Unit Commitment Using Nearest Neighbor as a Short-Term Proxy

Dalal, Gal; Gilboa, Elad; Mannor, Shie; Wehenkel, Louis

doi:10.23919/pscc.2018.8442516

Cited by 17 publications

(17 citation statements)

References 17 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the experiment described in this section, a dataset of 5000 UC problem instances was created. After obtaining this initial dataset, UCNN reduces computation time in several orders of magnitude, with relatively little compromise in quality [14]. A diagram visualizing the method is given in Fig.…”

Section: Machine Learning For a Short-term Proxymentioning

confidence: 99%

See 1 more Smart Citation

Chance-Constrained Outage Scheduling Using a Machine Learning Proxy

Dalal

Gilboa

Mannor

et al. 2019

IEEE Trans. Power Syst.

Self Cite

View full text Add to dashboard Cite

Outage scheduling aims at defining, over a horizon of several months to years, when different components needing maintenance should be taken out of operation. Its objective is to minimize operation-cost expectation while satisfying reliabilityrelated constraints. We propose a distributed scenario-based chance-constrained optimization formulation for this problem. To tackle tractability issues arising in large networks, we use machine learning to build a proxy for predicting outcomes of power system operation processes in this context. On the IEEE-RTS79 and IEEE-RTS96 networks, our solution obtains cheaper and more reliable plans than other candidates.

show abstract

Section: Machine Learning For a Short-term Proxymentioning

confidence: 99%

“…In addition to the direct UC approximation comparison in [14], we examine the resulting accuracy of outage scheduling assessment when using UCNN to solve the short-term subproblem instead of exact UC computations. To do so, we generate four arbitrary outage schedules under the configuration given in Section VI.…”

Section: Machine Learning For a Short-term Proxymentioning

confidence: 99%

Chance-Constrained Outage Scheduling Using a Machine Learning Proxy

Dalal

Gilboa

Mannor

et al. 2019

IEEE Trans. Power Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The more specific idea of using machine learning to build proxies of shorter-term decision-making contexts to be used when solving longer-term reliability assessment problems has been proposed and studied only recently [13], [1], [14], [2]. Within this context, the method presented in this paper, using machine learning to build control variates to speed up the Monte Carlo approach, is to our best knowledge entirely novel.…”

Section: Related Work and Contributionmentioning

confidence: 99%

Using Machine Learning to Enable Probabilistic Reliability Assessment in Operation Planning

Duchesne

Karangelos

Wehenkel

2018

2018 Power Systems Computation Conference (PSCC)

Self Cite

View full text Add to dashboard Cite

Abstract-In the context of operation planning, probabilistic reliability assessment essentially boils down to predicting, efficiently and with sufficient accuracy, various economic and reliability indicators reflecting the expected performance of the system over a certain look-ahead horizon, so as to guide the operation planner in his decision-making. In order to speedup the crude Monte Carlo approach, which would entail a very large number of heavy computations, we propose in this paper an approach combining Monte Carlo simulation, machine learning and variance reduction techniques such as control variates. We provide an extensive case study testing this approach on the three-area IEEE-RTS96 benchmark, in the context of day-ahead operation planning while using a security constrained optimal power flow model to simulate real-time operation according to the N-1 criterion. From this case study, we can conclude that the proposed approach allows to reduce the number of heavy computations by about an order of magnitude, without sacrificing accuracy.

show abstract

“…For instance, we refer the reader to [20] and [21], in which the authors have built proxies of respectively day-ahead unit commitment and real-time AC-OPF for a mid-term to long-term planning purpose. In [20] the nearest neighbor algorithm is used to predict the costs and decisions of a day-ahead unit commitment program while in [21], several supervised learning algorithms are tested to predict the cost and feasibility of an AC-OPF problem.…”

Section: Related Workmentioning

confidence: 99%

Machine learning of real-time power systems reliability management response

Duchesne

Karangelos

Wehenkel

2017

2017 IEEE Manchester PowerTech

Self Cite

View full text Add to dashboard Cite

Abstract-In this paper we study how supervised machine learning could be applied to build simplified models of realtime (RT) reliability management response to the realization of uncertainties. The final objective is to import these models into look-ahead operation planning under uncertainties. Our response models predict in particular the real-time reliability management costs and the resulting reliability level of the system. We tested our methodology on the IEEE-RTS96 benchmark.Among the supervised learning algorithms tested, extremely randomized trees, kernel ridge regression and neural networks appear to be the best methods for this application. Furthermore, by using feature "importances" computed by tree-based ensemble methods, we were able to extract the most relevant variables to predict the response of real-time reliability management, and thus obtain a better understanding of the system properties.

show abstract

Unit Commitment Using Nearest Neighbor as a Short-Term Proxy

Cited by 17 publications

References 17 publications

Chance-Constrained Outage Scheduling Using a Machine Learning Proxy

Chance-Constrained Outage Scheduling Using a Machine Learning Proxy

Using Machine Learning to Enable Probabilistic Reliability Assessment in Operation Planning

Machine learning of real-time power systems reliability management response

Contact Info

Product

Resources

About