machine learning for the grid
play

Machine Learning for the Grid D. Deka, S. Backhaus & M. Chertkov - PowerPoint PPT Presentation

Slide 1 Machine Learning for the Grid D. Deka, S. Backhaus & M. Chertkov + A. Lokhov, S. Misra, M. Vuffray and K. Dvijotham DOE/OE & LANL (Grid Science) + GMLC (1.4.9 + 2.0) UNCLASSIFIED Operated by Los Alamos National Security, LLC


  1. Slide 1 Machine Learning for the Grid D. Deka, S. Backhaus & M. Chertkov + A. Lokhov, S. Misra, M. Vuffray and K. Dvijotham DOE/OE & LANL (Grid Science) + GMLC (1.4.9 + 2.0) UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  2. Slide 2 D.Deka S. Backhaus A. Lokhov M. Vuffray S. Misra K. Dvijotham (Caltech) M. Chertkov UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  3. Slide 3 • Intro: Overview of Challenges and Approaches • Technical Intro: Direct and Inverse Stochastic Problem – Machine Learning for Grid Operations • Machine Learning for Distribution Grid • Machine Learning for Transmission Grid • Graphical Models & New Physics=Grid Informed Learning Tools UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  4. Slide 4 Data Analytics can improve resiliency in the Dynamic Grid Changes in the modern Grid: • Penetration of Renewables • Vision: Storage devices • Design Algorithms for smart meter data to Loads becomes active (not controlled) learn and control (state of the grid) Challenges • Strong fluctuations/uncertainty • Features: Needs real-time observability, control • • Build upon Physics of Power flow & the Millions of devices, many entities network/graph features. • New (available) Solutions Scalable and computationally tractable • • Hardware: Address desired (spatio-temporal) sparsity Smart meters, PMUs, micro-PMUs • Software/New algorithms: Machine Learning, IoT UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  5. Slide 5 • Intro: Overview of Challenges and Approaches • Technical Intro: Direct and Inverse Stochastic Problem – Machine Learning for Grid Operations • Machine Learning for Distribution Grid • Machine Learning for Transmission Grid • Graphical Models & New Physics=Grid Informed Learning Tools UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  6. Slide 6 Grid should operate in spite of uncertainty & fluctuations uncertainty: • Graph Layout (switching of lines) + other +/- variables (transformers) • State Estimation (consumption & production) • Deterministic static & dynamic models (e.g. relating s=(p,q) to v) • Probabilistic (statistical) models => ∗ 𝑤 𝑘 −𝑤 𝑙 fluctuations: 𝑡 𝑘 = 𝑤 𝑘 𝑨 𝑘𝑙 • Renewable generators (wind & solar) 𝑙~𝑘 • loads (especially if active = involved in Demand Response) Power Flow Eqs. UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  7. Slide 7 Direct Deterministic Problem: Power Flow (static/minutes) Given: • operational grid=graph, inductances/resistances • injections/consumptions (for example) Compute: ∗ 𝑤 𝑘 −𝑤 𝑙 • 𝑡 𝑘 = 𝑤 𝑘 power flows over lines 𝑨 𝑘𝑙 • 𝑙~𝑘 voltages Power Flow Eqs. • phases UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  8. Slide 8 Direct Stochastic Problem: Power Flow (static/minutes) Given: • operational grid=graph, inductances/resistances • Probability distribution (statistics) of injections/consumptions (for example) -- samples are assumed drawn (from the probability distribution), e.g. i.i.d. ∗ Compute statistics of: 𝑤 𝑘 −𝑤 𝑙 𝑡 𝑘 = 𝑤 𝑘 𝑨 𝑘𝑙 • power flows over lines 𝑙~𝑘 • voltages Power Flow Eqs. • phases joint & marginal probability distributions UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  9. Slide 9 Inverse Stochastic Problem: Power Flow (static/minutes) ∗ 𝑤 𝑘 −𝑤 𝑙 Given: 𝑡 𝑘 = 𝑤 𝑘 𝑨 𝑘𝑙 • operational grid=graph, inductances/resistances 𝑙~𝑘 • Power Flow Eqs. snapshots/measurements of power flows, voltages, phases • parametrized representation for statistics of injections/consumptions, e.g. Gaussian & white Infer/ Learn : • parameters for statistics of the injection/consumption • operational grid=graph Sample/Predict: • configurations of injection/consumption => direct problem (compute) UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  10. Slide 10 Machine Learning for the Grid (at least some part) = Automatic Solution of the Inverse Grid Problem(s) Many flavors: • static vs dynamic • transmission vs distribution • blind (black box) vs grid/physics informed • samples vs moments (sufficiency) • principal limits (IT) vs efficient algorithms • ML for model reduction • individual devices vs ensemble learning [focus only on some of these ``complexities” in the talk] UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  11. Slide 11 • Intro: Overview of Challenges and Approaches • Technical Intro: Direct and Inverse Stochastic Problem – Machine Learning for Grid Operations • Machine Learning for Distribution Grid • Machine Learning for Transmission Grid • Graphical Models & New Physics=Grid Informed Learning Tools UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  12. D. Deka, S. Backhaus, MC Slide 12 Machine Learning for Distribution Grid arxiv:1502.07820, 1501.04131, + Learn • Switch statuses • Load statistics, line impedances Challenges • Nodal Measurements (voltages) • Missing Nodes • Information limited to households Substation Load Nodes Key Ideas • Operated Radial structure • Linear-Coupled power flow model • Graph Learning tricks UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  13. D. Deka, S. Backhaus, MC Slide 13 Machine Learning for Distribution Grid arxiv:1502.07820, 1501.04131, + Linear-Coupled power flow model: a equivalent to LinDistFlow (Baran-Wu) c b d Slack Bus Inverse Matrices are computable reduced reduced explicitly on trees Laplacian Incidence matrix matrix UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  14. D. Deka, S. Backhaus, MC Slide 14 Machine Learning for Distribution Grid arxiv:1502.07820, 1501.04131, + Key Idea: • Use variance of voltage diff. as edge weights a 𝑑 𝑐 𝑐 𝑐 • Minimal value outputs the nearest neighbor 𝑑 𝑏 𝑏 𝑑 Learning Algorithm: • Min spanning tree with variance of voltage diff. as edge weights a 𝑐  No other information needed  Low Complexity: 𝑑  Can learn covariance of fluctuating loads UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  15. D. Deka, S. Backhaus, MC Slide 15 Machine Learning for Distribution Grid arxiv:1502.07820, 1501.04131, + Learning with missing nodes: • Missing nodes separated by 2 or more hops 𝑏 Learning Algorithm: 𝑏 • Min spanning tree with available 𝑐 nodes 𝑚 • Starting from leaf, check missing node Leaf Intermediate 𝑏 𝑐 𝑐 𝑑 𝑏 𝑑 𝑏 𝑏 𝑐 𝑑 UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  16. D. Deka, S. Backhaus, MC Slide 16 Machine Learning for Distribution Grid arxiv:1502.07820, 1501.04131, + Learning with missing nodes & reduced information: • Missing nodes separated by 2 or more hops • Model reduction, ensemble (sampling distributions) Extensions:  Learn using end-node (household) data accounting for  mix of active (with control) & passive  dynamics of loads/motors and inverters  emergencies, e.g. FIDVR  Coupling to other physical infrastructures  Learn 3 phase unbalanced networks - gas/water distribution  Learn loopy grid graph - thermal heating  cities (Manhattan) e.g. extending the learning methodology  rich exogenous correlations (loops to the more general ``physical flow” networks representing non-grid knowledge) UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

  17. Slide 17 Recently Awarded GMLC: Topic 1.4.9 Integrated Multi Scale Data Analytics and Machine Learning for the Grid PIs: Emma Stewart (LBNL) Michael Chertkov (LANL) NL involved: LBNL,LANL, SNL, ORNL, LLNL, NREL, ANL • Platform - review - development, - data collection • ML and Data Analytics for Visibility • ML and Data Analytics for Resilience UNCLASSIFIED Operated by Los Alamos National Security, LLC for the U.S. Department of Energy's NNSA

Recommend


More recommend