The integration of solar energy with a power system brings great economic and environmental benefits. However, the high penetration of solar power is challenging due to the operation and planning of the existing power system owing to the intermittence and randomicity of solar power generation. Achieving accurate predictions for power generation is important to provide high-quality electric energy for end-users. Therefore, in this paper, we introduce a deep learning-based dual-stream convolutional neural network (CNN) and long short-term nemory (LSTM) network followed by a self-attention mechanism network (DSCLANet). Here, CNN is used to learn spatial patterns and LSTM is incorporated for temporal feature extraction. The output spatial and temporal feature vectors are then fused, followed by a self-attention mechanism to select optimal features for further processing. Finally, fully connected layers are incorporated for short-term solar power prediction. The performance of DSCLANet is evaluated on DKASC Alice Spring solar datasets, and it reduces the error rate up to 0.0136 MSE, 0.0304 MAE, and 0.0458 RMSE compared to recent state-of-the-art methods.
The torque ripples in a switched reluctance motor (SRM) are minimized via an optimal adaptive dynamic regulator that is presented in this research. A novel reinforcement neural network learning approach based on machine learning is adopted to find the best solution for the tracking problem of the SRM drive in real time. The reference signal model which minimizes the torque pulsations is combined with tracking error to construct the augmented structure of the SRM drive. A discounted cost function for the augmented SRM model is described to assess the tracking performance of the signal. In order to track the optimal trajectory, a neural network (NN)-based RL approach has been developed. This method achieves the optimal tracking response to the Hamilton–Jacobi–Bellman (HJB) equation for a nonlinear tracking system. To do so, two neural networks (NNs) have been trained online individually to acquire the best control policy to allow tracking performance for the motor. Simulation findings have been undertaken for SRM to confirm the viability of the suggested control strategy.
This paper investigated a new speed regulator using an adaptive transitioning policy iteration learning technique for the variable reluctance motor (VRM) drive. A transitioning strategy is used in this unique scheme to handle the nonlinear behavior of the VRM by using a series of learning centers, each of which is an individual local learning controller at linear operational location that grows throughout the system’s nonlinear domain. This improved control technique based on an adaptive dynamic programming algorithm is developed to derive the prime solution of the infinite horizon linear quadratic tracker (LQT) issue for an unidentified dynamical configuration with a VRM drive. By formulating a policy iteration algorithm for VRM applications, the speed of the motor shows inside the machine model, and therefore the local centers are directly affected by the speed. Hence, when the speed of the rotor changes, the parameters of the local centers grid would be updated and tuned. Additionally, a multivariate transition algorithm has been adopted to provide a seamless transition between the Q-centers. Finally, simulation and experimental results are presented to confirm the suggested control scheme’s efficacy.
This study explores the speed adjustment characteristics of the adaptive control of estimated single-layer Bi-channel neural networks (NNs) for Variable Reluctance Motor (VRM) drives. The innovative algorithm incorporates an estimation method to manage the nonlinear behavior of a VRM through a collection of Bi-channel NNs nodes. Each node acts as a single-layer Bi-channel NNs controller at a local linear operating point extending across the nonlinear surface of the system. Although this algorithm demonstrates strong tracking performance, a significant challenge arises from the motor speed being integrated into the machine model, which means that the controller is directly influenced by speed variations. This results in a sluggish speed adjustment response due to the learning process involved. To address this challenge, a grid of NNs must update the NNs-matrices whenever rotational speed changes. Finally, a simulation of the proposed novel speed control has been conducted to illustrate the speed adjustment behavior of the VRM under various operating conditions and to validate the effectiveness of the control approach.