A Fused Load Curve Clustering Algorithm Based on Wavelet Transform

Jiang, Zigui; Lin, Rongheng; Yang, Fangchun; Wu, Bo

doi:10.1109/tii.2017.2769450

“…So to design the super-customers the discrete transform is good enough, for the final clusters, the continuous transform leads to better results. Let us remark that combining wavelets and clustering has recently been considered in [36] from a different viewpoint: details and approximations of the daily load curves are clustered separately leading to two different partitions which are then fused.…”

Section: Choice Of Methodsmentioning

confidence: 99%

Scalable Clustering of Individual Electrical Curves for Profiling and Bottom-Up Forecasting

Auder

¹

,

Cugliari

²

,

Goude

³

et al. 2018

View full text Add to dashboard Cite

Smart grids require flexible data driven forecasting methods. We propose clustering tools for bottom-up short-term load forecasting. We focus on individual consumption data analysis which plays a major role for energy management and electricity load forecasting. The first section is dedicated to the industrial context and a review of individual electrical data analysis. Then, we focus on hierarchical time-series for bottom-up forecasting. The idea is to decompose the global signal and obtain disaggregated forecasts in such a way that their sum enhances the prediction. This is done in three steps: identify a rather large number of super-consumers by clustering their energy profiles, generate a hierarchy of nested partitions and choose the one that minimize a prediction criterion. Using a nonparametric model to handle forecasting, and wavelets to define various notions of similarity between load curves, this disaggregation strategy gives a 16% improvement in forecasting accuracy when applied to French individual consumers. Then, this strategy is implemented using R-the free software environment for statistical computing-so that it can scale when dealing with massive datasets. The proposed solution is to make the algorithm scalable combine data storage, parallel computing and double clustering step to define the super-consumers. The resulting software is openly available.

show abstract

“…So to design the super-customers the discrete transform is good enough, for the final clusters, the continuous transform leads to better results. Let us remark that combining wavelets and clustering has recently been considered in [35] from a different viewpoint: details and approximations of the daily load curves are clustered separately leading to two different partitions which are then fused.…”

Section: Choice Of Methodsmentioning

confidence: 99%

Scalable Clustering of Individual Electrical Curves for Profiling and Bottom-up Forecasting

Auder¹,

Cugliari²,

Goude³

et al. 2018

Preprint

View full text Add to dashboard Cite

Smart grids require flexible data driven forecasting methods. We propose clustering tools for bottom-up short-term load forecasting. We focus on individual consumption data analysis which plays a major role for energy management and electricity load forecasting. The two first sections are dedicated to the industrial context and a review of individual electrical data analysis. We are interested in hierarchical time-series for bottom-up forecasting. The idea is to disaggregate the signal in such a way that the sum of disaggregated forecasts improves the direct prediction. The 3-steps strategy defines numerous super-consumers by curve clustering, builds a hierarchy of partitions and selects the best one minimizing a forecast criterion. Using a nonparametric model to handle forecasting, and wavelets to define various notions of similarity between load curves, this disaggregation strategy applied to French individual consumers leads to a gain of 16% in forecast accuracy. We then explore the upscaling capacity of this strategy facing massive data and implement proposals using R, the free software environment for statistical computing. The proposed solutions to make the algorithm scalable combines data storage, parallel computing and double clustering step to define the super-consumers.Keywords: Clustering; Forecasting; Hierarchical Time-Series; Individual Electrical Consumers; Scalable; Short Term; Smart Meters; Wavelets Industrial contextEnergy systems are facing a revolution and many challenges. On the one hand, electricity production is moving to more intermittency and complexity with the increase of renewable energy and the development of small distributed production units such as photovoltaic panels or wind farms. On the other hand, consumption is also changing with plug-in (hybrid) electric vehicles, heat pumps, the development of new technologies such as smart phones, computers, robots that often come with batteries. To maintain the electricity quality, energy stakeholders are developing smart grids (see [1,2] This results into new opportunities such as local optimisation of the grid, demand side management and smart control of storage devices. Exploiting the smart grid efficiently requires advanced data analytics and optimisation techniques to improve forecasting, unit commitment, and load planning at different geographical scales. Massive data sets are and will be produced as Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted:

show abstract

“…It is generally an unsupervised classification problem because the daily load curves do not contain any prior knowledge of load patterns. As a result, we adopt a clustering algorithm designed specially for load curve clustering in our previous work [2], the details of which are described in Algorithm 1.…”

Section: Phase 1: Load Pattern Extractionmentioning

confidence: 99%

“…Smart grid system, which is developed for the electric power energy management, aims to enhance the efficiency, reliability and safety of energy consumption by automated control and modern communications technologies [1,2]. The large amount of smart meter data collected in smart grid system contain plenty of knowledge about electricity consumption behaviors so that information processing or machine learning algorithms are required for data analysis [3].…”

Section: Introductionmentioning

confidence: 99%

“…Consumer categorization based on load profiling is the focus of this paper. In the studies of load profiling [2,10,11], the typical electricity consumption behaviors, also called load patterns, of each consumer can be extracted by daily load curve clustering using smart meter data. For electricity consumers in various types, such as residential, commercial and industrial, it is supposed that they may have diverse load patterns, even for their same types [12,13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Machine Learning Model for Electricity Consumer Categorization Using Smart Meter Data

Jiang

¹

,

Lin

²

,

Yang

³

2018

Self Cite

View full text Add to dashboard Cite

Time-series smart meter data can record precisely electricity consumption behaviors of every consumer in the smart grid system. A better understanding of consumption behaviors and an effective consumer categorization based on the similarity of these behaviors can be helpful for flexible demand management and effective energy control. In this paper, we propose a hybrid machine learning model including both unsupervised clustering and supervised classification for categorizing consumers based on the similarity of their typical electricity consumption behaviors. Unsupervised clustering algorithm is used to extract the typical electricity consumption behaviors and perform fuzzy consumer categorization, followed by a proposed novel algorithm to identify distinct consumer categories and their consumption characteristics. Supervised classification algorithm is used to classify new consumers and evaluate the validity of the identified categories. The proposed model is applied to a real dataset of U.S. non-residential consumers collected by smart meters over one year. The results indicate that large or special institutions usually have their distinct consumption characteristics while others such as some medium and small institutions or similar building types may have the same characteristics. Moreover, the comparison results with other methods show the improved performance of the proposed model in terms of category identification and classifying accuracy.

show abstract

A Fused Load Curve Clustering Algorithm Based on Wavelet Transform

Cited by 46 publications

References 24 publications

Scalable Clustering of Individual Electrical Curves for Profiling and Bottom-Up Forecasting

Scalable Clustering of Individual Electrical Curves for Profiling and Bottom-Up Forecasting

Scalable Clustering of Individual Electrical Curves for Profiling and Bottom-up Forecasting

A Hybrid Machine Learning Model for Electricity Consumer Categorization Using Smart Meter Data

Contact Info

Product

Resources

About