Cluster analysis for primary feeder identification using metering data

Khumchoo, Kanarat Y.; Kongprawechnon, Waree

doi:10.1109/ictemsys.2015.7110831

Cited by 7 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An algorithm for identifying the topology of LV networks when the customers are not equipped with smart meters, referred to as nodes, is proposed by [175], [176] and further verified by evaluating its performance on several customers with or without smart meters. Wavelet reduction-based clustering is suggested by [177] to accurately categorize clients. A model that builds the LV system while removing load distortion, or the variation in voltage from the feeder to the smart meter at the connecting point, is proposed by [178].…”

Section: E Low-voltage (Lv) Networkmentioning

confidence: 99%

Smart Meters for Smart Energy: A Review of Business Intelligence Applications

Raza,

Rind,

Javed

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Smart Energy (SE) has emerged as a critical technology in tackling global challenges like climate change while addressing the rising energy demands driven by today's data-intensive industrial revolution. SE integrates information and communication technologies into energy systems, optimizing them to meet these challenges effectively. At the core of SE operations are smart meters, playing a fundamental role in ensuring efficient functionality. These devices collect data, which is then leveraged to derive Business Intelligence (BI) for operations across the entire spectrum, from the sensing infrastructure to the cloud, primarily utilizing the Internet of Things (IoT) technology framework. With the increasing complexity of operations and the growing demand for optimization and enhanced functionality, the SE technology stack is evolving to integrate across all layers and domains. This integration has led to the stratification of computational load across IoT layers, intensifying the dependence on smart meter data for BI. Consequently, smart meters themselves have evolved to become more functional and complex. This paper's novelty lies in its comprehensive exploration of the integration of BI with smart meter data. It delves into various aspects, including the different layers of intelligent operations within SE systems, the current state of the art, and diverse implementations of smart meters and their applications across operational locations, ranging from consumers to fog computing. The paper concludes by identifying research gaps and future directions, offering insights into the evolving requirements for the next generation of SE systems and the necessary adaptations in smart metering infrastructure to support these roles. This work contributes to a better understanding of the evolving landscape of data and computation in the context of SE, facilitating more efficient and effective energy management solutions.

show abstract

Section: E Low-voltage (Lv) Networkmentioning

confidence: 99%

Smart Meters for Smart Energy: A Review of Business Intelligence Applications

Raza,

Rind,

Javed

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In recent years, some works consider classifying new consumers after consumer grouping. Khumchoo and Kongprawechnon [35] proposed a method combining two approaches: clustering and SVM classification. Clustering is applied in the first stage for customer categorization based on pattern similarity.…”

Section: Related Workmentioning

confidence: 99%

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

2018

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

“…Owing to the vast amount of data recorded by these meters [2], the concept of big data analytics is in the vogue. Recent research has explored using the data recorded by the smart‐meter for: detection of electricity theft [3–5], determining typical customer consumption patterns [6], load forecasting [6], and determining the topology and parameters of the low‐voltage (LV) network [7–19], among other aspects. This paper presents a contribution in the latter area of determining the topology of the LV distribution system.…”

Section: Introductionmentioning

confidence: 99%

“…The requirements are that the measurement noise is limited and the number of samples is sufficiently large. Khumchoo and Kongprawechnon [16] proposed the use of clustering based on the wavelet reduction to classify customers correctly. A similar procedure in this trial was unable to identify all customers correctly, probably due to the low ‘coverage ratio’ in our trial.…”

Section: Introductionmentioning

confidence: 99%