Measurements for non-intrusive load monitoring through machine learning approaches

Bucci, G.; Ciancetta, Fabrizio; Fiorucci, Edoardo; Mari, Simone; Fioravanti, Andrea

doi:10.21014/acta_imeko.v10i4.1184

Cited by 10 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the disaggregation of energy usage, ADL patterns can be established in a simple, unobtrusive, and inexpensive way [ 19 ]. By disaggregating the total energy load, it is possible to determine which appliances are being used on a certain day [ 20 - 23 ]. This technique, also known as nonintrusive load monitoring, makes it possible, by using algorithms, to infer the fine-grained energy usage patterns of different appliances in the household [ 20 , 24 - 26 ].…”

Section: Introductionmentioning

confidence: 99%

Monitoring the Well-being of Older People by Energy Usage Patterns: Systematic Review of the Literature and Evidence Synthesis

Korenhof¹,

Fang²,

Luo³

et al. 2023

JMIR Aging

View full text Add to dashboard Cite

Background Due to the aging population, there is a need for monitoring well-being and safety while living independently. A low-intrusive monitoring system is based on a person’s use of energy or water. Objective The study's objective was to provide a systematic overview of studies that monitor the health and well-being of older people using energy (eg, electricity and gas) and water usage data and study the outcomes on health and well-being. Methods CENTRAL, Embase, MEDLINE (Ovid), Scopus, Web of Science, and Google Scholar were searched systematically from inception until November 8, 2021. The inclusion criteria were that the study had to be published in English, have full-text availability, target independent-living people aged 60 years and older from the general population, have an observational design, and assess the outcomes of a monitoring system based on energy (ie, electricity, gas, or water) usage on well-being and safety. The quality of the studies was assessed by the QualSyst systematic review tool. Results The search strategy identified 2920 articles. The majority of studies focused on the technical algorithms underlying energy usage data and related sensors. One study was included in this review. This study reported that the smart energy meter data monitoring system was considered unobtrusive and was well accepted by the older people and professionals involved. Energy usage in a household acted as a unique signature and therefore provided useful insight into well-being and safety. This study lacked statistical power due to the small number of participants and the low number of observed events. In addition, the quality of the study was rated as low. Conclusions This review identified only 1 study that evaluated the impact of an energy usage monitoring system on the well-being and safety of older people. The absence of reliable evidence impedes any definitive guidance or recommendations for practice. Because this emerging field has not yet been studied thoroughly, many questions remain open for further research. Future studies should focus on the further development of a monitoring system and the evaluation of the implementation and outcomes of these systems. Trial Registration PROSPERO CRD42022245713; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=245713

show abstract

Section: Introductionmentioning

confidence: 99%

Monitoring the Well-being of Older People by Energy Usage Patterns: Systematic Review of the Literature and Evidence Synthesis

Korenhof¹,

Fang²,

Luo³

et al. 2023

JMIR Aging

View full text Add to dashboard Cite

show abstract

“…The appliance causing the harmonic content is identified using a k-nearestneighbor classifier. Similarly, in [11], the effects of switching operations on the absorbed current signal were evaluated to realize galvanically isolated measurement systems.…”

Section: Introductionmentioning

confidence: 99%

An Embedded Deep Learning NILM System: A Year-Long Field Study in Real Houses

Mari,

Bucci,

Ciancetta

et al. 2023

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

Abstract-Nonintrusive load monitoring (NILM) systems are used to identify the energy consumption patterns of individual devices in an electrical system, but broadening their market availability is a significant challenge. In this paper, a NILM system using edge processing is proposed, in which energy consumption data are processed directly on the device installed at the monitored facility. Specifically, it uses a sequence-to-point approach based on a convolutional neural network implemented on an Arm Cortex-M7 microcontroller. This paper also reports the results of an extensive 12-month testing phase. The NILM system was installed in two real houses in central Italy to evaluate its installation and potential application in real-world scenarios. This study presents a promising solution that enables the widespread adoption of NILM systems by reducing their implementation cost and complexity and addresses the privacy concerns associated with cloud-based data processing. The results of our real-world testing provide compelling evidence of the potential of the proposed NILM system in various applications, including smart homes, building automation, and industrial energy management.

show abstract

“…For example, in some studies [4,5], the energy disaggregation problem has been reformulated as an adaptive filtering problem; refs. [6,7] propose model-driven NILM systems and the works proposed in other studies [8][9][10] are based on hidden Markov chains, while others [11][12][13][14][15] use artificial neural networks. The latter types of algorithms learn from the data provided and can perform certain tasks.…”

Section: Introductionmentioning

confidence: 99%

A New NILM System Based on the SFRA Technique and Machine Learning

Mari

Bucci

Ciancetta

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

In traditional nonintrusive load monitoring (NILM) systems, the measurement device is installed upstream of an electrical system to acquire the total aggregate absorbed power and derive the powers absorbed by the individual electrical loads. Knowing the energy consumption related to each load makes the user aware and capable of identifying malfunctioning or less-efficient loads in order to reduce consumption through appropriate corrective actions. To meet the feedback needs of modern home, energy, and assisted environment management systems, the nonintrusive monitoring of the power status (ON or OFF) of a load is often required, regardless of the information associated with its consumption. This parameter is not easy to obtain from common NILM systems. This article proposes an inexpensive and easy-to-install monitoring system capable of providing information on the status of the various loads powered by an electrical system. The proposed technique involves the processing of the traces obtained by a measurement system based on Sweep Frequency Response Analysis (SFRA) through a Support Vector Machine (SVM) algorithm. The overall accuracy of the system in its final configuration is between 94% and 99%, depending on the amount of data used for training. Numerous tests have been conducted on many loads with different characteristics. The positive results obtained are illustrated and commented on.

show abstract

Measurements for non-intrusive load monitoring through machine learning approaches

Cited by 10 publications

References 20 publications

Monitoring the Well-being of Older People by Energy Usage Patterns: Systematic Review of the Literature and Evidence Synthesis

Monitoring the Well-being of Older People by Energy Usage Patterns: Systematic Review of the Literature and Evidence Synthesis

An Embedded Deep Learning NILM System: A Year-Long Field Study in Real Houses

A New NILM System Based on the SFRA Technique and Machine Learning

Contact Info

Product

Resources

About