LEAP Nets for System Identification and Application to Power Systems

Source

Publication And Credibility

  • Paper date: 2020.
  • Venue/status: Neurocomputing, DOI 10.1016/j.neucom.2019.12.135; HAL metadata retrieved.
  • Credibility: Peer-reviewed journal paper by the LEAP/Grid2Op lineage team. The HAL PDF endpoint returned an HTML access challenge from this environment, so the raw record is metadata and abstract only.

Core Claim

The paper extends LEAP nets to system identification for continuous multivariate systems whose structure changes around an operating point.

L2RPN / Grid2Op Notes

HAL metadata describes structural actionable variables, rare or unseen structural changes, and application to transmission grids where lines can disconnect or reconnect.

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 slotVerdictEvidenceMissing pieces
Causal structure, counterfactuals, and controlpartially closesUseful as representation evidence for structural context and topology-changing dynamics in power-grid time series.The full PDF was not retrieved locally; conclusions should be treated as metadata/abstract-level until the PDF is available.
Context interface: topology and channel contextpartially closesPower-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 leveladjacentL2RPN/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.