Research on carbon asset trading strategy based on PSO-VMD and deep reinforcement learning

Abstract

As the financialization of carbon emission right, developing effective carbon asset trading strategy is important for both investors and regulators. Traditional trading strategy based on technical analysis is hardly profitable due to high complexity inherent in carbon markets. In order to increase investment returns and reduce risk in carbon market, this paper introduces PSO-VMD-DRL, an innovative carbon asset trading strategy that integrates signal decomposition technology and deep reinforcement learning (DRL). Firstly, the carbon price is decomposed into multiple components by variational mode decomposition (VMD) optimized through particle swarm optimization (PSO) to extract frequency features and reduce noise. Then state representation of the environment (state space) is constructed based on the components and transaction data. Finally, deep reinforcement learning (PPO, A2C, DDPG) are performed separately based on state space to learn optimal trading strategy. Empirical studies based on the data from carbon markets of Hubei and Guangzhou validate that PSO-VMD-DRL can adapt to carbon asset with the better profitability and risk resistance. The PSO-VMD-DRL outperform the other comparison strategies with superiority in all evaluation indices, achieving annual return of 21.39%, 17.67%, 25.50% and 46.34%, 44.55%, 43.03% in carbon market of Hubei and Guangzhou.