AU2020103037A4 - A method of improving resilience in embedded iot networks by fault forecasting - Google Patents

A method of improving resilience in embedded iot networks by fault forecasting Download PDF

Info

Publication number
AU2020103037A4
AU2020103037A4 AU2020103037A AU2020103037A AU2020103037A4 AU 2020103037 A4 AU2020103037 A4 AU 2020103037A4 AU 2020103037 A AU2020103037 A AU 2020103037A AU 2020103037 A AU2020103037 A AU 2020103037A AU 2020103037 A4 AU2020103037 A4 AU 2020103037A4
Authority
AU
Australia
Prior art keywords
fault
resilience
service
embedded
forecasting
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
AU2020103037A
Inventor
Daniel D.
Sivaraman Eswaran
Dowlath Fathima
Duraisamy M.
Dinesh Mavaluru
Preethi N.
Jayabrabu Ramakrishnan
Mervin Retnadhas
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
D Daniel Dr
M Duraisamy Dr
N Preethi Dr
Fathima Dowlath Dr
Mavaluru Dinesh Dr
Ramakrishnan Jayabrabu Dr
Retnadhas Mervin Dr
Original Assignee
D Daniel Dr
M Duraisamy Dr
N Preethi Dr
Fathima Dowlath Dr
Mavaluru Dinesh Dr
Ramakrishnan Jayabrabu Dr
Retnadhas Mervin Dr
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by D Daniel Dr, M Duraisamy Dr, N Preethi Dr, Fathima Dowlath Dr, Mavaluru Dinesh Dr, Ramakrishnan Jayabrabu Dr, Retnadhas Mervin Dr filed Critical D Daniel Dr
Priority to AU2020103037A priority Critical patent/AU2020103037A4/en
Application granted granted Critical
Publication of AU2020103037A4 publication Critical patent/AU2020103037A4/en
Ceased legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0205—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system
    • G05B13/026—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system using a predictor
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Computer And Data Communications (AREA)

Abstract

A METHOD OF IMPROVING RESILIENCE IN EMBEDDED IOT NETWORKS BY FAULT FORECASTING ABSTRACT Everything that is around us today is automized with the internet of things. The automization requires resilience in embedded internet of things network, which in turn require a fault forecasting to sustain the quality of service. The status of the service is recorded in the cloud through the gateway, and the user can monitor the automization service. This invention provides a method of improving resilience in an embedded IoT where sensors and the cameras are deployed to get the information either the statistical or the image data. The data are computed by resilience embedded internet of things with high end computing resources. The extracted data are deployed by fault forecast to eliminate a problem before it happens and also respond to it after it happened. The status of the service is also recorded in the cloud through the gateway, and the user can monitor the automization service. This improved method of resilience embedded IoT networks by fault forecast provide quality of service such that it guarantees the service to the user. A METHOD OF IMPROVING RESILIENCE IN EMBEDDED IOT NETWORKS BY FAULT FORECASTING Drawings 0 o H HIGH END COMPUTER CLOUD DISPLAY INPUT RESILIENCE EMBEDDED IOT FAULTFORECASTING Fig. 1 Process flow diagram BACKUPANT)DIMENSION TIMELY RESPONSE PLANNING PROACTIVE APPROACH HETEROGENEITY FAULT-HYPOTHESIS Fig 2(a) Fault forecast - Proactive approach 1 P a g e

Description

A METHOD OF IMPROVING RESILIENCE IN EMBEDDED IOT NETWORKS BY FAULT FORECASTING
Drawings
0 o H HIGH END COMPUTER CLOUD DISPLAY INPUT RESILIENCE EMBEDDED IOT
FAULTFORECASTING
Fig. 1 Process flow diagram
BACKUPANT)DIMENSION TIMELY RESPONSE PLANNING PROACTIVE APPROACH HETEROGENEITY FAULT-HYPOTHESIS
Fig 2(a) Fault forecast - Proactive approach
1 Pag e
Editorial Note 2020103037 There is 5 pages of Description only.
A METHOD OF IMPROVING RESILIENCE IN EMBEDDED IOT NETWORKS BY FAULT FORECASTING
Description Field of the Invention.
The Field of the invention is related to embedded IoT
In today's technology world, everything needed to be automized with the internet of things. Especially, when designing a fault forecasting advanced application, there needs resilience in embedded internet of things network. This invention provides a method of improving resilience in an embedded IoT where sensors and the cameras are deployed to get the information either the statistical or the image data. The fault forecast on the approach that can eliminate a problem before it happens and also respond to it after it happened.
Background of the invention.
Earlier in any application, it can be related to mechanical services, medical or industrial oriented operation, it was wholly carried out manually. As technology developed day by day, now the world demands automation in any field. It may be related to services or applications. This automation impact requires resilience embedded in the internet of things for any services or application.
The internet of things relates all the devices over a network, which is like nodes in a network topology. This resilience embedded in the internet of things has improved by deploying fault forecast features in the automation of services.
When an automization is implemented in service, if any future problems are about to occur are known by the fault forecast feature, necessary supporting action can be taken to prevent this from happening.
One of the main proactive approaches is a timely response to the service. When the service has to complete a target in a stipulated time, it has to meet the requirements. If it is not completing the task in a stipulated time, it may have a significant impact on the services. Completing the task it makes ensures that it has all the resources and need to be deterministic.
Next, the backup and the dimension planning have to be made in any services to meet requirements at the time of resource lacking. Some times when there is an issue with the network where the nodes have to be minimized to avoid failure, the dimension of the network planning also exhibits a vital role.
Heterogeneity is another parameter to look after in case of handling emergency services with priority. But the rest of the task completes with the best effect though it is not handled with priority.
Fault-hypothesis is another parameter that needs to be concerned. The number of faults is known that occur due to software failure or accidents, which may affect the quality of service and have an impact on cost. The resilience is improved such that it guarantees the user about the service it provides.
Not only can it assist in proactive services, but it can also assist in a reactive approach with the M&C system (monitoring and control). During the functioning of any services, if the problems are detected by fault forecast in embedded IoT, the system responds to it immediately to solve the problem and bring back the normal function again.
Even for a reactive approach, the time constraint parameter is essential. If the task is missed or error occurred, it would affect the precision of the automated device. So, an efficient algorithm should be deployed to complete the task.
The fault forecasting is a behavior analysis on the services for precision forecasting of the exact fault in the services.
A non-centralized architecture can detect failures more accurately with minimized delay. Synchronization is deployed to provide optimal decisions globally. Objects of the Invention
The main object of the invention is to deploy a method of improving resilience in embedded internet of things networks by fault forecasting, for all the automized application that are involved with the internet of things, embedded with software approach for processing the statistical or the image data that are obtained from sensors and the cameras. But still, they are prone to failure as there are several factors relating to the function of the system to the ecosystem. The fault forecast on the approach that can eliminate a problem before it happens and also respond to it after it happened.
Summary of the Invention
The automized service requires resilience in embedded internet of things network. There is a need to improve resilience by deploying fault forecasting features in the system. For example, in an automized car, the data or the information are gathered by the sensors. Using a camera, an input image is obtained. Especially in case of a mechanical source that needs to be processed, it needs a control area network protocol to communicate with the system. It is then handled by resilience embedded internet of things to computer with high-end resources. The data extracted are further processed for fault forecasting. The fault forecast on the approach that can eliminate a problem before it happens and also respond to it after it happened. For a proactive approach, whether the tasks can complete before the deadline or whether it has sufficient backups to manage forthcoming traffic of service. It also deploys dimension planning to order to meet the requirement at the time of resource lacking. Heterogeneity is another parameter to look after in case of handling emergency services with priority. But the rest of the task completes with the best effect though it is not handled with priority. Fault-hypothesis is also a concern. Not only can it assist in proactive services, but it can also assist in a reactive approach with the M&C system (monitoring and control). Even for a reactive approach, the time constraint parameter is essential. If the task is missed or error occurred, it would affect the precision of the automated device. So, an efficient algorithm should be deployed to complete the task. The fault forecasting is a behavior analysis on the services for precision forecasting of the exact fault in the services. A non-centralized architecture can detect failures more accurately with minimized delay. Synchronization is deployed to provide optimal decisions globally. The resilience is improved to provide quality of service such that it guarantees the service to the user. The status of the service is recorded in the cloud through the gateway, and the user can monitor the automization service.
Detailed Description of the Invention
Fig 1. Shows the process flow diagram for a method of improving resilience in embedded internet of things networks by fault forecasting. For example, in an automized car, the data or the information is gathered by the sensors. The control area network protocol handles the sensor input and the input image as it is a communication of mechanical source to the system. It is processed by resilience embedded internet of things network, which is deployed by computer systems with high-end resources. The data extracted are further processed for fault forecasting. The fault forecast on the approach that can eliminate a problem before it happens and also respond to it after it happened. For a proactive approach, whether the tasks able to complete before the deadline, dimension planning, heterogeneity, and fault-hypothesis are concerned. Not only can it assist in proactive services, but it can also assist in a reactive approach with the M&C system (monitoring and control). Even for a reactive approach, the time constraint parameter is essential. It also concerns the fault forecasting behavior analysis, non-centralized architecture, and synchronization. The resilience is improved to provide quality of service such that it guarantees the service to the user. The status of the service is recorded in the cloud through the gateway, and the user can monitor the automization service from the display.
Fig. 2(a) & 2 (b) shows the proactive and reactive approach of the fault forecasting. One of the main proactive approaches is a timely response to the service. When the service has to complete a target in a stipulated time, it has to meet the requirements. If it is not completing the task in a stipulated time, it may have a significant impact on the services. For completing the task, it makes ensure it has all the resources and needs to be deterministic. Next is the backup, and the dimension planning has to be made in any services to meet requirements at the time of resource lacking. Some times when there is an issue with a network where the nodes have to be minimized to avoid failure, the dimension of the network planning also exhibits a vital role. Heterogeneity is another parameter to look after in case of handling emergency services with priority. But the rest of the task completes with the best effect though it is not handled with priority. Fault-hypothesis is another parameter that needs to be concerned. The number of faults is known that occur due to software failure or accidents, which may affect the quality of service and have an impact on cost. The resilience is improved such that it guarantees the user about the service it provides. Not only can it assist in proactive services, but it can also assist in a reactive approach with the M&C system (monitoring and control). During the functioning of any services, if the problems are detected by fault forecast in embedded IoT, the system responds to it immediately to solve the problem and bring back the normal function again. Even for a reactive approach, the time constraint parameter is significant. If the task is missed or error occurred, it would affect the precision of the automated device. So, an efficient algorithm should be deployed to complete the task. The fault forecasting is a behavior analysis on the services for precision forecasting of the exact fault in the services. A non-centralized architecture can detect failures more accurately with minimized delay. Synchronization is deployed to provide optimal decisions globally.

Claims (9)

A METHOD OF IMPROVING RESILIENCE IN EMBEDDED IOT NETWORKS BY FAULT FORECASTING CLAIMS: We Claim:
1. Sensors capture different feature parameters in the automized car.
2. Cameras capture images to be processed.
3. The Control area network protocol communicates mechanical resources to the system.
4. An optic fiber connection for computing.
5. Highly configured system to process the input resources.
6. Resilience embedded internet of things deployed with a high configured system to perform computation.
7. A fault forecast performs analysis to eliminate a problem before it happens and also respond to it after it happened.
8. The predictions for every service are recorded in the cloud platform through the gateway.
9. Users can monitor the status of the process in a smart device display.
1 Pag e
A METHOD OF IMPROVING RESILIENCE IN EMBEDDED 27 Oct 2020
IOT NETWORKS BY FAULT FORECASTING
Drawings 2020103037
Fig. 1 Process flow diagram
Fig 2(a) Fault forecast – Proactive approach
1|Page
Fig 2(b) Fault forecast – Reactive approach
2|Page
AU2020103037A 2020-10-27 2020-10-27 A method of improving resilience in embedded iot networks by fault forecasting Ceased AU2020103037A4 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2020103037A AU2020103037A4 (en) 2020-10-27 2020-10-27 A method of improving resilience in embedded iot networks by fault forecasting

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
AU2020103037A AU2020103037A4 (en) 2020-10-27 2020-10-27 A method of improving resilience in embedded iot networks by fault forecasting

Publications (1)

Publication Number Publication Date
AU2020103037A4 true AU2020103037A4 (en) 2020-12-24

Family

ID=73838751

Family Applications (1)

Application Number Title Priority Date Filing Date
AU2020103037A Ceased AU2020103037A4 (en) 2020-10-27 2020-10-27 A method of improving resilience in embedded iot networks by fault forecasting

Country Status (1)

Country Link
AU (1) AU2020103037A4 (en)

Similar Documents

Publication Publication Date Title
US10579453B2 (en) Stream-processing data
US10061989B2 (en) Information transfer apparatus and method for image recognition
CN105357038A (en) Method and system for monitoring virtual machine cluster
CN103685459A (en) Distributed system, server computer, distributed management server, and failure prevention method
EP3413202B1 (en) Automatic display unit backup during failures of one more display units through the utilization of graphic user interface objects defined for control transfer and reversion after resolution of the failures
CN108021430B (en) Distributed task processing method and device
JP6961740B2 (en) Use of AI to ensure data integrity of industrial controllers
US20180308002A1 (en) Data processing system with machine learning engine to provide system control functions
CN112835604B (en) System gray version release management method, system, equipment and medium
EP3591530B1 (en) Intelligent backup and recovery of cloud computing environment
AU2020101901A4 (en) A method of improving resilience in embedded iot networks by fault forecasting
CN113734195B (en) Unmanned vehicle control method and device, storage medium and unmanned vehicle
US11934855B2 (en) System and method to autonomously manage hybrid information technology (IT) infrastructure
JP2021077129A (en) Information processing system, model control method, and storage medium
CN115328741A (en) Exception handling method, device, equipment and storage medium
AU2020103037A4 (en) A method of improving resilience in embedded iot networks by fault forecasting
KR101656012B1 (en) IT Infra Quality Monitoring System and Method therefor
US10878690B2 (en) Unified status and alarm management for operations, monitoring, and maintenance of legacy and modern control systems from common user interface
CN112433733A (en) Controlling performance of deep learning models deployed on edge devices via predictive models
KR101026637B1 (en) Method for healing faults in sensor network and the sensor network for implementing the method
US20230305931A1 (en) Control device and non-transitory machine readable storage medium
CN109792617A (en) The application program elastic system and its method of application program for being deployed on platform
CN110401559A (en) A kind of server restorative procedure and device
WO2011087169A1 (en) Method for determining problem level in operating system
CN117135151B (en) Fault detection method of GPU cluster, electronic equipment and storage medium

Legal Events

Date Code Title Description
FGI Letters patent sealed or granted (innovation patent)
MK22 Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry