AI / ML for energy systems
| Title | Author / Year | Theme | Comment |
|---|---|---|---|
| Simulation of hydropower at subcontinental to global scales: a state-of-the-art review | Turner et al. (2022) | Provides an overview of different approaches to estimate hydropower, including machine learning | Literature review |
| Improving Large Scale Day-Ahead Security Constrained Unit Commitment Performance | Chen et al. (2016) | The article motivates solving the unit commitment problem faster. It also compares conventional approaches to solve the unit commitment problem. Machine learning models are not mentioned in this paper. | Introduction / problem statement |
| Large-scale unit commitment under uncertainty: an updated literature survey | Ackooij et al. (2018) | Provides a review of methods to solve the unit commitment problem and challenges encountered by the MIP solver. This article also focuses on stochastic optimization, which is not a widely adopted formulation of the unit commitment problem | Literature review |
| The voice of optimization | Bertsimas and Stellato (2020) | Provides a first-principle discussion in the literature review section on the role of machine learning models in optimization. Instead of predicting solution directly, the paper argues that we should predict the solution strategy, e.g. parameters of the solver, and nodes to explore. The experimental setup can also be of interest to demonstrate the application of the proposed approach. | Introduction - fundamentals of using ML in optimization |
| A survey for solving mixed integer programming via machine learning | Zhang et al. (2023) | Provides a review of solving mixed-integer programs with machine learning | Introduction - review of using ML in solving mixed-integer programs |
| Learn2Opt Framework to Speed-up Power System Modeling | Bunnak et al. (2023) | Provides a simple demonstration of training neural networks to speed-up PowNet 1.0 | Technical - example 1 |
| Learning optimization proxies for large-scale Security-Constrained Economic Dispatch | Chen et al. (2022) | Proposes an ML pipeline to solve the unit commitment problem in a real-world setting | Technical - example 2 |
| Learning to Solve Large-Scale Security-Constrained Unit Commitment Problems | Xavier et al. (2021) | Proposes using MP to improve the computational performance of MIP solvers when dealing with the unit commitment problem | Technical - example 3 |
