Energy Anomaly Detection in Industrial Applications with Long Short-term Memory-based Autoencoders

Kaymakci, Can; Wenninger, Simon; Sauer, Alexander

doi:10.1016/j.procir.2021.11.031

Cited by 14 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The convolutional autoencoder achieved the best performance. The paper [6] investigated using an autoencoder using an LSTM network to detect elevated energy consumption in industrial applications, making it possible to identify improperly controlled, improperly maintained, or obsolete subsystems. An autoencoder using multiple layers of LSTM (Stacked AE) was tested in [18] for short-term forecasting capabilities.…”

Section: Related Workmentioning

confidence: 99%

“…One of the most important functions of resource monitoring in management systems is anomaly detection, which can be done in Smart City systems based on data collected from various sources, primarily from electricity meters [1,2]. Detecting anomalies in energy consumption is a wellstudied problem in terms of different types of consumers: residential [3], commercial buildings [4,5], and industry [6]. It is fostered by the widespread installation of smart electricity meters (Smart Meters); for example, in Europe, the penetration rate of smart electricity meters has reached 56% by the end of 2022.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Autoencoder Application for Anomaly Detection in Power Consumption of Lighting Systems

Śmiałkowski,

Czyżewski

2023

IEEE Access

View full text Add to dashboard Cite

Detecting energy consumption anomalies is a popular topic of industrial research, but there is a noticeable lack of research reported in the literature on energy consumption anomalies for road lighting systems. However, there is a need for such research because the lighting system, a key element of the Smart City concept, creates new monitoring opportunities and challenges. This paper examines algorithms based on the deep learning method using the Autoencoder model with LSTM and 1D Convolutional networks for various configurations and training periods. The evaluation of the algorithms was carried out based on real data from an extensive lighting control system. A practical approach was proposed using real-time, unsupervised algorithms employing limited computing resources that can be implemented in industrial devices designed to control intelligent city lighting. An anomaly detection algorithm based on classic LSTM networks, single-layer and multi-layer, was used for comparison purposes. Error matrix calculus was used to assess the quality of the models. It was shown that based on the Autoencoder method, it is possible to construct an algorithm that correctly detects anomalies in power measurements of lighting systems, and it is possible to build a model so that the algorithm works correctly regardless of the season of the year.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Autoencoder Application for Anomaly Detection in Power Consumption of Lighting Systems

Śmiałkowski,

Czyżewski

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Experimental results of the combined method, on the electricity consumption dataset, achieved an F1 score of 0.981. Kaymakci et al [32] presented an end-to-end solution of an anomaly detection system. The system uses the concept of a Long Short-Term Memory-based AE as an unsupervised learning model.…”

Section: Anomaly Detection In Building's Consumption: a Brief Overvie...mentioning

confidence: 99%

Anomaly Detection of Consumption in Hotel Units: A Case Study Comparing Isolation Forest and Variational Autoencoder Algorithms

et al. 2022

View full text Add to dashboard Cite

Buildings are responsible for a high percentage of global energy consumption, and thus, the improvement of their efficiency can positively impact not only the costs to the companies they house, but also at a global level. One way to reduce that impact is to constantly monitor the consumption levels of these buildings and to quickly act when unjustified levels are detected. Currently, a variety of sensor networks can be deployed to constantly monitor many variables associated with these buildings, including distinct types of meters, air temperature, solar radiation, etc. However, as consumption is highly dependent on occupancy and environmental variables, the identification of anomalous consumption levels is a challenging task. This study focuses on the implementation of an intelligent system, capable of performing the early detection of anomalous sequences of values in consumption time series applied to distinct hotel unit meters. The development of the system was performed in several steps, which resulted in the implementation of several modules. An initial (i) Exploratory Data Analysis (EDA) phase was made to analyze the data, including the consumption datasets of electricity, water, and gas, obtained over several years. The results of the EDA were used to implement a (ii) data correction module, capable of dealing with the transmission losses and erroneous values identified during the EDA’s phase. Then, a (iii) comparative study was performed between a machine learning (ML) algorithm and a deep learning (DL) one, respectively, the isolation forest (IF) and a variational autoencoder (VAE). The study was made, taking into consideration a (iv) proposed performance metric for anomaly detection algorithms in unsupervised time series, also considering computational requirements and adaptability to different types of data. (v) The results show that the IF algorithm is a better solution for the presented problem, since it is easily adaptable to different sources of data, to different combinations of features, and has lower computational complexity. This allows its deployment without major computational requirements, high knowledge, and data history, whilst also being less prone to problems with missing data. As a global outcome, an architecture of a platform is proposed that encompasses the mentioned modules. The platform represents a running system, performing continuous detection and quickly alerting hotel managers about possible anomalous consumption levels, allowing them to take more timely measures to investigate and solve the associated causes.

show abstract

“…In recent years, research focused primarily on enhancing energy efficiency in energy systems to cut energy consumption. Examples are manifold [17] and range from anomaly detection in energy consumption [18] over research on forecasting energy consumption [19,20] to the optimization of greenhouse energy use [21]. However, with the rapid increase in volatile renewable energies, balancing supply and demand becomes increasingly important.…”

Section: Sector-coupled Energy Efficiency and Flexibilitymentioning

confidence: 99%

The Human’s Comfort Mystery—Supporting Energy Transition with Light-Color Dimmable Room Lighting

Wenninger

Wiethe

2022

Sustainability

Self Cite

View full text Add to dashboard Cite

The constant increase of intermittent renewable energies in the electricity grid complicates balancing supply and demand. Thus, research focuses on solutions in demand-side management using energy flexibility to resolve this problem. However, the interface between demand-side management and human behavior is often insufficiently addressed, although further potential could be leveraged here. This paper elaborates on the effect of light color on humans’ temperature and comfort perception in connection to energy flexibility. Researchers have found that people perceive blue light as colder and red light as warmer. To this end, we evaluate the effect of light color in a case study for a German industrial facility assuming sector-coupled electric heating. We simulate the entire heating period from October to April in an hourly granularity, using the well-established real options analysis and binomial trees as a decision support system to heuristically minimize energy expenditures by utilizing deferral options when energy prices are high. Our results show a 12.5% reduction in heating costs for sector-coupled electric heating, which extrapolated leads to CO2-eq emission savings of over 34,000 tons per year for the entire German industry, thereby supporting the energy transition.

show abstract

Energy Anomaly Detection in Industrial Applications with Long Short-term Memory-based Autoencoders

Cited by 14 publications

References 30 publications

Autoencoder Application for Anomaly Detection in Power Consumption of Lighting Systems

Autoencoder Application for Anomaly Detection in Power Consumption of Lighting Systems

Anomaly Detection of Consumption in Hotel Units: A Case Study Comparing Isolation Forest and Variational Autoencoder Algorithms

The Human’s Comfort Mystery—Supporting Energy Transition with Light-Color Dimmable Room Lighting

Contact Info

Product

Resources

About