Grid-Constrained Data Cleansing Method for Enhanced Busload Forecasting

A number of measurement data cleansing methods have been proposed aiming at improving the accuracy of busload forecasting (BLF). However, almost all these methods only exploit the temporal characteristics of a single measurement time series of busload data and neglect the information that can be extracted from the power grid. As a matter of fact, the power grid model derived from physical circuit laws can provide an entirely different dimension of information facilitating the cleansing of busload data. In view of this gap, a comprehensive data cleansing framework is proposed for the sake of enhancing BLF accuracy. Busload datasets are cleansed based on their consistencies with both the temporal statistics and the physical power grid model. Simulation results on the IEEE 30-bus system verify that the proposed method remarkably improves BLF accuracy under various types of measurement data corruption conditions, including random noise, temporary gross errors, permanent biases, and cyberattacks.

[1]  Ali Abur,et al.  A Highly Efficient Bad Data Identification Approach for Very Large Scale Power Systems , 2018, IEEE Transactions on Power Systems.

[2]  Agnaldo J. R. Reis,et al.  Feature extraction via multiresolution analysis for short-term load forecasting , 2005, IEEE Transactions on Power Systems.

[3]  Deepa Kundur,et al.  Noise Suppression of Corona Current Measurement From HVdc Transmission Lines , 2016, IEEE Transactions on Instrumentation and Measurement.

[4]  Hanchen Xu,et al.  Power System Parameter Attack for Financial Profits in Electricity Markets , 2020, IEEE Transactions on Smart Grid.

[5]  Behrooz Safarinejadian,et al.  Distributed Unsupervised Gaussian Mixture Learning for Density Estimation in Sensor Networks , 2010, IEEE Transactions on Instrumentation and Measurement.

[6]  Goran Strbac,et al.  Robust and automatic data cleansing method for short-term load forecasting of distribution feeders , 2020, Applied Energy.

[7]  N. Amjady,et al.  Short-Term Bus Load Forecasting of Power Systems by a New Hybrid Method , 2007, IEEE Transactions on Power Systems.

[8]  Chris Tofallis,et al.  A better measure of relative prediction accuracy for model selection and model estimation , 2014, J. Oper. Res. Soc..

[9]  Rob J Hyndman,et al.  Short-Term Load Forecasting Based on a Semi-Parametric Additive Model , 2012, IEEE Transactions on Power Systems.

[10]  Jing Zhao,et al.  Techniques of applying wavelet de-noising into a combined model for short-term load forecasting , 2014 .

[11]  Guillaume Foggia,et al.  Neural Network-Based Model Design for Short-Term Load Forecast in Distribution Systems , 2016, IEEE Transactions on Power Systems.

[12]  Tirza Routtenberg,et al.  Power Systems Topology and State Estimation by Graph Blind Source Separation , 2018, IEEE Transactions on Signal Processing.

[13]  G. Andersson,et al.  Multiple Bad Data Identification Considering Measurement Dependencies , 2011, IEEE Transactions on Power Systems.

[14]  Durga Toshniwal,et al.  Deep learning framework to forecast electricity demand , 2019, Applied Energy.

[15]  D. Georgakopoulos,et al.  Exercising the Dynamic Range of Active Power Meters Under Nonsinusoidal Conditions , 2007, IEEE Transactions on Instrumentation and Measurement.

[16]  Gonzalo Mateos,et al.  Load Curve Data Cleansing and Imputation Via Sparsity and Low Rank , 2013, IEEE Transactions on Smart Grid.

[17]  Jiguo Cao,et al.  Automated Load Curve Data Cleansing in Power Systems , 2010, IEEE Transactions on Smart Grid.

[18]  Felix F. Wu,et al.  Detection of Topology Errors by State Estimation , 1989, IEEE Power Engineering Review.

[19]  Quan Pan,et al.  Two denoising methods by wavelet transform , 1999, IEEE Trans. Signal Process..

[20]  Lorenzo Peretto,et al.  A statistical model for estimating the trend of electrical quantities in power systems , 2003, IEEE Trans. Instrum. Meas..

[21]  Gabriele D'Antona,et al.  Power System Static-State Estimation With Uncertain Network Parameters as Input Data , 2016, IEEE Transactions on Instrumentation and Measurement.

[22]  Jian Luo,et al.  Benchmarking robustness of load forecasting models under data integrity attacks , 2018 .

[23]  Donald W. K. Andrews,et al.  Consistent model and moment selection procedures for GMM estimation with application to dynamic panel data models , 2001 .

[24]  R. Weron,et al.  Energy Forecasting: A Review and Outlook , 2020, IEEE Open Access Journal of Power and Energy.

[25]  Mingjian Cui,et al.  Machine Learning-Based Anomaly Detection for Load Forecasting Under Cyberattacks , 2019, IEEE Transactions on Smart Grid.

[26]  Elias Kyriakides,et al.  The Effect of Variable Weights in a WLS State Estimator Considering Instrument Transformer Uncertainties , 2014, IEEE Transactions on Instrumentation and Measurement.

[27]  Djamel Bouchaffra,et al.  Genetic-based EM algorithm for learning Gaussian mixture models , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Junfeng Yang,et al.  Improving the Accuracy of Bus Load Forecasting by a Two-Stage Bad Data Identification Method , 2014, IEEE Transactions on Power Systems.