AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework

TL;DR

This paper develops a framework to analyze how geo-distributed AI inference can shift electricity demand geographically, balancing latency constraints with energy and carbon efficiency.

Contribution

It introduces a novel energy-geography model for inference placement, operational metrics, and a stylized simulation demonstrating the impact of latency and migration frictions.

Findings

Latency relaxation broadens feasible geographic regions for inference.

Migration frictions and legal constraints significantly limit relocation benefits.

Heterogeneous latency tolerance divides workloads into local, regional, and energy-focused layers.

Abstract

AI inference is becoming a persistent and geographically distributed source of electricity demand. Unlike many traditional electrical loads, inference workloads can sometimes be executed away from the user-facing service location, provided that latency, state locality, capacity, and regulatory constraints remain acceptable. This paper studies when such digital relocation of computation can be interpreted as latency-constrained relocation of electricity demand. We develop an energy-geography framework for geo-distributed AI inference. The framework models a three-layer architecture of clients, service nodes, and compute nodes, and formulates inference placement as a constrained optimization problem over electricity prices, marginal carbon intensity, power usage effectiveness, compute capacity, network latency, and migration frictions. The key object is the energy-latency frontier: the marginal cost and carbon benefit unlocked by relaxing inference latency budgets. The paper makes four contributions. First, it distinguishes physical electricity transmission from digital relocation of electricity-consuming computation. Second, it formulates a geo-distributed inference placement model with feasibility masks and migration frictions. Third, it introduces operational metrics, including relocatable inference demand, energy return on latency, carbon return on latency, and a relocation break-even condition. Fourth, it provides a transparent stylized simulation over representative global compute regions to show how heterogeneous latency tolerance separates workloads into local, regional, and energy-oriented execution layers. The results show that latency relaxation expands feasible geography, while migration frictions, egress costs, state locality, legal constraints, and capacity limits can sharply reduce realized benefits.