Power consumption behavior analysis based on cluster analysis

Yuan, Xinya; Cai, Qinyuan; Deng, Song

doi:10.1117/12.2605823

Cited by 4 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models have been adopted by researchers to explore household energy consumption routines and practices and identify factors that influence this consumption [24][25][26][27][28]. From this, intervention strategies have been developed, aimed at changing people's energy use behaviour resulting in energy savings and conservation [29][30][31][32][33][34].…”

Section: Home System Of Practicementioning

confidence: 99%

“…The dataset was analysed through a K-means clustering algorithm to recognise these patterns. This technique is widely used in electricity analysis to identify variations in energy profiles and to forecast consumption [31,33,44,46,48,53,[65][66][67]. This unsupervised approach to grouping the data into clusters aims to minimise the distance between all points of their cluster centre [68].…”

Section: K-means Clusteringmentioning

confidence: 99%

See 1 more Smart Citation

Distinguishing Household Groupings within a Precinct Based on Energy Usage Patterns Using Machine Learning Analysis

Malatesta

Breadsell

et al. 2023

Energies

View full text Add to dashboard Cite

The home can be a complex environment to understand, as well as to model and predict, due to inherent variability between people’s routines and practices. A one-size-fits-all approach does not consider people’s contextual and institutional influences that contribute to their daily routines. These contextual and institutional factors relate to the household structure and relationship between occupants, as well as the working lifestyle of the occupants. One household can consume resources and live quite differently compared to a similar size household with the same number of occupants due to these factors. Predictive analysis of consumption data can identify this difference to create household-specific modelling to predict occupant routines and practices. Using post-occupancy data from the Fairwater Living Laboratory in Sydney that monitored 39 homes built in a green-star community, this research has utilised machine learning approaches and a K-Means clustering method complemented by t-distributed Stochastic Neighbour Embedding (t-SNE) to show how households follow different daily routines and activities resulting in resource consumption. This analysis has identified energy usage patterns and household groupings with each group following similar daily routines and consumption. The comparison between modelling the precinct as a whole and modelling households individually shows how detail can be lost when aggregating household data at a precinct/community level. This detail can explain why policies or technologies are not as effective as their design due to ignoring the delicate aspects of household routines and practices. These household groupings can provide insight for policymakers to help them understand the different profiles that may be present in the community. These findings are useful for net-zero developments and decarbonization of the built environment through modelling occupant behaviour accurately and developing policies and technologies to suit.

show abstract

Section: Home System Of Practicementioning

confidence: 99%

Section: K-means Clusteringmentioning

confidence: 99%

Distinguishing Household Groupings within a Precinct Based on Energy Usage Patterns Using Machine Learning Analysis

Malatesta

Breadsell

et al. 2023

Energies

View full text Add to dashboard Cite

show abstract

“…The energy consumption data were analysed through a k-means clustering algorithm to recognise patterns in the dataset. This technique is often use for energy datasets and utilised in the electricity market to identify variation in energy profiles and to forecast future demand [59][60][61][62][63][64][65]. The k-means algorithm is an unsupervised approach to partitioning and grouping data into clusters that aims to minimise the distance between all points and their cluster centre [66,67].…”

Section: Data Collection and Analysismentioning

confidence: 99%

“…future demand [59][60][61][62][63][64][65]. The k-means algorithm is an unsupervised approach to partitioning and grouping data into clusters that aims to minimise the distance between all points and their cluster centre [66,67].…”

mentioning

confidence: 99%

Identifying Home System of Practices for Energy Use with K-Means Clustering Techniques

Malatesta

Breadsell

2022

Sustainability

View full text Add to dashboard Cite

Human behaviour is a major driver and determinant of household energy consumption, with routines and practices shaping daily energy profiles. These routines and practices are made up of individual lifestyles and other contextual factors that vary from home to home. Social and psychological theories aim to explain and describe how people consume resources in the home, which has resulted in the development of the home system of practice. This evaluates how occupants live and follow multiple routines which result in varying energy consumption practices. This paper develops a methodology to identify and support the concept of the home system of practice using a data analytical approach and link it to residential energy and distribution network management. This paper utilises k-means cluster analysis to identify these different home systems of practices and routines in energy use by using real-time energy consumption data from July 2019 to March 2021 from a living laboratory in Australia. The results of the analysis show the different daily energy profiles for each of the 39 households, with some homes observing large fluctuations and changes in the way they consume energy during the day. Specific homes were discussed as case studies in this paper focusing on linking the occupants’ contextual factors to their energy profiles. This variation is discussed in terms of the routines of the occupants and associated lifestyles that explain why some energy peaks occurred at different parts of the day and differed during the COVID-19 lockdown period in Australia. The paper conducts a comparison between these case studies to show how people’s lifestyles impact household energy consumption (and variation). These case studies investigated the heating and cooling practices of the occupants to demonstrate how they impact overall consumption. This variation is discussed in relation to energy management and prediction of when homes will consume energy to assist in net-zero energy developments and grid stabilisation operations.

show abstract

A Novel Multi-Objective Hybrid Evolutionary-Based Approach for Tuning Machine Learning Models in Short-Term Power Consumption Forecasting

Vakhnin,

Ryzhikov,

Niska

et al. 2024

View full text Add to dashboard Cite

Accurately forecasting power consumption is crucial important for efficient energy management. Machine learning (ML) models are often employed for this purpose. However, tuning their hyperparameters is a complex and time-consuming task. The article presents a novel multi-objective (MO) hybrid evolutionary-based approach, GA-SHADE-MO, for tuning ML models aimed at solving the complex problem of forecasting power consumption. The proposed algorithm simultaneously optimizes both hyperparameters and feature sets across six different ML models, ensuring enhanced accuracy and efficiency. The study focuses on predicting household power consumption at hourly and daily levels. The hybrid MO evolutionary algorithm integrates elements of genetic algorithms and self-adapted differential evolution. By incorporating MO optimization, GA-SHADE-MO balances the trade-offs between model complexity (the number of used features) and prediction accuracy, ensuring robust performance across various forecasting scenarios. Experimental numerical results show the superiority of the proposed method compared to traditional tuning techniques, and random search, showcasing significant improvements in predictive accuracy and computational efficiency. The findings suggest that the proposed GA-SHADE-MO approach offers a powerful tool for optimizing ML models in the context of energy consumption forecasting, with potential applications in other domains requiring precise predictive modeling. The study contributes to the advancement of ML optimization techniques, providing a framework that can be adapted and extended for various predictive analytics tasks.

show abstract

Power consumption behavior analysis based on cluster analysis

Cited by 4 publications

References 20 publications

Distinguishing Household Groupings within a Precinct Based on Energy Usage Patterns Using Machine Learning Analysis

Distinguishing Household Groupings within a Precinct Based on Energy Usage Patterns Using Machine Learning Analysis

Identifying Home System of Practices for Energy Use with K-Means Clustering Techniques

A Novel Multi-Objective Hybrid Evolutionary-Based Approach for Tuning Machine Learning Models in Short-Term Power Consumption Forecasting

Contact Info

Product

Resources

About