Grid-Oriented Probabilistic Load Forecasting for AI Data Centers

Classés selon la proximité de leur titre et de leur résumé avec ceux de cet article. Sélectionnez-en pour les lire ensemble.

Les articles les plus proches

1. Proche Autre approche du problème Pas pertinent

   Probabilistic Load Forecasting via Point Forecast Feature Integration

   Qicheng Chang, Yishen Wang, Xiao Lu et al. · 2019 · Machine Learning · cité 10 fois · Résumé IA disponible

   Probabilistic Load Forecasting via Point Forecast Feature Integration prédit la charge électrique avec une méthode en deux étapes, tandis que l’article évalue aussi calibration et scénarios temporels pour les centres IA.

   Résumé scientifique

   Short-term load forecasting is a critical element of power systems energy management systems. In recent years, probabilistic load forecasting (PLF) has gained increased attention for its ability to provide uncertainty information that helps to improve the reliability and economics of system operation performances. This paper proposes a two-stage probabilistic load forecasting framework by integrating point forecast as a key probabilistic forecasting feature into PLF. In the first stage, all related features are utilized to train a point forecast model and also obtain the feature importance. In the second stage the forecasting model is trained, taking into consideration point forecast feature…

2. Proche Contexte plus large Pas pertinent

   Benchmarking CPU, GPU, and ML Power-Flow Solvers from 14 to 70,000 Buses

   Benjamin Donnot, Sami Tazi, Eva Boguslawski et al. · 2026 · Distributed, Parallel, and Cluster Computing · Résumé IA disponible

   Benchmarking CPU, GPU, and ML Power-Flow Solvers compare des solveurs de flux de puissance sur différents réseaux, sans étudier les prévisions de charge des centres de données.

   En bref

   Sur les cas étudiés, des solveurs physiques CPU parallélisés ou GPU égalent ou dépassent le débit des substituts neuronaux évalués, avec une précision nettement supérieure.

3. Proche Contexte plus large Pas pertinent

   DxPU: Large Scale Disaggregated GPU Pools in the Datacenter

   Bowen He, Xiao Zheng, Yuan Chen et al. · 2023 · Distributed, Parallel, and Cluster Computing · cité 18 fois · Résumé IA disponible

   DxPU étudie la mise en pool et l’allocation de GPU dans les centres de données, plutôt que la prévision de leur consommation électrique.

   Résumé scientifique

   The rapid adoption of AI and convenience offered by cloud services have resulted in the growing demands for GPUs in the cloud. Generally, GPUs are physically attached to host servers as PCIe devices. However, the fixed assembly combination of host servers and GPUs is extremely inefficient in resource utilization, upgrade, and maintenance. Due to these issues, the GPU disaggregation technique has been proposed to decouple GPUs from host servers. It aggregates GPUs into a pool, and allocates GPU node(s) according to user demands. However, existing GPU disaggregation systems have flaws in software-hardware compatibility, disaggregation scope, and capacity. In this paper, we present a new implem…

4. Proche Contexte plus large Pas pertinent

   Matching Workloads to Blackwell: Power-Resolved Benchmarking of NVIDIA B200 and B300 across HPC and AI Workloads

   Mohsen Zand, Trung Dac Nguyen, H. Birali Runesha · 2026 · Distributed, Parallel, and Cluster Computing · Résumé IA disponible

   Matching Workloads to Blackwell mesure les performances et la puissance de GPU sur des charges IA et HPC, sans prévoir la demande électrique du centre.

   En bref

   Le B300 ne surpasse pas uniformément le B200 : ses performances dépendent de la charge, de la précision numérique et de la maturité logicielle.

5. Apparenté Autre approche du problème Pas pertinent

   Electricity Demand Forecasting with Hybrid Statistical and Machine Learning Algorithms: Case Study of Ukraine

   Tatiana Gonzalez Grandon, Johannes Schwenzer, Thomas Steens et al. · 2023 · Machine Learning · preprint, non relu par les pairs · cité 6 fois · Résumé IA disponible

   Electricity Demand Forecasting with Hybrid Statistical and Machine Learning Algorithms prévoit la demande électrique nationale ukrainienne à partir de données horaires, avec une approche hybride.

   Résumé scientifique

   This article presents a novel hybrid approach using statistics and machine learning to forecast the national demand of electricity. As investment and operation of future energy systems require long-term electricity demand forecasts with hourly resolution, our mathematical model fills a gap in energy forecasting. The proposed methodology was constructed using hourly data from Ukraine's electricity consumption ranging from 2013 to 2020. To this end, we analysed the underlying structure of the hourly, daily and yearly time series of electricity consumption. The long-term yearly trend is evaluated using macroeconomic regression analysis. The mid-term model integrates temperature and calendar reg…

6. Apparenté Contexte plus large Pas pertinent

   Not All GPUs Are Created Equal: Characterizing Variability in Large-Scale, Accelerator-Rich Systems

   Prasoon Sinha, Akhil Guliani, Rutwik Jain et al. · 2022 · Distributed, Parallel, and Cluster Computing · cité 47 fois · Pas encore résumé

   Not All GPUs Are Created Equal caractérise la variabilité des accélérateurs dans les grands systèmes, tandis que l’article prévoit la charge électrique d’un cluster GPU.

   Résumé scientifique

   Scientists are increasingly exploring and utilizing the massive parallelism of general-purpose accelerators such as GPUs for scientific breakthroughs. As a result, datacenters, hyperscalers, national computing centers, and supercomputers have procured hardware to support this evolving application paradigm. These systems contain hundreds to tens of thousands of accelerators, enabling peta- and exa-scale levels of compute for scientific workloads. Recent work demonstrated that power management (PM) can impact application performance in CPU-based HPC systems, even when machines have the same architecture and SKU (stock keeping unit). This variation occurs due to manufacturing variability and th…

7. Apparenté Autre approche du problème Pas pertinent

   TimeGPT in Load Forecasting: A Large Time Series Model Perspective

   Wenlong Liao, Fernando Porte-Agel, Jiannong Fang et al. · 2024 · Machine Learning · cité 92 fois · Pas encore résumé

   TimeGPT in Load Forecasting examine un modèle de séries temporelles pour prévoir la charge lorsque les données historiques sont rares, sans traiter calibration ni dimensionnement des réserves.

   Résumé scientifique

   Machine learning models have made significant progress in load forecasting, but their forecast accuracy is limited in cases where historical load data is scarce. Inspired by the outstanding performance of large language models (LLMs) in computer vision and natural language processing, this paper aims to discuss the potential of large time series models in load forecasting with scarce historical data. Specifically, the large time series model is constructed as a time series generative pre-trained transformer (TimeGPT), which is trained on massive and diverse time series datasets consisting of 100 billion data points (e.g., finance, transportation, banking, web traffic, weather, energy, health…

8. Apparenté Contexte plus large Pas pertinent

   A hybrid-model approach for reducing the performance gap in building energy forecasting

   Xia Chen, Tong Guo, Martin Kriegel et al. · 2022 · Advanced Engineering Informatics 52 (2022): 101627 · cité 39 fois · Résumé IA disponible

   A hybrid-model approach for reducing the performance gap in building energy forecasting combine simulation physique et apprentissage automatique pour prévoir la consommation énergétique des bâtiments.

   Résumé scientifique

   The performance gap between predicted and actual energy consumption in the building domain remains an unsolved problem in practice. The gap exists differently in both current mainstream methods: the first-principles model and the machine learning (ML) model. Inspired by the concept of time-series decomposition to identify different uncertainties, we proposed a hybrid-model approach by combining both methods to minimize this gap: 1. Use the first-principles method as an encoding tool to convert the building static features and predictable patterns in time-series simulation results; 2. The ML method combines the results as extra inputs with historical records simultaneously, trains the model t…