Short-term load forecasting has an extremely important role in the design, operation and planning of power system, especially on a power grid of Ho Chi Minh City (HCMC) - an active city has the highest power demand in Vietnam. Through the data survey, the load power in the HCMC area changes suddenly so that it causes disturbances in the load data. Accordingly, the reliability assessment of the load data will be essential in the processing stage of data-filtering before implementing load forecasting models. This study introduces a novel statistical data-filtering method that takes into account the reliability of the input-data source by analyzing many different confidence levels. Results of the proposed data-filtering method will be compared to previous data -iltering methods (such as Kalman, DBSCAN, Wavelet Transform and SSA filtering methods). The data source used in this study was collected from more than 50 substations uisng the SCADA system in Ho Chi Minh City's distribution network and was put into a neural network prediction model - ANN (Artificial Neural Network) and a ARIMA model (Autoregressive Integrated Moving Average), to demonstrate the effectiveness of the proposed data-filtering method. Numerical results derived from ANN and ARIMA predictive models show the effectiveness of the proposed data-filtering method, particularly, when the reliability of real data from the Ho Chi Minh city distribution network is determined at the 95% level, the forecasting results of ANN and ARIMA models using the proposed data-filtering method are obviously better than that without filtering method or using other data-filtering methods.
Applying statistical analysis for assessing the reliability of input data to improve the quality of short-term load forecasting for a Ho Chi Minh City distribution network
