Predicting Electricity Usage of Houses Incorporating Smart Meters

Musaib Amin; Dharminder Kumar; Dr. Satish Saini

doi:10.55524/ijircst.2022.10.5.10

Abstract

The need for smart grid user-side management is becoming more critical as smart power distribution networks evolve. This study suggests a short-term power load forecasting model based on K-means and Clustering to increase the precision of short-term electric load forecasting for individual customers. Local comparable daily data are used as characteristics for users with poor correlation at adjacent times. Based on the -means cluster analysis technique, a clustering module was created. The clustering module was validated using home load profiles based on smart meters. Utilizing daily and segmented load profiles from individual and collective smart meter data, many case studies were put into practice. The smallest segmentation time window yields the lowest clustering ratio, according to simulation findings described in terms of the correlation between the clustering ratio and the time window. Results also indicate that for strongly coupled load profiles, a limited number of clusters is advised. Last but not least, the feather vectors are sent into the BP Neural Network, which forecasts the short-term load. According to experimental findings, the suggested clustering algorithm matches the features of customers' power consumption pattern. The accuracy of clustering-based load forecasting is higher than that of non-clustering load forecasting when using the same forecasting methodology. This model offers superior predicting accuracy when compared to conventional BP, RBF, and GRNN Neural Network.

Keywords

K-means, Clustering, Smart Meters, Distributed Networks

References

The Irish Electricity Smart Metering Customer Behaviour Trials. (2011). 21-January-2018].
Hirotugu Akaike. A New Look at the Statistical Model Identification. IEEE Trans. Automat. Control 19, 6 (1974), 716–723.
M.S. Al-Musaylh, R.C. Deo, J.F. Adamowski, and Y. Li. Short-term electricity demand forecasting with MARS, SVR and ARIMA models using aggregated demand data in Queensland, Australia. Advanced Engineering Informatics 35, November 2017 (2018), 1–16.
Yin-Wen Chang, Cho-Jui Hsieh, Kai-Wei Chang, Michael Ringgaard, and ChihJen Lin. 2010. Training and Testing Low-degree Polynomial Data Mappings via Linear SVM. Journal of Machine Learning Research 11 (2010), 1471–1490.
C.S. Chen, Y.M. Tzeng, and J.C. Hwang. 1996. The application of artificial neural networks to substation load forecasting. Electric Power Systems Research 38, 1996 (1996), 153–160
Cédric Clastres. Smart grids: Another step towards competition, energy security and climate change objectives. Energy Policy 39, 9 (2011), 5399–5408.
Soma Shekara Sreenadh Reddy Depuru, Lingfeng Wang, and Vijay Devabhaktuni. Smart meters for power grid: Challenges, issues, advantages and status. Renewable and Sustainable Energy Reviews 15, 6 (2011), 2736–2742
T S Dillon, S Sestito, and S Leung. Short term load forecasting using an adaptive neural network. Electrical Power & Energy Systems (1991), 186–192.
Harris Drucker, Chris J C Burges, Linda Kaufman, Alex Smola, and Vladimir Vapnik. 1997. Support vector regression machines. Advances in Neural Information Processing Dystems 1 (1997), 155–161.
Abdollah Kavousi Fard and Mohammad-Reza Akbari-Zadeh. 2014. A hybrid method based on wavelet, ANN and ARIMA model for short-term load forecasting. Journal of Experimental & Theoretical Artificial Intelligence 26, 2 (2014), 167–182.
Commission for Energy Regulation (CER). 2012. CER Smart Metering Project Electricity Customer Behaviour Trial, 2009-2010 (2012). www.ucd.ie/issda/ CER electricity

Cites this article as

M. Amin, D. Kumar, D. S. Saini, "Predicting Electricity Usage of Houses Incorporating Smart Meters", International Journal of Innovative Research in Computer Science and Technology (IJIRCST), Vol-10, Issue-5, Page No-73-79, 2022. Available from: https://doi.org/10.55524/ijircst.2022.10.5.10

Corresponding Author

Musaib Amin

M. Tech Scholar, Department of Electrical Engineering, RIMT University, Mandi Gobingarh, Punjab, India

Download Full Paper

Download PDF

No. of Downloads: 41 | No. of Views: 1457

Predicting Electricity Usage of Houses Incorporating Smart Meters

Citations

Total View 1457

Total Download 41