Unmanned aerial vehicle trajectory design and power distribution method based on near-end strategy optimization
The invention discloses an unmanned aerial vehicle trajectory design and power distribution method based on near-end strategy optimization. The method comprises the steps of obtaining a current environment state; according to the standard deviation and a mean value output by a strategy network in a...
Saved in:
Main Authors | , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
20.12.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses an unmanned aerial vehicle trajectory design and power distribution method based on near-end strategy optimization. The method comprises the steps of obtaining a current environment state; according to the standard deviation and a mean value output by a strategy network in a preset PPO algorithm network, constructing a random variable obeying Gaussian distribution, selecting an action and storing an action selection probability, and when the action exceeds a preset acceleration upper limit, performing corresponding adjustment; when the execution of the updated action violates the constraint condition, making corresponding adjustment; each user randomly moves to a new position, calculates a system outage probability and current energy consumed by the unmanned aerial vehicle, further obtains an award, takes a current environment state, a current action, a current action selection probability and a current award as a group of data and stores the data into a preset buffer area, and when th |
---|---|
Bibliography: | Application Number: CN202211194735 |