METHOD FOR A DESIGN EVALUATION OF A SYSTEM

• US 20140052432A1
• Filed: 10/17/2013
• Published: 02/20/2014
• Est. Priority Date: 04/23/2011
• Status: Active Grant

• Current Assignee: Michael Deubzer
• Original Assignee: Michael Deubzer
• Inventors: Deubzer, Michael
• Granted Patent: US 9,405,864 B2
• Time in Patent Office: Days
• US Class Current: 703/21
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06F 30/33 Design verification, e.g. functional simulation or model checking
• CPC Class Codes: G06F 30/3308 using simulation
• CPC Class Codes: G06F 9/4881 Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
• CPC Class Codes: G06F 9/5038 considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration scheduling strategies G06F9/4881 and subgroups
• CPC Class Codes: G06Q 10/063112 Skill-based matching of a person or a group to a task
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network

Abstract

A method for the design evaluation of a system is described. The system is modelled and simulated on at least one computer. The model (1) of the system includes at least two functional units (40), each functional unit (40) capable of performing at least one type of task, and at least one scheduling unit (30), capable of assigning at least one task to at least one functional unit (40). At least one scheduling unit (30) is capable of assigning tasks to plural targets, wherein each target either is a functional unit (40) or a scheduling unit (30). Preferentially, the system is simulated by taking into account only instants of time (81) at which a state of the model (1) changes. External and internal stimuli (50) may be included in the simulation. The method may be used for optimizing the design of a system.

Claims

1. A method for the design evaluation of a system comprising the following steps:

providing the system with at least two functional units, each functional unit capable of performing at least one type of task, and at least one scheduling unit capable of assigning at least one task to at least one functional unit, the at least one scheduling unit capable of assigning tasks to plural targets, each target being either a functional unit of the at least two functional units or a further scheduling unit of the at least one scheduling unit;

providing as a set of parameters a description of the system to at least one computer;

running a simulation of the system on the at least one computer;

generating output representing simulation results; and

taking into account in the simulation the capability of the at least one scheduling unit for removing a task from a target of the targets and assigning the task to a different target.

2. The method as recited in claim 1 wherein a possibility of a change of targets is taken into account in the simulation for the at least one scheduling unit, wherein the at least one scheduling unit can assign tasks to.

3. The method as recited in claim 1 wherein a task is broken down into at least one sub-task to a degree predefined by a user of the method, and the removing the task from a target and assigning the task to a different target occurs between the execution of sub-tasks of the respective task.

4. The method as recited in claim 1 wherein each task is assigned a cost.

5. The method as recited in claim 4 wherein the cost assigned is a fixed value, or a value sampled from a distribution, or a value derived from at least one parameter assigned to the task and a state of the simulated system.

6. The method as recited in claim 3 wherein each sub-task is assigned a cost.

7. The method as recited in claim 6 wherein the cost assigned is a fixed value, or a value sampled from a distribution, or a value derived from at least one parameter assigned to the sub-task and a state of the simulated system.

8. The method as recited in claim 1 wherein the simulation takes into account events generated outside the system.

9. The method as recited in claim 1 wherein the system is a computer system and the functional units are selected from the group consisting of:

a processing unit, a storage element, and a bus element.

10. The method as recited in claim 1 wherein each task is broken down into at least one sub-task, and each sub-task is assigned a cost, wherein the cost comprises at least one of:

at least a number of cycles required to execute the sub-task and a value of an energy required to execute the respective sub-task.

11. The method as recited in claim 1 wherein the simulation takes into account the possibility of changing a clock cycle of at least one functional unit.

12. The method as recited in claim 1 wherein the at least one computer is an embedded system.

13. The method as recited in claim 1 wherein the system is a transport network, the functional units are connections in the transport network, and the scheduling units select alternative connections between given nodes of the network.

14. The method as recited in claim 1 wherein the system is a number of collaborating persons, each person being qualified for at least one particular task, functional units being groups of such persons having at least one member, and scheduling units being management systems or managers.

15. The method as recited in claim 1 wherein each functional unit is a production or manufacturing device configured to perform at least one task within a manufacturing process, and the scheduling units distribute workload to the production or manufacturing devices.

16. The method as recited in claim 1 wherein the system is an energy supply system, each functional unit is an energy production unit, or an energy storage unit, or an energy transfer unit, or an energy consumer, and scheduling units control the production of energy, as well as the distribution of energy via energy transfer units to energy storage units and to energy consumers.

17. A method for optimizing a system, the system having at least two functional units, each functional unit capable of performing at least one type of task, and at least one scheduling unit capable of assigning at least one task to at least one functional unit of the at least two functional units, the at least one scheduling unit capable of assigning tasks to plural targets, each target being either a functional unit of the at least two functional units or a further scheduling unit of the at least one scheduling unit, the method comprising the steps of:

defining optimization targets,

providing as a set of parameters a description of the system to at least one computer;

running a simulation of the system on the at least one computer;

generating output representing simulation results;

taking into account in the simulation the capability of the at least one scheduling unit for removing a task from a target of the targets and assigning the task to a different target;

evaluating the simulation results; and

modifying the set of parameters describing the system for the simulation depending on the simulation results, and the simulation is reiterated, until optimization targets are achieved to a degree desired by a user.