Unlock instant, AI-driven research and patent intelligence for your innovation.

A method for optimizing offload latency in mobile edge computing scenarios

An edge computing and optimization method technology, applied in the field of wireless communication, can solve the problems of large delay consumption and so on

Active Publication Date: 2021-04-09
NORTHWESTERN POLYTECHNICAL UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide an offloading delay optimization method in a mobile edge computing scenario to solve the problem of large delay consumption in the existing multi-user MEC scenario

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for optimizing offload latency in mobile edge computing scenarios
  • A method for optimizing offload latency in mobile edge computing scenarios
  • A method for optimizing offload latency in mobile edge computing scenarios

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0092] In the present invention, the reinforcement learning algorithm DQN is used to learn the NOMA-MEC system to find the best user combination scheme to minimize the total system delay. Basic process such as figure 2 As shown, 2M users can all be used as agents for learning. Taking user k as an example, in time slot t, user k chooses an action, that is, chooses a user as his transmission partner, acts on the environment, makes the environment reach the next state, and returns a reward value R to user k to reward user k The selected actions are evaluated. The goal of RL is to find an appropriate fixed policy π:s→a that probabilistically maps state s to action a in order to optimize the agent's cumulative long-run utility V. User k will change the strategy according to the feedback of the environment, and adjust the action to the direction of increasing the reward value, and finally make the long-term utility, that is, the unloading delay, reach the optimum.

[0093] The p...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The purpose of the present invention is to provide an unloading delay optimization method in a mobile edge computing scenario. Step 1: Build a system model: the system model includes 2M users and a MEC server, and each user has L tasks that need to be offloaded to the MEC server Perform calculations, assuming that only two users are allowed to uninstall at the same time using the hybrid NOMA strategy; step 2, set each user as an executor, and each executor performs action selection according to the DQN algorithm, that is, from the remaining 2M‑1 users Choose one as your own transmission partner to unload at the same time; step 3, use the DQN algorithm to optimize the system: after all user partners are selected, calculate the total unloading delay of the system, update the reward value, and then train the neural network, using the neural network as a function The approximator updates the Q function; iteratively optimizes the system until the optimal time delay is found. It solves the problem of large delay consumption in the existing multi-user MEC scenario.

Description

【Technical field】 [0001] The invention belongs to the technical field of wireless communication, and in particular relates to an unloading delay optimization method in a mobile edge computing scenario. 【Background technique】 [0002] At present, the evolution of mobile communication networks to 5G is further accelerated. In the face of rapid traffic growth and user experience requirements, mobile communication networks will be under tremendous pressure. The emergence of Mobile Edge Computing (MEC) has effectively alleviated this pressure. By sinking the service platform with computing, storage, and communication capabilities to the edge of the network, MEC enables mobile users to offload their computing-intensive tasks to MEC devices, emphasizing proximity to mobile users to reduce network operation and service delivery delays. It has developed and evolved into an important technology for 5G mobile communication systems, and is currently widely used in all aspects of commun...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L12/24H04L29/08G06N3/08G06N3/04
CPCH04L41/083H04L41/145H04L41/142H04L67/10G06N3/08G06N3/044G06N3/045
Inventor 李立欣杨佩彤梁微李旭张会生程岳
Owner NORTHWESTERN POLYTECHNICAL UNIV