Pub Date : 2025-06-10DOI: 10.1109/TSUSC.2025.3578517
Shiming He;Rui Liu;Bowen Chen;Kun Xie;Jigang Wen
Log analysis, especially log anomaly detection, can help debug systems and analyze root causes to provide reliable services. Deep learning is a promising technology for log anomaly detection. However, deep learning methods need a large amount of training data, which is hard for a newly deployed system to collect sufficient logs. Transfer learning becomes a possible method to solve the problem that can apply the knowledge from a long-term deployed system (source) to a newly deployed system (target). Existing transfer learning methods focus on transferring the knowledge from a source system to a single target system within the same service, in which the source and the target belong to the same service (e.g. operating system, supercomputer, or distributed system). They achieve low performance when applied to multiple target and different services systems because of the obvious differences in log format, syntax, semantics, and component call between different services and the individual training of multiple models for each target system. To tackle the problems, we propose an unsupervised multi-target cross-service log anomaly detection method based on transfer learning and contrastive learning (LogMTC). LogMTC exploits contrastive learning to learn a single model on combined data from the source and multiple target systems, which can fit multiple target systems simultaneously and improve efficiency. LogMTC exploits a hypersphere loss and two contrastive losses to minimize the feature differences crossing different services. Our experiments on two services (supercomputer and distributed system) and three log datasets show that our method is superior to the existing transfer learning methods in the same service, cross-service, and multi-target log anomaly detection. Compared with the best peer accurate transfer learning algorithm LogTAD, LogMTC improves 1.14%–8.28$%$ F1 score in multi-target transfer and is 1.12–1.22 times faster.
{"title":"Unsupervised Multi-Target Cross-Service Log Anomaly Detection","authors":"Shiming He;Rui Liu;Bowen Chen;Kun Xie;Jigang Wen","doi":"10.1109/TSUSC.2025.3578517","DOIUrl":"https://doi.org/10.1109/TSUSC.2025.3578517","url":null,"abstract":"Log analysis, especially log anomaly detection, can help debug systems and analyze root causes to provide reliable services. Deep learning is a promising technology for log anomaly detection. However, deep learning methods need a large amount of training data, which is hard for a newly deployed system to collect sufficient logs. Transfer learning becomes a possible method to solve the problem that can apply the knowledge from a long-term deployed system (source) to a newly deployed system (target). Existing transfer learning methods focus on transferring the knowledge from a source system to a single target system within the same service, in which the source and the target belong to the same service (e.g. operating system, supercomputer, or distributed system). They achieve low performance when applied to multiple target and different services systems because of the obvious differences in log format, syntax, semantics, and component call between different services and the individual training of multiple models for each target system. To tackle the problems, we propose an unsupervised multi-target cross-service log anomaly detection method based on transfer learning and contrastive learning (LogMTC). LogMTC exploits contrastive learning to learn a single model on combined data from the source and multiple target systems, which can fit multiple target systems simultaneously and improve efficiency. LogMTC exploits a hypersphere loss and two contrastive losses to minimize the feature differences crossing different services. Our experiments on two services (supercomputer and distributed system) and three log datasets show that our method is superior to the existing transfer learning methods in the same service, cross-service, and multi-target log anomaly detection. Compared with the best peer accurate transfer learning algorithm LogTAD, LogMTC improves 1.14%–8.28<inline-formula><tex-math>$%$</tex-math></inline-formula> F1 score in multi-target transfer and is 1.12–1.22 times faster.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"10 5","pages":"1056-1069"},"PeriodicalIF":3.9,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145248086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Internet of Things (IoT) has been increasingly applied in various applications in recent years. In IoT, many tasks are performed for a load operation, such as creating a cluster, preserving convergence/connectivity issues, etc. However, the energy consumption rate is also high due to more traffic in dense networks. Generally, a traditional IoT node’s battery power capacity is limited due to a short-range cycle. To address the energy shortage problem, researchers have tackled it through the Solar Powered (SP) energy harvesting technique. This method provides abundant energy to the IoT nodes at a lower cost. One issue arises from the target coverage area, which requires that each target must have at least one node for continuous monitoring in a given area. To address these issues, we have designed an effective solution called the Efficient Scheduling Target Coverage (ESTC) algorithm. This approach consists of various cover sets that work in an interleaving way. If only some node sets need to be active to satisfy coverage constraints, then there is no need to activate all sets simultaneously. ESTC provides robust coverage awareness with a perpetual network lifetime using scheduling techniques. Furthermore, the proposed work also promotes a green IoT network.
{"title":"An Efficient Scheduling Approach for Target Coverage in Solar Powered Internet of Things","authors":"Dipak Kumar Sah;Abhishek Hazra;Nabajyoti Mazumdar;Annavarapu Chandra Sekhara Rao;Tarachand Amgoth","doi":"10.1109/TSUSC.2025.3578433","DOIUrl":"https://doi.org/10.1109/TSUSC.2025.3578433","url":null,"abstract":"The Internet of Things (IoT) has been increasingly applied in various applications in recent years. In IoT, many tasks are performed for a load operation, such as creating a cluster, preserving convergence/connectivity issues, etc. However, the energy consumption rate is also high due to more traffic in dense networks. Generally, a traditional IoT node’s battery power capacity is limited due to a short-range cycle. To address the energy shortage problem, researchers have tackled it through the Solar Powered (SP) energy harvesting technique. This method provides abundant energy to the IoT nodes at a lower cost. One issue arises from the target coverage area, which requires that each target must have at least one node for continuous monitoring in a given area. To address these issues, we have designed an effective solution called the Efficient Scheduling Target Coverage (ESTC) algorithm. This approach consists of various cover sets that work in an interleaving way. If only some node sets need to be active to satisfy coverage constraints, then there is no need to activate all sets simultaneously. ESTC provides robust coverage awareness with a perpetual network lifetime using scheduling techniques. Furthermore, the proposed work also promotes a green IoT network.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"10 5","pages":"1043-1055"},"PeriodicalIF":3.9,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145248062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-09DOI: 10.1109/TSUSC.2025.3577218
Siqin Liu;Prakash Chand Kuve;Avinash Karanth
Graph convolutional networks (GCNs) have emerged as an effective approach to extend deep learning algorithms for graph-based data analytics. However, GCNs implementation over large, sparse datasets presents challenges due to irregular computation and dataflow patterns. Specialized GCN accelerators have emerged to deliver superior performance over generic processors. However, prior techniques that include specialized datapaths, optimized sparse computation, and memory access patterns, handle different phases of GCNs differently which results in excess energy consumption and reduced throughput due to sub-optimal dataflows. In this paper, we propose GreeNX, a computation and communication-aware GCN accelerator that uniformly applies three complementary techniques to all phases of GCN. First, we abstract two cascaded sparse-dense matrix multiplications that uniformly process the computation in both aggregation and combination phases of GCNs to improve throughput. Second, to mitigate the overheads of processing irregular sparse data, we develop a dynamic-voltage-and-frequency-scaling (DVFS) scheme by grouping a row of processing elements (PEs) that dynamically changes the applied voltage/frequency (V/F) to improve energy efficiency. Third, we conduct a comprehensive carbon footprint evaluation, analyzing both embodied and operational emissions for GCNs. Extensive simulation and experiments validate that our GreeNX consistently reduces memory accesses and energy consumption leading to an average 7.3× speedup and 5.6× energy savings on six real-world graph datasets over several state-of-the-art GCN accelerators including HyGCN, AWB-GCN, GCoD, GRIP, IGCN, and LW-GCN.
{"title":"GreeNX: An Energy-Efficient and Sustainable Approach to Sparse Graph Convolution Networks Accelerators Using DVFS","authors":"Siqin Liu;Prakash Chand Kuve;Avinash Karanth","doi":"10.1109/TSUSC.2025.3577218","DOIUrl":"https://doi.org/10.1109/TSUSC.2025.3577218","url":null,"abstract":"Graph convolutional networks (GCNs) have emerged as an effective approach to extend deep learning algorithms for graph-based data analytics. However, GCNs implementation over large, sparse datasets presents challenges due to irregular computation and dataflow patterns. Specialized GCN accelerators have emerged to deliver superior performance over generic processors. However, prior techniques that include specialized datapaths, optimized sparse computation, and memory access patterns, handle different phases of GCNs differently which results in excess energy consumption and reduced throughput due to sub-optimal dataflows. In this paper, we propose GreeNX, a computation and communication-aware GCN accelerator that uniformly applies three complementary techniques to all phases of GCN. First, we abstract two cascaded sparse-dense matrix multiplications that uniformly process the computation in both aggregation and combination phases of GCNs to improve throughput. Second, to mitigate the overheads of processing irregular sparse data, we develop a dynamic-voltage-and-frequency-scaling (DVFS) scheme by grouping a row of processing elements (PEs) that dynamically changes the applied voltage/frequency (V/F) to improve energy efficiency. Third, we conduct a comprehensive carbon footprint evaluation, analyzing both embodied and operational emissions for GCNs. Extensive simulation and experiments validate that our GreeNX consistently reduces memory accesses and energy consumption leading to an average 7.3× speedup and 5.6× energy savings on six real-world graph datasets over several state-of-the-art GCN accelerators including HyGCN, AWB-GCN, GCoD, GRIP, IGCN, and LW-GCN.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"10 5","pages":"1031-1042"},"PeriodicalIF":3.9,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145248071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-02DOI: 10.1109/TSUSC.2025.3575285
Yingnan Zhao;Ke Wang;Ahmed Louri
Graph Convolutional Networks (GCNs) have been proposed to extend machine learning techniques for graph-related applications. A typical GCN model consists of multiple layers, each including an aggregation phase, which is communication-intensive, and a combination phase, which is computation-intensive. As the size of real-world graphs increases exponentially, current customized accelerators face challenges in efficiently performing GCN inference due to limited on-chip buffers and other hardware resources for both data computation and communication, which degrades performance and energy efficiency. Additionally, scaling current monolithic designs to address the aforementioned challenges will introduce significant cost-effectiveness issues in terms of power, area, and yield. To this end, we propose HS-GCN, a high-performance, sustainable, and scalable chiplet-based accelerator for GCN inference with much-improved energy efficiency. Specifically, HS-GCN integrates multiple reconfigurable chiplets, each of which can be configured to perform the main computations of either the aggregation phase or the combination phase, including Sparse-dense matrix multiplication (SpMM) and General matrix-matrix multiplication (GeMM). HS-GCN implements an active interposer with a flexible interconnection fabric to connect chiplets and other hardware components for efficient data communication. Additionally, HS-GCN introduces two system-level control algorithms that dynamically determine the computation order and corresponding dataflow based on the input graphs and GCN models. These selections are used to further configure the chiplet array and interconnection fabric for much-improved performance and energy efficiency. Evaluation results using real-world graphs demonstrate that HS-GCN achieves significant speedups of 26.7×, 11.2×, 3.9×, 4.7×, 3.1×, along with substantial memory access savings of 94%, 89%, 64%, 85%, 54%, and energy savings of 87%, 84%, 49%, 78%, 41% on average, as compared to HyGCN, AWB-GCN, GCNAX, I-GCN, and SGCN, respectively.
{"title":"HS-GCN: A High-Performance, Sustainable, and Scalable Chiplet-Based Accelerator for Graph Convolutional Network Inference","authors":"Yingnan Zhao;Ke Wang;Ahmed Louri","doi":"10.1109/TSUSC.2025.3575285","DOIUrl":"https://doi.org/10.1109/TSUSC.2025.3575285","url":null,"abstract":"Graph Convolutional Networks (GCNs) have been proposed to extend machine learning techniques for graph-related applications. A typical GCN model consists of multiple layers, each including an aggregation phase, which is communication-intensive, and a combination phase, which is computation-intensive. As the size of real-world graphs increases exponentially, current customized accelerators face challenges in efficiently performing GCN inference due to limited on-chip buffers and other hardware resources for both data computation and communication, which degrades performance and energy efficiency. Additionally, scaling current monolithic designs to address the aforementioned challenges will introduce significant cost-effectiveness issues in terms of power, area, and yield. To this end, we propose HS-GCN, a high-performance, sustainable, and scalable chiplet-based accelerator for GCN inference with much-improved energy efficiency. Specifically, HS-GCN integrates multiple reconfigurable chiplets, each of which can be configured to perform the main computations of either the aggregation phase or the combination phase, including Sparse-dense matrix multiplication (SpMM) and General matrix-matrix multiplication (GeMM). HS-GCN implements an active interposer with a flexible interconnection fabric to connect chiplets and other hardware components for efficient data communication. Additionally, HS-GCN introduces two system-level control algorithms that dynamically determine the computation order and corresponding dataflow based on the input graphs and GCN models. These selections are used to further configure the chiplet array and interconnection fabric for much-improved performance and energy efficiency. Evaluation results using real-world graphs demonstrate that HS-GCN achieves significant speedups of 26.7×, 11.2×, 3.9×, 4.7×, 3.1×, along with substantial memory access savings of 94%, 89%, 64%, 85%, 54%, and energy savings of 87%, 84%, 49%, 78%, 41% on average, as compared to HyGCN, AWB-GCN, GCNAX, I-GCN, and SGCN, respectively.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"10 5","pages":"1019-1030"},"PeriodicalIF":3.9,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145256014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-21DOI: 10.1109/TSUSC.2025.3562738
Chandrajit Pal;Sangeet Saha;Xiaojun Zhai;Gareth Howells;Klaus D. McDonald-Maier
Embedded systems serving as IoT nodes are often vulnerable to malicious and unknown runtime software that could compromise the system, steal sensitive data, and cause undesirable system behaviour. Commercially available embedded systems used in automation, medical equipment, and automotive industries, are especially exposed to this vulnerability since they lack the resources to incorporate conventional safety features and are challenging to mitigate through conventional approaches. We propose a novel system design coined as APPARENT which can identify program characteristics by monitoring and counting the maximum possible low-level hardware events from Hardware Performance Counters (HPCs) that occur during the program's execution and analyse the correlation among the counts of various monitored events. To further utilise these captured events as features we propose a self-supervised machine learning algorithm that combines a Graph Attention Network GAT and a Generative Topographic Mapping GTM to detect unusual program behaviour as anomalies to enhance the system security. Our proposed methodology takes advantage of attributes like program counter, cycles per instruction, and physical and virtual timers at various exception levels of the embedded processor to identify abnormal activity. APPARENT identifies unknown program behaviours not present in the training phase with an accuracy of over 98.46% on Autobench EEMBC benchmarks.
{"title":"APPARENT: AI-Powered Platform Anomaly Detection in Edge Computing","authors":"Chandrajit Pal;Sangeet Saha;Xiaojun Zhai;Gareth Howells;Klaus D. McDonald-Maier","doi":"10.1109/TSUSC.2025.3562738","DOIUrl":"https://doi.org/10.1109/TSUSC.2025.3562738","url":null,"abstract":"Embedded systems serving as IoT nodes are often vulnerable to malicious and unknown runtime software that could compromise the system, steal sensitive data, and cause undesirable system behaviour. Commercially available embedded systems used in automation, medical equipment, and automotive industries, are especially exposed to this vulnerability since they lack the resources to incorporate conventional safety features and are challenging to mitigate through conventional approaches. We propose a novel system design coined as APPARENT which can identify program characteristics by monitoring and counting the maximum possible low-level hardware events from Hardware Performance Counters (HPCs) that occur during the program's execution and analyse the correlation among the counts of various monitored events. To further utilise these captured events as features we propose a self-supervised machine learning algorithm that combines a Graph Attention Network GAT and a Generative Topographic Mapping GTM to detect unusual program behaviour as anomalies to enhance the system security. Our proposed methodology takes advantage of attributes like program counter, cycles per instruction, and physical and virtual timers at various exception levels of the embedded processor to identify abnormal activity. APPARENT identifies unknown program behaviours not present in the training phase with an accuracy of over 98.46% on Autobench EEMBC benchmarks.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"10 5","pages":"965-981"},"PeriodicalIF":3.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145248060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-16DOI: 10.1109/TSUSC.2025.3561603
Ayesha Siddique;Khaza Anuarul Hoque
Deep neural networks are lucrative targets of adversarial attacks and approximate deep neural networks (AxDNNs) are no exception. Searching manually for adversarially robust AxDNN architectures incurs outrageous time and human effort. In this paper, we propose XAI-NAS, an explainable neural architecture search (NAS) method that leverages explainable artificial intelligence (XAI) to efficiently co-optimize the adversarial robustness and hardware efficiency of AxDNN architectures on systolic-array hardware accelerators. During the NAS process, AxDNN architectures are evolved layer-wise with heterogeneous approximate multipliers to deliver the best trade-offs between adversarial robustness, energy consumption, latency, and memory footprint. The most suitable approximate multipliers are automatically selected from an open-source Evoapprox8b library. Our extensive evaluations provide a set of Pareto optimal hardware efficient and adversarially robust solutions. For example, a Pareto-optimal DNN AxDNN for the MNIST and CIFAR-10 datasets exhibits up to 1.5× higher adversarial robustness, 2.1× less energy consumption, 4.39× reduced latency, and 2.37× low memory footprint when compared to the state-of-the-art NAS approaches.
{"title":"Explainable AI-Guided Neural Architecture Search for Adversarial Robustness in Approximate DNNs","authors":"Ayesha Siddique;Khaza Anuarul Hoque","doi":"10.1109/TSUSC.2025.3561603","DOIUrl":"https://doi.org/10.1109/TSUSC.2025.3561603","url":null,"abstract":"Deep neural networks are lucrative targets of adversarial attacks and approximate deep neural networks (AxDNNs) are no exception. Searching manually for adversarially robust AxDNN architectures incurs outrageous time and human effort. In this paper, we propose XAI-NAS, an explainable neural architecture search (NAS) method that leverages explainable artificial intelligence (XAI) to efficiently co-optimize the adversarial robustness and hardware efficiency of AxDNN architectures on systolic-array hardware accelerators. During the NAS process, AxDNN architectures are evolved layer-wise with heterogeneous approximate multipliers to deliver the best trade-offs between adversarial robustness, energy consumption, latency, and memory footprint. The most suitable approximate multipliers are automatically selected from an open-source Evoapprox8b library. Our extensive evaluations provide a set of Pareto optimal hardware efficient and adversarially robust solutions. For example, a Pareto-optimal DNN AxDNN for the MNIST and CIFAR-10 datasets exhibits up to 1.5× higher adversarial robustness, 2.1× less energy consumption, 4.39× reduced latency, and 2.37× low memory footprint when compared to the state-of-the-art NAS approaches.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"10 5","pages":"949-964"},"PeriodicalIF":3.9,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145248094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Federated learning (FL) has gained prominence in energy forecasting applications. Despite its advantages, FL remains vulnerable to adversarial attacks that threaten the reliability of predictive models. This study introduces a stealth attack, Federated Communication Round Attack (Fed-CRA), which increases communication rounds without affecting forecasting accuracy. Increased communication rounds can delay decision-making, reducing system responsiveness and cost-effectiveness in dynamic energy forecasting scenarios. Experimental validation on two datasets demonstrated that Fed-CRA increased communication rounds by 574% (from 72 to 485) in the AEP dataset and by 237% (from 92 to 310) in the COMED dataset. This led to a corresponding rise in energy consumption by 573% (from 41.04 kWh to 276.35 kWh) and 237% (from 52.44 kWh to 176.65 kWh), respectively, while preserving forecasting accuracy. To counter this attack, we proposed Federated Incentivized Averaging (Fed-InA), a game theory-inspired framework that rewards honest clients and penalizes dishonest ones based on their contributions. Results showed that Fed-InA reduced the additional communication rounds caused by Fed-CRA by 85% in the AEP dataset and 70% in the COMED dataset, while maintaining forecasting performance. Fed-InA achieves resource efficiency comparable to Federated Averaging (FedAvg) and demonstrates robustness in handling non-IID data.
联邦学习（FL）在能源预测应用中得到了突出的应用。尽管具有优势，但FL仍然容易受到威胁预测模型可靠性的对抗性攻击。本研究引入了一种隐形攻击，联邦通信回合攻击（federal Communication Round attack, Fed-CRA），它在不影响预测精度的情况下增加了通信回合。在动态能源预测场景中，增加的通信轮次可能会延迟决策，降低系统响应能力和成本效益。两个数据集的实验验证表明，Fed-CRA在AEP数据集中增加了574%（从72次增加到485次），在COMED数据集中增加了237%（从92次增加到310次）。在保持预测准确性的前提下，能耗相应增加573%（从41.04 kWh增加到276.35 kWh）和237%（从52.44 kWh增加到176.65 kWh）。为了应对这种攻击，我们提出了联邦激励平均（Fed-InA），这是一个博弈论启发的框架，奖励诚实的客户，并根据他们的贡献惩罚不诚实的客户。结果表明，在保持预测性能的同时，Fed-InA在AEP数据集中减少了85%由Fed-CRA引起的额外沟通轮数，在COMED数据集中减少了70%。Fed-InA实现了与联邦平均（fedag）相当的资源效率，并在处理非iid数据方面表现出鲁棒性。
{"title":"Novel Stealth Communication Round Attack and Robust Incentivized Federated Averaging for Load Forecasting","authors":"Habib Ullah Manzoor;Kamran Arshad;Khaled Assaleh;Ahmed Zoha","doi":"10.1109/TSUSC.2025.3570096","DOIUrl":"https://doi.org/10.1109/TSUSC.2025.3570096","url":null,"abstract":"Federated learning (FL) has gained prominence in energy forecasting applications. Despite its advantages, FL remains vulnerable to adversarial attacks that threaten the reliability of predictive models. This study introduces a stealth attack, Federated Communication Round Attack (Fed-CRA), which increases communication rounds without affecting forecasting accuracy. Increased communication rounds can delay decision-making, reducing system responsiveness and cost-effectiveness in dynamic energy forecasting scenarios. Experimental validation on two datasets demonstrated that Fed-CRA increased communication rounds by 574% (from 72 to 485) in the AEP dataset and by 237% (from 92 to 310) in the COMED dataset. This led to a corresponding rise in energy consumption by 573% (from 41.04 kWh to 276.35 kWh) and 237% (from 52.44 kWh to 176.65 kWh), respectively, while preserving forecasting accuracy. To counter this attack, we proposed Federated Incentivized Averaging (Fed-InA), a game theory-inspired framework that rewards honest clients and penalizes dishonest ones based on their contributions. Results showed that Fed-InA reduced the additional communication rounds caused by Fed-CRA by 85% in the AEP dataset and 70% in the COMED dataset, while maintaining forecasting performance. Fed-InA achieves resource efficiency comparable to Federated Averaging (FedAvg) and demonstrates robustness in handling non-IID data.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"10 5","pages":"1007-1018"},"PeriodicalIF":3.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145248080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recently, a plethora of promising green energy provisioning technologies has been discussed in the orientation of prolonging the lifetime of energy-limited devices (e.g., sensor nodes). Wireless rechargeable sensor networks (WRSNs) have emerged among other fields that could greatly benefit from such technologies. Such an ad-hoc network comprises a base station(s) and multiple sensor nodes, which are primarily deployed in harsh environments, meeting the requirements of transmitting, receiving, collecting, and processing data. Unlike existing works, this survey paper focuses on energy provisioning technologies within the context of WRSNs by reviewing two interrelated domains. First, we introduce various energy provisioning techniques and their associated challenges, including conventional energy harvesting methods (e.g., solar, thermal, and mechanical). We highlight wireless power transfer (WPT) as one of the most applicable technologies for WRSNs, covering both radiative and non-radiative WPT. Additionally, we present radio frequency (RF) energy harvesting, including simultaneous wireless information and power transfer (SWIPT) and wireless powered communication networks (WPCNs), as well as backscatter communications. Furthermore, we compare hybrid energy harvesting techniques (e.g., solar-RF, vibro-acoustic, solar-thermal, etc.). Second, we introduce the fundamentals of wireless charging, reviewing various charger types (static and mobile), charging policies (including full and partial charging), charging modes (offline and online), and charging schemes (periodic and on-demand). We also present the collaborative charging mechanisms. Additionally, we address several key challenges facing WRSNs, such as energy consumption, multi-charger coordination, dynamic network recharging, monitoring & security threats, vehicle-to-vehicle (V2V) charging, and hybrid WRSNs Finally, we highlight trends and future directions for integrating advanced artificial intelligence (AI) technologies into WRSNs.
{"title":"Wireless Rechargeable Sensor Networks: Energy Provisioning Technologies, Charging Scheduling Schemes, and Challenges","authors":"Samah Abdel Aziz;Xingfu Wang;Ammar Hawbani;Bushra Qureshi;Saeed H. Alsamhi;Aisha Alabsi;Liang Zhao;Ahmed Al-Dubai;A.S. Ismail","doi":"10.1109/TSUSC.2025.3549414","DOIUrl":"https://doi.org/10.1109/TSUSC.2025.3549414","url":null,"abstract":"Recently, a plethora of promising green energy provisioning technologies has been discussed in the orientation of prolonging the lifetime of energy-limited devices (e.g., sensor nodes). Wireless rechargeable sensor networks (WRSNs) have emerged among other fields that could greatly benefit from such technologies. Such an ad-hoc network comprises a base station(s) and multiple sensor nodes, which are primarily deployed in harsh environments, meeting the requirements of transmitting, receiving, collecting, and processing data. Unlike existing works, this survey paper focuses on energy provisioning technologies within the context of WRSNs by reviewing two interrelated domains. First, we introduce various energy provisioning techniques and their associated challenges, including conventional energy harvesting methods (e.g., solar, thermal, and mechanical). We highlight wireless power transfer (WPT) as one of the most applicable technologies for WRSNs, covering both radiative and non-radiative WPT. Additionally, we present radio frequency (RF) energy harvesting, including simultaneous wireless information and power transfer (SWIPT) and wireless powered communication networks (WPCNs), as well as backscatter communications. Furthermore, we compare hybrid energy harvesting techniques (e.g., solar-RF, vibro-acoustic, solar-thermal, etc.). Second, we introduce the fundamentals of wireless charging, reviewing various charger types (static and mobile), charging policies (including full and partial charging), charging modes (offline and online), and charging schemes (periodic and on-demand). We also present the collaborative charging mechanisms. Additionally, we address several key challenges facing WRSNs, such as energy consumption, multi-charger coordination, dynamic network recharging, monitoring & security threats, vehicle-to-vehicle (V2V) charging, and hybrid WRSNs Finally, we highlight trends and future directions for integrating advanced artificial intelligence (AI) technologies into WRSNs.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"10 5","pages":"873-890"},"PeriodicalIF":3.9,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145248058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-10DOI: 10.1109/TSUSC.2025.3549687
Guillaume Fieni;Romain Rouvoy;Lionel Seinturier
The energy consumption analysis and optimization of data centers have been an increasingly popular topic over the past few years. It is widely recognized that several effective metrics exist to capture the efficiency of hardware and/or software hosted in these infrastructures. Unfortunately, choosing the corresponding metrics for specific infrastructure and assessing its efficiency over time is still considered an open problem. For this purpose, energy efficiency metrics, such as the Power Usage Effectiveness (PUE), assess the efficiency of the computing equipment of the infrastructure. However, this metric stops at the power supply of hosted servers and fails to offer a finer granularity to bring a deeper insight into the Power Usage Effectiveness of hardware and software running in cloud infrastructure. Therefore, we propose to leverage complementary PUE metrics, coined $x$PUE, to compute the energy efficiency of the computing continuum from hardware components, up to the running software layers. Our contribution aims to deliver real-time energy efficiency metrics from different perspectives for cloud infrastructure, hence helping cloud ecosystems—from cloud providers to their customers—to experiment and optimize the energy usage of cloud infrastructures at large.
{"title":"$x$xPUE: Extending Power Usage Effectiveness Metrics For Cloud Infrastructures","authors":"Guillaume Fieni;Romain Rouvoy;Lionel Seinturier","doi":"10.1109/TSUSC.2025.3549687","DOIUrl":"https://doi.org/10.1109/TSUSC.2025.3549687","url":null,"abstract":"The energy consumption analysis and optimization of data centers have been an increasingly popular topic over the past few years. It is widely recognized that several effective metrics exist to capture the efficiency of hardware and/or software hosted in these infrastructures. Unfortunately, choosing the corresponding metrics for specific infrastructure and assessing its efficiency over time is still considered an open problem. For this purpose, energy efficiency metrics, such as the <i>Power Usage Effectiveness</i> (PUE), assess the efficiency of the computing equipment of the infrastructure. However, this metric stops at the power supply of hosted servers and fails to offer a finer granularity to bring a deeper insight into the <i>Power Usage Effectiveness</i> of hardware and software running in cloud infrastructure. Therefore, we propose to leverage complementary PUE metrics, coined <inline-formula><tex-math>$x$</tex-math></inline-formula>PUE, to compute the energy efficiency of the computing continuum from hardware components, up to the running software layers. Our contribution aims to deliver real-time energy efficiency metrics from different perspectives for cloud infrastructure, hence helping cloud ecosystems—from cloud providers to their customers—to experiment and optimize the energy usage of cloud infrastructures at large.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"10 5","pages":"908-920"},"PeriodicalIF":3.9,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145248043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-08DOI: 10.1109/TSUSC.2025.3567856
Haoyu Wang;Xinyi Li;Ti Zhou;Man Lin
Energy measurement of computer devices, which are widely used in the Internet of Things (IoT), is an important yet challenging task. Most of these IoT devices lack ready-to-use hardware or software for power measurement. In this paper, we propose an easy-to-use approach to derive a software-based energy estimation model with external low-end power meters based on data-driven analysis. Our solution is demonstrated with a Jetson Nano board and Ruideng UM25C USB power meter. Various machine learning methods combined with our smart data collection & profiling method and physical measurement are explored. Periodic Long-duration measurements are utilized in the experiments to derive and validate power models, allowing more accurate power readings from the low-end power meter. Benchmarks were used to evaluate the derived software-power model for the Jetson Nano board and Raspberry Pi. The results show that 92% accuracy can be achieved by the software-based power estimation compared to measurement. A kernel module that can collect running traces of utilization and frequencies needed is developed, together with the power model derived, for power prediction for programs running in a real environment. Our cost-effective method facilitates accurate instantaneous power estimation, which low-end power meters cannot directly provide.
{"title":"Data-Driven Software-Based Power Estimation for Embedded Devices","authors":"Haoyu Wang;Xinyi Li;Ti Zhou;Man Lin","doi":"10.1109/TSUSC.2025.3567856","DOIUrl":"https://doi.org/10.1109/TSUSC.2025.3567856","url":null,"abstract":"Energy measurement of computer devices, which are widely used in the Internet of Things (IoT), is an important yet challenging task. Most of these IoT devices lack ready-to-use hardware or software for power measurement. In this paper, we propose an easy-to-use approach to derive a software-based energy estimation model with external low-end power meters based on data-driven analysis. Our solution is demonstrated with a Jetson Nano board and Ruideng UM25C USB power meter. Various machine learning methods combined with our smart data collection & profiling method and physical measurement are explored. Periodic Long-duration measurements are utilized in the experiments to derive and validate power models, allowing more accurate power readings from the low-end power meter. Benchmarks were used to evaluate the derived software-power model for the Jetson Nano board and Raspberry Pi. The results show that 92% accuracy can be achieved by the software-based power estimation compared to measurement. A kernel module that can collect running traces of utilization and frequencies needed is developed, together with the power model derived, for power prediction for programs running in a real environment. Our cost-effective method facilitates accurate instantaneous power estimation, which low-end power meters cannot directly provide.","PeriodicalId":13268,"journal":{"name":"IEEE Transactions on Sustainable Computing","volume":"10 5","pages":"937-948"},"PeriodicalIF":3.9,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145248099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：