Capacity adequacy mechanisms are crucial pathways to ensure reliable power supply in electricity grids and are coupled with the spot electricity market. However, current studies on the impact of capacity adequacy mech...
详细信息
A Microgrid (MG) is formed by a collection of interconnected loads and distributed energy resources, operating collectively and under control as a distinct entity in relation to the grid. A Networked Microgrid (NMG) c...
详细信息
Fairness is a crucial element in sports tournaments, with numerous indicators devised to ensure balanced competitions. To minimize rest differences, which means the rest time difference between two opponents, previous...
详细信息
The construction sector is responsible for emitting 30% of worldwide greenhouse emissions. Sustainable construction addresses this problem by designing infrastructures under the energy-efficient concept. This paper pr...
详细信息
Reinforcement Learning (RL) has emerged as a promising solution for defining the optimal dispatch of Energy Storage Systems (ESS) in distributed energy systems. However, a notable gap exists in the literature: a lack ...
详细信息
In the preventive healthcare facility location problems (PHFLPs), explicitly modeling realistic aspects of the location decisions such as potential participants’ latent utility functions related to various attributes...
详细信息
In addressing the issue of exponential increase in solution time with the growing number of simulations when using mixed-integer linear programming methods to solve stochastic models based on Monte Carlo simulation, t...
详细信息
Increasing the share of Renewable Energy Sources (RES) in energy consumption is perceived today as essential to decarbonizing energy systems. In this context, the Renewable Energy Communities (RECs) have been recently...
详细信息
In recent years, there has been a growing research interest in decision-focused learning, which embeds optimization problems as a layer in learning pipelines and demonstrates a superior performance than the prediction...
详细信息
In recent years, there has been a growing research interest in decision-focused learning, which embeds optimization problems as a layer in learning pipelines and demonstrates a superior performance than the prediction-focused approach. However, for distributionally robust optimization (DRO), a popular paradigm for decision-making under uncertainty, it is still unknown how to embed it as a layer, i.e., how to differentiate decisions with respect to an ambiguity set. In this paper, we develop such differentiable DRO layers for generic mixed-integer DRO problems with parameterized second-order conic ambiguity sets and discuss its extension to Wasserstein ambiguity sets. To differentiate the mixed-integer decisions, we propose a novel dual-view methodology by handling continuous and discrete parts of decisions via different principles. Specifically, we construct a differentiable energy-based surrogate to implement the dual-view methodology and use importance sampling to estimate its gradient. We further prove that such a surrogate enjoys the asymptotic convergency under regularization. As an application of the proposed differentiable DRO layers, we develop a novel decision-focused learning pipeline for contextual distributionally robust decision-making tasks and compare it with the prediction-focused approach in experiments. Copyright 2024 by the author(s)
This work addresses the problem of optimizing the energy market-clearing of an integrated power system in a coupled market. More specifically, a wide range of market products (simple hourly, block, and complex orders)...
详细信息
暂无评论