摘要
光伏发电系统的故障检测对光伏发电系统的安全运行至关重要。为提高光伏发电系统的故障检测效率,提出一种基于改进粒子群算法优化长短期记忆(IPSO-LSTM)神经网络的故障检测方法。首先通过构建改进的粒子群算法优化双层LSTM网络,对光伏发电系统的发电功率进行实时预测;然后,将LSTM网络预测的发电功率和系统实际的发电功率的误差作为残差值,当残差值大于设定的故障检测阈值时,可以确定系统发生故障。试验结果表明:改进粒子群算法优化的LSTM神经网络比传统的LSTM网络的故障检测性能更优越。
Fault detection in photovoltaic power generation systems is essential for the safe operation of photovoltaic power generation systems(PV system).Therefore,a fault detection method using an optimized long short term memory neural network based on an improved particle swarm algorithm is proposed in order to improve the efficiency of fault detection in PV systems.Firstly,a two-layer LSTM network is constructed to predict the power output of the PV system in real time.Then,the predicted power of the LSTM network is compared with the actual power generated by the system to produce an error as the residual value.When the residual value is greater than the set fault detection threshold,a system fault can be determined.The experiment results show that the improved particle swarm algorithm optimized LSTM neural network has a superior fault detection performance than the traditional LSTM network.
作者
冯庆华
FENG Qing-hua(Jiangsu Vocational Institute of Architectural Technology,Xuzhou 221000,Jiangsu Province,China)
出处
《信息技术》
2023年第6期104-108,112,共6页
Information Technology
基金
江苏省建设系统科技基金项目(2021ZD15)。
关键词
改进粒子群算法
长短期记忆神经网络
故障检测
光伏发电系统
节能
improved particle swarm algorithm
long short-term memory neural networks
fault detection
photovoltaic power generation systems
energy saving
