20 September 2023 in IEEE Transactions on Power Systems
The article proposes a novel End-to-End Learning and Repair (E2ELR) architecture for training optimization proxies for economic dispatch problems. E2ELR combines deep neural networks with closed-form, differentiable repair layers, thereby integrating learning and feasibility in an end-to-end fashion. E2ELR is also trained with self-supervised learning, removing the need for labeled data and the solving of numerous optimization problems offline. E2ELR is evaluated on industry-size power grids with tens of thousands of buses using an economic dispatch that co-optimizes energy and reserves. The results demonstrate that the self-supervised E2ELR achieves state-of-the-art performance, with optimality gaps that outperform other baselines by at least an order of magnitude.
30 January 2025 in Applied Energy
2 August 2022 in Electric Power Systems Research
28 August 2018 in IEEE Transactions on Power Systems
Demand-response aggregators are faced with the challenge of how to best manage numerous and heterogeneous Distributed Energy Resources (DERs). This paper proposes a decentralized methodology for optimal coordination of DERs. The proposed approach is based on Dantzig-Wolfe decomposition and column generation, thus allowing to integrate any type of resource whose operation can be formulated within a mixed-integer linear program. We show that the proposed framework offers the same guarantees of optimality as a centralized formulation, with the added benefits of distributed computation, enhanced privacy, and higher robustness to changes in the problem data. The practical efficiency of the algorithm is demonstrated through extensive computational experiments, on a set of instances generated using data from Ontario energy markets. The proposed approach was able to solve all test instances to proven optimality, while achieving significant speed-ups over a centralized formulation solved by state-of-the-art optimization software.
26 July 2023 in IEEE Transactions on Power Systems
Reliability Assessment Commitment (RAC) Optimization is increasingly important in grid operations due to larger shares of renewable generations in the generation mix and increased prediction errors. Independent System Operators (ISOs) also aim at using finer time granularities, longer time horizons, and possibly stochastic formulations for additional economic and reliability benefits. The goal of this article is to address the computational challenges arising in extending the scope of RAC formulations. It presents RACLearn that 1) uses a Graph Neural Network (GNN) based architecture to predict generator commitments and active line constraints, 2) associates a confidence value to each commitment prediction, 3) selects a subset of the high-confidence predictions, which are 4) repaired for feasibility, and 5) seeds a state-of-the-art optimization algorithm with feasible predictions and active constraints. Experimental results on exact RAC formulations used by the Midcontinent Independent System Operator (MISO) and an actual transmission network (8965 transmission lines, 6708 buses, 1890 generators, and 6262 load units) show that the RACLearn framework can speed up RAC optimization by factors ranging from 2 to 4 with negligible loss in solution quality.
27 June 2022 in Mathematical Programming