Abstract
This paper builds a power consumption prediction model based on artificial neural networks, aiming at achieving accurate demand forecasting in the smart grid system as well as acquiring power consumption profiles for demand response purposes. The metering data processing framework consists of smart plugs, Zigbee gateways, WLAN access points, and a high-capacity data server. The power consumption sequence belongs to non-linear time series and usually takes the shape of square waves. Our neural network model consists of 5 input nodes for the previous 5 consecutive meter readings, 1 output node for predicted value, and 30 hidden nodes for inter-variable dependency. According to the accuracy evaluation after 500 training iterations, our model quite precisely detects rising and falling edges irrespective of the length of non-bottom levels. In addition, prediction error is mostly less than 0.2 and mainly brought by the underestimation of sharp drops.
This research was supported by the MKE (The Ministry of Knowledge Economy), Republic of Korea, under IT/SW Creative research program supervised by the NIPA (National IT Industry Promotion Agency) (NIPA-2012-(H0502-12-1002)).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Luan, S., Teng, J., Chan, S., Hwang, L.: Development of a Smart Power Meter for AMI Based on ZigBee Communication. In: Power Electronics and Drive Systems, pp. 661–665 (2009)
Silva, D., Yu, X., Alahakoon, D., Holmes, G.: Semi-Supervised Classification of Characterized Patterns for Demand Forecasting using Smart Electricity Meters. In: International Conference on Electrical Machines and Systems, pp. 1–6 (2011)
Morrow, K., Karner, D., Francfort, J.: Plug-in Hybrid Electric Vehicle Charging Infrastructure Review. Battelle Energy Alliance (2008)
Bonneville, E., Rialhe, A.: Demand side Management for Residential and Commercial End-Users (2006), http://www.leonardo-energy.org/Files/DSM-commerce.pdf
Abras, S., Pesty, S., Ploix, S., Jacomino, M.: An Anticipation Mechanism for Power Management in a Smart Home Using Multi-Agent Systems. In: 3rd International Conference on from Theory to Applications, pp. 1–6 (2008)
Lee, J., Kim, H., Park, G., Kang, M.: Energy Consumption Scheduler for Demand Response Systems in the Smart Grid. To appear in Journal of Information Science and Engineering (2012)
Methaprayoon, K., Yingvivatanapong, C., Lee, W., Liao, J.: An Integration of ANN Wind Power Estimation into Unit Commitment Considering the Forecasting Uncertainty. IEEE Transactions on Industry Applications 43, 1441–1448 (2007)
Tan, Y., Liu, W., Qiu, Q.: Adaptive Power Management Using Reinforcement Learning. In: IEEE/ACM International Conference on Computer-Aided Design, pp. 461–467 (2009)
Nissen, S.: Neural Network Made Simple. Software 2.0 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, J., Kim, Yc., Park, GL. (2012). An Analysis of Smart Meter Readings Using Artificial Neural Networks. In: Lee, G., Howard, D., Kang, J.J., Ślęzak, D. (eds) Convergence and Hybrid Information Technology. ICHIT 2012. Lecture Notes in Computer Science, vol 7425. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32645-5_23
Download citation
DOI: https://doi.org/10.1007/978-3-642-32645-5_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32644-8
Online ISBN: 978-3-642-32645-5
eBook Packages: Computer ScienceComputer Science (R0)