This paper proposes an image-based algorithm for detecting and cleaning the wind turbine abnormal data based on wind power curve (WPC) images. The abnormal data are categorized into three types, negative points, scattered points, and stacked points. The proposed algorithm includes three steps, data pre-cleaning, normal data extraction, and data marking. The negative abnormal points, whose wind speed is greater than cut-in speed and power is below zero, are first filtered in the data precleaning step. The scatter figure of the rest wind power data forms the WPC image and corresponding binary image. In the normal data extraction step, the principle part of the WPC binary image, representing the normal data, is extracted by the mathematical morphology operation (MMO). The optimal parameter setting of MMO is determined by minimizing the dissimilarity between the extracted principle part and the reference WPC image based on Hu moments. In the data mark step, the pixel points of scattered and stacked abnormal data are successively identified. The mapping relationship between the wind power points and image pixel points is built to mark the wind turbine normal and abnormal data. The proposed image-based algorithm is compared with kmeans, local outlier factor, combined algorithm based on change point grouping algorithm and quartile algorithm (CA). Numerous experiments based on 33 wind turbines from two wind farms are conducted to validate the effectiveness, efficiency, and universality of the proposed method.

No abstract

Prediction plays a vital role in the active distribution network voltage regulation under the high penetration of photovoltaics. Current prediction models aim at minimizing individual prediction errors but overlook their collective impacts on downstream decision-making. Hence, this paper proposes a safety-aware semi-end-to-end coordinated decision model to bridge the gap from the downstream voltage regulation to the upstream multiple prediction models in a coordinated differential way. The semi-end-to-end model maps the input features to the optimal var decisions via prediction, decision-making, and decisionevaluating layers. It leverages the neural network and the secondorder cone program (SOCP) to formulate the stochastic PV/load predictions and the var decision-making/evaluating separately. Then the var decision quality is evaluated via the weighted sum of the power loss for economy and the voltage violation penalty for safety, denoted by regulation loss. Based on the regulation loss and prediction errors, this paper proposes the hybrid loss and hybrid stochastic gradient descent algorithm to back-propagate the gradients of the hybrid loss with respect to multiple predictions for enhancing decision quality. Case studies verify the effectiveness of the proposed model with lower power loss for economy and lower voltage violation rate for safety awareness.