Data mining of smart meters for load category based disaggregation of residential power consumption

Zhang, Guanchen; Wang, G. Gary; Farhangi, Hassan; Palizban, Ali

doi:10.1016/j.segan.2017.03.006

Cited by 34 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The overall average of F-measure performance was analyzed to be 81.5%. Zhang et al [23] disaggregated each load every hour using the weighted least square (WLS) method. This algorithm identified load categories by power factors.…”

Section: Algorithmsmentioning

confidence: 99%

“…However, Zhang et al [23] and Bonfigli et al [25], who utilized real and reactive power as the signature, analyzed the identification accuracy to be over 80% and 90.2% (highest accuracy among many cases), respectively. As the real and reactive powers may have different identification However, Zhang et al [23] and Bonfigli et al [25], who utilized real and reactive power as the signature, analyzed the identification accuracy to be over 80% and 90.2% (highest accuracy among many cases), respectively. As the real and reactive powers may have different identification accuracies depending on research conditions, this study selected current as the identification signature.…”

Section: Signaturesmentioning

confidence: 99%

See 1 more Smart Citation

Load Disaggregation via Pattern Recognition: A Feasibility Study of a Novel Method in Residential Building

2018

View full text Add to dashboard Cite

Abstract:In response to the need to improve energy-saving processes in older buildings, especially residential ones, this paper describes the potential of a novel method of disaggregating loads in light of the load patterns of household appliances determined in residential buildings. Experiments were designed to be applicable to general residential buildings and four types of commonly used appliances were selected to verify the method. The method assumes that loads are disaggregated and measured by a single primary meter. Following the metering of household appliances and an analysis of the usage patterns of each type, values of electric current were entered into a Hidden Markov Model (HMM) to formulate predictions. Thereafter, the HMM repeatedly performed to output the predicted data close to the measured data, while errors between predicted and the measured data were evaluated to determine whether they met tolerance. When the method was examined for 4 days, matching rates in accordance with the load disaggregation outcomes of the household appliances (i.e., laptop, refrigerator, TV, and microwave) were 0.994, 0.992, 0.982, and 0.988, respectively. The proposed method can provide insights into how and where within such buildings energy is consumed. As a result, effective and systematic energy saving measures can be derived even in buildings in which monitoring sensors and measurement equipment are not installed.

show abstract

Section: Algorithmsmentioning

confidence: 99%

Section: Signaturesmentioning

confidence: 99%

Load Disaggregation via Pattern Recognition: A Feasibility Study of a Novel Method in Residential Building

2018

View full text Add to dashboard Cite

show abstract

“…The reliability of smart meters has a fundamental significance for heat distributors and consumers, since the quality of collected data, the correctness of billing of heat, and making proper decisions in managing heat distribution network depend on it. Unfortunately, studies on the smart meters' reliability are scarce, and most of the published papers focus on electricity meters and the prediction of power consumption, e.g., [9,10] described a non-intrusive load monitoring (NILM) algorithm to provide customers with the breakdown of their energy consumption.…”

Section: Introductionmentioning

confidence: 99%

Using Different ML Algorithms and Hyperparameter Optimization to Predict Heat Meters’ Failures

Pałasz

Przysowa

2019

Applied Sciences

View full text Add to dashboard Cite

The need to increase the energy efficiency of buildings, as well as the use of local renewable heat sources has caused heat meters to be used not only to calculate the consumed energy, but also for the active management of central heating systems. Increasing the reading frequency and the use of measurement data to control the heating system expands the requirements for the reliability of heat meters. The aim of the research is to analyze a large set of meters in the real network and predict their faults to avoid inaccurate readings, incorrect billing, heating system disruption, and unnecessary maintenance. The reliability analysis of heat meters, based on historical data collected over several years, shows some regularities, which cannot be easily described by physics-based models. The failure rate is almost constant and does depend on the past, but is a non-linear combination of state variables. To predict meters’ failures in the next billing period, three independent machine learning models are implemented and compared with selected metrics, because even the high performance of a single model (87% true positive for neural network) may be insufficient to make a maintenance decision. Additionally, performing hyperparameter optimization boosts the models’ performance by a few percent. Finally, three improved models are used to build an ensemble classifier, which outperforms the individual models. The proposed procedure ensures the high efficiency of fault detection (>95%), while maintaining overfitting at the minimum level. The methodology is universal and can be utilized to study the reliability and predict faults of other types of meters and different objects with the constant failure rate.

show abstract

“…The previous works on meters focus mainly on the so-called 'smart meters', which most frequently provide large amounts of information concerning the current consumption of electric energy ( [15], [16] or [17]). The analysis of this data usually regards the predicted energy consumption ( [18], [19]), rarely the reliability of the devices alone ( [15], [10]).…”

Section: Introductionmentioning

confidence: 99%

“…Visual Studio 2017 -integrated development environment supporting various programming languages, including PythonAll tests were performed on the computer equipped with the Intel Core i7-6820HQ@2.70GHz processor,16.0 GB RAM, Toshiba SSD PCIe M.2 512GB, with Windows 7 operating system. Building and evaluation of the models were always based on the same dataset (51890 records), randomly divided into the training set (80% -41512 records) and the testing set (20% -10378 records).…”

mentioning

confidence: 99%

Predicting Heat Meters’ Failures With Selected Machine Learning Models

Pałasz¹,

Przysowa²

2018

Preprint

View full text Add to dashboard Cite

Heat metres are used to calculate the consumed energy in central heating systems. The subject of this article is to prepare a method of predicting a failure of a heat meter in the next settlement period. Predicting failures is essential to coordinate the process of exchanging the heat metres and to avoid inaccurate readings, incorrect billing and additional costs. The reliability analysis of heat metres was based on historical data collected over many years. Three independent models of machine learning were proposed, and they were applied to predict failures of metres. The efficiency of the models was confirmed and compared using the selected metrics. The optimisation of hyperparameters characteristics for each of models was successfully applied. The article shows that the diagnostics of devices does not have to rely only on newly collected information, but it is also possible to use the existing big data sets.

show abstract

Data mining of smart meters for load category based disaggregation of residential power consumption

Cited by 34 publications

References 11 publications

Load Disaggregation via Pattern Recognition: A Feasibility Study of a Novel Method in Residential Building

Load Disaggregation via Pattern Recognition: A Feasibility Study of a Novel Method in Residential Building

Using Different ML Algorithms and Hyperparameter Optimization to Predict Heat Meters’ Failures

Predicting Heat Meters’ Failures With Selected Machine Learning Models

Contact Info

Product

Resources

About

Data mining of smart meters for load category based disaggregation of residential power consumption

Cited by 34 publications

References 11 publications

Load Disaggregation via Pattern Recognition: A Feasibility Study of a Novel Method in Residential Building

Load Disaggregation via Pattern Recognition: A Feasibility Study of a Novel Method in Residential Building

Using Different ML Algorithms and Hyperparameter Optimization to Predict Heat Meters’ Failures

Predicting Heat Meters&rsquo; Failures With Selected Machine Learning Models

Contact Info

Product

Resources

About

Predicting Heat Meters’ Failures With Selected Machine Learning Models