Feature-Driven Economic Improvement for Network-Constrained Unit Commitment: A Closed-Loop Predict-and-Optimize Framework
- 16 November 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 37 (4) , 3104-3118
Abstract
As an important application in the power system operation and electricity market clearing, the network-constrained unit commitment (NCUC) problem is usually executed by Independent System Operators (ISO) in an open-looped predict-then-optimize (O-PO) process, in which an upstream prediction (e.g., on renewable energy sources (RES) and loads) and a downstream NCUC are executed in a queue. However, in the O-PO framework, a statistically more accurate prediction may not necessarily lead to a higher NCUC economics against actual RES and load realizations. To this end, this paper presents a closed-loop predict-and-optimize (C-PO) framework for improving the NCUC economics. Specifically, the C-PO leverages structures (i.e., constraints and objective) of the NCUC model and relevant feature data to train a cost-oriented RES prediction model, in which the prediction quality is evaluated via the induced NCUC cost instead of the statistical forecast errors. Therefore, the loop between the prediction and the optimization is closed to deliver a cost-oriented RES power prediction for NCUC optimization. Lagrangian relaxation is adopted to accelerate the training process, making the C-PO applicable for real-world systems. Case studies on an IEEE RTS 24-bus system and an ISO-scale 5655-bus system with real-world data show that the proposed C-PO can effectively improve the NCUC economics as compared to the traditional O-PO.Keywords
Funding Information
- National Science Foundation (CNS-1915756)
- PSEG Foundation gift
This publication has 22 references indexed in Scilit:
- An Integrated Approach for Value-Oriented Energy Forecasting and Data-Driven Decision-Making Application to Renewable Energy TradingIEEE Transactions on Smart Grid, 2019
- The Big Data Newsvendor: Practical Insights from Machine LearningOperations Research, 2019
- A Distributionally Robust Optimization Model for Unit Commitment Based on Kullback–Leibler DivergenceIEEE Transactions on Power Systems, 2018
- Improving economic values of day‐ahead load forecasts to real‐time power system operationsIET Generation, Transmission & Distribution, 2017
- Toward Cost-Oriented Forecasting of Wind Power GenerationIEEE Transactions on Smart Grid, 2016
- Accelerating NCUC Via Binary Variable-Based Locally Ideal Formulation and Dynamic Global CutsIEEE Transactions on Power Systems, 2015
- Unit Commitment With Continuous-Time Generation and Ramping Trajectory ModelsIEEE Transactions on Power Systems, 2015
- Modeling and Solution of the Large-Scale Security-Constrained Unit CommitmentIEEE Transactions on Power Systems, 2013
- Stochastic Security-Constrained Unit CommitmentIEEE Transactions on Power Systems, 2007
- An Applications Oriented Guide to Lagrangian RelaxationInterfaces, 1985