Interpretable hybrid experimental learning for trading behavior modeling in electricity market
A modern electricity market is essentially a complex network, characterized by complicated interactions among cyber communications, physical systems, and social agents. Trading behavior modeling has always been complicated in the physical system-based market. In this paper, trading behavior modeling...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/172716 |
| _version_ | 1826126441292496896 |
|---|---|
| author | Liu, Wenxuan Zhao, Junhua Qiu, Jing Dong, Zhao Yang |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Liu, Wenxuan Zhao, Junhua Qiu, Jing Dong, Zhao Yang |
| author_sort | Liu, Wenxuan |
| collection | NTU |
| description | A modern electricity market is essentially a complex network, characterized by complicated interactions among cyber communications, physical systems, and social agents. Trading behavior modeling has always been complicated in the physical system-based market. In this paper, trading behavior modeling in the electricity market is solved by a data-driven method combining experimental economics and machine learning, called Hybrid Experimental Learning (HEL). Based on the historical and experiment simulated data, HEL models the trading behavior by a machine learning generative model which will be interpreted by a post hoc interpretation approach. Taking a simulated electricity market based on the trial spot market rule in Guangdong, China as an example, a generative adversarial network (GAN) is employed to generate the offering strategies of a gas generator. Local interpretable model-agnostic explanation (LIME) as a post hoc interpretation approach is applied to explain the relationship between the output of GAN and some of the inputs of HEL, which can be described as offering mechanisms for the gas generator. |
| first_indexed | 2024-10-01T06:52:42Z |
| format | Journal Article |
| id | ntu-10356/172716 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:52:42Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1727162023-12-18T02:26:00Z Interpretable hybrid experimental learning for trading behavior modeling in electricity market Liu, Wenxuan Zhao, Junhua Qiu, Jing Dong, Zhao Yang School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Electricity Markets Hybrid Experimental Learning A modern electricity market is essentially a complex network, characterized by complicated interactions among cyber communications, physical systems, and social agents. Trading behavior modeling has always been complicated in the physical system-based market. In this paper, trading behavior modeling in the electricity market is solved by a data-driven method combining experimental economics and machine learning, called Hybrid Experimental Learning (HEL). Based on the historical and experiment simulated data, HEL models the trading behavior by a machine learning generative model which will be interpreted by a post hoc interpretation approach. Taking a simulated electricity market based on the trial spot market rule in Guangdong, China as an example, a generative adversarial network (GAN) is employed to generate the offering strategies of a gas generator. Local interpretable model-agnostic explanation (LIME) as a post hoc interpretation approach is applied to explain the relationship between the output of GAN and some of the inputs of HEL, which can be described as offering mechanisms for the gas generator. This work was supported in part by the National Natural Science Foundation of China under Grants 72171206, 71931003, 72061147004, and 72192805 and in part by the Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS). 2023-12-18T02:26:00Z 2023-12-18T02:26:00Z 2023 Journal Article Liu, W., Zhao, J., Qiu, J. & Dong, Z. Y. (2023). Interpretable hybrid experimental learning for trading behavior modeling in electricity market. IEEE Transactions On Power Systems, 38(2), 1022-1032. https://dx.doi.org/10.1109/TPWRS.2022.3173654 0885-8950 https://hdl.handle.net/10356/172716 10.1109/TPWRS.2022.3173654 2-s2.0-85149440572 2 38 1022 1032 en IEEE Transactions on Power Systems © 2022 IEEE. All rights reserved. |
| spellingShingle | Engineering::Electrical and electronic engineering Electricity Markets Hybrid Experimental Learning Liu, Wenxuan Zhao, Junhua Qiu, Jing Dong, Zhao Yang Interpretable hybrid experimental learning for trading behavior modeling in electricity market |
| title | Interpretable hybrid experimental learning for trading behavior modeling in electricity market |
| title_full | Interpretable hybrid experimental learning for trading behavior modeling in electricity market |
| title_fullStr | Interpretable hybrid experimental learning for trading behavior modeling in electricity market |
| title_full_unstemmed | Interpretable hybrid experimental learning for trading behavior modeling in electricity market |
| title_short | Interpretable hybrid experimental learning for trading behavior modeling in electricity market |
| title_sort | interpretable hybrid experimental learning for trading behavior modeling in electricity market |
| topic | Engineering::Electrical and electronic engineering Electricity Markets Hybrid Experimental Learning |
| url | https://hdl.handle.net/10356/172716 |
| work_keys_str_mv | AT liuwenxuan interpretablehybridexperimentallearningfortradingbehaviormodelinginelectricitymarket AT zhaojunhua interpretablehybridexperimentallearningfortradingbehaviormodelinginelectricitymarket AT qiujing interpretablehybridexperimentallearningfortradingbehaviormodelinginelectricitymarket AT dongzhaoyang interpretablehybridexperimentallearningfortradingbehaviormodelinginelectricitymarket |