Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

DIDS task scheduling optimization method based on deep reinforcement learning

A task scheduling and reinforcement learning technology, applied in the field of network security, can solve the problems of DIDS load reduction, excessive state space and action space, and large memory space occupation, so as to achieve load reduction and solve the problem of excessive state space and action space Effect

Pending Publication Date: 2021-11-12
XI'AN POLYTECHNIC UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a DIDS task scheduling optimization method based on deep reinforcement learning, which can dynamically adjust the task scheduling strategy according to network changes in the edge computing environment, so that the load of DIDS can be effectively reduced, and at the same time, it can solve the problems of existing technologies. The large state space and action space in the middle cause the problem that the memory space is too large

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
  • DIDS task scheduling optimization method based on deep reinforcement learning
  • DIDS task scheduling optimization method based on deep reinforcement learning
  • DIDS task scheduling optimization method based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be described in detail below in combination with specific embodiments.

[0044] The DIDS task scheduling optimization method based on deep reinforcement learning of the present invention is specifically implemented according to the following steps:

[0045] Step 1. Before the work starts, evaluate the performance of each detection engine in DIDS, and collect the data volume da (unit bit) of the test traffic, detection time dt (unit ms), memory usage mu (unit Mb) and detection engine is CPU frequency Fi (unit Ghz) information, and define the calculation model of the performance index pi (performance index) of the detection engine as follows:

[0046]

[0047] After testing all the detection engines, they are divided into different grades d, d=1,...,D according to their performance. If the difference of d value is within 10%, it can be classified into the same grade;

[0048] Step 2. After starting to work, when a data packet arrives and nee...

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 discloses a DIDS task scheduling optimization method based on deep reinforcement learning, and the method comprises the following steps: carrying out the performance grade evaluation of a detection engine, carrying out the load evaluation of a detected data package, carrying out the modeling through a Markov decision process, and building a deep recurrent neural network model. A scheduler makes a decision and determines how to allocate a detection engine to detect a data packet. For a distributed intrusion detection system with a fixed number of detection engines, the task scheduling algorithm provided by the invention can make an optimal decision to reduce the overall load of the system, and also can solve the problem of too large memory space occupation caused by too large state space and action space.

Description

technical field [0001] The invention belongs to the technical field of network security, and relates to a DIDS task scheduling optimization method based on deep reinforcement learning. Background technique [0002] As a new computing model, edge computing is also facing new network security challenges while developing rapidly. The task allocation of distributed intrusion detection system (DIDS) in the edge computing environment with limited node performance is a typical resource-constrained task scheduling problem. Due to the limited performance of edge nodes, DIDS (DIDS, Distributed Intrusion Detection System), which relies on high-performance devices in cloud computing, needs to be improved to lower load in order to detect data near the edge of the network. In the existing technology, when using reinforcement learning to solve the above problems, if the state space and action space are too large or high-dimensional continuous, it will cause many problems such as too much ...

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
IPC IPC(8): G06F9/50G06N3/04G06N3/08
CPCG06F9/5072G06N3/084G06N3/044G06N3/045
Inventor 赵旭薛涛江晋
Owner XI'AN POLYTECHNIC UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com