Short-Term Load Forecasting Based on the Analysis of User Electricity Behavior

The smart meter is an important part of the smart grid, and in order to take full advantage of smart meter data, this paper mines the electricity behaviors of smart meter users to improve the accuracy of load forecasting. First, the typical day loads of users are calculated separately according to different date types (ordinary workdays, day before holidays, holidays). Second, the similarity between user electricity behaviors is mined and the user electricity loads are clustered to classify the users with similar behaviors into the same cluster. Finally, the load forecasting model based on the Online Sequential Extreme Learning Machine (OS-ELM) is applied to different clusters to conduct load forecasting and the load forecast is summed to obtain the system load. In order to prove the validity of the proposed method, we performed simulation experiments on the MATLAB platform using smart meter data from the Ireland electric power cooperation. The experimental results show that the proposed method is able to mine the user electricity behaviors deeply, improve the accuracy of load forecasting by the reasonable clustering of users, and reveal the relationship between forecasting accuracy and cluster numbers.

[1]  Yang Liu,et al.  Short-Term Load Forecasting Based on Big Data Technologies , 2014, CIT 2014.

[2]  Hiroyuki Mori,et al.  EPSO-based Gaussian Process for electricity price forecasting , 2015, 2015 IEEE Congress on Evolutionary Computation (CEC).

[3]  Narasimhan Sundararajan,et al.  Online Sequential Fuzzy Extreme Learning Machine for Function Approximation and Classification Problems , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  Jian Liu,et al.  Short-term load forecasting based on parallel frameworks , 2016, 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD).

[5]  Xin Wang,et al.  Factors that Impact the Accuracy of Clustering-Based Load Forecasting , 2015, IEEE Transactions on Industry Applications.

[6]  Mohamed Chaouch,et al.  Clustering-Based Improvement of Nonparametric Functional Time Series Forecasting: Application to Intra-Day Household-Level Load Curves , 2014, IEEE Transactions on Smart Grid.

[7]  Zhaohui Tang,et al.  The review of demand side management and load forecasting in smart grid , 2016, 2016 12th World Congress on Intelligent Control and Automation (WCICA).

[8]  Yao Min,et al.  Research on mid-long term load forecasting based on combination forecasting mode , 2015, SNPD 2015.

[9]  Saeid Nahavandi,et al.  Improving load forecast accuracy by clustering consumers using smart meter data , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[10]  Surapong Suwankawin,et al.  Short-term electricity load forecasting for Building Energy Management System , 2016, 2016 13th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON).

[11]  Zhang Suxian.  Short-term Power Load Forecasting Based on Big Data , 2015 .

[12]  Massoud Pedram,et al.  Designing the Optimal Pricing Policy for Aggregators in the Smart Grid , 2014, 2014 Sixth Annual IEEE Green Technologies Conference.

[13]  Antans Sauhats,et al.  Analysis and prediction of electricity consumption using smart meter data , 2015, 2015 IEEE 5th International Conference on Power Engineering, Energy and Electrical Drives (POWERENG).

[14]  Zubair A. Baig,et al.  Detection of compromised smart meters in the Advanced Metering Infrastructure , 2015, 2015 IEEE 8th GCC Conference & Exhibition.

[15]  Rubiyah Yusof,et al.  Online sequential-extreme learning machine based detector on training-learning-detection framework , 2015, 2015 10th Asian Control Conference (ASCC).

[16]  Hua Wang,et al.  Short-term load forecasting based on data mining , 2016, 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design (CSCWD).

[17]  Zhao Ten,et al.  Application Technology of Big Data in Smart Distribution Grid and Its Prospect Analysis , 2014 .

[18]  Toru Namerikawa,et al.  Dynamic electricity pricing via the H∞ control considering uncertainties in market participants' behavior , 2015, 2015 European Control Conference (ECC).

[19]  Heng Huang,et al.  Using Smart Meter Data to Improve the Accuracy of Intraday Load Forecasting Considering Customer Behavior Similarities , 2015, IEEE Transactions on Smart Grid.

[20]  Cansin Yaman Evrenosoglu,et al.  A Unified Approach for Power System Predictive Operations Using Viterbi Algorithm , 2014, IEEE Transactions on Sustainable Energy.

[21]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.

[22]  N. Loganathan,et al.  Demand side energy management system using ANN based linear programming approach , 2014, 2014 IEEE International Conference on Computational Intelligence and Computing Research.

[23]  Hui Xiao,et al.  Research on mid-long term load forecasting based on combination forecasting mode , 2015, 2015 IEEE/ACIS 16th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD).

[24]  Wang Baoy,et al.  A Distributed Load Forecasting Algorithm Based on Cloud Computing and Extreme Learning Machine , 2014 .

[25]  Zhang Feng,et al.  A novel ultra-short term load forecasting method based on load trend and fuzzy c-means clustering algorihm , 2014, 2014 International Conference on Power System Technology.

[26]  Xizhao Wang,et al.  Ensemble online sequential extreme learning machine for large data set classification , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[27]  Hossein Taherian,et al.  Short-term price forecasting under high penetration of wind generation units in smart grid environment , 2013, ICCKE 2013.

[28]  Zhigang Zeng,et al.  Power load forecasting based on support vector machine and particle swarm optimization , 2016, 2016 12th World Congress on Intelligent Control and Automation (WCICA).

[29]  Wei Liu,et al.  Medium and long term load forecasting method for distribution network with high penetration DGs , 2014, 2014 China International Conference on Electricity Distribution (CICED).

[30]  Karl Aberer,et al.  Electricity load forecasting for residential customers: Exploiting aggregation and correlation between households , 2013, 2013 Sustainable Internet and ICT for Sustainability (SustainIT).

[31]  Zhong Qin,et al.  Load and Power Forecasting in Active Distribution Network Planning , 2014 .

[32]  Qinmin Yang,et al.  Application of clustering technique to electricity customer classification for load forecasting , 2015, 2015 IEEE International Conference on Information and Automation.

[33]  George G. Polak,et al.  Optimal Clustering of Time Periods for Electricity Demand-Side Management , 2013, IEEE Transactions on Power Systems.