Demand Uncertainty

Demand uncertainty, the unpredictable fluctuation in the need for goods or services, presents a significant challenge across various sectors. Current research focuses on developing robust optimization and control strategies, employing techniques like deep reinforcement learning and graph-based neural networks to model and mitigate the impact of this uncertainty on resource allocation, supply chain management, and energy systems. These advancements aim to improve efficiency, reduce costs, and enhance sustainability in diverse applications, from cloud computing and network routing to mineral asset valuation and microgrid optimization. The ultimate goal is to create more resilient and adaptable systems capable of handling unpredictable demands effectively.

Papers

March 29, 2024

LACS: Learning-Augmented Algorithms for Carbon-Aware Resource Scaling with Uncertain Demand
Roozbeh Bostandoost, Adam Lechowicz, Walid A. Hanafy, Noman Bashir, Prashant Shenoy, Mohammad Hajiesmaili
Practical Algorithm Strong Scaling Resource Scaling Demand Uncertainty

March 1, 2023

A Deep Learning Perspective on Network Routing
Yarin Perry, Felipe Vieira Frujeri, Chaim Hoch, Srikanth Kandula, Ishai Menache, Michael Schapira, Aviv Tamar
Machine Learning Stochastic Optimization Dynamic Routing Routing Problem Multi Commodity Flow Traffic Engineering Demand Uncertainty

December 7, 2022

Learning on Graphs for Mineral Asset Valuation Under Supply and Demand Uncertainty
Yassine Yaakoubi, Hager Radi, Roussos Dimitrakopoulos
LeArning Abstract Graph Drawing Lead Time Mineral Prospectivity Demand Uncertainty Ore Image Mine Planning

November 11, 2022

Deep Reinforcement Learning Microgrid Optimization Strategy Considering Priority Flexible Demand Side
Jinsong Sang, Hongbin Sun, Lei Kou
DC Microgrid Application Energy Dispatch Demand Uncertainty

January 12, 2022

Multi-echelon Supply Chains with Uncertain Seasonal Demands and Lead Times Using Deep Reinforcement Learning
Julio César Alves, Geraldo Robson Mateus
Deep Reinforcement Learning Markov Decision Process Sequential Decision Making Problem Nonlinear Programming Lead Time Echelon Supply Chain Demand Uncertainty

Demand Uncertainty

Papers

LACS: Learning-Augmented Algorithms for Carbon-Aware Resource Scaling with Uncertain Demand

A Deep Learning Perspective on Network Routing

Learning on Graphs for Mineral Asset Valuation Under Supply and Demand Uncertainty

Deep Reinforcement Learning Microgrid Optimization Strategy Considering Priority Flexible Demand Side

Multi-echelon Supply Chains with Uncertain Seasonal Demands and Lead Times Using Deep Reinforcement Learning