IEEE Transactions on Computers最新文献

{"title":"HeShare: Energy-Aware and Efficient Multi-Task GPU Sharing in Heterogeneous GPU-Based Computing Systems","authors":"Zhuolong Jiang;Zinuo Cai;Hongyu Zhao;Baoheng Zhang;Tianqi Wu;Yiming Qiang;Ruhui Ma;Haibing Guan;Rajkumar Buyya","doi":"10.1109/TC.2025.3628924","DOIUrl":"https://doi.org/10.1109/TC.2025.3628924","url":null,"abstract":"With the rapid growth of artificial intelligence and large-scale model computing, the demand for GPUs in datacenters continues to increase, especially for large-scale training and inference tasks. Heterogeneous multi-GPU systems, which integrate GPUs with varying types and computational capabilities, have become critical computing resources. This leads to two main challenges. First, due to the differences in GPU performance and power consumption, task scheduling involves a complex multi-objective optimization to balance energy efficiency and performance. More importantly, the lack of coordinated mechanisms for multi-task sharing and energy-efficient resource management across heterogeneous GPUs can result in GPU overload or underutilization, leading to wasted resources and potential system risks. To address these challenges, we propose <sc>HeShare</small>, an energy-aware and efficient heterogeneous GPU framework for datacenters. First, we design an energy-aware task scheduling strategy that optimizes task allocation across different GPUs to achieve a balance between energy consumption and performance. Second, we introduce a GPU sharing optimization mechanism that adaptively configures MPS and DVFS settings for each GPU, enhancing resource utilization, reducing overall energy consumption, and ensuring task performance. Compared to the state-of-the-art framework, we reduce average energy costs by 26% and improve job completion time by 31%, achieving a balance between energy efficiency and performance.","PeriodicalId":13087,"journal":{"name":"IEEE Transactions on Computers","volume":"75 3","pages":"776-787"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148480246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SuperEncoder: Towards Efficient Neural Approximate Quantum State Preparation","authors":"Yilun Zhao;Bingmeng Wang;Wenle Jiang;Xiwei Pan;Bing Li;Yinhe Han;Ying Wang","doi":"10.1109/TC.2025.3644034","DOIUrl":"https://doi.org/10.1109/TC.2025.3644034","url":null,"abstract":"Numerous quantum algorithms assume that classical data has already been converted into quantum states, a process known as Quantum State Preparation (QSP). However, achieving precise QSP requires a circuit depth that scales exponentially with the number of qubits, posing a significant challenge to realizing quantum advantage. Recent research explores Parameterized Quantum Circuits (PQCs) as an approximate alternative, offering improved scalability with reduced circuit depth. However, the iterative, state-by-state optimization required by this approach creates substantial runtime overhead, which severely limits its practicality. To improve the efficiency of approximate QSP, we introduce a novel two-stage framework that can potentially generate QSP circuits for arbitrary quantum states. In the <i>offline training stage</i>, our model learns a direct mapping from target states to circuit parameters, thereby bypassing the need for <i>online, state-by-state optimization</i> during the <i>inference stage</i>. Extensive evaluations show that our approach significantly reduces runtime overhead by up to 132<inline-formula><tex-math>$times$</tex-math></inline-formula>, making a steady step towards efficient neural approximate QSP.","PeriodicalId":13087,"journal":{"name":"IEEE Transactions on Computers","volume":"75 3","pages":"916-927"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148480739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-Component Fault Tolerance and Path Construction in Interconnection Networks","authors":"Xueli Sun;Shuangxiang Kan;Jianxi Fan;Weibei Fan;Jin Qi;Zhenjiang Dong","doi":"10.1109/TC.2025.3645082","DOIUrl":"https://doi.org/10.1109/TC.2025.3645082","url":null,"abstract":"In the realm of interconnection networks, reliability analysis is of utmost importance, especially considering the increasing vulnerability of components as the network scales. Fault tolerance is a key aspect in this regard, and extra connectivity and component connectivity are two crucial metrics for its assessment. In this paper, we establish a theoretical framework for multi-component fault tolerance in the augmented &lt;inline-formula&gt;&lt;tex-math&gt;$k$&lt;/tex-math&gt;&lt;/inline-formula&gt;-ary &lt;inline-formula&gt;&lt;tex-math&gt;$n$&lt;/tex-math&gt;&lt;/inline-formula&gt;-cube &lt;inline-formula&gt;&lt;tex-math&gt;$AQ_{n,k}$&lt;/tex-math&gt;&lt;/inline-formula&gt;, a hypercube-derived interconnection network commonly used in distributed-memory architectures. We derive a general result for the &lt;inline-formula&gt;&lt;tex-math&gt;$r$&lt;/tex-math&gt;&lt;/inline-formula&gt;-component connectivity of &lt;inline-formula&gt;&lt;tex-math&gt;$AQ_{n,k}$&lt;/tex-math&gt;&lt;/inline-formula&gt; as &lt;inline-formula&gt;&lt;tex-math&gt;$4n(r-1)-leftlfloorfrac{5(r-1)^{2}}{2}rightrfloor$&lt;/tex-math&gt;&lt;/inline-formula&gt; (&lt;inline-formula&gt;&lt;tex-math&gt;$ngeq 4$&lt;/tex-math&gt;&lt;/inline-formula&gt;, &lt;inline-formula&gt;&lt;tex-math&gt;$kgeq 4$&lt;/tex-math&gt;&lt;/inline-formula&gt;, and &lt;inline-formula&gt;&lt;tex-math&gt;$2leq rleq n$&lt;/tex-math&gt;&lt;/inline-formula&gt;). Furthermore, we extend the result to explore the &lt;inline-formula&gt;&lt;tex-math&gt;$h$&lt;/tex-math&gt;&lt;/inline-formula&gt;-extra &lt;inline-formula&gt;&lt;tex-math&gt;$r$&lt;/tex-math&gt;&lt;/inline-formula&gt;-component connectivity of &lt;inline-formula&gt;&lt;tex-math&gt;$AQ_{n,k}$&lt;/tex-math&gt;&lt;/inline-formula&gt; as &lt;inline-formula&gt;&lt;tex-math&gt;$(8n-10)(r-1)-2(r-2)$&lt;/tex-math&gt;&lt;/inline-formula&gt; (&lt;inline-formula&gt;&lt;tex-math&gt;$ngeq 4$&lt;/tex-math&gt;&lt;/inline-formula&gt;, &lt;inline-formula&gt;&lt;tex-math&gt;$kgeq 4$&lt;/tex-math&gt;&lt;/inline-formula&gt;, &lt;inline-formula&gt;&lt;tex-math&gt;$h = 1$&lt;/tex-math&gt;&lt;/inline-formula&gt; and &lt;inline-formula&gt;&lt;tex-math&gt;$2leq rleq n$&lt;/tex-math&gt;&lt;/inline-formula&gt;). Based on these theoretical results, we propose a novel fault-tolerant path algorithm for &lt;inline-formula&gt;&lt;tex-math&gt;$AQ_{n,k}$&lt;/tex-math&gt;&lt;/inline-formula&gt; that handles &lt;inline-formula&gt;&lt;tex-math&gt;$h$&lt;/tex-math&gt;&lt;/inline-formula&gt;-extra &lt;inline-formula&gt;&lt;tex-math&gt;$r$&lt;/tex-math&gt;&lt;/inline-formula&gt;-component faults. The algorithm first preprocesses and classifies fault-free components, which efficiently determines whether two fault-free nodes belong to the same component, thereby avoiding ineffective path searches. When two fault-free nodes are in the same component, we employ a hybrid greedy-BFS algorithm to construct fault-free paths between them. To validate the algorithm, we conduct comprehensive simulations on &lt;inline-formula&gt;&lt;tex-math&gt;$AQ_{n,k}$&lt;/tex-math&gt;&lt;/inline-formula&gt; with varying parameters. The experimental results demonstrate that the proposed algorithm achieves constant-time path existence queries after preprocessing, significantly reduces path discovery time in multi-query scenarios compared to conventional methods, and maintains near-optimal path lengths while exhibiting superior scalability as network dimensions increase. Furthermore, the algorithm demonstrates ro","PeriodicalId":13087,"journal":{"name":"IEEE Transactions on Computers","volume":"75 3","pages":"1043-1057"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148479462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Viper: Priority-Based High-Visibility Per-Flow Packet Sampling for SDNs","authors":"Xiaodong Dong;Xiulong Liu;Lihai Nie;Jiuwu Zhang;Yinglong Wang","doi":"10.1109/TC.2025.3642321","DOIUrl":"https://doi.org/10.1109/TC.2025.3642321","url":null,"abstract":"Packet sampling is crucial for managing datacenter networks, serving fault diagnosis, traffic measurement, and intrusion detection functions. However, traditional sampling techniques, such as those based on sketches or ports, either lack packet-level granularity or provide insufficient visibility, leading to functional performance degradation. Recent research has employed the software-defined networking (SDN) model to enable flow-based packet sampling. However, these approaches often introduce substantial control and computation overhead, limiting their scalability. This paper presents Viper, a novel priority-based, high-visibility per-flow packet sampling mechanism tailored to address these challenges. Specifically, Viper leverages existing priority-based traffic scheduling mechanisms to prioritize shorter flows over longer ones. Then, a logical centralized controller orchestrates sampling policies for packets of different priorities. In-depth analysis indicates that the orchestration performed by the controller significantly impacts Viper’s performance. Consequently, we model this process as a nonlinear optimization problem, seeking to maximize the utility of sampling. Then, we propose an online primal-dual interior-point algorithm to address this optimization problem and prove the algorithm’s convergence, optimality, and efficiency. Experimental results show that Viper increases visibility by 3.83% to 8.3%, with negligible control overhead and a substantial reduction in sampling load by at least 20.51%.","PeriodicalId":13087,"journal":{"name":"IEEE Transactions on Computers","volume":"75 3","pages":"802-816"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148480248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficient Memristor Neural Networks for Edge AI: On-Chip Learning, Noise Robustness, Device-Variation Tolerance, and Sublinear Energy and Time Scaling","authors":"Mohammad Reza Eslami;Dhiman Biswas;Soheib Takhtardeshir;Sarah S. Sharif;Yaser M. Banad","doi":"10.1109/TC.2026.3661114","DOIUrl":"https://doi.org/10.1109/TC.2026.3661114","url":null,"abstract":"Memristor-based neural networks promise low-power, high-density neuromorphic hardware, yet most studies remain proof-of-concept with small inputs and qualitative reporting. We present a comprehensive investigation of on-chip learning in a scalable memristor network, modeling realistic non-idealities including device-to-device and cycle-to-cycle variability, conductance programming errors, and input noise. Using a 30-memristor architecture, we systematically scale inputs from 3x3 to 11x11 and evaluate classification robustness under noisy conditions. Results show that moderate training noise improves tolerance, enabling up to 99% accuracy with 20% noisy tests, whereas aggressive weight quantization at higher resolutions can degrade accuracy. We quantify average training time and energy across device types; chromium devices are most efficient, achieving 2.4 s average training time and 18.9mJ training energy for 3x3 tasks. We also report energy per classification versus input size, establishing concrete benchmarks often absent from prior work. A Big-O analysis indicates sub-linear growth of training time (n0^.26), training energy (n^0.28), and inference cost with input dimension, supporting suitability for edge deployment. Unlike earlier demonstrations that emphasized qualitative recognition, this study provides quantitative trade-offs among accuracy, noise robustness, energy, and training time, bridging device-level feasibility and practical memristor neural network accelerators. These results guide design choices for deployable edge systems.","PeriodicalId":13087,"journal":{"name":"IEEE Transactions on Computers","volume":"75 5","pages":"1723-1736"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reducing Write Amplification in LSM-Trees Through Orchestrated Fine-Grained Compaction and Persistent Memory","authors":"Licheng Shan;Jiang Zhou;Jinchao Zhang;Youyou Lu;Bo Li;Xiaoyan Gu;Weiping Wang","doi":"10.1109/TC.2026.3662419","DOIUrl":"https://doi.org/10.1109/TC.2026.3662419","url":null,"abstract":"This paper investigates how to leverage emerging non-volatile memory (NVM) to enhance the performance of Log-Structure Merge (LSM) tree based key-value (KV) stores. We propose KVFG-DB, which efficiently integrates fine-block granularity and single-NVM-level compaction, to deliver high write and read performance with minimal write amplification and reduced write stalls. KVFG-DB leverages a streamlined SSTable layout called CSSTable to manage data blocks (each containing ordered KV pairs) and their indexes (i.e., the minimal and maximal keys of every block), optimizing both storage costs and compaction performance. It organizes the LSM-tree data as CSSTables into a single level on NVM, with the left area serving as a buffer to receive flushed data with substantially greater capacity, and the right area storing compacted data in a global order among CSSTables. A fine-grained compaction is then performed under various conditions to select the most relevant data blocks with intersecting keys from CSSTables in both areas, facilitating byte-addressable, fast parallel execution across multiple threads. As a result, KVFG-DB adaptively compacts data and quickly moves them from the left area to the right area to enhance performance efficiency, significantly reducing write amplification and further mitigating write stalls. Our extensive experimental studies demonstrate that KVFG-DB achieves <inline-formula><tex-math>$1.2{boldsymbol{times}}$</tex-math></inline-formula> and <inline-formula><tex-math>$2{boldsymbol{times}}$</tex-math></inline-formula> lower write amplification, compared with state-of-the-art KV stores MioDB and SLM-DB. Accordingly, KVFG-DB shows a <inline-formula><tex-math>$1.1{boldsymbol{times}}$</tex-math></inline-formula> and <inline-formula><tex-math>$7.1{boldsymbol{times}}$</tex-math></inline-formula> improvement in random write performance compared to them, with tail latency reduced by <inline-formula><tex-math>$1.1{boldsymbol{times}}$</tex-math></inline-formula> and <inline-formula><tex-math>$7{boldsymbol{times}}$</tex-math></inline-formula>, respectively.","PeriodicalId":13087,"journal":{"name":"IEEE Transactions on Computers","volume":"75 5","pages":"1922-1936"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148511857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ByzTopia: Towards Practical Asynchronous BFT via Decoupling","authors":"Guoyu Yang;Chang Chen;Qi Chen;Ganqing Li;Jin Li;Debiao He","doi":"10.1109/TC.2026.3666176","DOIUrl":"https://doi.org/10.1109/TC.2026.3666176","url":null,"abstract":"The most efficient asynchronous Byzantine fault tolerant (BFT) framework in <i>n</i> agreement settings is due to Ben-Or, Kemler, and Rabin (BKR), where <i>n</i> is the total number of replicas. Despite recent efforts to bring BKR closer to practical deployment, state-of-the-art designs are still hampered by the inherent mutual waiting between the broadcast and agreement phases. In response, we propose ByzTopia, a new asynchronous BFT protocol that removes this performance bottleneck. Its technical core is to decouple these two phases without introducing additional cryptographic primitives. To enable a more efficient decoupling of the broadcast and agreement phases, we introduce multi-shot reliable broadcast (MRBC), which ensures that replicas deliver messages in a well-ordered sequence across consecutive slots. We implement ByzTopia and evaluate it in various settings. Experimental results show that ByzTopia achieves up to 6.54<inline-formula><tex-math>$times$</tex-math></inline-formula> the throughput of PACE (for <i>n</i> <inline-formula><tex-math>$=$</tex-math></inline-formula> 31), the state-of-the-art asynchronous BFT of the same type, and 2.65<inline-formula><tex-math>$times$</tex-math></inline-formula> that of FIN (for <i>n</i> <inline-formula><tex-math>$=$</tex-math></inline-formula> 16), the state-of-the-art signature-free asynchronous BFT.","PeriodicalId":13087,"journal":{"name":"IEEE Transactions on Computers","volume":"75 5","pages":"1878-1891"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148511809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Efficient and Fault-Tolerant Data Transmission Scheme in Data Center Networks","authors":"Mengjie Lv;Fu Xiao;Weibei Fan;Lei Han;Jian Qiao;Sun-Yuan Hsieh","doi":"10.1109/TC.2025.3644354","DOIUrl":"https://doi.org/10.1109/TC.2025.3644354","url":null,"abstract":"The rapid growth of cloud computing, large-scale distributed systems, and AI-driven applications has placed stringent demands on the performance and reliability of data center networks (DCNs). As DCNs scale in size and structural complexity, they become increasingly vulnerable to multiple concurrent node and/or link failures, which can lead to severe service disruptions and significant performance degradation. Existing data transmission approaches typically address node and link failures in isolation, frequently mitigating one type while overlooking the other, and thus fall short in effectively handling complex multi-failure scenarios. This paper presents a novel and efficient data transmission scheme designed to ensure robust communication under multiple node and/or link failures in DCNs. The proposed solution integrates a proactive path redundancy mechanism with a failure-aware routing strategy to enable rapid identification and avoidance of faulty components. We adopt the generalized hypercube network (GHN), a regular and scalable topology, as the underlying network model. Firstly, leveraging the method of Yang and Chang <xref>[44]</xref>, we construct multiple independent spanning trees (ISTs) in GHNs, which provide structural path diversity and fault isolation. Building upon these ISTs, we propose GFP-IST, an optimized routing algorithm with a time complexity of <inline-formula><tex-math>$O(Nlog N)$</tex-math></inline-formula>, where <inline-formula><tex-math>$N$</tex-math></inline-formula> denotes the number of nodes. GFP-IST enables efficient route computation and resilient packet forwarding in the presence of multiple simultaneous failures. Extensive simulation results demonstrate that our approach outperforms several fault-tolerant routing schemes in terms of average path length, path construction time, and fault recovery success rate, especially in large-scale and high-failure-rate network environments.","PeriodicalId":13087,"journal":{"name":"IEEE Transactions on Computers","volume":"75 3","pages":"987-999"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148480596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LoAPE: A Load-Aware and Power-Elastic Platform for Green Serverless Computing","authors":"Hanfei Geng;Yuanzhe Li;Jichao Leng;Feng Zhao;Yunxin Liu","doi":"10.1109/TC.2026.3663410","DOIUrl":"https://doi.org/10.1109/TC.2026.3663410","url":null,"abstract":"Energy efficiency in serverless computing has remained under-explored despite its growing adoption. To fill this gap, we propose LoAPE, a load-aware and power-elastic serverless platform. Unlike existing methods limited to CPU core frequency scaling or density-based consolidation, LoAPE leverages c-states and uncore frequency scaling, which offer greater energy benefits but pose deployment challenges. Uncore changes affect the performance of all co-located functions, and c-states require sustained idle periods for effective energy savings. LoAPE’s insight is to strategically exploit function elasticity. By creating idle intervals across cores and servers, it enables aggressive c-state activation and uncore frequency reduction. To achieve this goal, LoAPE adopts topology-aware instance scheduling and eviction, which scale the number of active servers along with serverless functions. Within servers, LoAPE proactively manages active cores based on incoming loads. Our evaluations demonstrate that LoAPE delivers a <inline-formula><tex-math>$3.02times$</tex-math></inline-formula> improvement in cluster energy reduction compared to frequency-scaling frameworks and extends savings by <inline-formula><tex-math>$1.17times$</tex-math></inline-formula> over state-of-the-art density-aware schedulers, while meeting performance requirements.","PeriodicalId":13087,"journal":{"name":"IEEE Transactions on Computers","volume":"75 5","pages":"2020-2033"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148511017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HRADP: A Heat-Recirculation-Aware Data Placement Approach for Energy-Efficient Cloud Data Centers","authors":"Jie Li;Yuhui Deng;Zijie Zhong;Biqing Zeng;Yi Zhong;Geyong Min","doi":"10.1109/TC.2026.3666368","DOIUrl":"https://doi.org/10.1109/TC.2026.3666368","url":null,"abstract":"With the proliferation of cloud computing, the exponential growth of data amount requires continuous expansion of storage capacity to meet the storage demand, consequently resulting in higher energy consumption in data centers. However, many of the conventional data placement strategies strive to save energy by optimizing the distribution of data requests, while overlooking the impact of heat recirculation among data nodes. To bridge this gap, we propose a heat-recirculation-aware data placement approach, termed HRADP, designed to optimize data placement in data centers while reducing energy consumption. First, based on the extent of heat recirculation, HRADP places data to the upper limit of the disk allowance for each data node. Second, during energy allocation, HRADP further eliminates disks with high current workloads to prevent localized hotspots. Finally, during request scheduling, HRADP selects dormant data nodes according to the request size, minimizing the startup energy consumption caused by data nodes waking up with small requests. We implement the HRADP approach on a data center simulation platform, CloudSim, and its performance with state-of-the-art, including the Energy-efficient and Thermal-aware Data Placement (ETDP) algorithm, Thermal-aware file assignment technique (TIGER), Storage and rack-sensitive replica placement algorithm (SRS), and Hadoop Distributed File System (HDFS). The experimental results reveal that HRADP revamps the cooling supply temperature, total energy, and data throughput by averages of 0.08<inline-formula><tex-math>$%$</tex-math></inline-formula>-0.6<inline-formula><tex-math>$%$</tex-math></inline-formula>, 8.22<inline-formula><tex-math>$%$</tex-math></inline-formula>-53.03<inline-formula><tex-math>$%$</tex-math></inline-formula>, and 9.58<inline-formula><tex-math>$%$</tex-math></inline-formula>-64.59<inline-formula><tex-math>$%$</tex-math></inline-formula>, respectively.","PeriodicalId":13087,"journal":{"name":"IEEE Transactions on Computers","volume":"75 5","pages":"1849-1862"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}