Capacity expansion under uncertainty in an oligopoly using indirect reinforcement-learning

被引:13
|
作者
Oliveira, Fernando S. [1 ]
Costa, Manuel L. G. [2 ]
机构
[1] Natl Univ Singapore, NUS Business Sch, Singapore, Singapore
[2] Univ Porto, Fac Econ, Ctr Econ & Finance, Porto, Portugal
关键词
OR in energy; Capacity expansion; Computational learning; Electricity markets; Oligopoly; INVESTMENT; MARKETS; OPTIONS; IMPACT; FLEXIBILITY; GENERATION; STRATEGIES; CONTRACTS; ECONOMICS; BEHAVIOR;
D O I
10.1016/j.ejor.2017.11.013
中图分类号
C93 [管理学];
学科分类号
12 ; 1201 ; 1202 ; 120202 ;
摘要
We model capacity expansion in oligopolistic markets, with endogenous prices, under uncertainty, considering multiple production technologies. As this environment is complex, capacity expansion is the outcome of a learning process by individual firms. We propose indirect reinforcement-learning to model the interaction between price determination and capacity decisions, in the context of an oligopoly game. We apply our model to the analysis of the Iberian electricity market, considering multiple technologies, focusing on how subsidies, the prices of CO2 emissions and gas affect the capacity expansion policies. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码:1039 / 1050
页数:12
相关论文
共 50 条
  • [41] Generation Capacity Expansion Planning Under Hydro Uncertainty Using Stochastic Mixed Integer Programming and Scenario Reduction
    Gil, Esteban
    Aravena, Ignacio
    Cardenas, Raul
    IEEE TRANSACTIONS ON POWER SYSTEMS, 2015, 30 (04) : 1838 - 1847
  • [42] Generation Capacity Expansion Planning under Hydro Uncertainty Using Stochastic Mixed Integer Programming and Scenario Reduction
    Gil, Esteban
    Aravena, Ignacio
    Cardenas, Raul
    2015 IEEE POWER & ENERGY SOCIETY GENERAL MEETING, 2015,
  • [43] Makespan reduction for dynamic workloads in cluster-based data grids using reinforcement-learning based scheduling
    Moghadam, Mahshid Helali
    Babamir, Seyed Morteza
    JOURNAL OF COMPUTATIONAL SCIENCE, 2018, 24 : 402 - 412
  • [44] Learning To Grasp Under Uncertainty Using POMDPs
    Garg, Neha P.
    Hsu, David
    Lee, Wee Sun
    2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2019, : 2751 - 2757
  • [45] Revealing principles of autonomous thermal soaring in windy conditions using vulture-inspired deep reinforcement-learning
    Flato, Yoav
    Harel, Roi
    Tamar, Aviv
    Nathan, Ran
    Beatus, Tsevi
    NATURE COMMUNICATIONS, 2024, 15 (01)
  • [46] Balancing Project Schedule, Cost, and Value under Uncertainty: A Reinforcement Learning Approach
    Szwarcfiter, Claudio
    Herer, Yale T.
    Shtub, Avraham
    ALGORITHMS, 2023, 16 (08)
  • [47] Compulsivity is linked to suboptimal choice variability but unaltered reinforcement learning under uncertainty
    Junseok K. Lee
    Marion Rouault
    Valentin Wyart
    Nature Mental Health, 2025, 3 (2): : 229 - 241
  • [48] Reinforcement learning-based control for waste biorefining processes under uncertainty
    Ji Gao
    Abigael Wahlen
    Caleb Ju
    Yongsheng Chen
    Guanghui Lan
    Zhaohui Tong
    Communications Engineering, 3 (1):
  • [49] Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty
    Chen, Fanfei
    Szenher, Paul
    Huang, Yewei
    Wang, Jinkun
    Shan, Tixiao
    Bai, Shi
    Englot, Brendan
    2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 5193 - 5199
  • [50] A Bayesian Reinforcement Learning Method for Periodic Robotic Control Under Significant Uncertainty
    Jia, Yuanyuan
    Eljuri, Pedro Miguel Uriguen
    Taniguchi, Tadahiro
    2023 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, IROS, 2023, : 384 - 391