Search

Accurate and effective wind power prediction plays an important role in wind power generation, distribution, and management. Inthis paper, a hybrid algorithm based on gradient descent and meta-heuristic optimization is designed to improve the accuracy of prediction and reduce the computational burden. The hybrid algorithm includes three steps: in the first step, we use the gradient descent algorithm to get the initial parameters. Secondly, we input the initial parameters into the meta-heuristic optimization algorithm to search for the "best parameters" (high-quality inferior solutions). Finally, we input optimized parameters into the RMSProp optimization algorithm and conduct gradient descent again to find a better solution. We used 2021 wind power data from Guangxi, China for the experiment. The results show that the hybrid prediction algorithm has better performance than the traditional Back Propagation (BP) in accuracy, stability, and efficiency. [ABSTRACT FROM AUTHOR]

In fault detection and the diagnosis of large industrial systems, whose chemical processes usually exhibit complex, high-dimensional, time-varying and non-Gaussian characteristics, the classification accuracy of traditional methods is low. In this paper, a kernel limit learning machine (KELM) based on an adaptive variation sparrow search algorithm (AVSSA) is proposed. Firstly, the dataset is optimized by removing redundant features using the eXtreme Gradient Boosting (XGBOOST) model. Secondly, a new optimization algorithm, AVSSA, is proposed to automatically adjust the network hyperparameters of KELM to improve the performance of the fault classifier. Finally, the optimized feature sequences are fed into the proposed classifier to obtain the final diagnosis results. The Tennessee Eastman (TE) chemical process is used to verify the effectiveness of the proposed method through multidimensional diagnostic metrics. The results show that our proposed diagnosis method can significantly improve the accuracy of TE process fault diagnosis compared with traditional optimization algorithms. The average diagnosis rate for 21 faults was 91.00%. [ABSTRACT FROM AUTHOR]

A significant growth in PV (photovoltaic) system installations have been observed during the last decade. The PV array has a nonlinear output characteristic because of weather intermittency. Partial shading is an environmental phenomenon that causes multiple peaks in the power curve and has a negative effect on the efficiency of the conventional maximum power point tracking (MPPT) methods. This tends to have a substantial effect on the overall performance of the PV system. Therefore, to enhance the performance of the PV system under shading conditions, the global MPPT technique is mandatory to force the PV system to operate close to the global maximum. In this paper, for the first time, a stochastic fractal search (SFS) optimization algorithm is applied to solve the dilemma of tracking the global power of PV system based triple-junction solar cells under shading conditions. SFS has been nominated because it can converge to the best solution at a fast rate. Moreover, balance between exploration and exploitation phases is one of its main advantages. Therefore, the SFS algorithm has been selected to extract the global maximum power point (MPP) under partial shading conditions. To prove the superiority of the proposed global MPPT–SFS based tracker, several shading scenarios have been considered. The idea of changing the shading scenario is to change the position of the global MPP. The obtained results are compared with common optimizers: Antlion Optimizer (ALO), Cuckoo Search (CS), Flower Pollination Algorithm (FPA), Firefly-Algorithm (FA), Invasive-Weed-Optimization (IWO), JAYA and Gravitational Search Algorithm (GSA). The results of comparison confirmed the effectiveness and robustness of the proposed global MPPT–SFS based tracker over ALO, CS, FPA, FA, IWO, JAYA, and GSA. [ABSTRACT FROM AUTHOR]