Optimization of computational budget for power system risk assessment

Source

• Raw Markdown: power-system-risk-assessment-2018
• Rendered / retrieved PDF: paper_power-system-risk-assessment-2018.pdf
• External source: https://arxiv.org/abs/1805.01174
• Official L2RPN reference list: https://l2rpn.chalearn.org/papers-references

Publication And Credibility

• Paper date: 2018-05-03.
• Venue/status: ISGT Europe 2018; arXiv preprint available.
• Credibility: Historical power-system ML source from the L2RPN lineage; older than one year and used as risk-assessment background.

Core Claim

The paper studies how to allocate limited simulator calls when estimating power-system risk across contingencies.

L2RPN / Grid2Op Notes

It separates cheap learned approximations from expensive physical simulations, a pattern that reappears in world-model planning and learned surrogate evaluation.

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	adjacent	Relevant to TSFM evaluation because learned proxy estimates and physical-simulator calls can have different cost/fidelity profiles.	It optimizes risk-estimation budget, not a full action-conditioned dynamics model or policy.
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
• Time-Series Benchmark Hygiene
• World Models
• Foundation Time-Series Model Research Agenda
• Fast Power system security analysis with Guided Dropout
• Anticipating contingengies in power grids using fast neural net screening