.png){kind=icon}
.png){kind=icon}
Return
k-Shape clustering algorithm for building energy usage patterns analysis and forecasting model accuracy improvement
.png){kind=icon}
PRE
AI
DOI：10.1016/j.enbuild.2017.03.071.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Clustering algorithms have been successfully applied in analyzing building energy consumption data. It has proven to be an effective technique to identify representative energy consumption patterns as well as being a pre-processing step for other techniques. In this paper, we propose a clustering method based on k-shape algorithm, which is a relatively novel method to identify shape patterns in time-series data. In the experiment, clustering is performed for each individual building according to its hourly consumption. The novelty of this paper is that a new k-shape algorithm is applied to detect building-energy usage patterns at different levels, and the clustering result is further utilized to improve the accuracy of forecasting models. Ten institutional buildings covering three different typologies are used as case studies and a set of hourly and weekly energy consumption data is further analyzed in this paper. The experimental results reveal that this proposed method can detect building energy usage patterns in different time granularity effectively and also proves that the forecasting accuracy of SVR model is significantly improved by utilizing the results of the proposed clustering method. (C) 2017 Elsevier B.V. All rights reserved.
Keywords:
LOAD
VALIDATION
PREDICTION
INDEXES
SYSTEMS
NUMBER
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.1
Papers:
1.5W
Citations:
6.8W