Abstract
Bad data as a result of measurement errors in secondary substation (SS) monitoring equipment is difficult to detect and negatively affects power system state estimation performance by both increasing the computational burden and jeopardizing the state estimation accuracy. In this paper a short-term load forecasting (STLF) hybrid strategy based on singular spectrum analysis (SSA) in combination with artificial neural networks (ANN), is presented. This STLF approach is aimed at detecting, identifying and eliminating and/or correcting such bad data before it is provided to the state estimator. This approach is developed to improve the accuracy of the load forecasts and it is tested against real power load data provided by electricity suppliers. Depending on the week considered, mean absolute percentage error (MAPE) values which range from 1.6% to 3.4% are achieved for STLF. Different systematic errors, such as gain and offset error levels and outliers, are successfully detected with a hit rate of 98%, and the corresponding measurements are corrected before they are sent to the control center for state estimation purposes.
Highlights
Power system state estimation (PSSE) has become an essential tool of energy and distribution management systems (EMS, DMS) aimed at controlling and planning of electric power grids [1,2].With the advent of renewable energy along with the penetration of distributed energy resources (DERs), state estimation is assuming an expanded and prominent role
The transformers account for an error not higher than ±1% [26,27] and the measurement equipment can introduce an error that ranges from ±0.5% to ±1% depending on the manufacturer [28]
Measurements provided by secondary substations are important since Low Voltage (LV)
Summary
Power system state estimation (PSSE) has become an essential tool of energy and distribution management systems (EMS, DMS) aimed at controlling and planning of electric power grids [1,2]. The processes of SE and BD detection need multiple state estimations, i.e., it is an iterative process, which further increases the computational time since a re-estimation of the system is needed after every BD elimination To overcome this drawback, the amount of BD provided to the state estimator should be reduced by implementing a BD pre-filtering stage at a decentralized level in the substations. The hybrid SSA-ANN model used in this paper differs from previous works in several ways: firstly, the grouping stage is automatized; secondly, it considers the residual as an important piece of information for the forecasting process; forecasting results are used for BD detection.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call