Shipboard power system control based on power fluctuation forecasting for photovoltaic penetrated all-electric ships

With the development of ship electrification and the wide application of renewable energy, the uncertainty of renewable energy output brings a serious challenge to the maintenance of ship power quality. This paper proposes a shipboard power generation system control method to maintain power quality by predicting photovoltaic power fluctuations and generating an additional signal to eliminate the volatility influence. In order to obtain the extra control signal, an adaptive kernel based online sequential extreme learning machine algorithm is designed to predict ship load power fluctuations, which is treated as an additional control signal for shipboard power system. Using an equivalent notional shipboard power system model, the proposed method was verified with various types of sea state scenarios. The test results demonstrate the accuracy of the prediction algorithm and the superiorities of the proposed power generation system control method.