The rapid growth of artificial intelligence workloads is accelerating the expansion and grid interconnection of data centers (DCs). Existing data center load accommodation (DCLA) assessments primarily focus on grid and resource adequacy and often imply that greater workload flexibility always increases accommodable capacity. However, workload flexibility has a dual effect. Workload deferral and temporal shifting can alleviate network congestion, whereas synchronized checkpointing of training workloads can cause large and rapid load reductions, threatening frequency stability. Therefore, DCLA cannot be determined solely by grid adequacy. This paper develops an optimal DCLA method that jointly accounts for workload quality of service (QoS), checkpoint-induced frequency security (FS), and grid adequacy. First, a QoS-aware model characterizes workload-dependent flexibility while ensuring service feasibility. Second, checkpoint-induced FS constraints are developed for periodic and event-triggered power variations, with key frequency-security limits reformulated in algebraic form. Third, a two-stage lexicographic model is developed to maximize DCLA and minimizes the required energy storage (ES) deployment, and then optimizes system operation under the given DC and ES siting and sizing decisions. Case studies show that the proposed method avoids a 40.3% overestimation of DCLA compared with the grid-adequacy benchmark. QoS is the primary limiting factor, while checkpoint-induced frequency-security constraints become more restrictive as training workloads increase. These findings highlight that reliable DCLA should account for both its grid-support value and the associated QoS and FS risks.
Transmission network security can substantially alter where large-scale data centers can connect and how much workload flexibility can unlock. This paper develops a hosting-capacity framework that couples computing demand, batch workload scheduling, and N-1 security constraints. A modified IEEE 118-bus case study revea...
Jia-Kai Wu, Peng-Yu Ren, Yi-Fan Wang et al.· 0 citations
The growing demand for edge computing, content delivery, and AI services is driving the interconnection of edge data centers (DCs) with distribution networks. Before interconnection, utilities evaluate how much DC capacity can be accommodated without violating feeder current and voltage limits. Fixed peak load represen...
Lin-Han Fang, Hao Wan, Anurag K. Srivastava et al.· 0 citations
Numerical results demonstrate that workload temporal shifting can provide quantifiable and grid-compatible demand flexibility for AI data centers with limited disruption to computing workloads.
Sun-Tao Su, Liang Du, Sheng-Yi Wang· arXiv.org· 0 citations
Grid connection constraints increasingly limit the expansion of AI data centers, yet the additional hosting capacity enabled by computational workload flexibility remains insufficiently quantified. This paper develops a two-stage electricity--computation co-optimization framework to quantify the individual and coordina...
Jia-Kai Wu, Wei Sun, Peng-Yu Ren et al.· 0 citations
The rapid proliferation of cloud computing and artificial intelligence workloads is fundamentally reshaping the magnitude, spatial concentration, and electrical characteristics of data center power demand. Data centers differ from conventional commercial loads because they combine high rack densities, converter-dominat...
Bibek Dhakal, Manohar Chamana, Biswambhar Gayen et al.· 0 citations
Multi-tenant data center (DC) facilities rent computing capacity on demand, placing controllable load within reach of anyone willing to pay for it. This paper considers a stealthy adversary who rents workstations and runs deliberately unoptimized large language model (LLM) training, synchronizing their consumption into...
Zaint A. Alexakis, Li Zhou, S. Krishnan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.