiration from nature and mimics the evolutionary process by iteratively applying a set of genetic operations on an initially randomly selected pool of candidate solutions [41,43,44].…”

Research on Economic Optimal Dispatching of Microgrid Based on an Improved Bacteria Foraging Optimization

“…Linear programming [ 3 , 4 , 5 ], dynamic programming [ 6 , 7 ], Lagrangian relaxation [ 8 ], and nonlinear programming [ 9 , 10 ] have many problems with large-scale power systems, such as traditional microgrid dispatching optimization methods. Various electrical constraints also increase the complexity and difficulty of microgrid dispatching optimization.…”