Research connecting computing, power and thermal management

In this paper, we consider the expansion of power grids under emerging large loads from data centers and electrified manufacturing. We develop a multi-period grid capacity expansion model to determine optimal investment profiles for power generation, storage, and transmission capacity while accounting for hourly power dispatch, such that electricity demand is satisfied and the total planning and operation cost is minimized. We also propose a new modeling approach regarding the spatial distribution of demand from large loads. The model is used to analyze the expansion of a synthetic grid that follows key characteristics of the ERCOT system over a seven-year planning horizon, under loads from data centers and electrified oil refining, which account for 17.5% and 4.7% of total annual electricity demand by the end of the planning horizon. The optimal investment policy leads to an 83.6% increase in generation capacity and exploits the short construction times of solar and storage as well as the operational flexibility of thermal generators. Finally, sensitivity analysis reveals that the construction time of grid assets substantially impacts investment timing, generation technology mix, and transmission capacity expansion. The proposed modeling framework is general and can be extended to other grid systems, enabling the exploration of diverse demand scenarios, policy assumptions, and regional characteristics.

At global scale, data-center electricity demand is growing faster than the grids that supply it, while system operators increasingly require large flexible loads that can adjust power within seconds to absorb variable wind and solar generation. For multi-megawatt AI/HPC facilities, the key unresolved question is practical and measurable: how quickly can the software stack translate a grid request into a real change in GPU power at the facility meter, where commitments are settled? We answer this on real hardware with GridPilot, a three-tier predictive controller operating across milliseconds, seconds, and hours, augmented by a deterministic safety-island bypass for fast response. On a three-GPU NVIDIA V100 testbed, GridPilot achieves a measured end-to-end trigger-to-target response of 97.2 ms, which is 6.9x faster than the 700 ms requirement of Nordic Fast Frequency Reserve. We further incorporate an instantaneous Power Usage Effectiveness (PUE) correction so dispatched commitments remain robust at meter level rather than only at IT load level. In replay experiments across six representative European grids (from Sweden to Poland), the PUE-aware controller closes 2.5-5.8 percentage points of cooling-overhead drag. GridPilot is released as open source and serves as a proof of concept that MW-scale AI/HPC demand can be engineered as controllable, grid-responsive flexibility by design.

High-Performance Computing (HPC) has recently entered the Exascale era, and considerable efforts are being made to fully harness this potential power for large-scale applications, such as cutting-edge generative AI (training and exploitation). The corresponding energy consumption is very high, and forecasts are alarming, making this metric a critical systemic bottleneck. Addressing this issue presents a genuine challenge for the entire cloud-edge-HPC continuum at all scales, from low-power IoT microcontrollers to multi-megawatt data centers. Beyond financial costs, green computing is driven by considerations related to climate change and environmental concerns such as carbon footprint ($CO_2e$), as well as constraints on energy production and supply, leading to a real need to regulate {\em information and communication technology} (ICT) activities. This article presents a comprehensive overview of energy-efficient computing, taking into account the most recent and significant contributions. Based on this exploration of the state of the art, we design and describe a holistic taxonomy of the aforementioned publications, structured around various perspectives, including {\em hardware and software aspects, measurement instrumentation, software optimizations, dynamic task scheduling, voltage scaling, workload consolidation, federated learning}, and {\em cooling}. Particular emphasis is placed on large-scale AI, which receives significant attention due to its considerable resource requirements. We conclude with an analysis of a forward-looking roadmap that considers the main perspectives of sustainable computing.

The rapid scaling of large language model training requires distributing GPU resources across multiple data center buildings and regions. We refer to such paradigm as "scale-across" training. As infrastructure expands, the system design space becomes increasingly intricate, encompassing new model architectures, hardware heterogeneity, and evolving communication patterns. Drawing from Meta's production experience, we highlight the complexities of deploying training jobs across a few data centers housing hundreds of thousands of GPUs. To accelerate exploration of the large design space and to enable efficient training for frontier model development, we conduct in-depth characterization of three key design dimensions: parallelism placement, parallelism scheduling, and network layer technologies. We then propose ScaleAcross Explorer, an optimizer that considers the interplay of design dimensions and holistically optimizes scale-across training. Testbed experiments and simulations demonstrate up to 64.62% training speedups over production configuration and up to 37.59% training speedups over the state-of-the-art baseline across a wide range of design points.

Liquid-cooled exascale supercomputers dissipate heat through cooling plants organized as multiple parallel subloops, but how to allocate coolant distribution units (CDUs) across subloops and how to distribute flow among them has not been systematically addressed for facilities at this scale. This paper presents a three-layer optimization framework that jointly determines the integer partition of CDUs across subloops, the continuous flow fraction allocation, and the per-timestep co-design optimization of total flow rate and supply temperature subject to per-subloop thermal safety constraints. The Modelica simulation model is built based on the data of Frontier exascale supercomputer at Oak Ridge National Laboratory. By developing a reduced-order surrogate model, all 611 feasible partitions of 25 CDUs are evaluated across the full year operational dataset of 49,353 timesteps. Three progressively richer operational strategies are compared, ranging from flow control optimization to full three-layer co-design optimization with dynamically adjusted flow fractions. The globally optimal design is a two-subloop plant achieving 35.48% annual cooling energy savings, only 0.18% above the current three-subloop Frontier design at 35.30%. Flow fraction optimization is shown to compensate for any feasible CDU-to-subloop assignment, reducing the design sensitivity by 93% and providing a low-cost software-only pathway to near-optimal performance on the existing Frontier hardware. The framework is transferable to other liquid-cooled high-performance computing plants.

Emerging connect-and-manage practices allow new transmission-connected mega-loads to connect while enforcing time-varying admissible power exchange limits at the point of common coupling (PCC) in real time. Hyperscale artificial intelligence data centers (AIDCs), whose demand can reach hundreds of megawatts and whose internal computing-cooling dynamics evolve rapidly, can therefore face frequent conflicts between workload continuity requirements and externally imposed PCC envelopes. This paper proposes a battery-assisted operational framework in which on-site battery energy storage (BESS) serves as a physical buffering interface to reconcile fast internal dynamics with time-varying interconnection limits. A continuity-aware energy-computation model is developed to jointly capture checkpoint-constrained AI training workloads, information technology (IT) computing power-throughput characteristics, and IT-cooling thermal dynamics. A two-stage decision framework is then formulated, consisting of scenario-based day-ahead workload commitment and a real-time receding-horizon delivery assurance controller that enforces battery, thermal, and grid-interaction constraints. Case studies on the IEEE 39-bus system with Australian real data demonstrate that BESS substantially increases credible day-ahead workload commitment and improves real-time delivery robustness under transmission congestion. Sensitivity analyses further reveal a regime-dependent role transition of BESS -- from feasibility-oriented continuity support when PCC limits are binding to economy-driven flexibility provision as transmission constraints are relaxed.

The rapid growth of foundation model training and large-scale AI services has driven ground data centers toward unprecedented power densities, intensifying challenges in energy supply, cooling, and spatial scalability. Space Data Centers (SDCs) have emerged as a promising paradigm for hosting energy-intensive computing infrastructures in orbit, leveraging continuous solar energy and radiative cooling advantages. However, unlike ground facilities primarily constrained by power and site availability, SDCs are fundamentally limited by communication capability. The gap between petabit-scale internal data exchange in ground data centers and the gigabit-scale capacity of ground-space links forms a critical bottleneck. This article systematically analyzes communication constraints in SDC architectures and explores semantic communication as a key enabling paradigm. By transmitting compact, task-relevant semantic representations instead of raw data, uplink pressure can be substantially reduced. The feasibility of communication-efficient orbital AI infrastructures is demonstrated through the evaluation of a multi-layer heterogeneous SDC framework consisting of relay satellites and orbital computing nodes operating under coupled energy and thermal constraints. The article further outlines open research challenges toward scalable deployment.

LLM inference is still evaluated mainly as a model or software problem: accuracy, latency, throughput, and hardware utilization. This is incomplete. At deployment scale, the relevant output is a quality-conditioned token produced under joint constraints from effective compute, delivered data-center power, cooling capacity, PUE, and utilization. We argue that the ML community should treat inference as \emph{energy-to-token production}. We formalize this view with a dimensionally consistent Token Production Function in which token rate is bounded by both compute-per-token and energy-per-token ceilings. Listed API prices vary by over an order of magnitude across providers, but we use price dispersion only as directional motivation, not as causal evidence of marginal cost. The core physical question is instead: under fixed quality and service targets, when does the binding constraint move from theoretical peak compute toward delivered power, cooling, and operational efficiency? Under this framing, system optimizations -- latent KV-cache compression, sparse or heavily compressed attention, quantization, routing, and difficulty-adaptive reasoning -- are not merely local engineering tricks. They are energy-to-token levers because they reduce FLOPs/token, joules/token, memory traffic, or utilization losses under fixed $(q^{*},s^{*})$. We therefore call for inference papers and benchmarks to report Joules/token, active binding constraint, PUE-adjusted delivered power, and utilization-adjusted token output alongside accuracy and latency.