Distributed simulation and synchronization

• US 8,069,021 B2
• Filed: 09/28/2007
• Issued: 11/29/2011
• Est. Priority Date: 09/28/2007
• Status: Active Grant

• Current Assignee: Rockwell Automation Technologies Incorporated (Allen-Bradley Co., Inc.)
• Original Assignee: Rockwell Automation Technologies Incorporated (Allen-Bradley Co., Inc.)
• Inventors: Glavach, Mark Anson, Sturrock, David Thayer, Drake, Glenn Richardson, Crooks, Cory R., Kolt, Genevieve O'Neill, Takus, A. David, Palmieri, Frank Anthony Jr.
• Primary Examiner(s): Thangavelu; Kandasamy
• Application Number:
  US11/864,620
• Publication Number:
  US 20090089030A1
• Time in Patent Office: 1,523 Days
• Field of Search: 703/13, 703/6, 703/11, 703/7, 703/22, 703/2, 703/21, 705/1, 706/10, 717/104, 717/109, 716/21, 700/245, 345/156, 701/3, 714/724, 718/104, 709/201
• US Class Current: 703/6
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30

Abstract

System(s) and method(s) facilitate a distributed simulation of an industrial control system. A model of the industrial control system is generated and computing resources are scheduled for simulating portions of a simulation according to the model. Computing resources are scheduled to mitigate computational bottlenecks in the simulation and synchronize portions of the simulation deployed in disparate computing resources. Sub-processes of a control process can be simulated in dedicated computing resources as a part of a distributed simulation of the control process. Execution time of one or more portions of a distributed simulation can be increased or slowed down to synchronize said portions.

Claims

1. A distributed simulation system, comprising:

at least one processor;

at least one memory communicatively coupled to the at least one processor, the at least one memory having stored therein computer-executable instructions to implement the system, including;

a simulation component configured to simulate a plurality of components associated with a controlled process of an industrial control system;

an optimization component configured to estimate computational demand to simulate a component of the plurality of components, wherein the optimization component is further configured to estimate the computational demand using a prototype simulation that employs simplified assumptions of the component based upon a degree of data dependence between the component and other components of the plurality of components.

2. The system of claim 1, wherein the simulation component includes two or more simulation units, each configured to execute a portion of a simulation.

3. The system of claim 2, further comprising a coordination component configured to schedule the two or more simulation units to perform a distributed simulation.

4. The system of claim 1, further comprising a timing component configured to increase or decrease execution time of the component.

5. The system of claim 4, wherein the timing component is further configured to employ an adaptive time step with feedback algorithm to speed up execution time of the component.

6. The system of claim 1, wherein the simulation component further comprises a storage component configured to store code modules to perform the simulation of the plurality of components of the industrial control system.

7. The system of claim 1, further comprising a distribution component configured to dynamically reassign simulation resources according to the estimated computational demand.

8. The system of claim 1, wherein the optimization component is further configured to analyze relationships between the plurality of components of the industrial control system to determine one or more relationships that inhibit parallel computing.

9. The system of claim 8, wherein the optimization component is further configured to infer a restructured process with substantially a same functionality as the controlled process, wherein the restructured process mitigates the one or more relationships that inhibit parallel computing.

10. The system of claim 8, wherein the optimization component is further configured to employ a prototyping simulation of two or more components of the industrial control system to determine at least one computational bottleneck that inhibits parallel computing.

11. The system of claim 10, further comprising a coordination component configured to schedule a first set of simulation units to simulate one or more components associated with the at least one computational bottleneck, and a second set of simulation units to simulate one or more components not associated with said at least one computational bottleneck.

12. A method for simulating an industrial control system, the method comprising:

receiving a model describing behavior of a plurality of industrial components associated with an industrial process;

estimating computational demand to simulate a component of the plurality of components based upon a degree of data dependence between the component and other components of the plurality of components, wherein the estimating the computational demand further comprises using a prototype simulation that employs simplified assumptions of the component;

distributing a simulation of the behavior of the plurality of industrial components among a plurality of computing resources based upon the estimated computational demand; and

executing the distributed simulation.

13. The method of claim 12, further comprising:

analyzing relationships between the plurality of industrial components including determining one or more relationships that inhibit parallel computing.

14. The method of claim 13, further comprising inferring a restructured process with substantially a same functionality as the industrial process, wherein the restructured process mitigates the one or more relationships that inhibit parallel computing.

15. The method of claim 14, further comprising:

performing a prototyping simulation of the plurality of industrial components to determine one or more computational bottlenecks; and

scheduling a first set of computing resources to simulate at least one industrial component associated with the one or more computational bottlenecks, and a second set of computing resources to simulate at least one industrial component not associated with said one or more computational bottlenecks.

16. The method of claim 12, further comprising synchronizing one or more portions of the distributed simulation by adapting a time step for speeding up or slowing down execution of one or more of said portions.

17. An apparatus that operates in an industrial environment, the apparatus comprising:

means for accessing a plurality of computational resources for simulating a plurality of components associated with an industrial process in an automated control system;

means for estimating computational demand to simulate a component of the plurality of components based upon a degree of data dependence between the component and other components of the plurality of components, wherein the estimating computational demand further comprises using a prototype simulation that employs simplified assumptions of the component;

means for deploying a simulation of the plurality of components on the plurality of computational resources in a distributed manner based upon the estimated computational demand; and

means for executing the distributed simulation.

18. A non-transitory computer-readable medium, comprising:

instructions for generating a computational model of a plurality of components associated with an industrial process in an industrial automation system;

instructions for estimating computational demand to simulate a component of the plurality of components as a function of a degree of data dependence between the component and other components of the plurality of components, wherein the estimating the computational demand further comprises using a prototype simulation that employs simplified assumptions of the component;

instructions for distributing a simulation of a behavior of the plurality of components onto a set of computing resources based upon the estimated computational demand;

instructions for executing the distributed simulation.