CN-121984645-A - Automatic retransmission method, device, equipment and storage medium

CN121984645ACN 121984645 ACN121984645 ACN 121984645ACN-121984645-A

Abstract

The invention provides an automatic retransmission method, an automatic retransmission device, automatic retransmission equipment and a storage medium, wherein the method comprises the steps of obtaining channel state and/or energy consumption information from a second device, determining a channel state and/or energy consumption prediction result based on the channel state and/or energy consumption information, or obtaining the channel state and/or energy consumption prediction result from the second device, determining an HARQ retransmission strategy and an MCS based on the channel state and/or energy consumption prediction result, and transmitting data based on the HARQ retransmission strategy, the MCS and the ARQ retransmission strategy, wherein the first device and the second device are connected through WiFi (wireless fidelity). According to the invention, the first device makes a joint decision on the HARQ retransmission strategy and the MCS according to the channel state and/or the energy consumption prediction result of the second device by predicting the future channel state and/or the energy consumption of the second device, and performs cross-layer cooperation with the ARQ retransmission strategy, so that the comprehensive optimization of throughput, time delay and energy efficiency in the WiFi retransmission process is realized.

Inventors

Request for anonymity
Request for anonymity

Assignees

芯带科技(无锡)有限公司

Dates

Publication Date: 20260505
Application Date: 20260130

Claims (10)

1. An automatic retransmission method, applied to a first device, comprising: Obtaining channel state and/or energy consumption information from the second equipment, and determining a channel state and/or energy consumption prediction result based on the channel state and/or energy consumption information; Determining a hybrid automatic repeat request (HARQ) retransmission strategy and a Modulation Coding Scheme (MCS) based on the channel state and/or the energy consumption prediction result; Transmitting data based on the hybrid automatic repeat request (HARQ) retransmission strategy, the Modulation and Coding Scheme (MCS) and the automatic repeat request (ARQ) retransmission strategy; the first device and the second device are connected through WiFi wireless.
2. The automatic retransmission method according to claim 1, characterized in that the channel state and/or energy consumption prediction result is obtained according to the following way: Taking the channel state and/or energy consumption information in preset time as a channel state and/or energy consumption sequence, inputting a trained time sequence prediction model, and determining a channel state and/or energy consumption prediction result; the time sequence prediction model is obtained by training a historical channel state and/or energy consumption sample sequence set with a real label.
3. The automatic retransmission method according to claim 1 or 2, characterized in that determining a hybrid automatic repeat request, HARQ, retransmission strategy and a modulation coding scheme, MCS, based on the channel status and/or energy consumption prediction results, comprises: Inputting the channel state and/or the energy consumption prediction result into an artificial intelligent AI decision maker to determine a hybrid automatic repeat request HARQ retransmission strategy and a modulation coding scheme MCS; The artificial intelligent AI decision maker takes the channel state and/or the energy consumption prediction result as a state space, takes different hybrid automatic repeat request (HARQ) retransmission strategies and different Modulation and Coding Schemes (MCS) as action spaces, and trains based on a reward function, wherein the reward function is constructed based on one or more of throughput, error rate and energy consumption.
4. The automatic retransmission method according to claim 1 or 2, characterized in that determining a hybrid automatic repeat request, HARQ, retransmission strategy and a modulation coding scheme, MCS, based on the channel status and/or energy consumption prediction results, comprises: inputting the channel state and/or the energy consumption prediction result into a trained classification model, and determining a hybrid automatic repeat request (HARQ) retransmission strategy and a Modulation Coding Scheme (MCS); The classification model takes each combination of the HARQ retransmission strategy and the Modulation Coding Scheme (MCS) as a class label, and is obtained by training based on a cross entropy loss function and a channel state and/or energy consumption sample data set with a real class label.
5. The automatic retransmission method according to claim 2, characterized in that the method further comprises: The prediction correction information is used for indicating the deviation between the channel state and/or energy consumption prediction result and the channel state and/or energy consumption actual value of the second equipment; and optimizing the time sequence prediction model based on the prediction correction information.
6. The automatic retransmission method according to claim 1, characterized in that transmitting data based on the hybrid automatic repeat request, HARQ, retransmission strategy, the modulation and coding scheme, MCS, and automatic repeat request, ARQ, retransmission strategy, comprises: Transmitting data based on the HARQ retransmission strategy and the Modulation Coding Scheme (MCS) under the condition that the retransmission times of the data are smaller than or equal to a preset threshold value; And transmitting data based on an automatic repeat request (ARQ) retransmission strategy and the Modulation Coding Scheme (MCS) under the condition that the number of data retransmission times is larger than a preset threshold.
7. The automatic retransmission method according to claim 6, characterized in that the preset threshold is determined based on the channel state and/or energy consumption information, the channel state and/or energy consumption prediction result and the traffic type of the data.
8. An automatic retransmission apparatus, applied to a first device, comprising: The prediction module is used for acquiring channel state and/or energy consumption information from the second equipment and determining a channel state and/or energy consumption prediction result based on the channel state and/or energy consumption information; The determining module is used for determining a hybrid automatic repeat request (HARQ) retransmission strategy and a Modulation Coding Scheme (MCS) based on the channel state and/or the energy consumption prediction result; a sending module, configured to send data based on the hybrid automatic repeat request HARQ retransmission policy, the modulation coding scheme MCS, and the automatic repeat request ARQ retransmission policy; the first device and the second device are connected through WiFi wireless.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor implements the automatic retransmission method according to any one of claims 1 to 7 when executing the computer program.
10. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the automatic retransmission method according to any one of claims 1 to 7.

Description

Automatic retransmission method, device, equipment and storage medium Technical Field The present invention relates to the field of wireless communications technologies, and in particular, to an automatic retransmission method, apparatus, device, and storage medium. Background The WiFi network has a higher Frame Error Rate (FER) and data retransmission overhead under the conditions of high interference, long distance or multi-user concurrence. Based on IEEE 802.11 protocol, the hybrid automatic repeat request (Hybrid Automatic Repeat Request, HARQ) mechanism in the prior art improves transmission reliability by combining error detection, redundancy coding and automatic retransmission, but a fixed or preset retransmission policy is often adopted under different channel conditions, so that performance cannot be adaptively optimized. In the existing scheme, most WiFi HARQ optimization strategies lack flexibility in the aspects of redundancy rate selection, HARQ type switching, retransmission frequency upper limit and the like, and global optimal performance is difficult to obtain in a complex scene. Disclosure of Invention The present invention provides an automatic retransmission method, apparatus, device and storage medium, which are used for solving the above-mentioned problems in the prior art. The invention provides an automatic retransmission method which is applied to first equipment and comprises the following steps: Obtaining channel state and/or energy consumption information from the second equipment, and determining a channel state and/or energy consumption prediction result based on the channel state and/or energy consumption information; Determining a hybrid automatic repeat request (HARQ) retransmission strategy and a Modulation Coding Scheme (MCS) based on the channel state and/or the energy consumption prediction result; transmitting data based on the HARQ retransmission policy, the MCS and an automatic repeat request ARQ retransmission policy; the first device and the second device are connected through WiFi wireless. According to the automatic retransmission method provided by the invention, the channel state and/or energy consumption prediction result is obtained according to the following modes: Taking the channel state and/or energy consumption information in preset time as a channel state and/or energy consumption sequence, inputting a trained time sequence prediction model, and determining a channel state and/or energy consumption prediction result; the time sequence prediction model is obtained by training a historical channel state and/or energy consumption sample sequence set with a real label. According to the automatic retransmission method provided by the invention, based on the channel state and/or the energy consumption prediction result, the HARQ retransmission strategy and the modulation coding scheme MCS are determined, and the method comprises the following steps: Inputting the channel state and/or the energy consumption prediction result into an artificial intelligent AI decision maker to determine a hybrid automatic repeat request HARQ retransmission strategy and a modulation coding scheme MCS; The AI decision maker takes the channel state and/or the energy consumption prediction result as a state space, takes different HARQ retransmission strategies and different MCSs as action spaces, and trains based on a reward function, wherein the reward function is constructed based on one or more of throughput, error rate and energy consumption. According to the automatic retransmission method provided by the invention, based on the channel state and/or the energy consumption prediction result, the HARQ retransmission strategy and the modulation coding scheme MCS are determined, and the method comprises the following steps: inputting the channel state and/or the energy consumption prediction result into a trained classification model, and determining a hybrid automatic repeat request (HARQ) retransmission strategy and a Modulation Coding Scheme (MCS); the classification model takes each combination of HARQ retransmission strategy and MCS as a class label, and is obtained by training based on a cross entropy loss function and a channel state and/or energy consumption sample data set with a real class label. According to the automatic retransmission method provided by the invention, the method further comprises the following steps: The prediction correction information is used for indicating the deviation between the channel state and/or energy consumption prediction result and the channel state and/or energy consumption actual value of the second equipment; and optimizing the time sequence prediction model based on the prediction correction information. According to the automatic retransmission method provided by the invention, based on the HARQ retransmission strategy, the MCS and the automatic retransmission request ARQ retransmission strategy, the data transmission method compris