Machine learning approaches for non-intrusive load monitoring: from qualitative to quantitative comparation

Nalmpantis, Christoforos; Vrakas, Dimitris

doi:10.1007/s10462-018-9613-7

Cited by 106 publications

(93 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is common practise that researchers evaluate their proposed NILM solutions on different datasets, with different criteria, and with the help of different metrics. From this follows that a direct comparison between two proposed algorithms is virtually impossible (Nalmpantis & Vrakas, 2018). To assess the validity of their proposed NILM approach, many researchers utilise the Zeifman requirements (Zeifman, 2012).…”

Section: Related Workmentioning

confidence: 99%

“…comparison of two candidate algorithms is possible or not (Nalmpantis & Vrakas, 2018). A requirements catalogue similar to the Zeifman requirements (Zeifman, 2012), a list of requirements that describe what characteristics a NILM algorithm should have, is likely to ease objective comparisons by providing clear guidelines how meaningful comparisons of several NILM approaches can be drawn.…”

mentioning

confidence: 99%

See 1 more Smart Citation

On performance evaluation and machine learning approaches in non-intrusive load monitoring

Klemenjak

2018

Energy Inform

View full text Add to dashboard Cite

Non-Intrusive Load Monitoring (NILM) is a set of techniques to gain deep insights into workflows inside buildings based on data provided by smart meters. In this way, the combined consumption needs only to be monitored at a single, central point in the household, providing advantages such as reduced costs for metering equipment. Over the years, a plethora of load monitoring algorithms has been proposed comprising approaches based on Hidden Markov Models (HMM), algorithms based on combinatorial optimisation, and more recently, approaches based on machine learning. However, reproducibility, comparability, and performance evaluation remain open research issues since there is no standardised way researchers evaluate their approaches and report performance. In this paper, the author points out open research issues of performance evaluation in NILM, presents a short survey of deep learning approaches for NILM, and formulates research questions related to open issues in NILM. An outline of future work is given including applied methodology and expected findings.

show abstract

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

On performance evaluation and machine learning approaches in non-intrusive load monitoring

Klemenjak

2018

Energy Inform

View full text Add to dashboard Cite

show abstract

“…The combination of the need for technologies promoting low-carbon emissions and the advances in machine learning and statistical techniques is generating a substantial amount of energy disaggregation review papers such as Nalmpantis and Vrakas (2018), Esa, Abdullah, and Hassan (2016), Abubakar, Khalid, Mustafa, Shareef, and Mustapha (2016), Wong, Ahmet Sekercioglu, Drummond, and Wong (2013), Butner, Reid, Hoffman, Sullivan, and Blanchard (2013), Makonin (2012), Zoha, Gluhak, Imran, and Rajasegarar (2012), Jiang, Li, Luo, Jin, and West (2011), and Zeifman and Roth (2011). In general NILM approaches are grouped into two categories: (a) event-based approaches and (b) event-less approaches (Bergés & Kolter, 2012).…”

Section: Introductionmentioning

confidence: 99%

Performance evaluation in non‐intrusive load monitoring: Datasets, metrics, and tools—A review

Pereira¹,

Nunes

2018

WIREs Data Min & Knowl

139

103

View full text Add to dashboard Cite

Non-intrusive load monitoring (also known as NILM or energy disaggregation) is the process of estimating the energy consumption of individual appliances from electric power measurements taken at a limited number of locations in the electric distribution of a building. This approach reduces sensing infrastructure costs by relying on machine learning techniques to monitor electric loads. However, the ability to evaluate and benchmark the proposed approaches across different datasets is key for enabling the generalization of research findings and consequently contributes to the large-scale adoption of this technology. Still, only recently researchers have focused on creating and standardizing the existing datasets in order to deliver a single interface to run NILM evaluations. Furthermore, there is still no consensus regarding, which performance metrics should be used to measure and report the performance of NILM systems and their underlying algorithms. This paper provides a review of the main datasets, metrics, and tools for evaluating the performance of NILM systems and technologies. Specifically, we review three main topics: (a) publicly available datasets, (b) performance metrics, and (c) frameworks and toolkits. The review suggests future research directions in NILM systems and technologies, including cross-datasets, performance metrics for evaluation and generalizable frameworks for benchmarking NILM technology.

show abstract

“…Throughout the years, a great number of algorithms have been proposed to solve the problem of energy disaggregation [3,4]. These algorithms are categorized into either event-based or event-less, based on the disaggregation approach [5].…”

Section: Introductionmentioning

confidence: 99%

Implementation Strategy of Convolution Neural Networks on Field Programmable Gate Arrays for Appliance Classification Using the Voltage and Current (V-I) Trajectory

Baptista

Mostafa

Pereira³

et al. 2018

Energies

View full text Add to dashboard Cite

Specific information about types of appliances and their use in a specific time window could help determining in details the electrical energy consumption information. However, conventional main power meters fail to provide any specific information. One of the best ways to solve these problems is through non-intrusive load monitoring, which is cheaper and easier to implement than other methods. However, developing a classifier for deducing what kind of appliances are used at home is a difficult assignment, because the system should identify the appliance as fast as possible with a higher degree of certainty. To achieve all these requirements, a convolution neural network implemented on hardware was used to identify the appliance through the voltage and current (V-I) trajectory. For the implementation on hardware, a field programmable gate array (FPGA) was used to exploit processing parallelism in order to achieve optimal performance. To validate the design, a publicly available Plug Load Appliance Identification Dataset (PLAID), constituted by 11 different appliances, has been used. The overall average F-score achieved using this classifier is 78.16% for the PLAID 1 dataset. The convolution neural network implemented on hardware has a processing time of approximately 5.7 ms and a power consumption of 1.868 W.

show abstract

Machine learning approaches for non-intrusive load monitoring: from qualitative to quantitative comparation

Cited by 106 publications

References 40 publications

On performance evaluation and machine learning approaches in non-intrusive load monitoring

On performance evaluation and machine learning approaches in non-intrusive load monitoring

Performance evaluation in non‐intrusive load monitoring: Datasets, metrics, and tools—A review

Implementation Strategy of Convolution Neural Networks on Field Programmable Gate Arrays for Appliance Classification Using the Voltage and Current (V-I) Trajectory

Contact Info

Product

Resources

About