An efficient hybrid model for appliances classification based on time series features

Aslan, Muzaffer; Zurel, Ebra Nur

doi:10.1016/j.enbuild.2022.112087

Cited by 11 publications

(10 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Appliance detection is a problem related to Non-Intrusive Load Monitoring (NILM), which aims at identifying the power consumption, pattern, or on/off state activation of individual appliances using only the total consumption series [29]. Even though detecting an appliance can be seen as a step of NILM-based methods [4,27,28,30,39,43,50], they differ from our objective for two main reasons. First, the vast majority of NILM studies relied on smart meter data recorded at 1Hz (or more), which is much more detailed than the datasets available in practice.…”

Section: Related Work and Problem Definition 21 Appliance Detectionmentioning

confidence: 99%

ADF & TransApp: A Transformer-Based Framework for Appliance Detection Using Smart Meter Consumption Series

Petralia,

Charpentier,

Palpanas

2023

Proc. VLDB Endow.

View full text Add to dashboard Cite

Over the past decade, millions of smart meters have been installed by electricity suppliers worldwide, allowing them to collect a large amount of electricity consumption data, albeit sampled at a low frequency (one point every 30min). One of the important challenges these suppliers face is how to utilize these data to detect the presence/absence of different appliances in the customers' households. This valuable information can help them provide personalized offers and recommendations to help customers towards the energy transition. Appliance detection can be cast as a time series classification problem. However, the large amount of data combined with the long and variable length of the consumption series pose challenges when training a classifier. In this paper, we propose ADF, a framework that uses subsequences of a client consumption series to detect the presence/absence of appliances. We also introduce TransApp, a Transformer-based time series classifier that is first pretrained in a self-supervised way to enhance its performance on appliance detection tasks. We test our approach on two real datasets, including a publicly available one. The experimental results with two large real datasets show that the proposed approach outperforms current solutions, including state-of-the-art time series classifiers applied to appliance detection.

show abstract

Section: Related Work and Problem Definition 21 Appliance Detectionmentioning

confidence: 99%

ADF & TransApp: A Transformer-Based Framework for Appliance Detection Using Smart Meter Consumption Series

Petralia,

Charpentier,

Palpanas

2023

Proc. VLDB Endow.

View full text Add to dashboard Cite

show abstract

“…Long short-term memory (LSTM) is a DL approach suitable for automatic feature-learning from data sequences [18], [19]. It has been used in a variety of areas, such as natural language-processing [17], as well as in electricity system applications (power grid impedance estimation [12], residential load forecasting [13], and consumer type classification [14]- [16]). Although [14] used a combination of handcrafted features, LSTM and conventional supervised ML to classify such household appliances as heat pumps, dishwashers and TVs, it was only applied to specific household appliances using synthetic high-resolution profiles.…”

Section: Introductionmentioning

confidence: 99%

“…It has been used in a variety of areas, such as natural language-processing [17], as well as in electricity system applications (power grid impedance estimation [12], residential load forecasting [13], and consumer type classification [14]- [16]). Although [14] used a combination of handcrafted features, LSTM and conventional supervised ML to classify such household appliances as heat pumps, dishwashers and TVs, it was only applied to specific household appliances using synthetic high-resolution profiles. Such an approach cannot be used directly to identify heating types at a large scale as measurements from individual appliances are not distinguishable from smart meter data collected at a household level.…”

Section: Introductionmentioning

confidence: 99%

Hierarchical LSTM-Based Classification of Household Heating Types Using Measurement Data

Fürst

Chen

2024

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

A lack of knowledge of the heating systems used by electricity consumers impedes distribution system operators in developing a sound grid upgrade plan and estimating potential demand flexibility from these consumers. The large-scale rollout of smart meters for electricity consumers provides an excellent opportunity to identify end users' heating types. This paper proposed a hierarchically structured deep-learning framework for identifying heating types of individual electricity consumers. The main contributions of the paper are: (a) We propose an effective framework based on long short-term memory (LSTM) that offers an effective automatic feature learning from sequential electricity consumption data and weather conditions. (b) We apply the proposed deep-learning architecture for household heating type classification which is among the first few successful reports on this application. We evaluate the performance using hourly measurement data collected over four years from one and two-family dwellings with either district heating, exhaust air heat pumps or direct electric heating as the heating type. Good performance was shown from the test results using the proposed framework, with an average test accuracy of 94.2%. Comparisons with four existing machine learning algorithms using handcrafted features and a single-layer LSTM-based deep-learning algorithm have shown marked improvement of the proposed method.

show abstract

“…This problem is closely related to Non-Intrusive Load Monitoring (NILM), which aims to identify the power consumption, pattern, or on/off state activation of individual appliances using only the total consumption series [29]. While detecting an appliance can be seen as a step in NILM-based methods [4,27,28,33,45,47,57], and diverse approaches have been proposed in the literature [4,27,28,33,45,47,57], they differ from our objective. Indeed, these studies essentially focus on detecting when a specific appliance is "ON" rather than if a household owns a specific appliance, and the presence of a specific appliance is in several cases already known before applying these approaches.…”

Section: Introductionmentioning

confidence: 99%

Appliance Detection Using Very Low-Frequency Smart Meter Time Series

Petralia,

Charpentier,

Boniol

et al. 2023

Proceedings of the 14th ACM International Conference on Future Energy Systems

View full text Add to dashboard Cite

In recent years, smart meters have been widely adopted by electricity suppliers to improve the management of the smart grid system. These meters usually collect energy consumption data at a very low frequency (every 30min), enabling utilities to bill customers more accurately. To provide more personalized recommendations, the next step is to detect the appliances owned by customers, which is a challenging problem, due to the very-low meter reading frequency. Even though the appliance detection problem can be cast as a time series classification problem, with many such classifiers having been proposed in the literature, no study has applied and compared them on this specific problem. This paper presents an in-depth evaluation and comparison of state-of-the-art time series classifiers applied to detecting the presence/absence of diverse appliances in very low-frequency smart meter data. We report results with five real datasets. We first study the impact of the detection quality of 13 different appliances using 30min sampled data, and we subsequently propose an analysis of the possible detection performance gain by using a higher meter reading frequency. The results indicate that the performance of current time series classifiers varies significantly. Some of them, namely deep learning-based classifiers, provide promising results in terms of accuracy (especially for certain appliances), even using 30min sampled data, and are scalable to the large smart meter time series collections of energy consumption data currently available to electricity suppliers. This paper appeared in ACM e-Energy 2023. CCS CONCEPTS• Computing methodologies → Learning paradigms.

show abstract

An efficient hybrid model for appliances classification based on time series features

Cited by 11 publications

References 49 publications

ADF & TransApp: A Transformer-Based Framework for Appliance Detection Using Smart Meter Consumption Series

ADF & TransApp: A Transformer-Based Framework for Appliance Detection Using Smart Meter Consumption Series

Hierarchical LSTM-Based Classification of Household Heating Types Using Measurement Data

Appliance Detection Using Very Low-Frequency Smart Meter Time Series

Contact Info

Product

Resources

About