An empirical investigation of V-I trajectory based load signatures for non-intrusive load monitoring

Hasan, Taha Mohammed; Javed, Fawad; Arshad, Naveed

doi:10.1109/pesgm.2014.6938824

Cited by 14 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A voltage-current ( -) trajectory was used as the load signature in [6] which has shown good performance in distinguishing between loads with similar patterns. A deeper vision of the -trajectory for load identification was introduced in [7], which improved the precision of predictions by 10% as compared to [6]. The features used in [7] include -, total harmonic distortion, and V-I wave-shape.…”

Section: Related Literaturementioning

confidence: 99%

“…A deeper vision of the -trajectory for load identification was introduced in [7], which improved the precision of predictions by 10% as compared to [6]. The features used in [7] include -, total harmonic distortion, and V-I wave-shape. Four learning algorithms were also used in [7], including artificial neural network (ANN), ANN coupled with an evolutionary algorithm, support vector machine (SVM), and Adaptive Boost.…”

Section: Related Literaturementioning

confidence: 99%

“…The features used in [7] include -, total harmonic distortion, and V-I wave-shape. Four learning algorithms were also used in [7], including artificial neural network (ANN), ANN coupled with an evolutionary algorithm, support vector machine (SVM), and Adaptive Boost. It was shown that the Adaptive Boost algorithm based on I-V wave-shape produces the highest accuracy in the predictions.…”

Section: Related Literaturementioning

confidence: 99%

See 2 more Smart Citations

Load Decomposition at Smart Meters Level Using Eigenloads Approach

Ahmadi

Martí²

2015

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

The deployment of the advanced metering infrastructure (AMI) in distribution systems provides an excellent opportunity for load monitoring applications. Load decomposition can be done at the smart meters level, providing a better understanding of the load behavior at near-real-time. In this paper, loads' current and voltage waveforms are processed offline to form a comprehensive library. This library consists of a set of measurements projected onto the eigenloads space. Eigenloads are basically the eigenvectors describing the load signatures space. Similar to human faces, every load has a distinct signature. Each load measurement is transformed into a photo and an efficient face recognition algorithm is applied to the set of photos. A list of all the online devices is always stored and can be accessed at any time. The proposed method can be implemented at the smart meters level. The distributed computation that can be achieved by performing simple calculations at each smart meter, without the need for sending intensive data to a central processor, is beneficial. From a system operator perspective, load composition in near-real-time provides the loads' voltage dependence that are needed, for example, in volt-VAR optimization (VVO) in distribution systems. Further applications of load composition data are also discussed.

show abstract

Section: Related Literaturementioning

confidence: 99%

Section: Related Literaturementioning

confidence: 99%

Section: Related Literaturementioning

confidence: 99%

See 1 more Smart Citation

Load Decomposition at Smart Meters Level Using Eigenloads Approach

Ahmadi

Martí²

2015

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

show abstract

“…However, due to the latency and quick response requirements of this system we considered using a load disaggregation [6] and forecasting [8]. The data that was collected was passed to the PCAT.…”

Section: Salemmentioning

confidence: 99%

SmartDSM: a layered model for development of demand side management in smart grids

Javed

Ali

Nabeel

et al. 2014

Proceedings of the 3rd International Workshop on Software Engineering Challenges for the Smart Grid

Self Cite

View full text Add to dashboard Cite

Growing power demand and carbon emissions is motivating utility providers to introduce smart power systems. One of the most promising technology to deliver cheaper and smarter electricity is demand side management. A DSM solution controls the devices at user premises in order to achieve overall goals of lower cost for consumer and utility. To achieve this various technologies from different domains come in to play from power electronics to sensor networks to machine learning and distributed systems design. The eventual system is a large, distributed software system over a heterogenous environment and systems. Whereas various algorithms to plan the DSM schedule have been proposed, no concerted effort has been made to propose models and architectures to develop such a complex software system. This lack of models provides for a haphazard landscape for researchers and practitioners leading to confused requirements and overlapping concerns of domains. This was observed by the authors in developing a DSM system for their lab and faculty housing. To this end in this paper we present a model to develop software systems to deliver DSM. In addition to the model, we present a road map of software engineering research to aid development of future DSM systems. This is based on our observations and insights of the developed DSM systems.

show abstract

“…The main drawback of CH based load feature is that some household appliances consisting of linear and largely resistive elements result in low harmonic content of the load current, and thus requires great effort for load identification. Appliance LSs based on V-I trajectory is broadly discussed in [11], [12]. Both load current and voltage information can be captured in the V-I curvature.…”

Section: Introductionmentioning

confidence: 99%

A Distinctive Load Feature Extraction Based on Fryze's Time-domain Power Theory

Teshome

Huang

Lian

2016

IEEE Power Energy Technol. Syst. J.

View full text Add to dashboard Cite

The performance of a non-intrusive load monitoring (NILM) system heavily depends on the uniqueness of the preferred load signature (LS) extracted from each appliance. Some electrical characteristics such as instantaneous current waveform (CW), instantaneous power waveform (IPW), current harmonic (CH) and voltage-current (V-I) trajectory have been proposed as appliance features in the literature. However, in some situations, these LSs cannot effectively distinguish different loads apart. In this paper, a time-domain based advanced power theory is used to decompose the load current into active and non-active orthogonal components. Then, two new LSs have been established based on the non-active component of the load current, namely the non-active current waveform (i f ) and the voltage-non-active current (V-I f ) characteristics curve. Simulation and experimental tests show that both of these features can distinguish different appliances. Hence, the proposed LSs can significantly enhance the existing NILM systems.

show abstract

An empirical investigation of V-I trajectory based load signatures for non-intrusive load monitoring

Cited by 14 publications

References 0 publications

Load Decomposition at Smart Meters Level Using Eigenloads Approach

Load Decomposition at Smart Meters Level Using Eigenloads Approach

SmartDSM: a layered model for development of demand side management in smart grids

A Distinctive Load Feature Extraction Based on Fryze's Time-domain Power Theory

Contact Info

Product

Resources

About