# OpenG2G: A Simulation Platform for AI Datacenter-Grid Runtime Coordination

arXiv: https://arxiv.org/abs/2605.05519 · HTML: https://mlsanity.com/paper/2605.05519/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 48 references that are in the map.
- First posted on arXiv 6 May 2026.

## Builds on (most cited first, 22 of 22)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization](https://mlsanity.com/paper/2505.06371/) (2025)
- [Measuring the environmental impact of delivering AI at Google Scale](https://mlsanity.com/paper/2508.15734/) (2025)
- [MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI](https://mlsanity.com/paper/2410.12032/) (2024)
- [Electricity Demand and Grid Impacts of AI Data Centers: Challenges and Prospects](https://mlsanity.com/paper/2509.07218/) (2025)
- [PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems](https://mlsanity.com/paper/2109.03970/) (2021)
- [Where Do the Joules Go? Diagnosing Inference Energy Consumption](https://mlsanity.com/paper/2601.22076/) (2026)
- [Optimization Algorithms as Robust Feedback Controllers](https://mlsanity.com/paper/2103.11329/) (2021)
- [RL2Grid: Benchmarking Reinforcement Learning in Power Grid Operations](https://mlsanity.com/paper/2503.23101/) (2025)
- [SustainDC: Benchmarking for Sustainable Data Center Control](https://mlsanity.com/paper/2408.07841/) (2024)
- [Learning the Optimal Power Flow: Environment Design Matters](https://mlsanity.com/paper/2403.17831/) (2024)
- [PyDCM: Custom Data Center Models with Reinforcement Learning for Sustainability](https://mlsanity.com/paper/2310.03906/) (2023)
- [Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training](https://mlsanity.com/paper/2601.17654/) (2026)
- [Real-Time Feedback-Based Optimization of Distribution Grids: A Unified Approach](https://mlsanity.com/paper/1711.01627/) (2017)
- [Agent Coordination via Contextual Regression (AgentCONCUR) for Data Center Flexibility](https://mlsanity.com/paper/2309.16792/) (2023)
- [Enhancing Data Center Low-Voltage Ride-Through](https://mlsanity.com/paper/2510.03867/) (2025)
- [GPU-to-Grid: Voltage Regulation via GPU Utilization Control](https://mlsanity.com/paper/2602.05116/) (2026)
- [Voltage Regulation in Distribution Systems with Data Center Loads](https://mlsanity.com/paper/2507.06416/) (2025)

## Abstract (arXiv)

AI's growing compute demand and new datacenter buildouts present major capacity and reliability challenges for the electricity grid, leading to multi-year interconnection delays for new datacenters and bottlenecking AI growth. To ease this strain, datacenters increasingly offer rapid power flexibility in response to grid signals, where the datacenter can increase or decrease its power consumption by adapting its workload in real time. In order to understand the impact of large datacenters on the grid and to facilitate the design of effective coordination strategies, we build OpenG2G, a simulation platform for AI datacenter-grid runtime coordination. We show that OpenG2G is capable of answering a wide range of coordination questions by allowing users to implement and compare various control paradigms (including classic, optimization, and learning-based controllers), and quantify how AI model and deployment choices affect datacenter flexibility and coordination outcomes. This versatility is enabled by OpenG2G's modular and extensible architecture: a datacenter backend driven by real measurements of production-grade AI services, a grid backend built on high-fidelity grid simulators, and a generic controller interface that closes the loop between them. We describe the design of OpenG2G and demonstrate its usefulness through realistic grid scenarios and AI workloads.