Learning to run a power network challenge for training topology controllers

Source

• Raw Markdown: l2rpn-topology-controllers-2020
• Rendered / retrieved PDF: paper_l2rpn-topology-controllers-2020.pdf
• External source: https://arxiv.org/abs/1912.04211
• Official L2RPN reference list: https://l2rpn.chalearn.org/papers-references

Publication And Credibility

• Paper date: 2019-12-05.
• Venue/status: PSCC 2020 reference; arXiv preprint available.
• Credibility: Credible challenge paper from the RTE/ChaLearn lineage. Older than one year; used as a benchmark-design and controller-training source.

Core Claim

The paper describes the earlier L2RPN topology-controller challenge and its framing of grid operation as sequential decision-making.

L2RPN / Grid2Op Notes

It establishes the basic observation/action/reward loop that later Grid2Op and L2RPN competitions expand: agents observe grid state and scenario context, choose topology actions, and are scored by maintaining safe operation.

Action-Time-Series Notes

This source is useful when Grid2Op is treated as an action-conditioned graph time-series environment:

power-grid observations + topology / redispatch / storage control input + scenario context
  -> next grid observations + safety/cost outcome

The terminology distinction matters. Topology changes, redispatching, curtailment, and storage commands are actions or control inputs when an agent chooses them. Line failures, maintenance outages, weather-driven renewable shifts, and demand variation are events or exogenous variables unless they are deliberately controlled by the experimenter.

Foundation TSFM Relevance

Agenda slot	Verdict	Evidence	Missing pieces
Causal structure, counterfactuals, and control	partially closes	Good local bridge between simulator environment design and action-conditioned model evaluation.	It predates later large-scale challenge tracks and does not by itself define current L2RPN practice.
Context interface: topology and channel context	partially closes	Power-grid state is naturally graph-structured and tied to physical assets, limits, and scenario metadata.	Needs a reusable schema that a general TSFM can consume across grids and non-grid operational systems.
Benchmark level	adjacent	L2RPN/Grid2Op provides simulator-backed trajectories with explicit controls and outcomes.	TSFM-ready comparisons require pinned environment versions, action sets, reward definitions, and train/test scenario splits.

Links Into The Wiki

• Grid2Op
• Action-Conditioned Time-Series Datasets
• Causal Time Series
• Time-Series Benchmark Hygiene
• Expert System for topological remedial action discovery in smart grids
• World Models
• Foundation Time-Series Model Research Agenda