Topic Editors

Department of Energy “Galileo Ferraris”, TEBE Research Group, BAEDA Lab, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Turin, Italy
Department of Energy, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Torino, Italy
Department of Architecture and Industrial Design, University of Campania Luigi Vanvitelli, Via San Lorenzo, 81031 Aversa, CE, Italy
College of Civil and Transportation Engineering, Shenzhen University, Shenzhen, China

Technologies and Applications of Data-Driven Anomaly Detection in Energy Systems

Abstract submission deadline
31 January 2025
Manuscript submission deadline
30 April 2025
Viewed by
7146

Topic Information

Dear Colleagues,

The energy sector is becoming more and more information-intensive due to the growing spread and penetration of IOT sensing and long-term smart monitoring infrastructures. The knowledge hidden in massive operational data, collected from energy systems, can bring significant benefits for the characterization and modeling of their actual performance during operation. As a consequence, the robust coupling of data-driven technologies and energy domain knowledge proved to be effective in achieving relevant energy savings by exploiting a variety of advanced energy management solutions. In this context, anomaly detection systems play a key role in the new paradigm of data-driven energy systems management allowing the prompt and automatic recognition of abnormal and non-optimal performance patterns, providing information for the identification of energy waste and for the prioritization of corrective interventions. Such tools typically rely on (i) the automatic recognition of typical/normal energy behaviour of the system under investigation (ii) and on the consequent detection of anomalous/infrequent energy patterns, often leveraging predictive analytics, data mining and pattern recognition techniques. The development of a data-driven anomaly detection process poses several challenges related to the definition of anomaly itself. In the case of energy systems the definition of anomaly is very domain-specific and may pertain to faulty operations of system appliances/components, incorrect system management/control strategies, abnormal system energy consumption and technical/non-technical energy losses. Despite data-driven anomaly detection processes being able to lead to systematic energy saving during the operation of energy systems with a short simple payback period, their market penetration is still not satisfactory. At present, interesting research and technological opportunities are wide open also considering the current momentum of AI, and the increasing need of automatic management solutions for energy systems in relevant sectors such as industry, renewables and buildings. In this context, there is the need to deepen research and improve the effectiveness and reliability of anomaly detection processes. The objective of this Topic Project is to showcase the diversity and advances in this research field and to contribute in exploring the scalability of such data-driven solutions for a large set of heterogeneous energy systems. Original papers based on the analysis of both experimental and simulated energy system data are welcome. We are particularly interested in receiving manuscripts that integrate energy, mechanical and computer engineering research. We invite researchers from all areas of engineering to submit manuscripts for this relevant Topic Project.

Dr. Marco Savino Piscitelli
Dr. Alfonso Capozzoli
Prof. Dr. Antonio Rosato
Dr. Cheng Fan
Topic Editors

Keywords

  • anomaly detection
  • fault detection and diagnosis
  • energy systems
  • data-driven
  • artificial intelligence
  • HVAC
  • renewable energy systems
  • buildings

Participating Journals

Journal Name Impact Factor CiteScore Launched Year First Decision (median) APC
Applied Sciences
applsci
2.5 5.3 2011 17.8 Days CHF 2400 Submit
Electronics
electronics
2.6 5.3 2012 16.8 Days CHF 2400 Submit
Energies
energies
3.0 6.2 2008 17.5 Days CHF 2600 Submit
Sci
sci
- 4.5 2019 27.4 Days CHF 1200 Submit
Sensors
sensors
3.4 7.3 2001 16.8 Days CHF 2600 Submit
Systems
systems
2.3 2.8 2013 17.3 Days CHF 2400 Submit

Preprints.org is a multidiscipline platform providing preprint service that is dedicated to sharing your research from the start and empowering your research journey.

MDPI Topics is cooperating with Preprints.org and has built a direct connection between MDPI journals and Preprints.org. Authors are encouraged to enjoy the benefits by posting a preprint at Preprints.org prior to publication:

  1. Immediately share your ideas ahead of publication and establish your research priority;
  2. Protect your idea from being stolen with this time-stamped preprint article;
  3. Enhance the exposure and impact of your research;
  4. Receive feedback from your peers in advance;
  5. Have it indexed in Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (6 papers)

Order results
Result details
Journals
Select all
Export citation of selected articles as:
16 pages, 2582 KiB  
Article
An Efficient Method for Detecting Abnormal Electricity Behavior
by Chao Tang, Yunchuan Qin, Yumeng Liu, Huilong Pi and Zhuo Tang
Energies 2024, 17(11), 2502; https://doi.org/10.3390/en17112502 - 23 May 2024
Viewed by 337
Abstract
The non-technical losses caused by abnormal power consumption behavior of power users seriously affect the revenue of power companies and the quality of power supply. To assist electric power companies in improving the efficiency of power consumption audit and regulating the power consumption [...] Read more.
The non-technical losses caused by abnormal power consumption behavior of power users seriously affect the revenue of power companies and the quality of power supply. To assist electric power companies in improving the efficiency of power consumption audit and regulating the power consumption behavior of users, this paper proposes a power consumption anomaly detection method named High-LowDAAE (Autoencoder model for dual adversarial training of high low-level temporal features). High-LowDAAE adds an extra “discriminator” named AE3 to USAD (UnSupervised Anomaly Detection on Multivariate Time Series), which performs the same function as AE2 in USAD. AE3 performs the same function as AE2 in USAD, i.e., it is trained against AE1 to enhance its ability to reconstruct average data. However, AE3 differs from AE2 because the two “discriminators” correspond to the high-level and low-level time series features output from the shared encoder network. By utilizing different levels of temporal features to reconstruct the data and conducting adversarial training, AE1 can reconstruct the time-series data more efficiently, thus improving the accuracy of detecting abnormal electricity usage. In addition, to enhance the model’s feature extraction ability for time-series data, the self-encoder is constructed with a long short-term memory (LSTM) network, and the fully connected layer in the USAD model is no longer used. This modification improves the extraction of temporal features and provides richer hidden features for the adversarial training of the dual “discriminators”. Finally, the ablation and comparison experiments are conducted using accurate electricity consumption data from users, and the results show that the proposed method has higher accuracy. Full article
Show Figures

Figure 1

20 pages, 3754 KiB  
Article
Spatiotemporal Masked Autoencoder with Multi-Memory and Skip Connections for Video Anomaly Detection
by Yan Fu, Bao Yang and Ou Ye
Electronics 2024, 13(2), 353; https://doi.org/10.3390/electronics13020353 - 14 Jan 2024
Cited by 5 | Viewed by 1479
Abstract
Video anomaly detection is a critical component of intelligent video surveillance systems, extensively deployed and researched in industry and academia. However, existing methods have a strong generalization ability for predicting anomaly samples. They cannot utilize high-level semantic and temporal contextual information in videos, [...] Read more.
Video anomaly detection is a critical component of intelligent video surveillance systems, extensively deployed and researched in industry and academia. However, existing methods have a strong generalization ability for predicting anomaly samples. They cannot utilize high-level semantic and temporal contextual information in videos, resulting in unstable prediction performance. To alleviate this issue, we propose an encoder–decoder model named SMAMS, based on spatiotemporal masked autoencoder and memory modules. First, we represent and mask some of the video events using spatiotemporal cubes. Then, the unmasked patches are inputted into the spatiotemporal masked autoencoder to extract high-level semantic and spatiotemporal features of the video events. Next, we add multiple memory modules to store unmasked video patches of different feature layers. Finally, skip connections are introduced to compensate for crucial information loss caused by the memory modules. Experimental results show that the proposed method outperforms state-of-the-art methods, achieving AUC scores of 99.9%, 94.8%, and 78.9% on the UCSD Ped2, CUHK Avenue, and Shanghai Tech datasets. Full article
Show Figures

Figure 1

25 pages, 2593 KiB  
Article
Anomaly Detection in a Smart Microgrid System Using Cyber-Analytics: A Case Study
by Preetha Thulasiraman, Michael Hackett, Preston Musgrave, Ashley Edmond and Jared Seville
Energies 2023, 16(20), 7151; https://doi.org/10.3390/en16207151 - 19 Oct 2023
Cited by 1 | Viewed by 1232
Abstract
Smart microgrids are being increasingly deployed within the Department of Defense. The microgrid at Marine Corps Air Station (MCAS) Miramar is one such deployment that has fostered the integration of different technologies, including 5G and Advanced Metering Infrastructure (AMI). The objective of this [...] Read more.
Smart microgrids are being increasingly deployed within the Department of Defense. The microgrid at Marine Corps Air Station (MCAS) Miramar is one such deployment that has fostered the integration of different technologies, including 5G and Advanced Metering Infrastructure (AMI). The objective of this paper is to develop an anomaly detection framework for the smart microgrid system at MCAS Miramar to enhance its cyber-resilience. We implement predictive analytics using machine learning to deal with cyber-uncertainties and threats within the microgrid environment. An autoencoder neural network is implemented to classify and identify specific cyber-attacks against this infrastructure. Both network traffic in the form of packet captures (PCAP) and time series data (from the AMI sensors) are considered. We train the autoencoder model on three traffic data sets: (1) Modbus TCP/IP PCAP data from the hardwired network apparatus of the smart microgrid, (2) experimentally generated 5G PCAP data that mimic traffic on the smart microgrid and (3) AMI smart meter sensor data provided by the Naval Facilities (NAVFAC) Engineering Systems Command. Distributed denial-of-service (DDoS) and false data injection attacks (FDIA) are synthetically generated. We show the effectiveness of the autoencoder on detecting and classifying these types of attacks in terms of accuracy, precision, recall, and F-scores. Full article
Show Figures

Figure 1

19 pages, 2810 KiB  
Article
Installation Principle and Calculation Model of the Representative Indoor Temperature-Monitoring Points in Large-Scale Buildings
by Mengyao Lu, Guitao Xu and Jianjuan Yuan
Energies 2023, 16(17), 6376; https://doi.org/10.3390/en16176376 - 2 Sep 2023
Viewed by 899
Abstract
Although indoor temperature was an important criterion for the evaluation of heating requirements, it was costly to install temperature-monitoring devices in every household for large-scale buildings. However, it was inexpensive to install the device at some representative locations, and the average temperature can [...] Read more.
Although indoor temperature was an important criterion for the evaluation of heating requirements, it was costly to install temperature-monitoring devices in every household for large-scale buildings. However, it was inexpensive to install the device at some representative locations, and the average temperature can be used to evaluate the heating requirement. In this case, it was obvious that the accuracy was limited by the location and number of installations and the calculation method. In this paper, first, the indoor temperature variation relationship between the object and adjacent households was analyzed. It was found that the correlation between the household situated above and the household in which the object was located was the strongest, which provides a new energy-saving regulation strategy. Then, the indoor temperature of households in different locations was classified using the k-means algorithm, and the installment location, number of representative points, and comprehensive indoor temperature calculation model were determined. Finally, the installment principle and calculation model were applied. The results show that, compared with the traditional method, the temperature obtained via the proposed method was closer to the actual temperature and was less affected by the instability of communication. Full article
Show Figures

Figure 1

16 pages, 632 KiB  
Article
Graph Complexity Reduction of Exergy-Based FDI—A Tennessee Eastman Process Case Study
by Rikus Styger, Kenneth R. Uren and George van Schoor
Energies 2023, 16(16), 6022; https://doi.org/10.3390/en16166022 - 17 Aug 2023
Viewed by 731
Abstract
When applying graph-based fault detection and isolation (FDI) methods to the attributed graph data of large and complex industrial processes, the computational abilities and speed of these methods are adversely affected by the increased complexity. This paper proposes and evaluates five reduction techniques [...] Read more.
When applying graph-based fault detection and isolation (FDI) methods to the attributed graph data of large and complex industrial processes, the computational abilities and speed of these methods are adversely affected by the increased complexity. This paper proposes and evaluates five reduction techniques for the exergy-graph-based FDI method. Unlike the graph reduction techniques available in literature, the reduction techniques proposed in this paper can easily be applied to the type of attributed graph used by graph-based FDI methods. The attributed graph data of the Tennessee Eastman process are used in this paper since it is a popular process to use for the evaluation of fault diagnostic methods and is both large and complex. To evaluate the proposed reduction techniques, three FDI methods are applied to the original attributed graph data of the process and the performance of these FDI methods used as control data. Each proposed reduction technique is applied to the attributed graph data of the process, after which all three FDI methods are applied to the reduced graph data to evaluate their performance. The FDI performance obtained with reduced graph data is compared to the FDI performance using the control data. This paper shows that, using the proposed graph reduction techniques, it is possible to significantly reduce the size and complexity of the attributed graph of a system while maintaining a level of FDI performance similar to that achieved prior to any graph reduction. Full article
Show Figures

Figure 1

22 pages, 1327 KiB  
Article
Data-Driven Estimation of Time-Varying Stochastic Effects on Building Heat Consumption Related to Human Interactions
by Christoffer Rasmussen, Niels Lassen, Peder Bacher, Tor Helge Dokka and Henrik Madsen
Energies 2023, 16(16), 5991; https://doi.org/10.3390/en16165991 - 15 Aug 2023
Viewed by 777
Abstract
Within the field of statistical modelling and data-driven characterisation of buildings’ energy performance, the focus is typically on parameter estimation of the building envelope and the energy systems. Less focus has been put on the stochastic human effect on energy consumption. We propose [...] Read more.
Within the field of statistical modelling and data-driven characterisation of buildings’ energy performance, the focus is typically on parameter estimation of the building envelope and the energy systems. Less focus has been put on the stochastic human effect on energy consumption. We propose a new method for estimating the thermal building properties while, in parallel, estimating time-varying effects caused by the humans’ interactions with the building. We do that by combining a smooth, non-linear formulation of the energy signature method known from the literature with a hidden state formulated as a random walk to describe the human interactions with the building. The method is demonstrated on data obtained from autumn 2019 to late spring 2021 from a 900 m2 newly built school building located south of Oslo, Norway. The demonstration case has shown that the model accuracy increases and the model bias decrease when cross-validated. The estimated hidden state has also been shown to resemble the estimated combined mechanical and natural ventilation pattern controlled by the building users and operational staff. These human interactions have increased the total heat loss expressed in kilowatts per kelvin by around 50% over the course of one year from before the COVID-19 pandemic to after its outbreak. Full article
Show Figures

Figure 1

Back to TopTop