Expert System for topological remedial action discovery in smart grids

Source

• Raw Markdown: expert-system-remedial-action-discovery-2018
• Rendered / retrieved PDF: paper_expert-system-remedial-action-discovery-2018.pdf
• External source: https://hal.science/hal-01897931
• Official L2RPN reference list: https://l2rpn.chalearn.org/papers-references

Publication And Credibility

• Paper date: 2018-11-12.
• Venue/status: MedPower 2018; HAL PDF retrieved.
• Credibility: Conference paper in the L2RPN/RTE lineage with HAL PDF retrieved locally. Older than one year; use as expert-system and remedial-action lineage.

Core Claim

The paper studies an expert-system approach for discovering topological remedial actions in smart grids.

L2RPN / Grid2Op Notes

It is relevant because it exposes an action-discovery framing before deep RL challenge agents became the dominant L2RPN narrative.

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	Useful baseline context for comparing learned action proposal against rule/expert search.	Expert-system action discovery is not a general learned transition model and may encode domain assumptions manually.
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
• World Models
• Foundation Time-Series Model Research Agenda
• Introducing machine learning for power system operation support
• Guided Machine Learning for power grid segmentation
• Learning to run a power network challenge for training topology controllers