A Pattern Recognition Approach for Peak Prediction of Electrical Consumption

Abstract : Predicting and mitigating demand peaks in electrical networks has become a prevalent research topic. Demand peaks pose a particular challenge to energy companies because these are difficult to foresee and require the net to support abnormally high consumption levels. In smart energy grids, time-differentiated pricing policies that increase the energy cost for the consumers during peak periods, and load balancing are examples of simple techniques for peak regulation. In this paper, we tackle the task of predicting power peaks prior to their actual occurrence in the context of a pilot Norwegian smart grid network.While most legacy studies formulate the problem as time-series-based estimation problem, we take a radically different approach and map it to a classical pattern recognition problem using a simple but subtle formulations. Among the key findings of this study is the ability of the algorithms to accurately detect 80% of energy consumption peaks up to one week ahead of time. Further, different classification methods have been rigorously tested and applied on real-life data from a Norwegian smart grid pilot project.
Document type :
Conference papers
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.inria.fr/hal-01391323
Contributor : Hal Ifip <>
Submitted on : Thursday, November 3, 2016 - 10:58:55 AM
Last modification on : Friday, December 1, 2017 - 1:16:36 AM
Long-term archiving on : Saturday, February 4, 2017 - 1:26:44 PM

File

978-3-662-44654-6_26_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Morten Goodwin, Anis Yazidi. A Pattern Recognition Approach for Peak Prediction of Electrical Consumption. 10th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2014, Rhodes, Greece. pp.265-275, ⟨10.1007/978-3-662-44654-6_26⟩. ⟨hal-01391323⟩

Share

Metrics

Record views

81

Files downloads

444