Papers for

it infrastructure planners

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Ai predicts data center heat to improve cooling and design

AI-driven Thermal-aware Data Center Capacity Planning

Abstract: The emerging of large language models (LLMs) has posed significant challenges to the thermal management of data center. Intense GPU computation for LLMs results in localized hotspots. Moreover, spiking thermal loads during training and inference bursts make real-time cooling response more difficult to predict and control. Thermal-aware capacity planning of data center requires massive expensive high-fidelity CFD simulations. AI models can perform real-time prediction for unseen designs. However, existing works either have large prediction error, or have over-simplified assumptions for data center operations. This work presents an AI-driven framework that can perform thermal-aware capacity planning for a real-world data center in seconds. The embedded AI model learns from numerous key parameters (rack power, server power, server placement, HVAC settings etc.), and provides temperature prediction within milliseconds. This AI model is tested against high-fidelity CFD simulations, and results show that for unseen data center designs, model can achieve high accuracy with 10000X speedup. Driven by the AI model, the authors design the thermal-aware capacity planning framework. This framework can help data center designers and operators instantaneously optimize both workload distribution and HVAC cooling efficiency.

Thu 1 OctMachine Learning
The gist
Data centers that run big AI models use a lot of power and create hot spots, which are tricky to cool efficiently. The authors created an AI system that quickly predicts how hot different parts of a data center will get based on many factors like server layout and cooling settings. This new system matches the accuracy of slow, detailed simulations but runs thousands of times faster. Because it works so quickly and accurately, data center managers can instantly find better ways to distribute work and manage cooling.
Open → 2610.02442v1

Faster method improves shortest paths in weighted undirected graphs

A Faster Undirected Single-Source Shortest Path Algorithm

Abstract: The single-source shortest paths (SSSP) problem in graphs with non-negative edge weights is one of the most classic problems in algorithms. For decades, the best known running time in the comparison-addition model was the $O(m+n\log n)$ bound of Dijkstra's algorithm with Fibonacci heaps. Recently, Duan, Mao, Shu, and Yin (FOCS'23) gave a randomized $O(m\log^{1/2} n \log\log^{1/2} n)$-time algorithm for SSSP in weighted undirected graphs. For weighted directed graphs, Duan, Mao, Mao, Shu, and Yin (STOC'25) gave an $O(m\log^{2/3} n)$-time algorithm for SSSP. Very recently, Duan, Mao, Shu, and Yin (ICALP'26) obtained an algorithm for directed graphs whose running time matches the $O(m\log^{1/2} n \log\log^{1/2} n)$ time of the undirected case. In this paper, we present a faster algorithm for SSSP in weighted undirected graphs, giving the first improvement in running time since the FOCS'23 breakthrough of Duan, Mao, Shu, and Yin. Our algorithm runs in $O(m\log^{1/2} n \log\log^{1/4} n \log\log\log^{1/4} n)$ time, improving the previous running time by a factor of $(\frac{\log\log n}{\log\log\log n})^{1/4}$. Our main contribution is a simple and efficient tool that computes, for every vertex, its distance to the nearest vertex in a random sample; this tool may be of independent interest.

Mon 14 SeptData Structures and Algorithms
The gist
Finding the shortest path from one point to all others in a network with weighted connections is a common problem in computer science. Previously, faster methods than the classic algorithm only appeared recently. The authors present an even quicker way to find these shortest paths in networks where connections have weights and directions don’t matter. Their key new idea is a simple tool that quickly finds the closest special points to every location in the network. This improvement speeds up the overall process by a small but meaningful amount.
Open → 2609.15247v1