Computer-Aided Quantum Algorithms for Real-Time Energy Market Trading
This study presents an innovative approach for optimizing real-time energy market trading strategies by integrating Proximal Policy Optimization (PPO) with Quantum Annealing (QA). The primary objective is to enhance trading performance by leveraging the adaptive capabilities of PPO alongside the opt...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10935622/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study presents an innovative approach for optimizing real-time energy market trading strategies by integrating Proximal Policy Optimization (PPO) with Quantum Annealing (QA). The primary objective is to enhance trading performance by leveraging the adaptive capabilities of PPO alongside the optimization power of QA. The methodology involves using PPO to develop a dynamic trading strategy that adapts to real-time market conditions. PPO’s reinforcement learning framework is employed to manage state representations, action spaces, and reward functions, thereby continuously refining the trading policy. The optimization of trading parameters is achieved through Quantum Annealing, which solves Quadratic Unconstrained Binary Optimization (QUBO) problems derived from the trading strategy formulation. Key findings from the study demonstrate significant improvements in trading outcomes. The integration of QA with PPO led to a 25% increase in total return, a 15% enhancement in Sharpe ratio, a 10% reduction in maximum drawdown, and a 20% decrease in transaction costs. These results highlight the effectiveness of combining quantum optimization techniques with reinforcement learning for superior trading strategy development. The significance of this study lies in its contribution to advancing real-time trading strategy optimization through the synergistic use of machine learning and quantum computing. This approach offers potential applications across various financial sectors and domains requiring sophisticated real-time decision-making and optimization. Future research is suggested to further explore the scalability and practical implementation of this integrated methodology in more complex and larger-scale optimization problems. |
|---|---|
| ISSN: | 2169-3536 |