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

Abstract

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.

An improved fault analysis method based on bus-voltage thresholds determination for distribution networks with distributed generators

“…Theo các nghiên cứu của Duong Minh Bui và Phuc Duy Le et al (2020) [11][12][13] , mặc dù bộ dữ liệu phụ tải được thu thập bằng hệ thống quản lý thời gian thực (RTMS-Real-time Management System) có độ chính xác cao, nhưng vẫn chứa khá nhiều dữ liệu gây nhiễu ngẫu nhiên do các nguyên nhân gồm: i) đặc tính vận hành ngẫu nhiên của phụ tải, ii) sự dao động của nguồn lưới hoặc của các nguồn DG, iii) khi LĐPP xảy ra mất điện do sự cố; iv) kế hoạch bảo trì định kỳ; v) đóng/cắt tụ bù; hoặc vi) do đường truyền kết nối không ổn định. Do đó, độ tin cậy của bộ dữ liệu phụ tải thường khó có thể đạt mức độ tin cậy cao nhất là 100%.…”

Application of Sarima Model in Load Forecasting in Hanoi City

“…Domestic and foreign research on load forecasting through ARIMA and SARIMA models: Numerous research carried out overseas use the ARIMA and SARIMA models to forecast shortterm load and electricity loads. Regarding load forecasting, there is research (2019) conducted by Le et al (2019) on applying ANN and ARIMA models in forecasting to improve the quality of short-term load forecasting on the HCMC power grid. Ngoc (2020) mentioned the application of ARIMA model in short-term capacity forecasting.…”

Load Forecasting Method Based on Improved Deep Learning in Cloud Computing Environment

“…On the other hand, due to the extensive use of sensors and smart meters in the power grid, it can quickly obtain massive power consumption data with high dimension and fine granularity, thus forming user power big data. e load big data contains rich user characteristic information, which can be deeply mined to give full play to its maximum value [6,7]. At present, the commonly used load data analysis and application methods can include two types.…”