A Demand Response Scheme in Smart Grid with Clustering of Residential Customers

Dai, Bijian; Wang, Ran; Zhu, Kun; Hao, Jie; Wang, Ping

doi:10.1109/smartgridcomm.2019.8909776

Cited by 7 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Equations ( 3)- (5) show the formulations for the entropy calculation. In Eq.3, 𝛤 𝑐 is the sum of values of feature z related to each sample 𝑥 𝑖,𝑧 in an individual cluster c .…”

Section: A Structure Of the Proposed Methodsmentioning

confidence: 99%

“…In [4], a demand response (DR) model is proposed for residential consumers to change their consumption pattern with the aim of maximizing their utility. In [5], residential customers are clustered in a flexible DR scheme for which customers' electricity consumption habits is analyzed utilizing historical data. In [6], energy consumption of customers is classified using smart meters data.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Change Detection in Electricity Consumption Patterns Utilizing Adaptive Information Theoretic Algorithms

Kojury-Naftchali

Fereidunian

Savaghebi

et al. 2021

IEEE Systems Journal

View full text Add to dashboard Cite

Section: A Structure Of the Proposed Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

Change Detection in Electricity Consumption Patterns Utilizing Adaptive Information Theoretic Algorithms

Kojury-Naftchali

Fereidunian

Savaghebi

et al. 2021

IEEE Systems Journal

View full text Add to dashboard Cite

“…[Liu et al, 2015] proposed Periodic Auto Regression [PAR] algorithm to excerpt consumption profiles of consumers and the time series similarity search algorithms to discover analogous consumers to form cluster. A flexible DR scheme in smart grid with K-means clustering algorithm of residential customers and broadly considering the factors such as Building type, House construction year, Total room number, Total square footage, Total appliance number were proposed by authors to extract new features from past data to describe customers' characteristics and clustering methods applied to explore their electricity consumption behaviours [Dai et al, 2019]. [Kleiminger et al, 2013] offered and assessed an approach that influences electricity smart meters as occupancy sensors using stateless and stateful classification algorithms where stateless classifiers were Support Vector Machines [SVM], K-Nearest Neighbour [KNN] and Thresholding [THR] and stateful classifier was Hidden Markov model [HMM] using a data set collected during an 8-month long experiment run in 5 households.…”

Section: Literature Reviewmentioning

confidence: 99%

Electricity Consumption Patterns Using Som-Based Twolevel Clustering of Residential Households

Chavda¹,

Pandya²,

Kotwal³

2022

INDJCSE

View full text Add to dashboard Cite

Electricity consumption in residential households' accounts for a huge share of energy use, which encourages researchers, policy makers towards energy conservation of residential household. The goal of Clustering using Unsupervised Machine Learning algorithms is to find likenesses in the data point of D-EC and cluster similar data points of D-EC together. This paper emphasis on application of machine learning techniques for pattern identification with the implementation of dimension reduction technique Self-Organizing Map algorithm trailed by unsupervised clustering algorithms such as K-means, Gaussian Mixture clustering, MiniBatchKMeans, Agglomerative Clustering, Spectral Clustering on D-EC data of electrical usage. Consumers classified into 4 clusters and labelled as per the usage pattern, also identified as a consistent and non-consistent consumer based on their electricity usage. A proposed methodology concluded using SOM followed by Kmeans algorithm which helpful for awareness and alerts to consumers based on consumption patterns participates in demand-supply decision making with timely recommendation.

show abstract

“…A model was proposed to generate data by monitoring the residential load with respect to frequency regulation. [30] Focused on extracting new features (e.g. : energy consumption pattern, consumer behavior, etc.)…”

Section: Google Trends On Analytics Machine Learning and Artificial Intelligencementioning

confidence: 99%

Simple and effective descriptive analysis of missing data anomalies in smart home energy consumption readings

Prakash¹,

Kumar²

2021

Journal of Energy Systems

View full text Add to dashboard Cite

Smart grids evolution is ramping up in the global energy scenario by offering deregulated markets, demandside management, prosumer culture, demand response, contingency forecasting, outage management, etc., functionalities. These functionalities help to manage the grid effectively by taking informed decisions timely. Further, the progressive developments in information and communication technologies improve smartness in the power grids. Especially, smart homes are playing a key role, which possesses the communication between various devices/appliances and collect their functional data in terms of energy consumption readings, timestamp, etc. However, the availability of high-quality data is always desired to achieve superior benefits with respect to all the above-mentioned functionalities. But, the failures of communication networks, metering devices, server station issues, etc., create anomalies in the data collection. Hence, there is a dire need of identifying the ways of analyzing the smart home data to find the irregularities that occurred because of aforesaid failures. Especially, it has been a common problem to see missing data at some particular instants in the overall database captured. In this view, this paper proposes a simple and effective descriptive analysis to find missing data anomalies in smart home energy consumption data. A real-time dataset is used to execute the proposed method. For which, a clear enumeration of missing data is visualized using comprehensive simulation results. This helps to realize the actual problems that are hidden in the energy consumption data.

show abstract

A Demand Response Scheme in Smart Grid with Clustering of Residential Customers

Cited by 7 publications

References 13 publications

Change Detection in Electricity Consumption Patterns Utilizing Adaptive Information Theoretic Algorithms

Change Detection in Electricity Consumption Patterns Utilizing Adaptive Information Theoretic Algorithms

Electricity Consumption Patterns Using Som-Based Twolevel Clustering of Residential Households

Simple and effective descriptive analysis of missing data anomalies in smart home energy consumption readings

Contact Info

Product

Resources

About