Fault Diagnosis of Data-Driven Photovoltaic Power Generation System Based on Deep Reinforcement Learning

Abstract

Aiming at the problem of fault diagnosis of the photovoltaic power generation system, this paper proposes a photovoltaic power generation system fault diagnosis method based on deep reinforcement learning. This method takes data-driven as the starting point. Firstly, the compressed sensing algorithm is used to fill the missing photovoltaic data and then state, action, strategy, and return functions from the environment. Based on the interaction rules and other factors, the fault diagnosis model of the photovoltaic power generation system is established, and the deep neural network is used to approximate the decision network to find the optimal strategy, so as to realize the fault diagnosis of the photovoltaic power generation system. Finally, the effectiveness and accuracy of the method are verified by simulation. The simulation results show that this method can accurately diagnose the fault types of the photovoltaic power generation system, which is of great significance to enhance the security of the photovoltaic power generation system and improve the intelligent operation and maintenance level of the photovoltaic power generation system.

Development of a machine-learning-based method for early fault detection in photovoltaic systems

“…One method [47] can detect two types of faults (short-circuit fault, mismatch faults), and six methods [44,45,48,49,51,52] can detect only one type of fault (open-circuit fault, arc fault, mismatch faults, short-circuit fault, arc fault, mismatch faults respectively). Regarding the accuracy of fault detection, nine methods [41,42,45,[47][48][49][50][51]53] show an accuracy of more than 95%, while one method [46] shows fluctuating accuracy depending on the type of the fault (89.6-98%). Finally, only two methods [43,50] provide information about their computational cost, it has to be noted though that the method presented in [50] provides data only for its execution time.…”

“…The method is based in principal component analysis (PCA) that used data from I-V curves to detect faults with significant accuracy. Finally, Dai et al [53] suggested a deep reinforcement learning-based PVS fault detection technique. The starting premise for this approach is data-driven.…”

Research on fault diagnosis of electromechanical actuator based on convolution neural network

“…Increasing the number of convolution layer and sampling layer will increase the network complexity and increase the network learning time. [4] In order to adapt to one-dimensional input data, the convolution kernel is set as one-dimensional convolution kernel. Different convolution kernels extract different features of the input data, and then through the dimensionality reduction operation of the sampling layer, the output nodes of the sampling layer are greatly reduced, and the network computation is also reduced, but the output of the sampling layer cannot be used as the classification result, It is necessary to connect the full connection layer and the Softmax regression layer behind the sampling layer to obtain the probability corresponding to various states.…”

“…LM method can correct the error of the algorithm. The algorithm always follows the direction of negative gradient during the iteration, and searches the error in the ascending direction, and finds the appropriate control factor u through repeated iteration, thus solving the problem of the lower bound in the network (4).…”

Fault‐resilient control of parallel PV inverters using multi‐agent twin‐delayed deep deterministic policy gradient approach

“…Fault detection problem in GTPS is often considered as a classification challenge. 36 However, the realm of DRL is chiefly designed to address sequential decision-making predicaments. Drawing inspiration from prior references, this study reframes inverter fault diagnosis as a form of deduction game.…”