Search

ObjectivesDistributed photovoltaic power prediction is of great significance for the operation and scheduling of photovoltaic power plants. Point prediction methods are difficult to comprehensively describe the uncertainty of distributed photovoltaic power. This article proposed a distributed photovoltaic power interval prediction model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and sparrow search algorithm optimized least squares support vector machine (SSA-LSSVM).MethodsFirstly, the photovoltaic sequence was broken down into multimodal components through CEEMDAN, and then the high-frequency non-stationary components obtained from the first decomposition were decomposed twice. Secondly, sample entropy (SE) was used to reconstruct all components into trend and oscillation components. Then, the point prediction values of the two components were obtained through SSA-LSSVM. Finally, the probability density estimation was performed on the point prediction error of the oscillation component, and the stacked point prediction value was used to obtain the overall prediction interval result.ResultsThe interval prediction model proposed in this paper has higher interval coverage and narrower average interval width.ConclusionsAdding secondary modal decomposition to distributed photovoltaic power data processing and combining sample entropy to reconstruct its sub-sequences can effectively reduce the complexity of the original prediction components and improve the accuracy of model prediction.

In response to the current challenge of fixed time-of-use pricing strategies that struggle to incentivize electric vehicles （EVs） to participate in wind power consumption， an optimal scheduling strategy for wind-integrated systems considering the regulatory potential of large-scale electric vehicles. Firstly， based on schedulable time and space， assessment indicators of regulatory potential of EVs are developed to establish a potential assessment model for the large-scale involvement of electric vehicles in grid regulation. Subsequently， EVs are categorized based on the regulatory potential assessment results， and a clustering-based time-of-use pricing model is devised that considers the differences between wind power consumption and EV clusters. Moreover， with the objectives of minimizing the peak-valley difference in total load on grid side and minimizing charging costs for EV users， and charging and discharging states of EV clusters serving as decision variables， a model is established， taking into consideration interests of both grid and EV user. Ultimately， the feasibility and effectiveness of the proposed method are verified through example simulations.