# LOOP-MAC: Learning-Based Multi-Agent Coordination with Guaranteed Local Feasibility in a Virtual Power Plant

arXiv: https://arxiv.org/abs/2310.17882 · HTML: https://mlsanity.com/paper/2310.17882/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 53 references that are in the map.
- First posted on arXiv 27 Oct 2023.

## Builds on (most cited first, 8 of 8)

- [Learning to Solve Optimization Problems with Hard Linear Constraints](https://mlsanity.com/paper/2208.10611/) (2022)
- [Incentivizing Energy Trading for Interconnected Microgrids](https://mlsanity.com/paper/1609.07576/) (2016)
- [Learning Regionally Decentralized AC Optimal Power Flows with ADMM](https://mlsanity.com/paper/2205.03787/) (2022)
- [Empowering Distributed Solutions in Renewable Energy Systems and Grid Optimization](https://mlsanity.com/paper/2310.15468/) (2023)
- [Distributed coordination of DERs with storage for dynamic economic dispatch](https://mlsanity.com/paper/1605.00721/) (2016)
- [The Powerful Use of AI in the Energy Sector: Intelligent Forecasting](https://mlsanity.com/paper/2111.02026/) (2021)
- [Leveraging Predictions in Power System Frequency Control: an Adaptive Approach](https://mlsanity.com/paper/2305.12044/) (2023)
- [Coordinating Distributed Energy Resources for Reliability can Significantly Reduce Future Distribution Grid Upgrades and Peak Load](https://mlsanity.com/paper/2306.08717/) (2023)

## Abstract (arXiv)

By aggregating distributed energy resources (DERs) into a single dispatchable resource, virtual power plants (VPPs) enable the grid to use the flexibility of numerous small-scale DERs. Delivering an aggregate VPP commitment requires multi-agent coordination, where agents manage local DER models and operating constraints while jointly meeting a power commitment within limited communication rounds. Classical distributed optimization is computationally intensive, requiring iterative local optimization and repeated communication to reach consensus. Learning-based methods can accelerate coordination but often lack guarantees of local feasibility and accurate commitment tracking. This paper proposes LOOP-MAC (Learning to Optimize the Optimization Process for Multi-Agent Coordination), a fully decentralized learning-based framework that ensures local feasibility by construction while efficiently reducing the aggregate commitment gap. LOOP-MAC employs a two-stage decision process. Learned coordination uses neural optimizers equipped with a gauge layer to produce locally feasible schedules through a few rounds of message exchange. Local adjustment then rebalances each schedule toward feasible flexibility extremes using a commitment-gap estimate inferred from messages already received. The adjusted schedule remains locally feasible as a convex combination of feasible schedules, and the adjustment requires no additional communication round. On a 100-agent VPP, five communication rounds followed by local adjustment reduce the mean commitment gap from 5.1% to 0.75% of the agents' aggregate absolute power and the optimality gap from 3.93% to 3.07% relative to learned coordination alone. Per-agent online computation takes approximately 1.1 ms, including the adjustment.