On-line adaptive computing offloading method and system for marine tasks

An adaptive computing and computing offloading technology, applied in the field of network communication, can solve the problems of difficult to accurately train the model, difficult to determine reward information, affecting the effectiveness of computing offloading, etc., to ensure QoS and reduce task delay.

Active Publication Date: 2022-07-05
SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, if reinforcement learning is used in ocean-oriented computing tasks, due to the lack of user information and the complex dynamics of the ocean environment, the reward information is difficult to determine, which makes it difficult to train the model accurately and affects the effectiveness of computing offloading, making it difficult for ocean tasks to quickly improve quality finish

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
  • On-line adaptive computing offloading method and system for marine tasks
  • On-line adaptive computing offloading method and system for marine tasks
  • On-line adaptive computing offloading method and system for marine tasks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] like figure 1 As shown, this embodiment provides an online adaptive computing offloading method oriented to marine tasks, including the following steps:

[0030] S101: Obtain maritime edge network information and device computing task request information;

[0031] S102: Obtain a marine task computing offloading decision based on the maritime edge network information and the device computing task request information and the constructed computing offloading decision-making system model;

[0032] Wherein, the construction process of the unloading decision-making system model includes: building an objective function with the goal of minimizing the average task completion delay constrained by the energy budget of the equipment, with QoS requirements and the total energy consumption of the equipment as constraints, constructing unloading based on the objective function and the constraints decision system model;

[0033] S103: Execute the computing task based on the marine t...

Embodiment 2

[0131] This embodiment provides an online adaptive computing offloading system oriented to marine tasks, including:

[0132] an information acquisition module, configured to: acquire maritime edge network information and device computing task request information;

[0133] The offloading decision computing module is configured to: obtain the marine task computing offloading decision based on the maritime edge network information and the device computing task request information and the constructed computing offloading decision system model;

[0134] Wherein, the construction process of the unloading decision-making system model includes: with the goal of minimizing the average task completion delay constrained by the energy budget of the equipment, with the QoS requirements and the total energy consumption of the equipment as the constraints, building the unloading decision-making system model;

[0135] The task execution result output module is configured to: execute the devic...

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 invention belongs to the technical field of network communication, and provides an online self-adaptive computing offloading method and system oriented to marine tasks, obtains environmental information and user information in real time, and establishes an accurate model to describe the current system, thereby realizing efficient task allocation and ensuring timely extension. Therefore, unlike traditional offline methods, we build an offloading model and optimize it in real-time to achieve efficient offloading of device tasks by learning from historical assignment policies to provide current decisions without future information, based on reinforcement learning. The solution of the present invention can not only make full use of energy, but also effectively reduce task delay and ensure QoS.

Description

technical field [0001] The invention belongs to the technical field of network communication, and in particular relates to an online self-adaptive computing offloading method and system for marine tasks. Background technique [0002] Ocean buoys play an important role in marine hydrology, water quality and meteorological monitoring, but they will generate computationally intensive and delay-sensitive data processing tasks during operation, which brings great challenges to the computational delay of ocean service tasks. . [0003] Mobile edge computing can effectively enhance the computing power of mobile devices. The mobile device offloads its own computing tasks to the edge server, and the edge server completes the computing processing of the offloading task and feeds back the calculation results to the mobile device, thereby satisfying the task execution requirements of the mobile device. However, due to the limitations of the special geographical environment at sea, it i...

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): G06F9/445
CPCG06F9/44594Y02D30/70
Inventor 王英龙张玮杨美红吴晓明郝昊史慧玲刘礼彬
Owner SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap