Forecasting and risk analysis for Vietnam industrial full market price (FMP) / spot price
Loading...
URL
Journal Title
Journal ISSN
Volume Title
School of Business |
Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Authors
Date
Department
Major/Subject
Mcode
Language
en
Pages
62
Series
Abstract
As Vietnam transitions toward a competitive wholesale electricity market under the Net Zero 2050 directive, the introduction of Decree 57/2025/ND-CP and the Direct Power Purchase Agreement (DPPA) has altered the risk landscape for energy participants. This thesis investigates the stochastic modeling and risk quantification of the Vietnam electricity spot price (Full Market Price - FMP) using a newly released five-year dataset (2020–2024) from the National Power System and Market Operation Company (NSMO). The research evaluates three distinct time-series forecasting frameworks: Seasonal Autoregressive Integrated Moving Average (SARIMA), Extreme Gradient Boosting (XGBoost), and Long Short-Term Memory (LSTM) networks. The results suggest that univariate models, trained on historical prices, consistently outperformed multivariate models incorporating exogenous weather and fuel variables. These findings provide corporate offtakers and generators with a validated quantitative tool for managing basis risk and structuring Contracts for Difference (CfD) within Vietnam’s evolving energy market.Description
Supervisor
Leppänen, IlkkaThesis advisor
Ho, TungStuart, Marc