Power distribution method and power distribution device for downlink of low-earth-orbit satellite

Abstract

The invention provides a power distribution method for the downlink of a low-orbit satellite. The method comprises the steps of: initializing the low-orbit satellite, and building a Markov decision process; observing the current state St; randomly selecting an action or selecting an optimal action according to the probability of an exploration factor; obtaining a new state St+1 and the instant reward rt of the current state St according to an action at, and storing the (st, at, rt, st+1) tetrad into an experience pool; under the condition that a cycle period is greater than a training number,training a current network; under the condition that the current time slot is integer multiples of the updating frequency of a target network, updating parameters of the target network; adding 1 to the current time slot; repeating the above steps until the current time slot is greater than a time slot counter, setting the current time slot to be 1 and adding 1 to the count of the cycle period; andrepeating the steps until the cycle period is greater than the training network period number. According to the distribution method, a deep reinforcement learning algorithm is adopted to dynamicallydistribute the subcarrier power of the multi-beam low-orbit satellite, so that the capacity of the low-orbit satellite is maximized, and the spectral efficiency is improved.

Description

Technical field [0001] The invention belongs to the field of satellite communication, and particularly relates to a low-orbit satellite downlink power distribution method and a power distribution device. Background technique [0002] In recent years, with the rapid development of satellite communication networks, there has been a massive increase in access users. Low-orbit satellites (LEO satellites) are widely favored due to their low satellite-to-earth link delay and lower antenna power and size requirements. At present, the available frequency resources of satellite communication systems are very limited. In addition, compared with terrestrial cellular networks, the power resources on low-orbit satellites are limited. When the solar panels of the satellite are in the shadow, the satellite can only use battery energy. Therefore, improving the efficiency of satellite frequency bands and energy efficiency through reasonable allocation of power resources has become an important re...

AI Technical Summary

Problems solved by technology

However, this method does not fully consider multi-beam interference and is not suitable for low-orbit satellite communication systems

[0004] The deficiencies of the existing technology mainly have two aspects. One is to ignore the influence of co-channel interference, which is not suitable for the actual channel environment. Since the current satellites mostly use multi-beam technology to improve the system capacity and make the energy more concentrated, there are The interference problem of the same frequency channel, the frequency band of the multi-beam satellite is limited, and the system capacity is not high under the influence of interference and noise

The second is that the existing technology is mostly aimed at the relatively static environment of the satellite channel. The power allocation adopts an offline algorithm, and the update speed is relatively slow. The efficiency of the formula algorithm is low, the convergence speed is slow, and it is difficult to adjust it online in real time

Images