Liquid Cooling and AI Data Center Daily | 2026-09-12
A daily English mirror of liquid cooling, AI data center efficiency, research papers, products, policy, financing, and supply-chain signals.
1. Executive brief
This English edition mirrors the same public-source dataset used by the Chinese daily report for 2026-09-12.
- Collection window: 2026-09-11 08:00 北京时间 - 2026-09-12 08:00 北京时间.
- Coverage snapshot: 0 industry items; 0 technology items; 8 paper or white-paper items; 8 video signals.
- Current hot topics: 电力并网与能源约束, AI 芯片供给与交付, 液冷路线（冷板/浸没/两相）, PUE/WUE 与能效优化.
- The heat score is 6/10 and should be read as a source-density signal, not as an investment indicator.
All claims should be verified against the original source links listed at the end of this report.
Academic and Industry Briefs
Papers, videos, industry updates, policy, financing, and projects are compressed into scannable tags with a title, summary, and source link.
Academic
Research papers, methods, research-oriented videos, and academic signals.
Spatial LLM Workload Shifting Needs Foresight: Model Commitment for AI Da…
AI data centers may face power supply shortages during certain periods, requiring operators to shift large language model (LLM) inf…
Expand
Spatial LLM Workload Shifting Needs Foresight: Model Commitment for AI Data Center Operation under Power Grid Constraints
- Published
- 2026-09-09
- Authors
- Bojun Du, Hongyang Jia, Tonghui Li, Qingchun Hou, Ze Wang, Ershun Du, Ning Zhang
- Theme
- 算电协同
Abstract
AI data centers may face power supply shortages during certain periods, requiring operators to shift large language model (LLM) inference workloads spatially to maintain service rates. However, existing workload-shifting methods typically assume that any data center with sufficient computing resources can immediately serve shifted requests, which may lead to infeasible transfers and unserved demand. This letter proposes model commitment (MC), a mixed-integer linear programming framework that jointly schedules model deployment and cross-site request routing under power constraints and electricity-price signals. First, MC formulates the intertemporal coupling introduced by model replica loading. Second, it translates prefill and decode latency requirements into the amount of demand that each replica can serve. Case studies based on real-world data show that MC enables AI data center operators to achieve a 100% service rate under time-varying grid conditions and reduce total operating cost by 29.0%.
Chinese interpretation
背景：AI 数据中心负载、功率密度和能源约束同步上升，算力负载与电网侧资源的协同调度正在成为智算中心设计的关键变量。问题：论文聚焦现有方案在效率、可靠性或工程协同上的瓶颈。方法：摘要显示作者采用框架构建和频域/系统级分析，把运行负载、冷却/能源系统和基础设施约束放在同一分析框架中。结果：研究重点指向AI 负载波动对电网设备寿命和调频边界的影响。意义：对日报读者而言，它可用于判断智算中心建设是否受电网容量、负载波动和调度机制约束。仍需结合全文实验条件、样本范围和成本假设核验。
Reference
Bojun Du, Hongyang Jia, Tonghui Li, 等. Spatial LLM Workload Shifting Needs Foresight: Model Commitment for AI Data Center Operation under Power Grid Constraints[J/OL]. (2026-09-09)[2026-09-12]. http://arxiv.org/abs/2609.09787v1.
A Theory of Probabilistic Power Provisioning for Data Centers with Distri…
The growing power demands and variability of AI workloads make electrical power delivery a critical constraint in data-center opera…
Expand
A Theory of Probabilistic Power Provisioning for Data Centers with Distributed Energy Storage
- Published
- 2026-08-13
- Authors
- Can Emre Koksal, Richard A. Barry, Artun Sel
- Theme
- 芯片与算力
Abstract
The growing power demands and variability of AI workloads make electrical power delivery a critical constraint in data-center operation. Distributed energy storage can reduce the power capacity required to support stochastic loads, but its benefits depend fundamentally on the statistics and time scales of demand. This paper develops a probabilistic framework that jointly characterizes provisioned power, energy-storage capacity, and the probability of overdraw. We show that storage-assisted provisioning separates into two operating regimes. In the Small Battery Region, overdraw is dominated by short-lived demand excursions and storage provides nearly linear reductions in the required power margin. In the Large Battery Region, overdraw results from sustained demand fluctuations over longer spans of time, and the required margin exhibits diminishing returns with storage. For this regime we introduce effective power, an analogue of effective bandwidth that captures the temporal statistics of the demand and gives an asymptotically tight characterization of the required power. We further quantify how temporal correlation and spatial aggregation affect storage requirements and statistical multiplexing gains, and extend the analysis to loads with multiple demand time scales. Finally, we evaluate the framework using power-demand traces from three production data centers spanning HPC, GPU-training, and cloud-service workloads. Despite their heterogeneous, cyclo-stationary and multi-modal behavior, the measured workloads exhibit the predicted regimes, and a simple four-parameter two-state model captures the dynamics governing their storage-power tradeoffs. The resulting framework provides both a probabilistic foundation and practical dimensioning principles for storage-assisted power provisioning in next-generation AI data centers.
Chinese interpretation
背景：AI 数据中心负载、功率密度和能源约束同步上升，芯片、服务器和高密度算力部署正在成为智算中心设计的关键变量。问题：论文聚焦现有方案在效率、可靠性或工程协同上的瓶颈。方法：摘要显示作者采用框架构建和频域/系统级分析，把运行负载、冷却/能源系统和基础设施约束放在同一分析框架中。结果：研究重点指向跨地域数据中心负载与电力资源之间的调度关系。意义：对日报读者而言，它可用于判断芯片路线和服务器密度变化如何传导到机房设计。仍需结合全文实验条件、样本范围和成本假设核验。
Reference
Can Emre Koksal, Richard A. Barry, Artun Sel. A Theory of Probabilistic Power Provisioning for Data Centers with Distributed Energy Storage[J/OL]. (2026-08-13)[2026-09-12]. http://arxiv.org/abs/2608.12993v1.
From Grid to Chip: Power Architecture, Stability, and Flexibility of AI D…
The rapid growth of artificial intelligence (AI) computing is transforming data centers into large, dynamic electrical loads. Their…
Expand
From Grid to Chip: Power Architecture, Stability, and Flexibility of AI Data Centers
- Published
- 2026-09-10
- Authors
- Yubo Song, Rui Kong, Takuro Umihara, Pooya Davari, Frede Blaabjerg, Subham Sahoo
- Theme
- 算电协同
Abstract
The rapid growth of artificial intelligence (AI) computing is transforming data centers into large, dynamic electrical loads. Their deployment is primarily constrained by energy availability and grid-connection capacity, which is further aggravated by the ability of power-delivery architectures, control systems, and computing workloads to operate reliably during fast grid disturbances. This article presents a technological perspective on AI data centers as grid-interactive computing systems. First, it reviews grid-integration bottlenecks, evolving connection policies, grid-code requirements, which has fostered new technological trends via spatio-temporal flexibility available through workload orchestration, cooling systems, on-site resources, and energy storage. Second, it maps the evolution of power-delivery architectures from medium-voltage grid interfaces to chip-level, discussing higher-voltage DC distribution, solid-state transformers, wide-bandgap devices, advanced chip-level power delivery, and liquid cooling. Third, it establishes a three-level stability framework spanning rack-level DC-bus dynamics, facility-level converter interactions, and system-level grid-coupled behavior. The framework connects dominant instability mechanisms, including constant power load effects, impedance interactions, forced oscillations, and operating-mode transitions, with suitable modeling, assessment, and mitigation approaches. Synthesizing these topics, this article highlights grid-to-chip co-design as a central requirement for scalable AI infrastructure, linking computing workloads, power-delivery systems, energy buffers, and grid operation.
Chinese interpretation
背景：AI 数据中心负载、功率密度和能源约束同步上升，算力负载与电网侧资源的协同调度正在成为智算中心设计的关键变量。问题：论文聚焦现有方案在效率、可靠性或工程协同上的瓶颈。方法：摘要显示作者采用综述归纳和指标比较，把运行负载、冷却/能源系统和基础设施约束放在同一分析框架中。结果：研究重点指向AI 负载波动对电网设备寿命和调频边界的影响。意义：对日报读者而言，它可用于判断智算中心建设是否受电网容量、负载波动和调度机制约束。仍需结合全文实验条件、样本范围和成本假设核验。
Reference
Yubo Song, Rui Kong, Takuro Umihara, 等. From Grid to Chip: Power Architecture, Stability, and Flexibility of AI Data Centers[J/OL]. (2026-09-10)[2026-09-12]. http://arxiv.org/abs/2609.11649v1.
LLM-Powered Predictive Decision-Making for Sustainable Data Center Operat…
The growing demand for AI-driven workloads, particularly from Large Language Models (LLMs), has raised concerns about the significa…
Expand
LLM-Powered Predictive Decision-Making for Sustainable Data Center Operations
- Published
- 2026-08-19
- Authors
- Hanzhao Wang, Jingxuan Wu, Yumeng Li, Yu Pan, Guanting Chen
- Theme
- 芯片与算力
Abstract
The growing demand for AI-driven workloads, particularly from Large Language Models (LLMs), has raised concerns about the significant energy and resource consumption in data centers. This work introduces a novel LLM-based predictive scheduling system designed to enhance operational efficiency while reducing the environmental impact of data centers. Our system utilizes an LLM to predict key metrics such as execution time and energy consumption from source code, and it has the potential to extend to other sustainability-focused metrics like water usage for cooling and carbon emissions, provided the data center can track such data. The predictive model is followed by a real-time scheduling algorithm that allocates GPU resources, aiming to improve sustainability by optimizing both energy consumption and queuing delays. With fast inference times, the ability to generalize across diverse task types, and minimal data requirements for training, our approach offers a practical solution for data center scheduling. This framework demonstrates strong potential for advancing sustainability objectives in AI-driven infrastructure. Through our collaboration with a data center, we achieved a 32% reduction in energy consumption and a 30% decrease in waiting time.
Chinese interpretation
背景：AI 数据中心负载、功率密度和能源约束同步上升，芯片、服务器和高密度算力部署正在成为智算中心设计的关键变量。问题：论文聚焦现有方案在效率、可靠性或工程协同上的瓶颈。方法：摘要显示作者采用建模优化、调度分析或算法评估，把运行负载、冷却/能源系统和基础设施约束放在同一分析框架中。结果：研究重点指向能效评价口径、运营指标和优化目标的系统化梳理。意义：对日报读者而言，它可用于判断芯片路线和服务器密度变化如何传导到机房设计。仍需结合全文实验条件、样本范围和成本假设核验。
Reference
Hanzhao Wang, Jingxuan Wu, Yumeng Li, 等. LLM-Powered Predictive Decision-Making for Sustainable Data Center Operations[J/OL]. (2026-08-19)[2026-09-12]. http://arxiv.org/abs/2608.18503v1.
Grid-Mode-Aware Model Predictive Control of Hybrid Energy Storage Systems…
To facilitate the grid-friendly integration of highly variable AI data center loads, this paper proposes a grid-mode-aware model pr…
Expand
Grid-Mode-Aware Model Predictive Control of Hybrid Energy Storage Systems for AI Data Center Power Smoothing
- Published
- 2026-09-04
- Authors
- Xin Chen
- Theme
- 算电协同
Abstract
To facilitate the grid-friendly integration of highly variable AI data center loads, this paper proposes a grid-mode-aware model predictive control (G-MPC) framework for managing a hybrid energy storage system (HESS) to smooth grid-side power demand. The framework optimally coordinates a battery energy storage system (BESS) and a supercapacitor (SC) by solving a multi-step optimization problem in a receding-horizon manner. In particular, band-pass filter dynamics are directly embedded in the G-MPC formulation to extract and suppress grid-side power components associated with vulnerable grid oscillatory modes, thus mitigating load-induced grid oscillations. The resulting G-MPC optimization jointly minimizes violations of grid-side power-envelope, ramp-rate, and modal-power requirements and the degradation and power-ramping costs of the BESS and SC, while satisfying power limits, state-of-charge limits, and other operational constraints. To enable real-time implementation, a fix-and-re-optimize algorithm is developed to solve each G-MPC problem efficiently while preventing simultaneous charging and discharging. Extensive simulations demonstrate the effectiveness, flexibility, and computational efficiency of the proposed framework. The results also highlight the importance of explicitly suppressing power components associated with vulnerable grid modes, rather than merely reducing overall load variations, to effectively mitigate grid oscillations.
Chinese interpretation
背景：AI 数据中心负载、功率密度和能源约束同步上升，算力负载与电网侧资源的协同调度正在成为智算中心设计的关键变量。问题：论文聚焦现有方案在效率、可靠性或工程协同上的瓶颈。方法：摘要显示作者采用建模优化、调度分析或算法评估，把运行负载、冷却/能源系统和基础设施约束放在同一分析框架中。结果：研究重点指向AI 负载波动对电网设备寿命和调频边界的影响。意义：对日报读者而言，它可用于判断智算中心建设是否受电网容量、负载波动和调度机制约束。仍需结合全文实验条件、样本范围和成本假设核验。
Reference
Xin Chen. Grid-Mode-Aware Model Predictive Control of Hybrid Energy Storage Systems for AI Data Center Power Smoothing[J/OL]. (2026-09-04)[2026-09-12]. http://arxiv.org/abs/2609.04398v1.
Hosting Capacity Assessment of Data Centers with Voltage Ride-Through Cap…
Large data centers are emerging as concentrated, power-electronic grid loads whose abrupt disconnection or transfer to on-site back…
Expand
Hosting Capacity Assessment of Data Centers with Voltage Ride-Through Capability in Power Systems
- Published
- 2026-09-03
- Authors
- Pengyu Ren, Wei Sun, Fei Teng
- Theme
- 算电协同
Abstract
Large data centers are emerging as concentrated, power-electronic grid loads whose abrupt disconnection or transfer to on-site backup supply during voltage disturbances can remove large demand from the power system, and may create a system-level stability problem. Their interconnection feasibility therefore depends not only on steady-state thermal and voltage limits, but also on whether internal power-conditioning systems can maintain IT service while limiting customer-initiated load reduction. This paper presents a voltage ride-through (VRT)-aware data center and grid co-planning framework that couples transmission-level fault simulation with an internal data center ride-through model. Python-based dynamic simulations generate point-of-interconnection (POI) voltage trajectories under selected network faults, and the resulting waveforms drive an internal model incorporating IT and cooling-load dynamics, DC-link, Uninterruptible Power Supply (UPS) response, and converter apparent power limits. The IEEE 118-bus case study shows that internal VRT capability can become a binding interconnection constraint: steady-state planning alone can overestimate feasible data center capacity, whereas increased UPS converter headroom progressively restores hosting capacity. Under the reduced-order response models studied, the grid-forming mode provides greater ride-through margin than the current-limited grid-following mode under the same network fault conditions. The results further show that VRT constraints can materially change both the total hosting capacity of data centers and its spatial allocation across candidate interconnection buses.
Chinese interpretation
背景：AI 数据中心负载、功率密度和能源约束同步上升，算力负载与电网侧资源的协同调度正在成为智算中心设计的关键变量。问题：论文聚焦现有方案在效率、可靠性或工程协同上的瓶颈。方法：摘要显示作者采用框架构建和频域/系统级分析，把运行负载、冷却/能源系统和基础设施约束放在同一分析框架中。结果：研究重点指向AI 负载波动对电网设备寿命和调频边界的影响。意义：对日报读者而言，它可用于判断智算中心建设是否受电网容量、负载波动和调度机制约束。仍需结合全文实验条件、样本范围和成本假设核验。
Reference
Pengyu Ren, Wei Sun, Fei Teng. Hosting Capacity Assessment of Data Centers with Voltage Ride-Through Capability in Power Systems[J/OL]. (2026-09-03)[2026-09-12]. http://arxiv.org/abs/2609.03030v1.
InFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers
The rapid growth of LLM inference is shifting sustainability concerns from one-time training to continuous serving, where infrastru…
Expand
InFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers
- Published
- 2026-08-13
- Authors
- Nicoletta Tsiopani, Moysis Symeonides, George Pallis, Marios D. Dikaiakos
- Theme
- 算电协同
Abstract
The rapid growth of LLM inference is shifting sustainability concerns from one-time training to continuous serving, where infrastructure decisions shape energy use, carbon emissions, water consumption, and service quality. Yet operators often need to compare deployment alternatives before large-scale infrastructure is built, making direct measurement costly, slow, and sometimes infeasible. We present InFactPlanner, a trace-driven decision-support framework for what-if analysis of sustainable AI data center deployment for LLM inference across single and geo-distributed sites. InFactPlanner combines query traces, hardware-model profiles, candidate site configurations, PUE/WUE parameters, renewable generation models, and time-varying grid carbon intensity to estimate power, energy, carbon emissions, water use, latency, and server utilization. The framework abstracts low-level serving effects into configurable hardware-model profiles, enabling rapid comparison of site selection, capacity placement, hardware, model, renewable integration, and routing choices. We validate the energy accounting pipeline by reproducing reference LLM inference energy estimates with less than 10% deviation, evaluate scalability across multiple data centers and server counts, and demonstrate scenario-driven decision analyses for hardware selection, renewable placement, geographic deployment, and carbon-aware routing. Our results show that sustainability-optimal choices can differ from latency-optimal ones, and that the carbon value of deployment depends strongly on the local grid mix.
Chinese interpretation
背景：AI 数据中心负载、功率密度和能源约束同步上升，算力负载与电网侧资源的协同调度正在成为智算中心设计的关键变量。问题：论文聚焦现有方案在效率、可靠性或工程协同上的瓶颈。方法：摘要显示作者采用框架构建和频域/系统级分析，把运行负载、冷却/能源系统和基础设施约束放在同一分析框架中。结果：研究重点指向AI 负载波动对电网设备寿命和调频边界的影响。意义：对日报读者而言，它可用于判断智算中心建设是否受电网容量、负载波动和调度机制约束。仍需结合全文实验条件、样本范围和成本假设核验。
Reference
Nicoletta Tsiopani, Moysis Symeonides, George Pallis, 等. InFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers[J/OL]. (2026-08-13)[2026-09-12]. http://arxiv.org/abs/2608.12915v1.
Exploiting the Benefits of V2B Application on Peak Shaving of Data Center…
The accelerated growth in data center projects has introduced a demand-driven bottleneck throughout power grids and contributed to …
Expand
Exploiting the Benefits of V2B Application on Peak Shaving of Data Center Loads
- Published
- 2026-09-01
- Authors
- Arya Joshi, Hamed Haggi, Chinmay Morankar
- Theme
- 算电协同
Abstract
The accelerated growth in data center projects has introduced a demand-driven bottleneck throughout power grids and contributed to a substantial increase in carbon emissions. These concerns are fueling discussions on methods to use existing energy assets to drive operational efficiency. To this end, this paper explores the benefits of Vehicle-to-Building (V2B) applications to support peak shaving of data center cooling loads. Initially, a literature review was conducted considering V2B constraints and optimization methods including SoC limitations, EV participation, tariffs, and building loads. This analysis was then used to develop a conceptual case study of a 10 MW data center in Loudoun County, VA by simulating a temperature-dependent load profile and adjusting the V2B participation of 40 commercial and passenger EVs. Simulation results indicate that, depending on seasonal variations in cooling load demands, strategic deployment of V2B assets between 12-5pm can offset gross cooling loads by 13-36%.
Chinese interpretation
背景：AI 数据中心负载、功率密度和能源约束同步上升，算力负载与电网侧资源的协同调度正在成为智算中心设计的关键变量。问题：论文聚焦现有方案在效率、可靠性或工程协同上的瓶颈。方法：摘要显示作者采用综述归纳和指标比较，把运行负载、冷却/能源系统和基础设施约束放在同一分析框架中。结果：研究重点指向AI 负载波动对电网设备寿命和调频边界的影响。意义：对日报读者而言，它可用于判断智算中心建设是否受电网容量、负载波动和调度机制约束。仍需结合全文实验条件、样本范围和成本假设核验。
Reference
Arya Joshi, Hamed Haggi, Chinmay Morankar. Exploiting the Benefits of V2B Application on Peak Shaving of Data Center Loads[J/OL]. (2026-09-01)[2026-09-12]. http://arxiv.org/abs/2609.00204v1.
SAVE YOURSELF AS A DCIM ENGINEER #dcim #controls #datacentermanagement #d…
Timothy Hobbs · Query: data center thermal management seminar。Useful as technical or research context.
Expand
Data Center 101: Single-Phase Immersion Cooling
GIGABYTE · Query: data center thermal management seminar。Useful as technical or research context.
Expand
Data Center Cooling - A thermal efficiency approach
Anixter · Query: data center thermal management seminar。Useful as technical or research context.
Expand
Energy Efficiency of Data Centers
Institute for Systems Research · Query: IEEE data center energy efficiency lecture。Useful as technical or research context.
Expand
Understanding data centre electricity use
IEA Webinars · Query: AI datacenter power grid university lecture。Useful as technical or research context.
Expand
电力并网与能源约束
Same-source item from the Chinese report. Verify details against the original linked source: 电力并网与能源约束
展开全文
AI 芯片供给与交付
Same-source item from the Chinese report. Verify details against the original linked source: AI 芯片供给与交付
展开全文
液冷路线（冷板/浸没/两相）
Same-source item from the Chinese report. Verify details against the original linked source: 液冷路线（冷板/浸没/两相）
展开全文
Industry
Industry news, products, policy, financing, projects, and market-oriented videos.
Data Center and AI Infrastructure in Arizona: A Knowledge Exchange | Util…
ASU Energy Forward · Query: AI infrastructure datacenter panel discussion。Useful for product, market, or deployment context.
Expand
Datacenter Cooling Focus on HPC
Institution of Mechanical Engineers - IMechE · Query: high performance computing data center cooling workshop。Useful for product, m…
Expand
Advanced Fabrics, Ethernet and the Future of AI Infrastructure
650 Group (650 Group) · Query: AI infrastructure datacenter panel discussion。Useful for product, market, or deployment context.
Expand
产业热度指数 6/10
Same-source item from the Chinese report. Verify details against the original linked source: 产业热度指数 6/10
展开全文
NVIDIA Blackwell/GB200/GB300
Same-source item from the Chinese report. Verify details against the original linked source: NVIDIA Blackwell/GB200/GB300
Expand
AI 芯片供给与交付
Same-source item from the Chinese report. Verify details against the original linked source: AI 芯片供给与交付
展开全文
智算中心 CapEx/扩建
Same-source item from the Chinese report. Verify details against the original linked source: 智算中心 CapEx/扩建
展开全文
4. Video signals
Data Center and AI Infrastructure in Arizona: A Knowledge Exchange | Utilities Panel with Kelly Barr
专家圆桌 · ASU Energy Forward · Query: AI infrastructure datacenter panel discussion
Open on YouTubeDatacenter Cooling Focus on HPC
技术研讨会 · Institution of Mechanical Engineers - IMechE · Query: high performance computing data center cooling workshop
Open on YouTubeSAVE YOURSELF AS A DCIM ENGINEER #dcim #controls #datacentermanagement #datacenter
专家讲座 · Timothy Hobbs · Query: data center thermal management seminar
Open on YouTubeAdvanced Fabrics, Ethernet and the Future of AI Infrastructure
专家圆桌 · 650 Group (650 Group) · Query: AI infrastructure datacenter panel discussion
Open on YouTubeData Center 101: Single-Phase Immersion Cooling
专家讲座 · GIGABYTE · Query: data center thermal management seminar
Open on YouTubeData Center Cooling - A thermal efficiency approach
专家讲座 · Anixter · Query: data center thermal management seminar
Open on YouTubeEnergy Efficiency of Data Centers
学术讲座 · Institute for Systems Research · Query: IEEE data center energy efficiency lecture
Open on YouTubeUnderstanding data centre electricity use
专家讲座 · IEA Webinars · Query: AI datacenter power grid university lecture
Open on YouTubeSources
Collection notes
- 公开 RSS/Atom：Data Center Dynamics：检索失败，原因：fetch failed
- 公开 RSS/Atom：The Register：检索失败，原因：fetch failed
- 公开 RSS/Atom：ServeTheHome：检索失败，原因：fetch failed
- 公开 RSS/Atom：Data Center Knowledge：检索失败，原因：fetch failed
- 公开 RSS/Atom：HPCwire：检索失败，原因：fetch failed
- 公开 RSS/Atom：NVIDIA Blog：检索失败，原因：fetch failed
- 论文池：已从本地论文池读取 21 条候选；池更新时间 2026-09-11 14:34。
- YouTube：检索失败，原因：fetch failed
- 视频推荐：当日未形成新候选，按上一日排序池顺延补位。
- When optional automation services are unavailable, this page uses traceable public sources and conservative rule-based summaries only; unverifiable facts are not filled in.