Look-Ahead Unit Commitment With Adaptive Horizon Based on Deep Reinforcement Learning

被引:1
|
作者
Yan, Jiahao [1 ]
Li, Yaping [1 ]
Yao, Jianguo [1 ]
Yang, Shengchun [1 ]
Li, Feng [1 ]
Zhu, Kedong [1 ]
机构
[1] China Elect Power Res Inst, Dept Power Automat, Nanjing 210000, Peoples R China
基金
中国国家自然科学基金;
关键词
Renewable energy integration; look-ahead unit commitment; adaptive horizon; reinforcement learning; IMPACT; OPTIMIZATION; SYSTEMS;
D O I
10.1109/TPWRS.2023.3286094
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The highly variable nature of renewable energy has led to the concept of intra-day look-ahead unit commitment (LAUC), which aims to determine the on/off status and power outputs of generating units in a rolling-horizon fashion. LAUC is traditionally performed based on look-ahead horizon (LAH) with fixed length and resolution. Such practice can neither capture the high-risk time periods, nor achieve maximum computational efficiency. To address these issues, this article proposes a LAUC method with adaptive horizon (LAUC-AH). The method uses three parameters to describe the shape of LAH, namely length, resolution, and myopia. Taking these parameters, the forecast profile of renewable energy and load demand is aggregated using a hierarchical clustering procedure to form the LAH, which is then used to construct the LAUC optimization model. Furthermore, a deep reinforcement learning-based agent is used to dynamically adjust the parameters of LAH, such that the LAUC model can adapt to different operation statuses of the power grid. The case studies are carried out on a modified IEEE-118 test case to validate the feasibility and effectiveness of the proposed method.
引用
收藏
页码:3673 / 3684
页数:12
相关论文
共 50 条
  • [21] Look-ahead radar and horizon sensing for coal cutting drums
    Bausov, I. Y.
    Stolarczyk, G. L.
    Stolarczyk, L. G.
    Koppenjan, Sc. D. S.
    2007 4TH INTERNATIONAL WORKSHOP ON ADVANCED GROUND PENETRATING RADAR, 2007, : 192 - +
  • [22] A Decentralized Multi-agent Energy Management Strategy Based on a Look-Ahead Reinforcement Learning Approach
    Khalatbarisoltani A.
    Kandidayeni M.
    Boulon L.
    Hu X.
    SAE International Journal of Electrified Vehicles, 2021, 11 (02):
  • [23] Adaptive inter CU partitioning based on a look-ahead stage for HEVC
    Cebrian-Marquez, Gabriel
    Luis Martinez, Jose
    Cuenca, Pedro
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2019, 76 : 97 - 108
  • [24] Reinforcement Learning Optimized Look-Ahead Energy Management of a Parallel Hybrid Electric Vehicle
    Liu, Teng
    Hu, Xiaosong
    Li, Shengbo Eben
    Cao, Dongpu
    IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2017, 22 (04) : 1497 - 1507
  • [25] Extending unit propagation look-ahead of DPLL procedure
    Anbulagan
    PRICAI 2004: TRENDS IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2004, 3157 : 173 - 182
  • [26] LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active Learning
    Kim, Yoon-Yeong
    Song, Kyungwoo
    Jang, Joonho
    Moon, Il-Chul
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [27] Data-Driven Look-Ahead Unit Commitment Considering Forbidden Zones and Dynamic Ramping Rates
    Jin, Ziliang
    Pan, Kai
    Fan, Lei
    Ding, Tao
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2019, 15 (06) : 3267 - 3276
  • [28] Look-ahead based SAT solvers
    Front. Artif. Intell. Appl., 2009, 1 (155-184):
  • [29] On look-ahead and pathology in decision tree learning
    Elomaa, T
    Malinen, T
    JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, 2005, 17 (1-2) : 19 - 33
  • [30] Multistage Robust Look-Ahead Unit Commitment with Probabilistic Forecasting in Multi-Carrier Energy Systems
    Zhou, Yizhou
    Shahidehpour, Mohammad
    Wei, Zhinong
    Sun, Guoqiang
    Chen, Sheng
    IEEE TRANSACTIONS ON SUSTAINABLE ENERGY, 2021, 12 (01) : 70 - 82