Load modelling and non-intrusive load monitoring to integrate distributed energy resources in low and medium voltage networks

Jaramillo, Andres F. Moreno; Laverty, David; Morrow, D. John; Rincón, Jesús Martínez del; Foley, Aoife

doi:10.1016/j.renene.2021.07.056

Cited by 39 publications

(20 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The used metrics are accuracy ( A CC ), recall ( Re ), precision ( Pr ), and F 1 score, which are the most common metrics used among NILM studies. These metrics are defined as defined in Equations (10) to (13) [18].

A_{C C} = \frac{T P + T N}{T P + F P + T N + F N}

P_{r} = \frac{T P}{T P + F P}

R_{e} = \frac{T P}{T P + F N}

F_{1} S c o r e = 2 \frac{P_{r} \times R_{e}}{P_{r} + R_{e}}

where TP , TN , FP , and FN are true positive, true negative, false positive and false negative predictions, respectively.…”

Section: Principle and Methodsmentioning

confidence: 99%

“…The used metrics are accuracy (A CC ), recall (Re), precision (Pr), and F 1 score, which are the most common metrics used among NILM studies. These metrics are defined as defined in Equations ( 10) to (13) [18].…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…In contrast, unsupervised methods using cluster techniques, such as k‐means, deep learning, Hidden Markov Models (HMM) and variations thereof do not require labelling. The disadvantage of these methods is their higher complexity compared with supervised techniques [18].…”

Section: Work To Datementioning

confidence: 99%

“…In [18], the authors previously presented a state of the art covering load modelling and NILM methods for DER electrical profile identification/forecasting. Relevant research studies were filtered finding the majority of NILM focussed on conventional loads rather than DER electrical profiles.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Effective identification of distributed energy resources using smart meter net‐demand data

et al. 2022

Self Cite

View full text Add to dashboard Cite

International policies and targets to globally reduce carbon dioxide emissions have contributed to increasing penetration of distributed energy resources (DER) in lowvoltage distribution networks. The growth of technologies such as rooftop photovoltaic (PV) systems and electric vehicles (EV) has, to date, not been rigorously monitored and record keeping is deficient. Non-intrusive load monitoring (NILM) methods contribute to the effective integration of clean technologies within existing distribution networks. In this study, a novel NILM method is developed for the identification of DER electrical signatures from smart meter net-demand data. Electrical profiles of EV and PV systems are allocated within aggregated measurements including conventional electrical appliances. Data from several households in the United States are used to train and test classification and regression models. The usage of conventional machine learning techniques provides the proposed algorithm with fast processing times and low system complexity, key factors needed to differentiate highly variable DER power profiles from other loads. The results confirm the effectiveness of the proposed methodology to individually classify DER with performance metrics of 96% for EV and 99% for PV. This demonstrates the potential of the proposed method as an embedded function of smart meters to increase observability in distribution networks. K E Y W O R D Sdemand-side management, distributed energy resources, non-intrusive load monitoring, smart grids, supervised machine learning methodsThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

A_{C C} = \frac{T P + T N}{T P + F P + T N + F N}

P_{r} = \frac{T P}{T P + F P}

R_{e} = \frac{T P}{T P + F N}

F_{1} S c o r e = 2 \frac{P_{r} \times R_{e}}{P_{r} + R_{e}}

where TP , TN , FP , and FN are true positive, true negative, false positive and false negative predictions, respectively.…”

Section: Principle and Methodsmentioning

confidence: 99%

“…The used metrics are accuracy (A CC ), recall (Re), precision (Pr), and F 1 score, which are the most common metrics used among NILM studies. These metrics are defined as defined in Equations ( 10) to (13) [18].…”

Section: Evaluation Metricsmentioning

confidence: 99%

Section: Work To Datementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Effective identification of distributed energy resources using smart meter net‐demand data

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…All the literature works related to data analytics in the smart home application are segregated into general works [12]- [26] and works related to specific cases. To understand these specific cases, this paper investigates the research conducted on real-time datasets, viz., U.S.A. based Pecan Street power consumption dataset [27]- [35], Germany and Australia based Tracebase dataset [36]- [63], etc. Table 1, Table 2, and Table 3 elucidate all these state-of-the-art literature work respectively in terms of research works done on general energy consumption data as well as specific datasets.…”

Section: Analysis Of State-of-the-art Literature Workmentioning

confidence: 99%

Simple and effective descriptive analysis of missing data anomalies in smart home energy consumption readings

Prakash¹,

Kumar²

2021

Journal of Energy Systems

View full text Add to dashboard Cite

Smart grids evolution is ramping up in the global energy scenario by offering deregulated markets, demandside management, prosumer culture, demand response, contingency forecasting, outage management, etc., functionalities. These functionalities help to manage the grid effectively by taking informed decisions timely. Further, the progressive developments in information and communication technologies improve smartness in the power grids. Especially, smart homes are playing a key role, which possesses the communication between various devices/appliances and collect their functional data in terms of energy consumption readings, timestamp, etc. However, the availability of high-quality data is always desired to achieve superior benefits with respect to all the above-mentioned functionalities. But, the failures of communication networks, metering devices, server station issues, etc., create anomalies in the data collection. Hence, there is a dire need of identifying the ways of analyzing the smart home data to find the irregularities that occurred because of aforesaid failures. Especially, it has been a common problem to see missing data at some particular instants in the overall database captured. In this view, this paper proposes a simple and effective descriptive analysis to find missing data anomalies in smart home energy consumption data. A real-time dataset is used to execute the proposed method. For which, a clear enumeration of missing data is visualized using comprehensive simulation results. This helps to realize the actual problems that are hidden in the energy consumption data.

show abstract

Energy performance optimization of phase change materials considering the building micro‐environment

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Summary Phase change materials (PCMs) attached to building envelopes have been widely investigated, but there are rare studies to evaluate the influence of micro‐environments of PCMs. This paper, therefore, aims to study the action mechanism of PCMs under the micro‐environment systematically and provides the optimization of PCMs parameters, to realize a further reduction in building energy use. Simulation results indicate that a big difference in the heat transfer of envelopes appears in different orientations due to differences in solar radiation. Then, the optimal transition temperature Tp and amount of use of PCMs increase with the increase in solar radiation intensity Isr. Compared with other envelopes, the west‐facing wall and roof need higher Tp and amount of PCMs, under Isr from 400 to 1000 W/m2 the optimal Tp increases from 28 to 34°C with a difference high up to 6°C. The result also shows that the building energy‐saving of optimal PCMs parameters would rise by 16.6% compared to the fixed PCMs parameters.

show abstract

Load modelling and non-intrusive load monitoring to integrate distributed energy resources in low and medium voltage networks

Cited by 39 publications

References 87 publications

Effective identification of distributed energy resources using smart meter net‐demand data

Effective identification of distributed energy resources using smart meter net‐demand data

Simple and effective descriptive analysis of missing data anomalies in smart home energy consumption readings

Energy performance optimization of phase change materials considering the building micro‐environment

Contact Info

Product

Resources

About