Intelligent Control Method for Distributed Photovoltaic Power Generation Based on FKNN Algorithm

In response to the problem that existing methods are difficult to effectively suppress grid connected power fluctuations, this study proposes a distributed photovoltaic power generation intelligent control method based on the fuzzy k-nearest neighbor algorithm. Firstly, a mapping model is constructed using the FKNN algorithm to predict power; then, based on the predicted results, a power allocation model is established with the goal of smoothing grid connected power fluctuations, which includes energy storage charging and discharging strategies and inverter control; finally, the optimal output instructions for each unit are solved through rolling optimization. The test results show that the predicted values obtained by this method are closest to the actual values, indicating that this method has high prediction accuracy. After applying this method, the stability of the photovoltaic power generation curve is relatively high, indicating that this method can quickly adjust the charging and discharging state of the energy storage system, keeping the grid connected power within the set stable range.