Open Access
Open access
Electronics (Switzerland), volume 13, issue 8, pages 1420

Comparative Analysis of Machine Learning Techniques for Non-Intrusive Load Monitoring

Publication typeJournal Article
Publication date2024-04-09
Q2
Q2
SJR0.644
CiteScore5.3
Impact factor2.6
ISSN20799292
Electrical and Electronic Engineering
Hardware and Architecture
Computer Networks and Communications
Control and Systems Engineering
Signal Processing
Abstract

Non-intrusive load monitoring (NILM) has emerged as a pivotal technology in energy management applications by enabling precise monitoring of individual appliance energy consumption without the requirements of intrusive sensors or smart meters. In this technique, the load disaggregation for the individual device is accrued by the recognition of their current signals by employing machine learning (ML) methods. This research paper conducts a comprehensive comparative analysis of various ML techniques applied to NILM, aiming to identify the most effective methodologies for accurate load disaggregation. The study employs a diverse dataset comprising high-resolution electricity consumption data collected from an Estonian household. The ML algorithms, including deep neural networks based on long short-term memory networks (LSTM), extreme gradient boost (XgBoost), logistic regression (LR), and dynamic time warping with K-nearest neighbor (DTW-KNN) are implemented and evaluated for their performance in load disaggregation. Key evaluation metrics such as accuracy, precision, recall, and F1 score are utilized to assess the effectiveness of each technique in capturing the nuanced energy consumption patterns of diverse appliances. Results indicate that the XgBoost-based model demonstrates superior performance in accurately identifying and disaggregating individual loads from aggregated energy consumption data. Insights derived from this research contribute to the optimization of NILM techniques for real-world applications, facilitating enhanced energy efficiency and informed decision-making in smart grid environments.

Mirza Z.T., Anderson T., Seadon J., Brent A.
2024-06-01 citations by CoLab: 17 Abstract
A successful and just energy transition is subject to policies that adhere to a multi-dimensional approach to renewable energy development. To achieve success in renewable energy development, well-thought-out and efficient policies must be implemented. This paper aims to address a major shortcoming in renewable energy development in terms of understanding and recognising the policy space that promotes or hampers renewable energy growth. The paper examines the relevant literature to identify major themes and factors in renewable energy development. A thematic analysis was conducted using a hybrid inductive and deductive approach and resulted in the identification of 5 major themes namely Institutional, Environmental, Financial, Socio-cultural, Technical and 144 factors. The identified themes and factors will assist to make a policy action decisive, just, and sustainable. Recommendations including comprehensive incentivisation, regulatory support for renewable energy technologies in developing nations, environment impact assessment programs, promotion of financial transparency and opting for a just transition to benefit local and vulnerable communities.
Hernández Á., Nieto R., de Diego-Otón L., Pérez-Rubio M.C., Villadangos-Carrizo J.M., Pizarro D., Ureña J.
Sensors Q1 Q2 Open Access
2024-01-14 citations by CoLab: 5 PDF Abstract
The massive deployment of smart meters in most Western countries in recent decades has allowed the creation and development of a significant variety of applications, mainly related to efficient energy management. The information provided about energy consumption has also been dedicated to the areas of social work and health. In this context, smart meters are considered single-point non-intrusive sensors that might be used to monitor the behaviour and activity patterns of people living in a household. This work describes the design of a short-term behavioural alarm generator based on the processing of energy consumption data coming from a commercial smart meter. The device captured data from a household for a period of six months, thus providing the consumption disaggregated per appliance at an interval of one hour. These data were used to train different intelligent systems, capable of estimating the predicted consumption for the next one-hour interval. Four different approaches have been considered and compared when designing the prediction system: a recurrent neural network, a convolutional neural network, a random forest, and a decision tree. By statistically analysing these predictions and the actual final energy consumption measurements, anomalies can be detected in the undertaking of three different daily activities: sleeping, breakfast, and lunch. The recurrent neural network achieves an F1-score of 0.8 in the detection of these anomalies for the household under analysis, outperforming other approaches. The proposal might be applied to the generation of a short-term alarm, which can be involved in future deployments and developments in the field of ambient assisted living.
Giannuzzo L., Minuto F.D., Schiera D.S., Lanzini A.
Energy and AI Q1 Q1 Open Access
2024-01-01 citations by CoLab: 10 Abstract
The successful implementation of Renewable Energy Communities (RECs) involves maximizing the self-consumption within a community, particularly in regulatory contexts in which shared energy is incentivized. In many countries, the absence of a metering infrastructure that provides data at an hourly or sub-hourly resolution level for low-voltage users (e.g., residential and commercial users) makes the design of a new energy community a challenging task. This study proposes a non-intrusive machine learning methodology that can be used to generate residential electrical consumption profiles at an hourly resolution level using only monthly consumption data (i.e., billed energy), with the aim of estimating the energy shared by RECs. The proposed methodology involves three phases: first, identifying the typical load patterns of residential users through k-Means clustering, then implementing a Random Forest algorithm, based on monthly energy bills, to identify typical load patterns and, finally, reconstructing the hourly electrical load profile through a data-driven rescaling procedure. The effectiveness of the proposed methodology has been evaluated through an REC case study composed by 37 residential users powered by a 70 kWp photovoltaic plant. The Normalized Mean Absolute Error (NMAE) and the Normalized Root Mean Squared Error (NRMSE) were evaluated over an entire year and whenever the energy was shared within the REC. The Relative Absolute Error was also measured when estimating the shared energy at both a monthly (MRAE) and at an annual basis. (RAE). A comparison between the REC load profile reconstructed using the proposed methodology and the real load profile yielded an overall NMAE of 20.04%, an NRMSE of 26.17%, and errors of 18.34% and 23.87% during shared energy timeframes, respectively. Furthermore, our model delivered relative absolute errors for the estimation of the shared energy at a monthly and annual scale of 8.31% and 0.12%, respectively.
Shabbir N., Ahmadiahangar R., Rosin A., Jawad M., Kilter J., Martins J.
2023-12-03 citations by CoLab: 1
Du Z., Yin B., Zhu Y., Huang X., Xu J.
2023-12-02 citations by CoLab: 2 PDF Abstract
AbstractWith the increasing number and types of global power loads and the development and popularization of smart grid technology, a large number of researches on load-level non-intrusive load monitoring technology have emerged. However, the unique power characteristics of the load make NILM face the difficult problem of low robustness of feature extraction and low accuracy of classification and identification in the recognition stage. This paper proposes a structured V-I mapping method to address the inherent limitations of traditional V-I trajectory mapping methods from a new perspective. In addition, for the verification of the V-I trajectory mapping method proposed in this paper, the complexity of load characteristics is comprehensively considered, and a lightweight convolutional neural network is designed based on AlexNet. The experimental results on the NILM dataset show that the proposed method significantly improves recognition accuracy compared to existing VI trajectory mapping methods.
Koasidis K., Marinakis V., Doukas H., Doumouras N., Karamaneas A., Nikas A.
Energies Q1 Q3 Open Access
2023-10-28 citations by CoLab: 1 PDF Abstract
Energy behaviours will play a key role in decarbonising the building sector but require the provision of tailored insights to assist occupants to reduce their energy use. Energy disaggregation has been proposed to provide such information on the appliance level without needing a smart meter plugged in to each load. However, the use of public datasets with pre-collected data employed for energy disaggregation is associated with limitations regarding its compatibility with random households, while gathering data on the ground still requires extensive, and hitherto under-deployed, equipment and time commitments. Going beyond these two approaches, here, we propose a novel data acquisition protocol based on multiplexing appliances’ signals to create an artificial database for energy disaggregation implementations tailored to each household and dedicated to performing under conditions of time and equipment constraints, requiring that only one smart meter be used and for less than a day. In a case study of a Greek household, we train and compare four common algorithms based on the data gathered through this protocol and perform two tests: an out-of-sample test in the artificially multiplexed signal, and an external test to predict the household’s appliances’ operation based on the time series of a real total consumption signal. We find accurate monitoring of the operation and the power consumption level of high-power appliances, while in low-power appliances the operation is still found to be followed accurately but is also associated with some incorrect triggers. These insights attest to the efficacy of the protocol and its ability to produce meaningful tips for changing energy behaviours even under constraints, while in said conditions, we also find that long short-term memory neural networks consistently outperform all other algorithms, with decision trees closely following.
Shabbir N., Ahmadiahangar R., Rosin A., Husev O., Jalakas T., Martins J.
2023-08-13 citations by CoLab: 4
Shareef H., Asna M., Errouissi R., Prasanthi A.
Sensors Q1 Q2 Open Access
2023-08-03 citations by CoLab: 4 PDF Abstract
Monitoring electricity energy usage can help to reduce power consumption considerably. Among load monitoring techniques, non-intrusive load monitoring (NILM) provides a cost-efficient solution to identify individual load consumption details from the aggregate voltage and current measurements. Existing load monitoring techniques often require large datasets or use complex algorithms to obtain acceptable performance. In this paper, a NILM technique using six non-redundant current waveform features with rule-based set theory (CRuST) is proposed. The architecture consists of an event detection stage followed by preprocessing and framing of the current signal, feature extraction, and finally, the load identification stage. During the event detection stage, a change in connected loads is ascertained using current waveform features. Once an event is detected, the aggregate current is processed and framed to obtain the event-causing load current. From the obtained load current, the six features are extracted. Furthermore, the load identification stage determines the event-causing load, utilizing the features extracted and the appliance model. The results of the CRuST NILM are evaluated using performance metrics for different scenarios, and it is observed to provide more than 96% accuracy for all test cases. The CRuST NILM is also observed to have superior performance compared to the feed-forward back-propagation network model and a few other existing NILM techniques.
Angelis G.F., Timplalexis C., Salamanis A.I., Krinidis S., Ioannidis D., Kehagias D., Tzovaras D.
2023-08-01 citations by CoLab: 17
Feng Z., Wang M., He J., Xiao W.
2023-04-21 citations by CoLab: 1
Nuran A.S., Murti M.A., Suratman F.Y.
2023-03-08 citations by CoLab: 3
Jawad M., Asghar H., Arshad J., Javed A., Qureshi M.B., Ali S.M., Shabbir N., Rassõlkin A.
2023-03-01 citations by CoLab: 3 Abstract
Environmental and economic improvements prevailed by Electric Vehicles (EVs) cannot be fully achieved unless renewable energy sources partially or fully charge the EVs. However, due to the intermittent nature of renewable energy, it is challenging to rely solely on renewable energy. Previous works attempted to accurately predict renewable power generation considering the intermittent nature of temperature and wind, but adequate renewable power supply cannot always guarantee. To address this problem, we proposed a novel area-based EV parking-lot model for charge scheduling of EVs with a predefined Service Level Objective (SLO). Moreover, power demand of each area is fulfilled with distributed solar and wind generators whose probability to produce energy no less than the SLO of the parking-lot area and have predicted energy no less than that area’s power demand. The Energy Storage Supply (ESS) is incorporated to ensure sufficient power to avoid SLO violations. Deep learning technique is used to predict the probability of generating renewable power no less than the power demand of the area for each EV parking-lot area. A linear optimization problem is formulated to map distributed renewable power generators to different parking-lot areas for minimization of SLO violations, total monetary cost of energy and carbon emission, and maximize the number of charged EVs at each time interval. The evaluation on real data traces shows that for 500 EV arrived per day case, our model is effective to minimize monetary cost of power consumption by 0.88% and carbon emission by 1.89% while having very less SLO violations in a day.
Abumohsen M., Owda A.Y., Owda M.
Energies Q1 Q3 Open Access
2023-02-27 citations by CoLab: 104 PDF Abstract
Forecasting the electrical load is essential in power system design and growth. It is critical from both a technical and a financial standpoint as it improves the power system performance, reliability, safety, and stability as well as lowers operating costs. The main aim of this paper is to make forecasting models to accurately estimate the electrical load based on the measurements of current electrical loads of the electricity company. The importance of having forecasting models is in predicting the future electrical loads, which will lead to reducing costs and resources, as well as better electric load distribution for electric companies. In this paper, deep learning algorithms are used to forecast the electrical loads; namely: (1) Long Short-Term Memory (LSTM), (2) Gated Recurrent Units (GRU), and (3) Recurrent Neural Networks (RNN). The models were tested, and the GRU model achieved the best performance in terms of accuracy and the lowest error. Results show that the GRU model achieved an R-squared of 90.228%, Mean Square Error (MSE) of 0.00215, and Mean Absolute Error (MAE) of 0.03266.
Schirmer P.A., Mporas I.
2023-01-01 citations by CoLab: 96 Abstract
The rapid development of technology in the electrical energy sector within the last 20 years has led to growing electric power needs through the increased number of electrical appliances and automation of tasks. In parallel the global climate protection goals, energy conservation and efficient energy management arise interest for reduction of the overall energy consumption. These requirements have led to the recent adoption of smart-meters and smart-grids, as well as to the rise of Load Monitoring id=RW1,comment=C1(LM) using energy disaggregation, also referred to as Non-Intrusive Load Monitoring (NILM), which enables appliance-specific energy monitoring by only observing the aggregated energy consumption of a household. The real-time information on appliance level can be used to get deeper insights in the origin of energy consumption and to make optimization, strategic load scheduling and demand management feasible. The three main contributions are as follows: id=.,comment=First, id=RW2,comment=C1a generalized up-to-date review of NILM approaches including a high-level taxonomy of NILM methodologies is provided. Second, previously published results are grouped based on the experimental setup which allows direct comparison. Third, the article is accompanied by a software implementation of the described NILM approaches.
Barbosa M.T., Barros E.B., Mota V.F., Filho D.M., Sampaio L.N., Kuehne B.T., Batista B.G., Turgut D., Peixoto M.L.
2025-02-01 citations by CoLab: 0
Young T.L., Gopsill J., Valero M., Eikevåg S., Hicks B.
Energy and AI Q1 Q1 Open Access
2024-09-01 citations by CoLab: 1 Abstract
The combination of Machine Learning (ML), smart energy meters, and availability of household appliance energy profile data has opened new opportunities for Non-Intrusive Load Monitoring (NILM). However, the number of options makes it challenging in selecting optimal combinations for different energy applications, which requires studies to examine their trade-offs. This paper contributes one such study that investigated four established ML approaches – K Nearest Neighbour (KNN), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost) and Convolutional Neural Network (CNN) – and their performance in classifying appliance events from Alternating Current (AC) and Root Mean Square (RMS) energy data where the sampling frequency and training dataset set size was varied (10 Hz–1 kHz and 50–2000 examples per class, respectively). The computational expense during training, testing and storage was also assessed and evaluated with reference to real-world applications. The CNN classifier trained on AC data at 500 Hz and 11,000 examples gave the best F1-score 0.989 followed by the KNN classifier 0.940. The storage size required by the CNN models was 3̃MB, which is very close to fitting on cost-effective embedded system microcontrollers. This would prevent high-rate data needing to be sent to the cloud as analysis could be performed on edge computing Internet-of-Things (IoT) devices.
Pradeep P., Zhao W., Kowalski M., Bakeev C.
2024-08-16 citations by CoLab: 0
Stanescu D., Enache F., Popescu F.
Smart Cities Q1 Q1 Open Access
2024-07-23 citations by CoLab: 3 PDF Abstract
Much of today’s power grid was designed and built using technologies and organizational principles developed decades ago. The lack of energy resources and classic power networks are the main causes of the development of the smart grid to efficiently use energy resources, with stable and safe operation. In such a network, one of the fundamental priorities is provided by non-intrusive appliance load monitoring (NIALM) in order to analyze, recognize and determine the electricity consumption of each consumer. In this paper, we propose a new smart system approach for the characterization of the appliance load signature based on a data-driven method, namely the phase diagram. Our aim is to use the non-intrusive load monitoring of appliances in order to recognize different types of consumers that can exist within a smart building.
Zaboli A., Kasimalla S.R., Park K., Hong Y., Hong J.
Energies Q1 Q3 Open Access
2024-05-24 citations by CoLab: 2 PDF Abstract
Behind the meter (BTM) distributed energy resources (DERs), such as photovoltaic (PV) systems, battery energy storage systems (BESSs), and electric vehicle (EV) charging infrastructures, have experienced significant growth in residential locations. Accurate load forecasting is crucial for the efficient operation and management of these resources. This paper presents a comprehensive survey of the state-of-the-art technologies and models employed in the load forecasting process of BTM DERs in recent years. The review covers a wide range of models, from traditional approaches to machine learning (ML) algorithms, discussing their applicability. A rigorous validation process is essential to ensure the model’s precision and reliability. Cross-validation techniques can be utilized to reduce overfitting risks, while using multiple evaluation metrics offers a comprehensive assessment of the model’s predictive capabilities. Comparing the model’s predictions with real-world data helps identify areas for improvement and further refinement. Additionally, the U.S. Energy Information Administration (EIA) has recently announced its plan to collect electricity consumption data from identified U.S.-based crypto mining companies, which can exhibit abnormal energy consumption patterns due to rapid fluctuations. Hence, some real-world case studies have been presented that focus on irregular energy consumption patterns in residential buildings equipped with BTM DERs. These abnormal activities underscore the importance of implementing robust anomaly detection techniques to identify and address such deviations from typical energy usage profiles. Thus, our proposed framework, presented in residential buildings equipped with BTM DERs, considering smart meters (SMs). Finally, a thorough exploration of potential challenges and emerging models based on artificial intelligence (AI) and large language models (LLMs) is suggested as a promising approach.

Top-30

Journals

1
1

Publishers

1
2
1
2
  • We do not take into account publications without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.
Share
Cite this
GOST | RIS | BibTex | MLA
Found error?