智算中心论文观察｜2026-07-15

Current Issue

Volume 2026 · Issue 07-15

按期刊卷期页方式整理本期论文。每条仅使用日报已列出的可追溯公开来源，不新增未经核验事实。

Research Article算电协同

Why Computing–Electricity Coordination Has Not Scaled in Practice

Aijia Luo, Nianfeng Tian, Qinglai Guo

Published 2026-07-07 · Semantic Scholar · Credibility S

Abstract, interpretation and reference

Abstract

The rapid growth of LLM‐driven artificial intelligence (AI) and data center deployment is imposing a new paradigm of massive and highly dynamic power demand on the grid. Volatility in both computing and renewable energy resources introduces severe challenges to power system operation. Although typical computing workloads are technically flexible, their responsive capacity remains largely untapped in real‐world scenarios. This paper argues that the main barriers to scalable computing–electricity coordination are not solely technical, but arise from weak electricity cost pass‐through, limited cost visibility, and misaligned compute‐side incentives. In leasing and cloud‐service modes, electricity costs of data centres are often bundled into broader service charges, reducing their influence on workload scheduling. Meanwhile, compute‐side actors prioritise GPU utilisation, return on investment, latency, throughput, and service quality over flexible load profiles supporting power‐system operation. Therefore, green operational constraints and new pricing mechanisms that expose carbon or electricity signals to compute‐side decision‐makers are critical to making computing–electricity coordination scalable in practice. Flexible computing loads can support power systems only when technical flexibility is matched with actionable economic, contractual, and operational incentives.

Full text 中文海报

Research Article芯片与算力

Piezo-Actuated Enhanced Nucleate Boiling: from Saturated to Controlled Flash Regimes In Two-Phase Direct-To-Chip Cooling for AI Superchips and Data Centers

A. Narain, Hardik Bhutka, Ranjeeth R. Naik, Nirgun Mohite, Yagel Belikoff

Published 2026-07-01 · Semantic Scholar · Credibility S

Abstract, interpretation and reference

Abstract

Two-phase direct-to-chip cooling is emerging as an important thermal management pathway for the rapidly increasing thermal design powers of modern AI superchips while maintaining data center energy efficiency. This paper presents a combined passive-active approach that transitions high-performance saturated nucleate boiling to a stabilized controlled flash-nucleate boiling regime using low-power piezoelectric actuation. Experiments on microstructured copper cold plates with dielectric fluids establish baseline nucleate boiling performance in partial flow-boiling configurations typical of direct-to-chip flow loops. These results quantify cold-plate behavior and indicate that physics-guided modifications to both microstructures and flow-loop design can substantially increase heat-transfer coefficients and critical heat flux. Activation of megahertz piezo actuators with low-frequency modulation near anti-resonance generates small micro-vibrations that modify nucleating bubble dynamics and trigger a rapid transition to controlled flash boiling. The transition alters boiling through microlayer heating, acoustic streaming, and a short-duration increase in interfacial mass transfer, producing transient heat extraction of 200-400 joules from the heated surface. Three-dimensional transient conduction simulations predict chip-level temperature reductions of about 15-20 degrees Celsius for low-thermal-inertia test vehicles and future chip implementations. Baseline experiments show nucleate boiling heat transfer with critical heat flux near 50-60 watts per square centimeter. The proposed architecture integrates optimized microstructures, refined flow control, and piezo actuation to stabilize flash boiling, enabling lower junction temperatures, improved chip reliability, and more energy-efficient next-generation AI data centers.

Full text 中文海报

Research Article算电协同

Capacity optimization of data center microgrid coupling computing-power and electricity consumption

Haichao Yang, Yang Si, Youping Liu, Shuyu Mu, JianQiang Huang, Yong Luo

Published 2026-07-01 · Semantic Scholar · Credibility S

暂无可展示摘要。

Abstract, interpretation and reference

Abstract

暂无可展示摘要。

Full text 中文海报

Research Article算电协同

Vehicle-to-Grid Systems for Renewable Energy Integration: Scheduling, Economics, and User Engagement

Peiying Zhang, Xiangguo Zheng, Yujie Yuan, Xi Chen, Chun Sing Lai

Published 2026-07-06 · Semantic Scholar · Credibility S

Abstract, interpretation and reference

Abstract

With the rapid growth of electric vehicles (EVs) and renewable energy generation, Vehicle-to-Grid (V2G) technology has emerged as a promising approach for transforming EVs from passive charging loads into flexible distributed energy storage resources. By enabling bidirectional power exchange between EV batteries and the power grid, V2G can support renewable energy accommodation, peak shaving, demand response, ancillary services, and local grid balancing. This review provides a systematic synthesis of recent advances in V2G systems for renewable energy integration, with particular emphasis on coordinated scheduling, economic mechanisms, battery degradation, and user engagement. First, the technical foundations of V2G are introduced, including Vehicle-to-Everything operating modes, bidirectional charging architecture, aggregation mechanisms, grid-support services, and renewable accommodation pathways. Second, major scheduling strategies are reviewed, including price-based, load-based, renewable-forecast-driven, centralized, distributed, and hybrid approaches. Third, the economic feasibility of V2G is examined from the perspectives of revenue streams, pricing mechanisms, business models, battery aging costs, and compensation schemes. In addition, user participation barriers, such as range anxiety, battery lifetime concerns, loss of control, uncertain financial returns, and data privacy, are discussed. Key challenges related to communication standards, interoperability, cybersecurity, market access, policy design, and pilot-scale validation are also summarized. Finally, future development directions are identified, including AI-based scheduling, aggregator platforms, fleet-scale V2G, degradation-aware optimization, carbon-aware electricity markets, and user-centered participation mechanisms. This review highlights that large-scale V2G deployment requires the integrated coordination of technical scheduling, economic incentives, battery health protection, and user acceptance in renewable-rich power systems.

Full text 中文海报

Research Article芯片与算力

Server-Level Demonstration of Package-Integrated, Two-Phase Jet Impingement Cooling on AI Chipsets

Sidharth Rajeev, Ketan Yogi, Venkata Achyuth Kunchapu, Yunchun Yang, Harish Kumar Lattupalli, Scott N. Schiffres, Tiwei Wei, S. Rangarajan, B. Sammakia

Published 2026-06-26 · Semantic Scholar · Credibility S

Abstract, interpretation and reference

Abstract

The rapid growth of digitalization and data-driven technologies is driving large-scale deployment of data centers worldwide. As societies become increasingly data-hungry, the energy consumption of data centers continues to rise at an unprecedented rate, with a significant fraction of this energy being expended on thermal management and cooling infrastructure. Improving cooling efficiency has therefore become a critical challenge for the thermal management community, directly impacting both the sustainability and scala-bility of future computing systems. In this manuscript, we demonstrate an energy-efficient cooling solution based on chip-integrated two-phase cooling, which leverages liquid to vapor phase-change heat transfer to achieve high heat-flux dissipation at reduced pumping power and thermal resistance. This paper investigates an aggressive cooling architecture utilizing direct-on-die two-phase jet impingement on an NVIDIA Tesla V100 GPU. By eliminating the TIM and impinging the working fluid?R1233zd(E), a low-GWP (< 1) refrigerant?directly onto the silicon backside, the primary thermal bottleneck is removed. Experimental results demonstrate a remarkably low thermal resistance of 0.056 °C/W and a theoretical pumping power of only 0.172 W. The system exhibits superior ther- mal stability and rapid transient response compared to conventional air-cooled solutions. Furthermore, the reliability of the direct-exposure manifold was validated through 200 hours of continuous, stable operation. This study positions direct jet impingement as a highly efficient, compact, and sustainable solution for next-generation high-performance computing (HPC) environments.

Full text 中文海报

Research Article算电协同

Large-Load Demand Flexibility as Virtual Storage

Chandan Chaudhary, Mohammed Ben-Idris, Joydeep Mitra

Published 2026-07-06 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

Water electrolysis plants, hyperscale data centers, and aluminum potlines represent gigawatts of demand-side flexibility for bulk power system balancing, operational planning, and procurement services. Such loads are scheduled through per-interval power bounds and horizon energy windows, whereas co-located battery energy storage systems (BESS) operate under state-of-charge dynamics. The two formulations share no common mathematical structure, and the joint procurement value of co-located loads and storage goes unrealized as a result. This paper establishes the connection between the two formulations through a virtual storage (VS) equivalence. Every feasible large-load trajectory under power-bound and energy-window constraints is a valid charge trajectory of a VS device that operates at unity accounting efficiency in the grid power balance. Production and service-level costs lie outside this abstraction and enter the dispatch through curtailment opportunity costs. For a portfolio co-located with a BESS, aggregation reduces the constraint count from O(NT) to O(T) and yields a co-dispatch price for both resources. Validation on the IEEE RTS-GMLC with three representative load classes shows that virtual storage delivers the dominant share of joint procurement savings. In the tested case, savings are additive because the two resources dispatch to non-overlapping intervals, and the curtailment shadow price tracks the peak-price band onset rather than the daily peak price.

Full text 中文海报

Research Article算电协同

How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization

Xinyi Wu, Siyuan Liu, Ali Jadbabaie

Published 2026-07-08 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

Rotary Position Embeddings (RoPE) provide transformers with a fixed grid of positional frequencies, yet trained models use these frequencies highly non-uniformly. We study what determines this frequency usage and propose a data-centered explanation: RoPE frequencies are selected to match the relative-distance structure of the training data. Viewing each frequency as a positional lens, we formalize a field-resolution tradeoff and show that, for a data-induced dependency profile of width $W$, the optimal frequency scales as $1/W$. This frequency-matching principle explains controlled observations on synthetic and text-based data, and suggests that the mid-low frequency bands observed in language models arise from the multi-scale dependency structure of natural language. We further connect frequency selection to position-interpolation-based length generalization: scaling frequencies down expands the effective field while reducing resolution. This helps when longer-context dependencies are approximate dilations of those seen during training, but can fail when relevant dependencies do not scale with context length. Empirically, we show that natural language exhibits approximate self-similarity across positional scales, explaining why test-time frequency scaling can support long-context generalization. Overall, our results identify a data-driven mechanism behind emergent RoPE frequency usage and show that long-context generalization depends on two forms of scale matching: between learned frequencies and training-time dependencies, and between frequency scaling and how those dependencies extend to longer contexts.

Full text 中文海报

Research Article芯片与算力

AI-on-Chip Systems: A Cross-Layer Review of Architectures, Interconnects, Design Automation, and Embedded Intelligence

Mohamed M. Morsy

Published 2026-06-15 · Semantic Scholar · Credibility S

Abstract, interpretation and reference

Abstract

The rapid growth of artificial intelligence (AI) workloads is reshaping semiconductor design across architecture, interconnect, memory hierarchy, packaging, timing, and design automation. Rather than converging on a single hardware solution, the field is expanding into a heterogeneous ecosystem that includes data-center graphics processing units (GPUs), edge neural processing units (NPUs), and application-specific integrated circuits (ASICs), field-programmable gate array (FPGA)-based and hybrid AI system-on-chip (SoC) platforms, chiplet-enabled systems, and emerging beyond-conventional-silicon approaches such as photonic, neuromorphic, and analog in-memory processors. This paper presents a comprehensive review of AI-on-chip systems from a cross-layer perspective. It examines AI chip architectures and hardware platforms, network-on-chip (NoC) designs for AI communication patterns, and algorithm–hardware co-design methods for model acceleration, including compression, quantization, and sparsity-aware optimization. It also reviews clocking, synchronization, and clock-domain-crossing (CDC) challenges in large heterogeneous systems and chiplets, as well as manufacturing, advanced packaging, and reliability issues, including two-and-a-half-dimensional (2.5D) and three-dimensional (3D) integration, thermal and mechanical constraints, assembly quality, and long-term yield considerations. In parallel, the paper surveys the growing role of AI in chip design itself, covering machine-learning-assisted analysis, Bayesian and reinforcement-learning-based optimization, and the emerging use of large language models (LLMs) and AI agents for register-transfer level (RTL) generation, design-space exploration, and autonomous electronic design automation (EDA) workflows. Finally, it discusses beyond-silicon AI chip directions and the broader economic and industry context shaping cloud, on-premises, and edge deployment. By integrating these topics into a unified framework, this review highlights the key technological drivers, system-level tradeoffs, and future research directions that will define next-generation scalable, reliable, and energy-efficient AI-on-chip systems.

Full text 中文海报

Research Article芯片与算力

Hierarchical Multi-Agent Reinforcement Learning for Carbon-Aware AI Data Centers in Power Distribution Systems

Hyunsoo Lee, Panggah Prabawa, Dae-Hyun Choi, Joongheon Kim

Published 2026-07-03 · Semantic Scholar · Credibility S

Abstract, interpretation and reference

Abstract

Eco-friendly energy management for artificial intelligence data centers (AIDCs) is crucial because of the significant increase in energy consumption-induced carbon emissions from AIDCs resulting from the rapid expansion of AI applications. This paper proposes a hierarchical carbon-aware multi-agent reinforcement learning (CA-MARL) framework for robust and efficient operations of AIDCs under uncertainties while ensuring low-carbon operation of power distribution systems. The framework comprises a workload manager (WM) agent and multiple local AIDC agents trained using a multi-agent transformer method, corresponding to a global AIDC aggregator and a local AIDC operator, respectively. Leveraging AIDC operation data along with nodal carbon intensity (NCI) calculated from the carbon emission flow-integrated distribution system operator problem, the WM agent spatially allocates AI training and inference jobs among all AIDCs. Based on the jobs allocated from the WM agent and NCI information, each AIDC agent schedules economical and eco-friendly operations of the AIDC by performing the following tasks: i) temporal shifting of training jobs, ii) spatial allocation of training graphics processing unit (GPU) blocks and inference GPUs within the AIDC, and iii) control of the supply air temperature of the cooling system. The effectiveness of the proposed framework was assessed using an IEEE 33-node power distribution system.

Full text 中文海报

Research ArticleAI 运维优化

Storage as a Transmission Asset (SATA) for Large-Load Congestion Relief

Abanish Tiwari, Chandan Chaudhary, Yansong Pei, Mohammed Ben-Idris, Joydeep Mitra

Published 2026-07-05 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

Hyperscale data centers and other large concentrated loads can impose substantial new demand on existing transmission networks. If import corridors lack sufficient transfer capability, operators may need to curtail load, delay interconnection, or reinforce the network to maintain reliable service. An energy storage system (ESS) deployed as a storage-as-transmission asset (SATA) offers a non-wires alternative by providing operator-directed support to constrained import corridors. However, the operating-level reliability value of SATA dispatch remains insufficiently quantified. This paper evaluates operator-directed SATA using a day-ahead DC optimal power flow that co-optimizes generation, ESS dispatch, and load curtailment across Monte Carlo scenarios of demand and generator availability. Operating reliability is assessed using expected energy not served (EENS), loss-of-load hours (LOLH), and the conditional value at risk (CVaR) of daily unserved energy. Congestion-price and flow-sensitivity metrics are used to identify the limiting corridor and storage location. The interconnection is then screened to determine whether SATA is suitable, reinforcement is required, or storage would provide little transmission value. Results show that operator-directed SATA reduces average unserved energy, loss-of-load exposure, and tail risk compared with deploying the same ESS for pure arbitrage. These results demonstrate that the operating designation of storage is a primary driver of its transmission value.

Full text 中文海报

Research Article热管理与液冷

AI-Driven Thermal Mapping and Management in 3D Integrated Photonic Circuits

Liton Kumar Biswas, Katayoon Yahyaei, Shajib Ghosh, M Shafkat M Khan, Himanandhan Reddy Kottur, Rayhane Ghane-Motlagh, Mahdi Nikdast, Navid Asadizanjani

Published 2026-06-25 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

Photonic Integrated Circuits (PICs) are advancing high-performance computing, data centers, and sensing, yet three-dimensional (3D) PICs introduce critical thermal management challenges due to high-density bonding and heterogeneous materials. Traditional methods like thermal microscopes and in-package sensors yield sparse data, limiting full thermal profile visibility. This paper presents a dual-method solution combining an AI-driven thermal modeling framework with a design-based heuristic approach. The AI method integrates sparse sensor data with design layer and density information to predict multilayer temperature variations, while the heuristic approach uses localized material properties, design layout, component geometries, and sensor coordinates to refine thermal estimations in specific regions. A 2D thermal map of a 3D PIC is generated by interpolating sensor data and adjusting for local thermal resistivity using comparative analysis between design regions. The heuristic method complements the AI model, improving estimation accuracy without extensive training data. Together, these methods offer a scalable, accurate solution for real-time thermal mapping and design-time simulation, enabling reliable thermal management in next-generation 3D photonic systems.

Full text 中文海报

Research Article芯片与算力

WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs

Mauricio Fadel Argerich, Jonathan Fürst, Marta Patiño-Martínez

Published 2026-07-02 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

Large Language Model (LLM) inference workloads are a rapidly growing contributor to data center energy consumption. Optimizing these deployments requires matching specific LLMs to the most efficient GPUs, but operators currently lack the tools to do so without exhaustively profiling each combination. While some predictive models exist, they still require profiling data and struggle to generalize to hardware unseen during training. To address this, we introduce \textit{WattGPU}, featuring two predictive models for mean GPU power draw and Inter-Token Latency (ITL). Our approach leverages only publicly available LLM metadata and GPU specifications, eliminating the need for hardware access or profiling while enabling generalization to unseen NVIDIA server-grade GPUs and LLMs. We evaluate our models using rigorous leave-one-GPU-out and leave-one-LLM-out cross-validation on a dataset of 42 open-source LLMs (0.1B--27B parameters) and 8 GPUs under both offline and server scenarios. The mean power draw model achieves a median absolute percentage error of $\leq3.4\%$ for offline and $\leq13.5\%$ for server scenarios on unseen GPUs, while the latency model achieves $\leq8.5\%$ in server mode, both maintaining strong GPU ranking correlations for server scenarios (Kendall $τ\geq0.76$). Compared to standard physically grounded baselines -- Load-Scaled Thermal Design Power (TDP) for power draw and roofline for latency -- our models reduce median absolute percentage error by approximately 4$\times$ on unseen LLM-GPU combinations for server scenarios or approximately 2$\times$ for completely unseen GPUs. WattGPU's data and code are publicly available at https://github.com/maufadel/wattgpu.

Full text 中文海报

Research Article热管理与液冷

Financing Artificial Intelligence Infrastructure: Mapping AI Infrastructure Investment and Compute Governance Across Africa

Kai-Hsin Hung, Sumaya Nur Adan, Krupa Suchak, Armita Sadeghian Barzoki, Kofi Yeboah, Mohammad Amir Anwar

Published 2026-06-24 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

Artificial intelligence depends on large-scale compute resources and their supporting infrastructure. However, AI governance debates treat compute primarily as a technical input rather than as an outcome of investment, ownership, and financial control. This paper examines AI infrastructure investment flows across Africa through a systematic analysis of 46 publicly announced projects totalling USD $12.7 billion between 2019 and 2025. Using a value chain framework, we analyze who invests in AI-relevant infrastructure and where investments concentrate. Our findings reveal a highly concentrated landscape dominated by global data center operators, hyperscale technology firms, and development finance institutions, clustering in South Africa, Kenya, Nigeria, and Egypt. We introduce asymmetrical interdependence to describe a structural condition in which capital and physical infrastructure account for 73% of total funding while control remains concentrated in the compute layer among a small number of global technology firms. We argue that compute governance must account for capital flows, ownership, and control, not only geographic access, because these dynamics shape AI compute equity. Infrastructure presence is necessary but insufficient for meaningful governance capacity.

Full text 中文海报

Research Article算电协同

Grid-Interactive Thermal Management of AI Data Centers via Contextual Distributionally Robust Optimization

Jiachen Shen, Jian Shi, Yijie Yang, Chenye Wu, Dan Wang, Ju Bin Song, Zhu Han

Published 2026-06-30 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

Thermal management in AI data centers is increasingly challenged by bursty workloads and uncertain heat generation. To prevent thermal violations, existing cooling strategies either enforce conservative, rigid bounds that severely limit grid responsiveness, or rely on forecast-driven controllers that perform poorly under AI workload uncertainty and distribution shifts. To overcome the above challenges, this paper proposes a Contextual Distributionally Robust Optimization (CDRO) framework for grid-interactive cooling control. Unlike standard DRO with fixed ambiguity sets, the proposed approach dynamically adapts the Wasserstein radius using real-time AI and grid context. This safely shrinks uncertainty bounds during stable regimes, unlocking deep demand-side flexibility. Theoretically, we formulate the control as an infinite-dimensional inf-sup problem, derive an exact tractable reformulation for the Wasserstein worst-case expected-cost term, and then derive a tractable conservative deterministic counterpart for the Distributionally Robust Conditional Value at Risk (DR-CVaR) thermal safety constraint. Solved via a scalable nested Alternating Direction Method of Multipliers (ADMM) algorithm, the CDRO controller achieves near-zero thermal violations under extreme workload spikes in high-fidelity EnergyPlus co-simulations. Simultaneously, it reduces the operational cost premium of robustness by approximately 13.7 percentage points relative to standard Min-Max Model Predictive Control (MPC).

Full text 中文海报

Research Article热管理与液冷

AI Data Centers and the Water Use Feedback Loop

Basit A. Akinade, Amobichukwu C. Amanambu, Jonathan M. Frame, Shaolei Ren

Published 2026-06-19 · arXiv · Credibility S

AI data centres consume water for cooling, water scarcity constrains siting, and AI tools can improve water system efficiency. These dynamics are studied separately yet form a feedback loop. This review formalises the Water and AI Feedback Loop, introduces the Water Consumption Impact index to quantify community-scale utility burden, and demonstrates across ten US sites that burden spans three orders of magnitude, f…

Abstract, interpretation and reference

Abstract

Full text 中文海报

Research ArticleAI 运维优化

Hot AI in Cold Space: Thermal-Crosstalk-Aware Scheduling for Sustainable Orbital AI Clusters

Shuyi Chen, Zhengchang Hua, Nikos Tziritas, Georgios Theodoropoulos

Published 2026-06-23 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

Terrestrial AI training faces an unsustainable energy and water crisis, positioning Orbital Data Centers (ODCs) as a "zero operational carbon" alternative. However, the sub-$10μ\text{s}$ communication latency required for synchronized scientific workloads, such as distributed Large Language Model (LLM) training, forces ODCs into extreme physical density, triggering a critical "Proximity-Thermal Paradox." As these high-density systems scale into Monolithic Structures or Proximity Swarms, they suffer from intense thermal-fluid crosstalk (heat traps in shared cooling loops) and thermal-radiative crosstalk (mutual heating that blocks deep-space cooling radiators). If left unmitigated, this persistent heat stagnation not only triggers severe thermal throttling that degrades training throughput, but also induces severe thermal fatigue, drastically shortening hardware lifespans and generating premature space e-waste. To make orbital AI truly sustainable, this position paper challenges traditional uniform load-sharing. We propose the Thermal-Aware Heterogeneity Thesis, which treats spatial cooling variances as a primary resource management dimension. Building on this, we introduce Thermal-Load Balancing (TLB), a software framework that dynamically migrates these intensive workloads to the coolest available units based on instantaneous fluid temperatures or absorbed radiation. Our analysis demonstrates that TLB resolves thermal bottlenecks to restore Model Flops Utilization (MFU), while simultaneously reducing physical thermal stress. Extending the operational lifespan of orbital hardware is crucial to amortize the massive embodied carbon of rocket launches, outlining a necessary pathway to scale orbital AI without accelerating e-waste.

Full text 中文海报

Research Article算电协同

AI Data Centers and Power System Sustainability: Understanding the Sustainability Implications of AI-Driven Data Centers on Power Systems

Yuhao Huang, Novarun Deb, Hamidreza Zareipour

Published 2026-06-19 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

The rapid expansion of artificial intelligence (AI) has driven unprecedented growth in data center electricity demand. The scale and pace of this load growth carry significant implications for the sustainability of electric power systems. On the one hand, rapid, spatially concentrated data center load growth is outpacing clean energy deployment in several major regions, raising emissions and challenging both grid flexibility and reliability. On the other hand, this fast-developing and capital-intensive sector offers abundant opportunities to advance sustainability through clean energy integration and operational innovations. This article provides an overview of the mechanisms through which data center affect power system sustainability, underscoring both risks and the potential. Specifically, this article (i) characterizes AI data center load behavior and categorizes electricity supply configurations by function and sustainability profile, as well as situates these loads within global and regional electricity demand trends; (ii) analyzes sustainability impacts across short-run operational and long-run planning mechanisms, evaluates effects on grid carbon emissions and renewable energy utilization, and feasibility of offering system flexibility and participating in ancillary service; and (iii) evaluates real-world corporate sustainability pathways and highlighting both the system benefits and feasibility limits of current carbon accounting practices. The goal of this work is to synthesize existing knowledge and technological developments and to guide research and development toward a more sustainable integration of AI data centers and electric power systems.

Full text 中文海报

Research Article算电协同

GaN Power Devices and Converter Architectures for AI Data Centers: Efficiency, Reliability, and Deployment Pathways

Donald Intal, Abasifreke Ebong

Published 2026-06-24 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

The growth of artificial-intelligence workloads is increasing the electrical and thermal demands on data-center power-delivery systems, making conversion efficiency, power density, and reliability critical design priorities. This review examines how gallium-nitride (GaN) power devices can be matched to specific stages of the grid-to-load conversion chain, including power-factor correction, isolated DC/DC conversion, 48-V intermediate-bus conversion, and point-of-load regulation. Si, SiC, and GaN are compared using converter-relevant metrics, and lateral, vertical, and specialized GaN architectures are evaluated in terms of voltage scalability, switching behavior, reverse conduction, thermal pathways, gate control, and technology maturity. The analysis shows that GaN provides a stage-dependent rather than universal advantage. Commercial lateral GaN HEMTs are particularly effective in high-frequency, low-to-mid-voltage stages, while specialized and hybrid devices support bidirectional operation, normally-off control, extreme conversion ratios, and integration. Vertical GaN remains an emerging option for higher-voltage and higher-power conversion. A quantitative framework links cascaded converter efficiency to electrical-loss reduction, cooling demand, annual facility energy use, and operational carbon emissions. Broad deployment further requires low-parasitic packaging, disciplined gate-drive and EMI co-design, mission-profile reliability qualification, scalable manufacturing, and supply-chain resilience. GaN is therefore best treated as a stage-specific system lever whose value depends on coordinated device, topology, package, and thermal co-design.

Full text 中文海报

Research Article算电协同

From Tokens to Energy Flexibility: Quantization-Enabled Demand Response for Data Centers with LLM Inference Workloads

Bojun Du, Xiaoyi Fan, Ershun Du, Long Chen, Jianpei Han, Qingchun Hou, Ning Zhang, Chongqing Kang

Published 2026-06-17 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

The rapid growth of large language model (LLM) inference is creating significant data-center loads that face increasing energy-management challenges under tightening grid conditions and demand response (DR) requirements. Conventional data-center energy management mainly relies on temporal and spatial workload shifting and campus-level energy asset scheduling, but it usually treats LLM inference demand as an aggregate load. As a result, these approaches fail to exploit the internal characteristics of LLM serving and therefore overlook the flexibility offered by LLM-specific techniques such as model quantization. To unlock this flexibility, this paper proposes a quantization-enabled energy management framework for grid-responsive LLM inference data centers. First, a quantization-to-power model is established to map each model--quantization configuration to a compact set of dispatchable parameters. Second, a two-stage quantization-enabled DR model is developed to account for model instance switching, request routing, and precision selection. Third, a multi-campus co-optimization method is introduced for DR participation by integrating grid-side electricity and carbon signals with the quantization-enabled DR model. Case studies show that the proposed framework reduces total data-center operating cost by 34.3\% without curtailing served token volume, validating model quantization as an effective flexibility lever for grid-responsive LLM data-center energy management.

Full text 中文海报

Research Article芯片与算力

Node-Level Performance and Energy Characterization of Flagship Science Applications on SuperMUC-NG Phase 2

Salvatore Cielo, Elmira Birang, Alexander Pöppl, Sajad Azizi, Plamen Dobrev, Margarita Egelhofer, Ivan Pribec, Gerald Mathias

Published 2026-06-22 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

We present a systematic performance and energy-efficiency characterization of five flagship scientific workloads on SuperMUC-NG phase 2, the 28 PetaFLOPs system at the Leibniz Supercomputing Center (LRZ) equipped with Intel Xeon Platinum 8480+ and Intel Data Center GPU Max 1550 (Ponte Vecchio, PVC) accelerators. The selected codes span molecular dynamics (gromacs, lammps), astrophysics and cosmology (OpenGadget3, AthenaK), and finite-element PDE solvers from the dealii-X Center of Excellence. For each code we measure throughput and energy efficiency expressed as compute-elements per wall-clock second (or per Joule of consumed energy) on a single compute node, comparing CPU-only (SPR) against combined CPU+GPU (SPR+PVC) configurations where available. Energy measurements rely on lightweight code instrumentation with p3em, or the Energy Aware Runtime (EAR) present on the system. Our results show that GPU offload yields $4-12\times$ higher throughput and up to $15\times$ better energy efficiency compared to CPU-only execution, with lammps and AthenaK benefiting most. However, both throughput and energy gains are sensitive to problem granularity: insufficient work per GPU tile erodes the accelerator advantage, as clearly observed in AthenaK at small mesh-block sizes. The power-budget utilization is systematically lower for CPUs than it is for GPUs, indicating that even at peak useful-work rate, most applications running on CPUs leave a significant fraction of the node's thermal envelope unused.

Full text 中文海报

Research Article算电协同

A Bilevel Framework for Data Center-Grid Coordination with DLMPs in Unbalanced Three-Phase Distribution Systems

Arash Baharvandi, Duong Tung Nguyen

Published 2026-06-24 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

This paper proposes a grid-aware coordination framework between data centers and distribution grids using a DLMP-based bilevel optimization model. The data center aggregator (DCA) determines active power demand in response to distribution locational marginal prices (DLMPs), while the distribution system operator (DSO) solves a network-constrained optimal power flow problem to determine DLMPs in an unbalanced three-phase system. The model incorporates both active and reactive power consumption of data centers to evaluate their impacts on voltage regulation and phase imbalance. To mitigate adverse network effects, two operating cases are analyzed: without reactive power compensation and with static var generator (SVG)-based compensation. The proposed approach is validated on the IEEE 37-bus unbalanced distribution test system. Simulation results show that DLMP-based coordination captures economically efficient data center operation, and phase- and location-dependent network conditions, while SVG-based compensation improves voltage profiles and reduces phase unbalance.

Full text 中文海报

Research Article热管理与液冷

Toward Next-Generation AI Data Centers: Power Delivery Architecture Shifts, Emerging Technologies, and Challenges

Sangwhee Lee, Rafal P. Wojda, Cheol-Hee Jo, Shuntaro Inoue, Pedro Ribeiro, Gui-Jia Su, Mostak Mohammad, Himel Barua, Nishanth Gadiyar, Praveen Kumar, Spencer Cochran, Subho Mukherjee, W. Vinson, Vandana Rallabandi, Shajjad Chowdhury, B. Ozpineci

Published 2026-06-23 · Semantic Scholar · Credibility S

Abstract, interpretation and reference

Abstract

The rapid growth of AI workloads is driving unprecedented increases in data center power demand, current transients, and thermal stress, exposing fundamental limitations in traditional 48 V rack architectures, low-voltage AC distribution, and line-frequency transformer interfaces. This paper reviews the three stages of architectural shifts required to support next-generation AI data centers and identifies three enabling technological building blocks: high-voltage conversion-ratio DC/DC converters, facility-level low-voltage DC distribution, and medium-voltage solid-state transformers. The advantages, technical challenges, and potential solutions associated with each building block are reviewed. Finally, future research directions and open challenges are discussed.

Full text 中文海报

Research Article算电协同

Contextual Robust Optimization for AI Data Center Scheduling with Statistical Guarantees

Yijie Yang, Xiaochong Weng, Yue Chen

Published 2026-06-16 · Semantic Scholar · Credibility S

Abstract, interpretation and reference

Abstract

The rapid growth of AI workloads is substantially increasing data center electricity demand and carbon emissions, motivating the development of carbon-aware scheduling methods. However, effective scheduling is challenging because renewable generation and AI workloads are subject to forecast errors, while training and inference workloads exhibit heterogeneity in computational characteristics. This paper proposes a contextual robust optimization framework for AI data center operation. The proposed model explicitly captures the heterogeneous computational characteristics of AI training and inference workloads. To deal with renewable generation and workload forecast errors, we develop loss-based uncertainty learning models that directly map contextual features to covariate-dependent uncertainty sets. The resulting contextual joint chance-constrained scheduling problem is reformulated into a tractable robust optimization problem, and a calibration algorithm is developed to provide finite-sample probabilistic feasibility guarantees for multiple joint chance constraints. Numerical experiments based on real-world AI workload traces and renewable generation data show that the proposed method reduces operating costs by an average of 5.57% compared to benchmark methods while maintaining reliable feasibility and strong computational scalability.

Full text 中文海报

Research Article算电协同

Power-Flexible AI Data Centers: A New Paradigm for Grid-Responsive Compute

Chris Williams, Philip Colangelo, Ayse Coskun, Ethan Levine, Andy Neale, Ciaran Roberts, Shayan Sengupta, Nikhil Shirolkar, Varun Sivaram, Sarah Soares, Ethan Tiao, Scott Underwood, Daniel Wilson, Frank Sharp, Luke Wainwright, Harry Petty, Scott Wallace, Brandon Records

Published 2026-06-23 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

The rapid expansion of artificial intelligence (AI) infrastructure is driving unprecedented growth in electricity demand from data centers. Traditional power-system planning treats large computing facilities as inflexible peak loads, leading to costly infrastructure upgrades and long delays in grid interconnection. Recent work has shown that AI clusters can reduce electricity consumption during peak demand through software-based workload orchestration. This article explores how modern GPU-based AI data centers can operate as grid-interactive assets that respond dynamically to power system conditions. We describe an architecture integrating grid signals, workload scheduling, and power telemetry for fine-grained cluster power control. Experimental results from a real-world deployment on a 130 kW GPU cluster demonstrate multiple forms of flexibility, including rapid load reduction, sustained curtailment, and carbon-aware operation while preserving service levels for priority jobs. We further demonstrate performance-aware load shifting across geographically distributed clusters, enabling workloads to migrate toward regions with lower grid stress. Together, these capabilities transform AI infrastructure from static electricity consumers into flexible resources that support grid reliability, accelerate interconnection, and improve computing sustainability.

Full text 中文海报

Research ArticleAI 运维优化

Learning Burst-Aware Early Warning Models for Capacity Stress under AI Workload Surges in Hyperscale Data Centers

Zihan Yu, Xianling Zeng, Zhiming Xue, Yalun Qi, Sichen Zhao

Published 2026-06-19 · arXiv · Credibility S

Abstract, interpretation and reference

Abstract

The rapid growth of large-scale AI workloads, particularly Large Language Model (LLM) training and inference, is fundamentally reshaping the operational dynamics of hyperscale data centers. Unlike traditional cloud workloads, AI-driven jobs exhibit bursty, high-intensity, and rapidly shifting resource demands, often leading to sudden capacity stress that cannot be effectively handled by reactive threshold-based mechanisms. In this paper, we propose a deployment-oriented, burst-aware early warning framework for proactive capacity stress prediction under AI workload surges. We formulate the problem as a high-recall forecasting task over multivariate telemetry windows, with the explicit goal of enabling operational intervention before system degradation occurs. The proposed framework integrates workload intensity, temporal variation, and system pressure signals, and employs a lightweight tree-based learning model to capture nonlinear interactions in highly imbalanced environments. To evaluate the system under realistic conditions, we introduce an AI workload surge injection methodology that simulates burst-driven demand patterns observed in large-scale AI systems. Our XGBoost-based model achieves an ROC AUC of 0.697 and an AP of 0.670, significantly outperforming baseline methods. Under deployment-oriented threshold selection, the framework achieves a Recall of 0.914, enabling the detection of the majority of stress-prone periods with acceptable false-alarm cost. Beyond predictive performance, we show how the proposed framework can be integrated into operational control loops to support proactive actions such as workload throttling and resource scaling. Our results highlight the practical value of high-recall, learning-based early warning systems in enabling resilient and adaptive data center operations in the era of AI-driven workloads.

Full text 中文海报

智算中心论文专站

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract