A wind power optimization control method based on brain-like computing

By employing a brain-inspired computing-based wind power optimization control method, which utilizes multi-source data encoding and hierarchical pulse neural networks, the problems of adaptability and resource constraints in wind power control are solved, achieving low-power and high-efficiency wind power control.

CN122178432APending Publication Date: 2026-06-09DATANG RENEWABLE ENERGY RES INST CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
DATANG RENEWABLE ENERGY RES INST CO LTD
Filing Date
2026-02-03
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing wind power control technologies struggle to achieve efficient adaptive control when faced with the intermittent, random, and nonlinear characteristics of wind energy. Traditional AI controllers are difficult to deploy in resource-constrained scenarios and lack effective spiking neural network architectures and online learning solutions.

Method used

A wind power optimization control method based on brain-like computing is adopted. A hierarchical spiking neural network controller is constructed by bio-inspired event encoding of multi-source heterogeneous sensor data. Combined with spiking reinforcement learning and safety supervision, it achieves lifelong online adaptive fine-tuning and is deployed on a neuromorphic computing chip.

Benefits of technology

It achieves low-power, millisecond-level response wind power control, improves power generation efficiency, reduces mechanical load, extends equipment life, and adapts to complex wind conditions, providing a hardware-friendly solution.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122178432A_ABST
    Figure CN122178432A_ABST
Patent Text Reader

Abstract

This invention discloses a wind power optimization control method based on brain-like computing, comprising the following steps: Step 1, bio-inspired event encoding of multi-source heterogeneous sensor data; Step 2, constructing a hierarchical spiking neural network controller model with spatiotemporal memory; Step 3, spiking reinforcement learning training based on multi-objective reward signals; Step 4, robust decoding and safe constraint execution of spiking decision output; Step 5, lifelong online adaptive fine-tuning based on performance monitoring; Revolutionary performance and efficiency improvement: The event-driven characteristics enable the system to consume almost zero power under steady-state or slowly changing conditions, and the overall control loop energy consumption can be reduced by 1-2 orders of magnitude compared to traditional AI solutions; Millisecond-level real-time response: The spiking processing mechanism is naturally matched to asynchronous sensor data, and the end-to-end latency from perception to decision is extremely low (less than 1ms), which can accurately capture and respond to rapid disturbances such as gusts.
Need to check novelty before this filing date? Find Prior Art