Deep learning method for efficient energy storage arbitrage

This technology is an energy storage arbitrage algorithm that uses deep learning predicted opportunity value functions.

Unmet Need: Model to maximize arbitrage profit predictions of energy market prices

Current power systems are transitioning to more sustainable outlets that make it difficult to balance electricity supply and demand in real-time. Precise prediction of real-time energy market prices can ensure profitable energy market arbitrage. However, various methods that predict real-time price are disadvantaged with having a high mean absolute percentage error, due to the highly stochastic and confidential nature of energy market prices.

The Technology: Deep learning-based arbitrage for improved energy storage

This technology is an energy storage price arbitrage algorithm that uses deep learning to predict opportunity value functions. The opportunity value function offers more stability compared to the highly unpredictable real-time price. Moreover, transfer learning is used to increase the robustness of the model, promoting high performance even with minimal data and low computational power, making it scalable for market implementation.

This technology has been validated in a case study on historical prices in NYISO.

Applications:

• Method for accurate energy storage price prediction
• Tool to predict energy demands for real-world applications
• Approach to support more modern and sustainable power systems
• Model for deep learning-based arbitrage
• Research model for other market price predictions

Advantages:

• Requires low computational power
• Functional with small datasets
• Optimizes energy storage
• Uses opportunity value function as opposed to real-time prices to enhance predictability
• Cost-effective
• Compatible with sustainable power systems
• Scalable for market implementation

Lead Inventor:

Bolun Xu, Ph.D.

Related Publications:

• Zheng N, Liu X, Xu B, Shi Y. “Energy storage price arbitrage via opportunity value function prediction” arXiv. 2022 Nov 20.

• Zheng N, Qin X, Wu D, Murtaugh G, Xu B. “Energy storage state-of-charge market model” arXiv. 2022 Nov 11.

• Zheng N, Jaworski J, Xu B. “Arbitraging variable efficiency energy storage using analytical stochastic dynamic programming” IEEE Transactions on Power Systems. 2022 Feb 24; 37(6): 4785-4795.

Tech Ventures Reference:

• IR CU23095, CU23109

• Licensing Contact: Dovina Qu