Shuo Huang
Market power analysis and detection in the Italian electricity markets based on data analysis and deep learning.
Rel. Tao Huang. Politecnico di Torino, Corso di laurea magistrale in Ict For Smart Societies (Ict Per La Società Del Futuro), 2020
|
PDF (Tesi_di_laurea)
- Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (3MB) | Preview |
Abstract: |
This paper mainly focuses on market power in the Italian electricity spot market. Aims at analyzing the market power level in the Italian electricity spot market and design an anomaly detection model to do the preliminary detection of market power. The first two chapters give an introduction about the background and some fundamental economic theories and to help have a better understanding of the current status of the Italian electricity market and competition and market power in it. Chapter three introduces the technics and algorithms used in this paper, including the introduction of big data framework and deep learning, the detailed inference of variational auto-encoder, which is the algorithm of anomaly detection model. In chapter four, we analyzed market power in the Italian electricity spot market by long-term and short term indicators. The results show that there still exists a medium level of potential market power Italian electricity market. This also is the actual support of the anomaly detection model. Then we processed raw data and training the model based on the variational auto-encoder algorithm. In chapter five, we evaluated the performance of the anomaly detection model. We analyzed some anomaly points which are filtered by model, using economic theories and experimental methods, and took two cases as examples. The results show that most of the filtered points indeed have suspicions of exercising market power, which means that the performance is acceptable. In the last chapter, we summarised the whole paper and talked about the shortcomings, meaning, and prospects. |
---|---|
Relators: | Tao Huang |
Academic year: | 2020/21 |
Publication type: | Electronic |
Number of Pages: | 90 |
Subjects: | |
Corso di laurea: | Corso di laurea magistrale in Ict For Smart Societies (Ict Per La Società Del Futuro) |
Classe di laurea: | New organization > Master science > LM-27 - TELECOMMUNICATIONS ENGINEERING |
Aziende collaboratrici: | UNSPECIFIED |
URI: | http://webthesis.biblio.polito.it/id/eprint/16609 |
Modify record (reserved for operators) |