Extracting Effective Features for Descriptive Analysis of Household Energy Consumption Using Smart Home Data

The household energy consumption has a large share of global energy consumption. To have better understanding of energy generation, management and surplus storage, we need to discover implicit patterns of consumers’ behavior and identify the factors affecting their performance. The main goal of this paper is to descriptively analyze the pattern of household energy consumption using RECS2015 dataset. To this end, we focus on selecting the most effective subset of features from high dimensional dataset that leads to a better understanding of data, reducing computation time and improving prediction performance. The result of this study can help decision makers to investigate the living conditions of families in different levels of society to ensure that their life style is well enough or should be improved.

[1]  Chunyu Bai,et al.  Exploring the influencing factors and decoupling state of residential energy consumption in Shandong , 2018, Journal of Cleaner Production.

[2]  Mansour Sheikhan,et al.  Neural-based electricity load forecasting using hybrid of GA and ACO for feature selection , 2011, Neural Computing and Applications.

[3]  B. Dong,et al.  A survey on energy consumption and energy usage behavior of households and residential building in urban China , 2017 .

[4]  Xiaojun Wang,et al.  Short-term load forecasting based on big data technologies , 2015 .

[5]  Irena Koprinska,et al.  Correlation and instance based feature selection for electricity load forecasting , 2015, Knowl. Based Syst..

[6]  Krzysztof Gajowniczek,et al.  Data Mining Techniques for Detecting Household Characteristics Based on Smart Meter Data , 2015 .

[7]  Ivan V. Bajic,et al.  Incorporating time-of-day usage patterns into non-intrusive load monitoring , 2017, 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[8]  R. Inglesi‐Lotz,et al.  Analysing the South African residential sector's energy profile , 2018, Renewable and Sustainable Energy Reviews.

[9]  Raymond Chiong,et al.  Hybrid filter-wrapper feature selection for short-term load forecasting , 2015, Eng. Appl. Artif. Intell..

[10]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[11]  Alicia Troncoso Lora,et al.  Finding Electric Energy Consumption Patterns in Big Time Series Data , 2016, DCAI.

[12]  Nikola Bogunovic,et al.  A review of feature selection methods with applications , 2015, 2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO).

[13]  Farshid Keynia,et al.  Day-ahead price forecasting of electricity markets by a new feature selection algorithm and cascaded neural network technique , 2009 .