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

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Applied Sciences applsci	2.5	5.3	2011	18.4 Days	CHF 2400	Submit
Electronics electronics	2.6	5.3	2012	16.4 Days	CHF 2400	Submit
Energies energies	3.0	6.2	2008	16.8 Days	CHF 2600	Submit
Sci sci	-	4.5	2019	37.1 Days	CHF 1200	Submit
Sensors sensors	3.4	7.3	2001	18.6 Days	CHF 2600	Submit
Systems systems	2.3	2.8	2013	19.6 Days	CHF 2400	Submit

40 pages, 1112 KiB

Open AccessArticle

Assessment of Indoor Thermo-Hygrometric Conditions and Energy Demands Associated to Filters and Dampers Faults via Experimental Tests of a Typical Air-Handling Unit During Summer and Winter in Southern Italy

by Antonio Rosato, Mohammad El Youssef, Rita Mercuri, Armin Hooman, Marco Savino Piscitelli and Alfonso Capozzoli

Energies 2025, 18(3), 618; https://doi.org/10.3390/en18030618 - 29 Jan 2025

Viewed by 385

Abstract

Faults of heating, ventilation, and air-conditioning (HVAC) systems can cause significant consequences, such as negatively affecting thermal comfort of occupants, energy demand, indoor air quality, etc. Several methods of fault detection and diagnosis (FDD) in building energy systems have been proposed since the [...] Read more.

Faults of heating, ventilation, and air-conditioning (HVAC) systems can cause significant consequences, such as negatively affecting thermal comfort of occupants, energy demand, indoor air quality, etc. Several methods of fault detection and diagnosis (FDD) in building energy systems have been proposed since the late 1980s in order to reduce the consequences of faults in heating, ventilation, and air-conditioning (HVAC) systems. All the proposed FDD methods require laboratory data, or simulated data, or field data. Furthermore, the majority of the recently proposed FDD methods require labelled faulty and normal data to be developed. Thus, providing reliable ground truth data of HVAC systems with different technical characteristics is of great importance for advances in FDD methods for HVAC units. The primary objective of this study is to examine the operational behaviour of a typical single-duct dual-fan constant air volume air-handling unit (AHU) in both faulty and fault-free conditions. The investigation encompasses a series of experiments conducted under Mediterranean climatic conditions in southern Italy during summer and winter. This study investigates the performance of the AHU by artificially introducing seven distinct typical faults: (1) return air damper kept always closed (stuck at 0%); (2) fresh air damper kept always closed (stuck at 0%); (3) fresh air damper kept always opened (stuck at 100%); (4) exhaust air damper kept always closed (stuck at 0%); (5) supply air filter partially clogged at 50%; (6) fresh air filter partially clogged at 50%; and (7) return air filter partially clogged at 50%. The collected data from the faulty scenarios are compared to the corresponding data obtained from fault-free performance measurements conducted under similar boundary conditions. Indoor thermo-hygrometric conditions, electrical power and energy consumption, operation time of AHU components, and all key operating parameters are measured for all the aforementioned faulty tests and their corresponding normal tests. In particular, the experimental results demonstrated that the exhaust air damper stuck at 0% significantly reduces the percentage of time with indoor air relative humidity kept within the defined deadbands by about 29% (together with a reduction in the percentage of time with indoor air temperature kept within the defined deadbands by 7.2%) and increases electric energy consumption by about 13% during winter. Moreover, the measured data underlined that the effects on electrical energy demand and indoor thermo-hygrometric conditions are minimal (with deviations not exceeding 5.6% during both summer and winter) in the cases of 50% clogging of supply air filter, fresh air filter, and return air filter. The results of this study can be exploited by researchers, facility managers, and building operators to better recognize root causes of faulty evidences in AHUs and also to develop and test new FDD tools. Full article

(This article belongs to the Topic Technologies and Applications of Data-Driven Anomaly Detection in Energy Systems)

20 pages, 1136 KiB

Open AccessArticle

Video Anomaly Detection with Hyperbolic Graph Embedding and Masked Normalizing Flows

by Yan Xu, Bowen Huang, Chao Zhou, Haoyuan Wang and Xuening Li

Electronics 2024, 13(24), 5013; https://doi.org/10.3390/electronics13245013 - 20 Dec 2024

Viewed by 546

Abstract

Video anomaly detection plays a vital role in intelligent video monitoring systems. It has found extensive applications in the fields of public safety and social security. Nevertheless, the area of video anomaly detection continues to be a formidable task because of the intricate [...] Read more.

Video anomaly detection plays a vital role in intelligent video monitoring systems. It has found extensive applications in the fields of public safety and social security. Nevertheless, the area of video anomaly detection continues to be a formidable task because of the intricate nature of actual data and the challenge of precisely identifying anomalies. Current anomaly detection approaches suffer from overpowered generalization ability, weak spatio-temporal feature extraction capability, and insufficient global information aggregation ability. Therefore, an unsupervised Hyperbolic Graph-based Normalizing Flows (HGNF) model is proposed in this paper, which is constructed with a Spatio-temporal Encoder (STEncoder) and stacked normalizing flows to reduce the overgeneralization of auto-encoder-based anomaly detection models. STEncoder consists of spatio-temporal attention and inter-frame feature aggregation. In normalizing flows, a Poincaré ball graph extractor is developed to improve the representation ability of the dynamic changes of the input data, and a masked affine coupling block is established to improve the performance of this model in global information aggregation. According to the experimental results obtained on four public datasets, HGNF achieves excellent performance and the best AUC (Area Under the Curve) score of 74.5% on the UBnormal dataset. Full article

(This article belongs to the Topic Technologies and Applications of Data-Driven Anomaly Detection in Energy Systems)

► Show Figures

Figure 1

36 pages, 10624 KiB

Open AccessArticle

Predicting Dependent Edges in Nonequilibrium Complex Systems Based on Overlapping Module Characteristics

by Qingyu Zou, Lin Yan, Yue Gong and Jingfei Hou

Systems 2024, 12(10), 433; https://doi.org/10.3390/systems12100433 - 14 Oct 2024

Viewed by 1045

Abstract

Problem: Predicting dependency relationships in nonequilibrium systems is a critical challenge in complex systems research. Solution proposed: In this paper, we propose a novel method for predicting dependent edges in network models of nonequilibrium complex systems, based on overlapping module features. This approach [...] Read more.

Problem: Predicting dependency relationships in nonequilibrium systems is a critical challenge in complex systems research. Solution proposed: In this paper, we propose a novel method for predicting dependent edges in network models of nonequilibrium complex systems, based on overlapping module features. This approach addresses the many-to-many dependency prediction problem between nonequilibrium complex networks. By transforming node-based network models into edge-based models, we identify overlapping modular structures, enabling the prediction of many-to-many dependent edges. Experimental evaluation: This method is applied to dependency edge prediction in power and gas networks, curriculum and competency networks, and text and question networks. Results: The results indicate that the proposed dependency edge prediction method enhances the robustness of the network in power–gas networks, accurately identifies supporting relationships in curriculum–competency networks, and achieves better information gain in text–question networks. Conclusion: These findings confirm that the overlapping module-based approach effectively predicts dependencies across various nonequilibrium complex systems in diverse fields. Full article

(This article belongs to the Topic Technologies and Applications of Data-Driven Anomaly Detection in Energy Systems)

► Show Figures

Figure 1

16 pages, 2582 KiB

Open AccessArticle

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

Cited by 1 | Viewed by 765

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

(This article belongs to the Topic Technologies and Applications of Data-Driven Anomaly Detection in Energy Systems)

► Show Figures

Figure 1

20 pages, 3754 KiB

Open AccessArticle

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 13 | Viewed by 2345

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

(This article belongs to the Topic Technologies and Applications of Data-Driven Anomaly Detection in Energy Systems)

► Show Figures

Figure 1

25 pages, 2593 KiB

Open AccessFeature PaperArticle

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 1752

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

(This article belongs to the Topic Technologies and Applications of Data-Driven Anomaly Detection in Energy Systems)

► Show Figures

Figure 1

19 pages, 2810 KiB

Open AccessArticle

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 1173

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

(This article belongs to the Topic Technologies and Applications of Data-Driven Anomaly Detection in Energy Systems)

► Show Figures

Figure 1

16 pages, 632 KiB

Open AccessArticle

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 1011

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

(This article belongs to the Topic Technologies and Applications of Data-Driven Anomaly Detection in Energy Systems)

► Show Figures

Figure 1

22 pages, 1327 KiB

Open AccessFeature PaperArticle

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 1066

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

(This article belongs to the Topic Technologies and Applications of Data-Driven Anomaly Detection in Energy Systems)

► Show Figures

Figure 1

Topic Menu

Topic Editors

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

Topic Information

Keywords

Participating Journals

Published Papers (9 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI