Feature Mapping based Deep Neural Networks for Non-intrusive Load Monitoring of Similar Appliances in Buildings

Gopinath, R.; Kumar, Mukesh; Srinivas, K.

doi:10.1145/3408308.3427622

Cited by 13 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…air conditioners). In such scenarios, it would be much difficult to perform effective load identification and energy disaggregation due to overlapping signatures of loads [5,6,14]. Therefore, effective methodologies need to be developed for energy disaggregation of similar loads.…”

Section: Research Challengesmentioning

confidence: 99%

Non-intrusive load monitoring

Rajendiran

2022

Proceedings of the Thirteenth ACM International Conference on Future Energy Systems

View full text Add to dashboard Cite

Responsible use of energy resources, conserving environment and improving well-being of the society are the major goals towards developing smart sustainable cities, and energy management is the inherent part of the smart sustainable cities programme. Due to high demand of energy in various sectors, energy management has become essential to utilize the available energy efficiently and understand energy usage behavior of the users in order to avoid possible energy wastage. In recent years, non-intrusive load monitoring (NILM) technique has become popular and emerging approach to monitor events and energy consumption of appliances/electrical utilities in buildings using single energy meter. The information about energy consumption at appliance level would help consumers to understand their appliance usage behavior and take necessary steps for reducing energy consumption. The recent advancements in smart metering and internet of things (IoT) have made significant progress in real time implementation of non-intrusive load monitoring (NILM) algorithms in residential and industrial environments.The motivation of this presentation is to address the challenges towards developing more accurate NILM systems and its future perspectives for effective energy management in buildings. NILM can also be used for anomaly detection, predictive maintenance, load forecasting, and energy disaggregation of distributed energy resources in buildings. Therefore, creating awareness about the importance of NILM and incorporating its potential applications as the features of NILM system would help achieve responsible energy utilization in residential/industrial environments and conserve energy consumption towards developing smart sustainable cities for the society. CCS CONCEPTS• Computing methodologies → AI; • Hardware → Energy metering.

show abstract

Section: Research Challengesmentioning

confidence: 99%

Non-intrusive load monitoring

Rajendiran

2022

Proceedings of the Thirteenth ACM International Conference on Future Energy Systems

View full text Add to dashboard Cite

show abstract

“…The active power value is the most widely used steadystate feature in NILM systems [10,19]. Additionally, the current harmonics [22,23], voltage-current trajectory [24], and current waveform [15] have also been extracted as features. The voltage transients [21] and power transients [8] have been extracted as transient-state features.…”

Section: Introductionmentioning

confidence: 99%

“…Among the supervised learning approaches, pattern recognition is the most commonly used method [6,7]. Support vector machines (SVM) [23,25] artificial neural networks (ANN) [19,26], and k-nearest neighbor (k-NN) [15] are a few examples of such commonly used pattern recognition-based algorithms.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Non-Intrusive Load Monitoring for Low-Power Appliances Using Odd Current Harmonics

Madhushan,

Perera,

Wijewardhana

et al. 2023

IJEETC

View full text Add to dashboard Cite

Non-intrusive load monitoring (NILM) systems have gained immense popularity in the last two decades. Although many solutions were developed using the NILM approach, the majority of solutions failed to identify low-power-consuming appliances. However, a NILM system deployed in a domestic installation should be capable of identifying low-power-consuming appliances precisely. Therefore, we propose two real-time NILM solutions that can identify low-power residential appliances. These two solutions rely on active power and harmonic information extracted from the measured current waveform. We analyzed the performances of the two solutions using simulations and real-world experiments. Results indicate that both solutions can correctly identify appliances with an average accuracy above 90 percent.

show abstract

“…Deep learning-based models have presented new opportunities for the electrical utility industry [7], and are the most representative structures applied to NILM [8,9,10,11], which have been proved to be more effective than other traditional models. However, most deep learning-based NILM models are centralized [12], which may not be feasible in the era of big data due to data privacy concerns and excessive communication overhead from numerous smart meter devices.…”

Section: Introduction 1background and Motivationsmentioning

confidence: 99%

DP$^2$-NILM: A Distributed and Privacy-preserving Framework for Non-intrusive Load Monitoring

Dai¹,

Meng²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Non-intrusive load monitoring (NILM), which usually utilizes machine learning methods and is effective in disaggregating smart meter readings from the household-level into appliance-level consumption, can help analyze electricity consumption behaviours of users and enable practical smart energy and smart grid applications. Recent studies have proposed many novel NILM frameworks based on federated deep learning (FL). However, there lacks comprehensive research exploring the utility optimization schemes and the privacy-preserving schemes in different FL-based NILM application scenarios. In this paper, we make the first attempt to conduct FL-based NILM focusing on both the utility optimization and the privacy-preserving by developing a distributed and privacy-preserving NILM (DP 2 -NILM) framework and carrying out comparative experiments on practical NILM scenarios based on real-world smart meter datasets. Specifically, two alternative federated learning strategies are examined in the utility optimization schemes, i.e., the FedAvg and the FedProx. Moreover, different levels of privacy guarantees, i.e., the local differential privacy federated learning and the global differential privacy federated learning are provided in the DP 2 -NILM. Extensive comparison experiments are conducted on three real-world datasets to evaluate the proposed framework.

show abstract

Feature Mapping based Deep Neural Networks for Non-intrusive Load Monitoring of Similar Appliances in Buildings

Cited by 13 publications

References 7 publications

Non-intrusive load monitoring

Non-intrusive load monitoring

Real-Time Non-Intrusive Load Monitoring for Low-Power Appliances Using Odd Current Harmonics

DP$^2$-NILM: A Distributed and Privacy-preserving Framework for Non-intrusive Load Monitoring

Contact Info

Product

Resources

About