JP4509951B2 - Simulation execution control device and program - Google Patents

Description

  The present invention relates to a distributed simulation system in which individual simulation elements of the simulation execution are shared and executed by a plurality of logical processors in a simulation system for various uses such as training simulation and simulation for planning / prediction / analysis. It belongs to a technical field in which elements are optimally arranged in a logical processor.

  A distributed simulation system is a system in which individual simulation elements constituting a simulation are shared and executed by a plurality of logical processors. In a distributed simulation system, the processing load of individual simulation elements and the frequency of event exchange between simulation elements vary depending on the simulation processing content and processing status, so the processing load per logical processor, data communication frequency, etc. are unbalanced. Is likely to occur, and it is difficult to optimize the processing speed of the entire system. For this reason, conventionally, a method for dynamically adjusting the load balance between logical processors has been proposed.

  Japanese Patent Laid-Open No. 2002-342297 discloses a simulation based on system resources such as CPU load and memory usage consumed by execution of simulation elements on each logical processor, and data communication volume required for event exchange between simulation elements. This is a proposal for a distributed simulation controller that determines the placement of elements in a logical processor. In this proposal, the CPU load factor and memory usage consumed by the simulation elements on the logical processor are measured during the execution of the logical processor, and the data communication required for event exchange between the simulation elements is measured, and their statistics are measured. Based on the data, the placement location of the simulation element for each logical processor in the next simulation to be executed is determined and placed.

  Conventional proposals improve the efficiency of distributed simulation execution by determining the placement of simulation elements between logical processors based on the CPU load factor, memory usage, and network load statistical information in actual simulation element execution. Although it can be performed, there are the following problems.

  First, in the conventional proposal, it is difficult to optimally arrange the simulation elements in a situation in which the CPU usage rate, the memory usage amount, and the network load of the simulation elements change greatly in the execution of the simulation. .

In addition, the conventional proposal is effective in the case where the CPU usage rate, the memory usage amount, and the network load are statistically the same in the next simulation execution, but the dynamic simulation parameter value can be changed by humans. In the case of such a simulation or a simulation in which the result changes every time depending on random number generation or the like, the effect cannot be exhibited.
JP 2002-342297 A

  The present invention, which has been a conventional problem, is a situation where the CPU usage rate, the memory usage amount, and the network load of the simulation elements change dynamically during simulation execution, or a dynamic simulation parameter by a human being Distributed simulation for always allocating the optimal simulation elements to logical processors, even in the case of simulations that allow value changes or simulations that change the results each time depending on random number generation, etc. The main purpose is to provide a system.

The simulation execution control apparatus according to the present invention is:
A simulation execution control device for controlling the execution of a plurality of simulation elements,
For each simulation element, specify other simulation elements that are the counterpart of data transmission and reception, and a transmission / reception determination unit that determines the frequency of data transmission / reception with the other specified simulation elements,
A processor selection unit that selects an execution processor that executes a simulation element from among the plurality of processors, for each of the plurality of simulation elements based on a determination result of the transmission / reception determination unit.

The processor selection unit includes:
2. The simulation execution control apparatus according to claim 1, wherein execution processors of two simulation elements having a high frequency of data transmission / reception between each other are the same processor.

  According to the present invention, the relationship and frequency of data transmission / reception between simulation elements are determined, and an execution processor that executes the simulation element is selected based on the determination result. Therefore, by performing communication processing between simulation elements with high communication frequency within the same logical processor, communication processing with other logical processors can be reduced, and the processing efficiency of the entire system can be improved. it can.

Embodiment 1 FIG.
A distributed simulation system is a system in which individual simulation elements constituting a simulation are shared and executed by a plurality of logical processors. In a distributed simulation system, the processing load of individual simulation elements and the frequency of event exchange between simulation elements vary depending on the simulation processing content and processing status, so the processing load per logical processor, data communication frequency, etc. are unbalanced. Is likely to occur, and it is difficult to optimize the processing speed of the entire system.
In this embodiment, in order to always arrange the optimal simulation element for the logical processor, it is not an element that fluctuates according to the situation of the CPU usage rate, the memory usage amount, and the network load, which has been used in the conventional proposal, Focus on the simulation situation that causes these factors to fluctuate.

In the first embodiment of the present invention, execution distribution focusing on the relationship and frequency of data transmission / reception between simulation elements, which is determined according to the simulation status, will be described as a form of execution distribution of simulation elements to logical processors.
FIG. 1 shows a configuration example of a distributed simulation system according to Embodiment 1 of the present invention.
In FIG. 1, reference numeral 101 denotes a plurality of logical processors constituting the distributed simulation system according to the present embodiment (hereinafter also simply referred to as processors).
Reference numeral 102 denotes a plurality of simulation elements, which are execution element programs of the distributed simulation system according to the present embodiment, and the execution state is in two states: a pause state or an active state. The same number of simulation elements 102 of the same type are arranged in each logical processor 101, and only one simulation element 102 is in an “active” state as a whole of the distributed simulation system.
Reference numeral 103 denotes a simulation element management unit that manages the simulation elements 102 in each logical processor 101 in each logical processor.
Reference numeral 104 denotes a simulation element execution state control unit (simulation execution control device) that controls the execution state (pause state or active state) of the simulation element 102 in each logical processor 101 in each logical processor 101.
Reference numeral 105 denotes an inter-simulation element communication control unit that controls transmission / reception of data to / from other simulation elements 102 in each logical processor 101 in an event or the like that occurs during the simulation of the simulation elements 102 in each logical processor 101. .

FIG. 2 shows an internal configuration example of the simulation element execution control unit 104.
In FIG. 2, the communication control unit interface 1041 serves as an interface with the inter-simulation element communication control unit 105 in the simulation element execution control unit 104.
The transmission / reception determination unit 1042 specifies, for each simulation element 102, other simulation elements that are data transmission / reception destinations, and determines the frequency of data transmission / reception with the other specified simulation elements.
Based on the determination result of the transmission / reception determination unit 1042, the processor selection unit 1043 selects an execution processor that executes the simulation element for each of the plurality of simulation elements from the plurality of processors. As will be described later, the processor selection unit 1043 sets the execution processors of the two simulation elements having a high data transmission / reception frequency between the same processor as the same processor. In addition, the processor selection unit 1043 sets the execution processors of the two simulation elements that do not perform data transmission / reception to be different processors.

In the present embodiment, in the distributed simulation system, the processing efficiency of the entire system is improved by controlling the activity / hibernation state of simulation elements executed by each logical processor in accordance with the simulation status.
That is, paying attention to the processing load of individual simulation elements and the simulation situation that causes the event exchange frequency between simulation elements to fluctuate, the execution distribution of the simulation elements to the logical processors is performed according to the simulation situation. Specifically, the transmission / reception determination unit 1042 specifies, for each simulation element 102, other simulation elements that are data transmission / reception destinations, determines the data transmission / reception frequency with the other specified simulation elements, and selects the processor. The unit 1043 selects, from each of the plurality of processors 101, an execution processor that executes the simulation element for each of the plurality of simulation elements based on the determination result.

FIG. 12 is a diagram illustrating an example of hardware resources of the distributed simulation system according to the first embodiment. The distributed simulation system is realized by a computer device.
In FIG. 12, the distributed simulation system includes a processor 911 (also referred to as a CPU (Central Processing Unit), a central processing unit, a processing unit, an arithmetic unit, a microprocessor, and a microcomputer) that executes simulation elements and programs. The processor 911 is connected to, for example, a ROM (Read Only Memory) 913, a RAM (Random Access Memory) 914, a communication board 915, a display device 901, a keyboard 902, a mouse 903, and a magnetic disk device 920 via a bus 912. May be. The processor 911 also controls these hardware devices. Further, the processor 911 may be connected to an FDD 904 (Flexible Disk Drive), a compact disk device 905 (CDD), a printer device 906, and a scanner device 907. Further, instead of the magnetic disk device 920, a storage device such as an optical disk device or a memory card read / write device may be used.
In FIG. 12, a single processor 911 is shown, but this is for drawing reasons. In this embodiment, a plurality of processors are arranged.
The RAM 914 is an example of a volatile memory. The storage media of the ROM 913, the FDD 904, the CDD 905, and the magnetic disk device 920 are an example of a nonvolatile memory. These are examples of a storage device or a storage unit.
The communication board 915, the keyboard 902, the scanner device 907, the FDD 904, and the like are examples of an input unit and an input device.
Further, the communication board 915, the display device 901, the printer device 906, and the like are examples of an output unit and an output device.

The communication board 915 is connected to the network. For example, the communication board 915 may be connected to a LAN (local area network), the Internet, a WAN (wide area network), or the like.
The magnetic disk device 920 stores an operating system 921 (OS), a window system 922, a program group 923, and a file group 924. The programs in the program group 923 are executed by the processor 911, the operating system 921, and the window system 922.

The program group 923 stores programs for executing functions described as “˜unit” and “˜means” in the following description. The program is read and executed by the processor 911.
In addition, each simulation element 102 is stored as a program group 923 and read and executed by the processor 911.
In the file group 924, information, data, signal values, etc. described as “determination result of”, “calculation result of”, “processing result of”, “evaluation result of”, etc. Variable values and parameters are stored as items of “˜file” and “˜database”. The “˜file” and “˜database” are stored in a recording medium such as a disk or a memory. Information, data, signal values, variable values, and parameters stored in a storage medium such as a disk or memory are read out to a main memory or a cache memory by a processor 911 via a read / write circuit, and extracted, searched, referenced, and compared. Used for processor operations such as computation, calculation, processing, output, printing, and display. Information, data, signal values, variable values, and parameters are stored in the main memory, cache memory, and buffer memory during the extraction, search, reference, comparison, operation, calculation, processing, output, printing, display, and extraction processor operations. Temporarily stored.
The arrows in the flowchart described below mainly indicate input / output of data and signals. The data and signal values are the RAM 914 memory, FDD 904 flexible disk, CDD 905 compact disk, magnetic disk device 920 magnetic disk, In addition, it is recorded on a recording medium such as an optical disc, a mini disc, or a DVD. Data and signals are transmitted online via a bus 912, signal lines, cables, or other transmission media.

  In addition, what is described as “to part” and “to means” in the following description may be “to circuit”, “to apparatus”, “to apparatus”, and “to means”. It may be “step”, “˜procedure”, “˜processing”. That is, what is described as “˜unit” and “˜means” may be realized by firmware stored in the ROM 913. Alternatively, it may be implemented only by software, or only by hardware such as elements, devices, substrates, and wirings, by a combination of software and hardware, or by a combination of firmware. Firmware and software are stored as programs in a recording medium such as a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, and a DVD. The program is read by the processor 911 and executed by the processor 911. That is, the program causes the computer to function as “to part” and “to means” described below. Alternatively, the procedure or method of “˜unit” and “˜means” described below is executed by a computer.

  As described above, the distributed simulation system shown in the present embodiment and the embodiments described below includes a processor as a processing device, a memory as a storage device, a magnetic disk, a keyboard as an input device, a mouse, and a display device as an output device, A computer including a communication board and the like, and as described above, functions indicated as “˜unit” and “˜means” are realized by using these processing devices, storage devices, input devices, and output devices.

  Next, based on a simulation execution example, the operation will be described with reference to FIGS.

FIG. 3 is an example of a simulation executed in the distributed simulation system of FIG. 3, the distributed simulation system includes two logical processors (101) in FIG. 1, that is, a logical processor 1 (201) and a logical processor 2 (211).
As the simulation element 102 of FIG. 1 of each logical processor, the logical processor 1 (201) includes four types of logic processors: aircraft 1 (207), aircraft 2 (208), radar 1 (209), and air traffic control 1 (210). 2 (211) is arranged with four types of aircraft 1 (216), aircraft 2 (217), radar 1 (218), and air traffic control 1 (219).
In addition, the execution state of each simulation element has four types of the active state of the aircraft 1 (207), the aircraft 2 (208), the radar 1 (209), and the air traffic control 1 (210) of the logical processor 1 (201). The four types of aircraft 1 (216), aircraft 2 (217), radar 1 (218), and air traffic control 1 (219) of the logical processor 2 (211) are in a dormant state.

Here, the operation until the execution state of each simulation element as shown in FIG. 3 is determined by the simulation element execution control unit 104 in FIG. 1 will be described with reference to FIGS.
FIG. 4 is a diagram showing an example of a simulation situation executed by the distributed simulation system of FIG. 3. Based on the aircraft position information detected by the radar 1 by the air traffic control 1, the aircraft 1 and the aircraft 2. It represents a simulation situation where two aircraft are in communication.
5 is given as an initial setting for the inter-simulation element communication control unit 1 (205) and the inter-simulation element communication control unit 2 (215) in FIG. 3, or the simulation inter-element communication control unit 1 (205) 4 shows the relationship and frequency of data transmission / reception between simulation elements in the simulation situation of FIG. 4 held by the inter-element communication control unit 2 (215) dynamically monitoring the data transmission / reception situation of each simulation element. ing. FIG. 6 is a diagram showing the data transmission / reception relationship between the simulation elements shown in FIG. 5 in a tabular format.

Here, among the simulation element execution control unit 1 (204) and the simulation element execution control unit 2 (214) in FIG. 3, the simulation element execution control unit 1 (204) represents the execution processor as a representative.
Specifically, the transmission / reception determination unit 1042 of the simulation element execution control unit 1 (204) in FIG. 3 is connected to the simulation element communication control unit 1 (205) in FIG. 6 is obtained, and the processor selection unit 1043 of the simulation element execution control unit 1 (204) in FIG. 3 determines the execution state of each simulation element of each logical processor according to the following rules.
Rule 1: Two simulation elements having a data transmission / reception relationship and having a high communication frequency are set in an active state in the same logical processor.
Rule 2: An active state and a dormant state are set so that two simulation elements not related to data transmission / reception are shared and executed by two different logical processors.
Rule 3: When the application result of Rule 1 and the application result of Rule 2 are in conflict, the application result of Rule 1 is prioritized.

When the above rules are applied to the information shown in FIGS. 5 and 6, the following results are obtained.
Application result of rule 1: Aircraft 1 and radar 1, aircraft 2 and radar 1, radar 1 and air traffic control 1 are active in the same logic processor.
Application result of rule 2: Aircraft 1 and aircraft 2 are activated in different logical processors.
Application result of rule 3: Application result of rule 1 (aircraft 1 and aircraft 2 are active in the same logical processor) and application result of rule 2 (aircraft 1 and aircraft 2 are active in different logical processors) Therefore, priority is given to the application result of rule 1.

  Based on the application results of Rule 1, Rule 2, and Rule 3, the simulation element execution control unit 1 (204) in FIG. 3 is the aircraft 1 (207) and aircraft 2 (208) which are the simulation elements of the logical processor 1 (201). ), Radar 1 (209) and Air Traffic Control 1 (210) are in the active state, and the simulation element execution control unit 2 (214) is the simulation element of the logical processor 2 (211), the aircraft 1 (216), the aircraft 2 ( 217), Radar 1 (218), and Air Traffic Control 1 (219) are put into a dormant state.

Next, an operation example of the simulation element execution control unit 104 will be described with reference to the flowchart of FIG.
First, the transmission / reception determination unit 1042 acquires the data transmission / reception status information shown in FIG. 5 or 6 from the inter-simulation element communication control unit 105 via the communication control unit interface 1041 (S701).
Next, the transmission / reception determination unit 1042 identifies, for each simulation element, another simulation element that is a partner of data transmission / reception based on the acquired data transmission / reception status information, and determines the data transmission / reception frequency with the simulation element that is the partner. Determination (S702) (transmission / reception determination step).
Next, the processor selection unit 1043 selects an execution processor from a plurality of logical processors for each simulation element based on the rules 1 to 3 described above (S703) (processor selection step).
Next, the processor selection unit 1043 generates processor selection result information indicating the execution processor selected in S703 for each simulation element (S704).
Next, the communication control unit interface 1041 transmits the processor selection result information to the inter-simulation element communication control unit 105 (S705).
As a result, the simulation element communication control unit 105 transmits the processor selection result information to the simulation element communication control unit 105 of another logical processor via the network, and the simulation element execution control unit of the other logical processor selects the processor. In accordance with the result information, the managed simulation element is set to either an active state or a dormant state.

  Simulation element execution control by such a simulation element execution control unit activates simulation elements with high communication frequency in the same logical processor, so data communication between simulation elements is performed via a network with a large processing delay. There is no need to execute communication processing for other logical processors.

  As described above, in this embodiment, in a distributed simulation system in which simulation elements are shared and executed by a plurality of logical processors, each logical processor is determined according to the relationship and frequency of data transmission / reception between the simulation elements determined according to the simulation status. By controlling the active state and hibernation state of the simulation elements executed in, data communication between simulation elements with high communication frequency is executed in the logical processor, and communication to other logical processors via a network with a large processing delay A distributed simulation system that can improve the processing efficiency of the entire system because processing execution is reduced has been described.

Embodiment 2. FIG.
FIG. 3 shows an example of the simulation element execution control result according to the first embodiment. In this example, only the simulation element of the logical processor 1 (201) is processed and the simulation of the logical processor 2 (211) is performed. Since the elements are not processed at all, the load is concentrated only on the logical processor 1 (201) as a whole, resulting in an inefficient execution state.
Therefore, a form in which execution control of more efficient simulation elements is performed will be described by paying attention to the communication frequency and conditions between the simulation elements shown in FIG. 8 and the simulation status.
In the present embodiment, as shown in FIG. 8, each logical processor includes a simulation element / activity stop management unit 107. The simulation element / activity stop management unit 107 sets a simulation element to be managed to an active state or a dormant state based on the execution processor selection result by the simulation element execution control unit 110.
In this embodiment, the simulation element execution control unit 110 is independent of the logical processor that executes the simulation element and is connected to each logical processor via a network. However, unlike the configuration of FIG. 8, the simulation element execution control unit 110 may be realized in one of the logical processors.
The internal configuration of the simulation element execution control unit 110 according to the present embodiment is the same as that shown in FIG.
In the present embodiment, the transmission / reception determination unit 1042 specifies, for each simulation element, another simulation element that is a partner of data transmission / reception based on a preset simulation scenario, and other specified simulation elements The data transmission / reception frequency is determined for each unit time.
Further, the processor selection unit 1043 sets the execution processors of the two simulation elements as the same processor during the time when the data transmission / reception frequency between the two simulation elements is high. To do.

  FIG. 9 shows the positional relationship of each simulation element 102 with respect to the coordinates (latitude and longitude). Of the simulation elements, the aircraft 1 and the aircraft 2 are both moving bodies whose positions change during execution of the simulation. Position information for each simulation logic time (LT) indicating the progress degree of progress is shown. For the radar 1, a radar 1 coverage area that is the maximum detection range of the radar is shown.

According to the information in FIG. 6 showing the relationship of data transmission / reception between the simulation elements, the radar 1 transmits the detection result to the air traffic control 1 based on the position information received from the aircraft 1 and the aircraft 2. That is, when the aircraft 1 and the aircraft 2 are located outside the detection area of the radar 1, the radar 1 cannot transmit the detection results of the aircraft 1 and the aircraft 2 to the air traffic control 1. Communication of position information between the radar 1, the aircraft 1 and the aircraft 2 is a wasteful process.
Therefore, when the position information of the aircraft 1 and the aircraft 2 at each simulation logical time (LT) shown in FIG. 9 is set in advance as a simulation scenario, the simulation element execution control unit 110 sets the logical time set in the simulation scenario. By applying rule 1, rule 2, and rule 3 for each (LT), a schedule for assigning the active state of simulation elements as shown in FIG. 10 is created, and execution control of the simulation elements is performed.

That is, the transmission / reception determination unit 1042 of the simulation element execution control unit 110 acquires the data transmission / reception status information illustrated in FIG. 5 or 6 and the simulation scenario illustrated in FIG. 9 from one or a plurality of simulation element communication control units 105. For each simulation element 102, another simulation element that is a partner of data transmission / reception is specified, and the data transmission / reception frequency with the other specified simulation element is determined for each unit time.
Then, the processor selection unit 1043 selects an execution processor from a plurality of logical processors for each simulation element based on the rules 1 to 3 described above. Specifically, as shown in FIG. 10, for two simulation elements in which data transmission / reception is performed between the two simulation elements, the execution processor of the two simulation elements during a time when the data transmission / reception frequency between the two simulation elements is high. Are the same processor.
Thereafter, as in the first embodiment, the processor selection unit 1043 generates processor selection result information (FIG. 10) indicating the execution processor selected in S703 for each simulation element for each unit time, and the communication control unit interface 1041 displays the processor. The selection result information is transmitted to each inter-simulation element communication control unit 105 via the network. In each logical processor, the simulation element / activity stop management unit 107 activates the managed simulation element according to the processor selection result information. Set to either state or hibernation.

  Since simulation element execution control by such a simulation element execution control unit is based on information set in advance in a simulation scenario, the simulation element becomes active in the same logical processor only when communication is always performed. It is no longer necessary to perform data communication between them as a communication process for other logical processors via a network with a large processing delay, and efficient execution control of simulation elements can be performed for each logical processor.

  As described above, in this embodiment, in a distributed simulation system in which simulation elements are shared and executed by a plurality of logical processors, data transmission / reception between simulation elements determined according to a simulation situation depending on a preset simulation scenario is performed. By controlling the active state and sleep state of the simulation elements executed in each logical processor according to the relationship and frequency, data communication between simulation elements with high communication frequency is executed within the logical processor, and a network with a large processing delay is created. A distributed simulation system that can improve the processing efficiency of the entire system has been described because the execution of communication processing with respect to other logical processors is reduced.

Embodiment 3 FIG.
In the second embodiment, the execution control of the simulation element based on the information of the simulation element set in advance in the simulation scenario has been described.
In the third embodiment, execution control of a simulation element when the state of the simulation element changes dynamically instead of preset information will be described.

The configuration of the distributed simulation system according to the present embodiment is the same as that shown in FIG. Similarly to the second embodiment, unlike the configuration of FIG. 8, the simulation element execution control unit 110 may be realized in any one of the logical processors.
The internal configuration of the simulation element execution control unit 110 according to the present embodiment is the same as that shown in FIG.
In the present embodiment, when a change is made to a preset simulation scenario, the transmission / reception determination unit 1042 analyzes the change made to the simulation scenario, and for each simulation element, the data transmission / reception destination and The other simulation elements are estimated, and the data transmission / reception frequency with the estimated other simulation elements is estimated for each unit time.
Further, the processor selection unit 1043 is configured to perform two simulations for two simulation elements that are estimated to perform data transmission / reception between the two simulation elements during a time when the data transmission / reception frequency between the two simulation elements is estimated to be high. The execution processor of the element is the same processor.

  FIG. 11 shows a situation in which the coordinate parameter which is the position information of the aircraft 2 is changed by the operation of the simulation user (human) during the simulation. In such a case, when the coordinate value is changed, the simulation element execution control unit 110 uses a general dead-reckoning navigation algorithm that uses information such as the position, orientation, and speed of the aircraft. The position information of the aircraft 2 at each logical time is estimated, a schedule for assigning the active state of the simulation element is created, and execution control of the simulation element is performed.

In other words, after the execution processor is selected for each simulation element 102 by the processor selection unit 1043, when the simulation scenario is changed by the simulation user while the simulation is being executed, the transmission / reception determination unit 1042 has already been acquired. Based on the simulation scenario (FIG. 9), the data transmission / reception status information (FIG. 5 or FIG. 6), and the change contents of the simulation scenario, for example, the changes made to the simulation scenario by the dead reckoning algorithm described above (aircraft position, etc.) ), And for each simulation element, based on the state after the simulation scenario change is estimated, other simulation elements that are data transmission / reception destinations are estimated, and data transmission / reception with the estimated other simulation elements is performed. Guess degrees per unit time.
Then, the processor selection unit 1043 applies the above-described rules 1 to 3 to the estimation result of the transmission / reception determination unit 1042, and selects an execution processor from a plurality of logical processors for each simulation element. Specifically, with respect to two simulation elements that are estimated to perform data transmission / reception between each other, the execution of the two simulation elements is performed during a time when the frequency of data transmission / reception between the two simulation elements is estimated to be high. The processor is the same processor.
Thereafter, as in the second embodiment, the processor selection unit 1043 generates processor selection result information (FIG. 10) indicating the execution processor selected in S703 for each simulation element for each unit time, and the communication control unit interface 1041 displays the processor. The selection result information is transmitted to each inter-simulation element communication control unit 105 via the network. In each logical processor, the simulation element / activity stop management unit 107 activates the managed simulation element according to the processor selection result information. Set to either state or hibernation.

  Even if the simulation status is dynamically changed by a human operation or the like by the execution control of the simulation element by the simulation element execution control unit, the simulation element is assumed to be in the same logical processor by assuming that communication is performed. Therefore, it is possible to efficiently control execution of simulation elements for each logical processor.

  As described above, in the present embodiment, in a distributed simulation system in which simulation elements are shared and executed by a plurality of logical processors, data transmission / reception between simulation elements determined in accordance with a simulation situation that dynamically changes according to a human operation or the like. By inferring the relationship and frequency and controlling the active state and sleep state of the simulation elements executed in each logical processor, data communication between simulation elements with high communication frequency is executed within the logical processor, resulting in a large processing delay. A description has been given of a distributed simulation system capable of improving the processing efficiency of the entire system because the execution of communication processing with respect to other logical processors via the network is reduced.

  In the above description, the aircraft navigation simulation has been described as an example. However, the distributed simulation system described in Embodiment 1-3 for the simulation system for various uses such as the simulation for planning / prediction / analysis is described below. Applicable.

  In the distributed simulation system described in Embodiment 1-3, the communication frequency is controlled by controlling the active state and the sleep state of the simulation element executed by each logical processor according to the relationship and frequency of data transmission / reception between the simulation elements. Data communication between high simulation elements is executed in the logical processor, the load balance between the logical processors can be optimized, and hardware resources of the logical processor can be effectively utilized. In addition, since the execution of communication processing with other logical processors is reduced, the processing efficiency of the entire system can be improved.

1 is a diagram illustrating a configuration example of a distributed simulation system according to a first embodiment. The figure which shows the internal structural example of a simulation element execution control part. FIG. 3 is a diagram illustrating an execution example of the distributed simulation system according to the example of the first embodiment. The figure which shows the example of the simulation condition performed with the distributed simulation system of FIG. FIG. 5 is a relationship diagram of data transmission / reception between simulation elements in the example of FIG. 4. FIG. 6 is a relationship table of data transmission / reception between simulation elements in the example of FIG. FIG. 3 is a flowchart showing an operation example of a simulation element execution control unit according to the first embodiment. FIG. 4 is a diagram illustrating a configuration example of a distributed simulation system according to a second embodiment. The figure which shows the positional relationship of each simulation element with respect to a coordinate (latitude, longitude). The figure which shows the schedule of the allocation of the active state of a simulation element. The situation figure in which the coordinate parameter of the aircraft 2 was changed by human operation. The figure which shows the hardware structural example of the distributed simulation system which concerns on Embodiment 1-3.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 101 Logical processor, 102 Simulation element, 103 Simulation element management part, 104 Simulation element execution control part, 105 Simulation element communication control part, 107 Simulation element and activity stop management part, 201 Logical processor, 202 Simulation element, 203 Simulation element management Unit, 204 simulation element execution control unit, 205 inter-simulation element communication control unit, 206 network, 1041 communication control unit interface, 1042 transmission / reception determination unit, 1043 processor selection unit.

Claims (5)

A simulation execution control device for controlling the execution of a plurality of simulation elements,
Prior to the execution of the simulation, for each simulation element, based on a simulation scenario set in advance, the other simulation element that is the partner of data transmission / reception is specified, and the frequency of data transmission / reception with the specified other simulation element is determined . A transmission / reception determination unit for determining each simulation logical time indicating the progress of simulation progress ;
Prior to execution of the simulation, based on the determination result of the transmission / reception determination unit, for each of the plurality of simulation elements, an execution processor that executes the simulation element is selected from among the plurality of processors at each simulation logic time. Processor selection that creates a schedule for two simulation elements that perform data transmission / reception between the two simulation elements during the simulation logic time when the frequency of data transmission / reception between the two simulation elements is high. A simulation execution control device. The processor selection unit includes:
The simulation execution control apparatus according to claim 1, wherein a schedule is created in which execution processors of two simulation elements that do not transmit and receive data between each other are different processors. The transmission / reception determination unit includes:
When a change is made to a preset simulation scenario, the change made to the simulation scenario is analyzed, and for each simulation element, other simulation elements that are the destinations of data transmission / reception are estimated, and the estimated other The simulation execution control device according to claim 1, wherein a frequency of data transmission / reception with the simulation element is estimated at each simulation logic time . The processor selection unit includes:
For two simulation elements that are estimated to transmit / receive data to / from each other, the execution processors of the two simulation elements are the same during the simulation logic time when the frequency of data transmission / reception between the two simulation elements is estimated to be high. The simulation execution control apparatus according to claim 3, wherein the simulation execution control apparatus is a processor. A program for causing a computer to execute execution control of a plurality of simulation elements,
Prior to the execution of the simulation, for each simulation element, based on a simulation scenario set in advance, the other simulation element that is the partner of data transmission / reception is specified, and the frequency of data transmission / reception with the specified other simulation element is determined . A transmission / reception determination process for determining each simulation logical time indicating the progress of simulation progress ;
Prior to the execution of the simulation, based on the determination result of the transmission / reception determination process, for each of the plurality of simulation elements, an execution processor that executes the simulation element is selected from the plurality of processors at each simulation logic time , Processor selection that creates a schedule for two simulation elements that perform data transmission / reception between the two simulation elements during the simulation logic time when the frequency of data transmission / reception between the two simulation elements is high. A program that causes a computer to execute processing.

Images