A secure edge monitoring approach to unsupervised energy disaggregation using mean shift algorithm in residential buildings

Liu, Qi; Nakoty, Francis Mawuli; Wu, Xueyan; Anaadumba, Raphael; Liu, Xiaodong; Zhang, Yonghong; Qi, Lianyong

doi:10.1016/j.comcom.2020.08.024

Cited by 11 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under the background of the various power acquisition equipment and the rapid development of the Internet of Smart Grids (IoSG), Intelligent equipment is gradually used for load data RT acquisition at various power consumption sides. [1][2][3][4][5] The popularity of smart sockets creates favorable conditions for using edge computing when processing and analyzing a large number of power load data. 6,7 Since the end of the epidemic, the society has resumed business and production, and the load power consumption of the whole society has increased sharply.…”

Section: Introductionmentioning

confidence: 99%

A spatio‐temporal graph convolutional approach to real‐time load forecasting in an edge‐enabled distributed Internet of Smart Grids energy system

Liu,

Pan,

Cao

et al. 2024

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

SummaryAs the edge nodes of the Internet of Smart Grids (IoSG), smart sockets enable all kinds of power load data to be analyzed at the edge, which create conditions for edge calculation and real‐time (RT) load forecasting. In this article, an edge‐cloud computing analysis energy system is proposed to collect and analyze power load data, and a combination of graph convolutional network (GCN) with LSTM, called KGLSTM is used to achieve mid‐long term mixed sequential mode RT forecasting. In the proposed edge‐cloud framework, distributed intelligent sockets are regarded as edge nodes to collect, analyze and upload data to cloud services for further processing. The proposed KGLSTM network adopts a double branch structure. One branch extracts the data characteristics of mid‐short term time‐series data through an encoding–decoding LSTM module; the other branch extracts the data features of long term timing data through an adapted GCN. GCN is used to extract spatial correlations between different nodes. In addition, by combining a dynamic weighted loss function, the accuracy of peak forecasting is effectively improved. Finally, through various experimental indicators, this article shows that KGLSTM and weighted KGLSTM have achieved significant performance improvement over recent methods in mid‐long term time‐series forecasting and peak forecasting.

show abstract

Section: Introductionmentioning

confidence: 99%

A spatio‐temporal graph convolutional approach to real‐time load forecasting in an edge‐enabled distributed Internet of Smart Grids energy system

Liu,

Pan,

Cao

et al. 2024

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning has been applied to identify and disaggregate loads, including SVM [12,26], k-NN [27], DT [7], RF [6], k-means [12], FCM [13], mean-shift [28], etc. In [26], load state transition events are detected heuristically and classified by an SVM model, featuring duration, average power, maximum power and power variance.…”

Section: Introductionmentioning

confidence: 99%

“…However, prior knowledge including the number of clusters is required. For breaking this limitation, Liu et al apply mean-shift algorithm to group the transient states detected based on their magnitudes [28]. Note that small bandwidth is set for guaranteeing NILM performance while increasing convergence duration.…”

Section: Introductionmentioning

confidence: 99%

Apply Graph Signal Processing on NILM: An Unsupervised Approach Featuring Power Sequences

Zhao

Luan

et al. 2023

Sensors

View full text Add to dashboard Cite

As a low-cost demand-side management application, non-intrusive load monitoring (NILM) offers feedback on appliance-level electricity usage without extra sensors. NILM is defined as disaggregating loads only from aggregate power measurements through analytical tools. Although low-rate NILM tasks have been conducted by unsupervised approaches based on graph signal processing (GSP) concepts, enhancing feature selection can still contribute to performance improvement. Therefore, a novel unsupervised GSP-based NILM approach with power sequence feature (STS-UGSP) is proposed in this paper. First, state transition sequences (STS) are extracted from power readings and featured in clustering and matching, instead of power changes and steady-state power sequences featured in other GSP-based NILM works. When generating graph in clustering, dynamic time warping distances between STSs are calculated for similarity quantification. After clustering, a forward-backward power STS matching algorithm is proposed for searching each STS pair of an operational cycle, utilizing both power and time information. Finally, load disaggregation results are obtained based on STS clustering and matching results. STS-UGSP is validated on three publicly accessible datasets from various regions, generally outperforming four benchmarks in two evaluation metrics. Besides, STS-UGSP estimates closer energy consumption of appliances to the ground truth than benchmarks.

show abstract

“…However, HMM-based NILM methods require good quality data to build the models, suffer from noise caused by unknown appliances, and are ineffective for rarely used appliances or appliances that are never used alone [ 8 , 11 , 25 ]. Some other unsupervised methods include: time-series approaches ( e.g., [ 26 ]) that require building a database of time-series signatures necessary for pattern matching; fuzzy-clustering regression trees-based approaches [ 27 , 28 ]; various edge detectors, e.g., mean shift proposed in [ 29 ]; and optimization-based methods [ 30 ] that are limited to small number of appliances. Bonfigli et al [ 31 ] provided an overview of unsupervised NILM methods with performance comparison.…”

Section: Introductionmentioning

confidence: 99%

Building a Graph Signal Processing Model Using Dynamic Time Warping for Load Disaggregation

Stanković

2020

Sensors

View full text Add to dashboard Cite

Building on recent unsupervised Non-intrusive load monitoring (NILM) algorithms that use graph Laplacian regularization (GLR) and achieve state-of-the-art performance, in this paper, we propose a novel unsupervised approach to design an underlying graph to model the correlation within time-series smart meter measurements. We propose a variable-length data segmentation approach to extract potential events, assign all measurements associated with an identified event to each graph node, employ dynamic time warping to define the adjacency matrix of the graph, and propose a robust cluster labeling approach. Our simulation results on four different datasets show up to 10% improvement in classification performance over competing approaches.

show abstract

A secure edge monitoring approach to unsupervised energy disaggregation using mean shift algorithm in residential buildings

Cited by 11 publications

References 32 publications

A spatio‐temporal graph convolutional approach to real‐time load forecasting in an edge‐enabled distributed Internet of Smart Grids energy system

A spatio‐temporal graph convolutional approach to real‐time load forecasting in an edge‐enabled distributed Internet of Smart Grids energy system

Apply Graph Signal Processing on NILM: An Unsupervised Approach Featuring Power Sequences

Building a Graph Signal Processing Model Using Dynamic Time Warping for Load Disaggregation

Contact Info

Product

Resources

About