CN115801601A - Performance evaluation method for space measurement and control resource scheduling algorithm - Google Patents
Performance evaluation method for space measurement and control resource scheduling algorithm Download PDFInfo
- Publication number
- CN115801601A CN115801601A CN202211501252.3A CN202211501252A CN115801601A CN 115801601 A CN115801601 A CN 115801601A CN 202211501252 A CN202211501252 A CN 202211501252A CN 115801601 A CN115801601 A CN 115801601A
- Authority
- CN
- China
- Prior art keywords
- layer
- model
- performance
- resource scheduling
- measurement
- 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.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for evaluating the performance of a space measurement and control resource scheduling model, wherein the method takes a space measurement and control resource scheduling model as an evaluation object, gives out index calculation methods and normalization methods by constructing a performance evaluation index system of the space measurement and control resource scheduling model, determines index weights of each level of the index system by adopting an analytic hierarchy process, and obtains a comprehensive evaluation result of the performance of the space measurement and control resource scheduling model by linear weighted summation on the basis. The invention provides a fine, objective and comprehensive coverage performance evaluation method aiming at the problem that the performance evaluation of the existing aerospace measurement and control resource scheduling model is difficult to systematize, meticulous and comprehensive.
Description
Technical Field
The invention relates to the technical field of aerospace measurement and control network scheduling, in particular to a method and a system for evaluating the performance of an aerospace measurement and control resource scheduling model.
Background
The resource scheduling model is a core model of the space measurement and control resource scheduling system, and the performance of the resource scheduling model directly determines the quality of a resource scheduling plan and influences the full play of the operation management capability of space measurement and control resources. The main purpose of the resource scheduling model performance evaluation comprises two aspects: on one hand, the performance of the resource scheduling model is comprehensively judged, and the quality degree of the model is scientifically evaluated; on one hand, weak links of the model performance are found, and guidance suggestions are provided for optimization and improvement of the model. The development situation of the current satellite presents the characteristics of miniaturization, low orbit, constellation and batch, the measurement and control resource scale is continuously expanded due to the increase of the number of the on-orbit satellites, and the excellent performance of a resource scheduling model becomes the focus of the aerospace measurement and control network management party. The existing technology has the problems that the performance evaluation of the resource scheduling model still stays on an isolated index evaluation level, the evaluation process only calculates for a single index, the scattered indexes are relatively one-sided and difficult to comprehensively reflect the performance of the resource scheduling model, and an effective evaluation index system and method are lacked.
Disclosure of Invention
The invention provides a method and a system for evaluating the performance of a space measurement and control resource scheduling model, which are used for overcoming the defects that indexes are one-sided and the performance of the resource scheduling model is difficult to comprehensively reflect in the prior art and the like.
In order to achieve the purpose, the invention provides a method for evaluating the performance of a space measurement and control resource scheduling model, which comprises the following steps:
determining performance statistical data of a space measurement and control resource scheduling model; the model performance statistical data comprises task completion conditions, resource utilization conditions and model running time;
constructing a performance evaluation index system of the space measurement and control resource scheduling model according to the model performance statistical data; the evaluation index system comprises a first layer, a second layer and a third layer;
designing a piecewise linear normalization function of the third layer according to the evaluation index system, and performing normalization processing on the third layer by using the piecewise linear normalization function;
determining the weight of each index in the evaluation index system in a hierarchical analysis mode;
and comprehensively evaluating the performance of the space measurement and control resource scheduling model through linear weighting according to the weight of each index in the evaluation index system.
In order to achieve the above object, the present invention further provides a system for evaluating performance of a space measurement and control resource scheduling model, including:
the data acquisition module is used for determining performance statistical data of the space measurement and control resource scheduling model; the model performance statistical data comprise task completion conditions, resource utilization conditions and model operation time;
the system construction module is used for constructing a performance evaluation index system of the space measurement and control resource scheduling model according to the model performance statistical data; the evaluation index system comprises a first layer, a second layer and a third layer; designing a piecewise linear normalization function of the third layer according to the evaluation index system, and performing normalization processing on the third layer by using the piecewise linear normalization function;
the weight analysis module is used for determining the weight of each index in the evaluation index system in a hierarchical analysis mode;
and the evaluation module is used for comprehensively evaluating the performance of the space measurement and control resource scheduling model through linear weighting according to the weight of each index in the evaluation index system.
To achieve the above object, the present invention further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.
To achieve the above object, the present invention further proposes a computer-readable storage medium having a computer program stored thereon, which, when being executed by a processor, implements the steps of the above method.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a method for evaluating the performance of a space measurement and control resource scheduling model, which takes a space measurement and control resource scheduling model as an evaluation object, gives out a calculation method and a normalization method of each index by constructing a performance evaluation index system of the space measurement and control resource scheduling model, determines the index weight of each level of the index system by adopting an analytic hierarchy process, and obtains a comprehensive evaluation result of the performance of the space measurement and control resource scheduling model by linear weighted summation on the basis. The invention provides a fine, objective and comprehensive coverage performance evaluation method aiming at the problem that the performance evaluation of the existing aerospace measurement and control resource scheduling model is difficult to systematize, meticulous and comprehensive evaluation.
The invention provides a comprehensive and systematic performance evaluation index system of a space flight measurement and control resource scheduling model, which comprises three layers of indexes, covers various aspects such as task satisfaction, resource utilization, timeliness and the like, and can comprehensively, scientifically and reasonably evaluate the performance of the space flight measurement and control resource scheduling model based on the system.
The invention designs a set of spaceflight measurement and control resource scheduling model performance calculation model, and can carry out quantitative and objective evaluation on the spaceflight measurement and control resource scheduling model performance by carrying out piecewise linear normalization processing on the bottom layer index and then calculating indexes of different layers step by step.
The invention has the characteristics of wide application range and good engineering adaptability. The method is not only applied to the design links of space measurement and control resource scheduling models, such as single model performance evaluation, performance quality comparison of multiple models and the like; the method is also suitable for optimization iteration of an actual engineering model, finds specific weak links of the model performance, and provides guidance suggestions for optimization and improvement of the model.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a basic flow diagram of a method for evaluating the performance of a space measurement and control resource scheduling model according to the present invention;
FIG. 2 is a performance evaluation index system of a space measurement and control resource scheduling model provided by the invention;
FIG. 3 is a graph of a piecewise linear normalization function of the low-track task satisfaction rate and the medium-high-track task satisfaction rate provided by the present invention;
FIG. 4 is a piecewise linear normalization function graph of the utilization of the resources of the entire network according to the present invention;
FIG. 5 is a piecewise linear normalization function of resource utilization balance, resource average fragmentation rate, and model runtime provided by the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In addition, the technical solutions in the embodiments of the present invention may be combined with each other, but it must be based on the realization of the technical solutions by those skilled in the art, and when the technical solutions are contradictory to each other or cannot be realized, such a combination of the technical solutions should not be considered to exist, and is not within the protection scope of the present invention.
The invention provides a method for evaluating the performance of a space measurement and control resource scheduling model, which comprises the following steps as shown in figure 1:
101: determining performance statistical data of a space measurement and control resource scheduling model; the model performance statistics include task completion, resource utilization, and model run time.
102: according to the model performance statistical data, constructing a performance evaluation index system of the space measurement and control resource scheduling model, as shown in fig. 2; the evaluation index system includes a first layer, a second layer, and a third layer.
103: and designing a piecewise linear normalization function of the third layer according to the evaluation index system, and performing normalization processing on the third layer by using the piecewise linear normalization function.
104: and determining the weight of each index in the evaluation index system in a hierarchical analysis mode.
105: and comprehensively evaluating the performance of the space measurement and control resource scheduling model through linear weighting according to the weight of each index in the evaluation index system.
In one embodiment, for step 101, the task completion condition refers to the task completion condition of each low-earth orbit satellite measurement and control requirement and each medium-high earth orbit satellite measurement and control requirement, and the statistical data includes the task number of each low-earth orbit satellite measurement and control requirement, the task number of each medium-high earth orbit satellite measurement and control requirement, and the task number of each medium-high earth orbit satellite measurement and control requirement;
the resource utilization condition refers to the task allocation condition of each resource, and the statistical data comprises the available time length of each resource, the occupied time length of each resource task and the time length of each resource fragment.
In the next embodiment, for step 102, the first layer is the overall performance of the space measurement and control resource scheduling model; the second layer is a criterion layer and comprises task satisfaction, resource utilization and timeliness; the third layer is an index layer and comprises low-orbit task satisfaction rate, medium-orbit and high-orbit task satisfaction rate, the utilization rate of the resources of the whole network, resource utilization balance, the average fragmentation rate of the resources and model operation time.
In a certain embodiment, for step 102, the second layer and the third layer have a correspondence as follows:
the task satisfaction is used for measuring the satisfaction degree of the resource scheduling model generation result on the measurement and control task requirements of each satellite and is represented by two indexes, namely low-orbit task satisfaction rate and medium-high orbit task satisfaction rate;
the resource utilization is used for measuring the utilization degree of the resource scheduling model generation result to each resource and is represented by the utilization rate of the resources of the whole network, the utilization balance of the resources and the average fragment rate of the resources;
the timeliness criterion is used for measuring the time effect of the resource scheduling model and is directly represented by the model running time.
The third layer is defined as follows:
1) Low rail task satisfaction rate
The low-orbit satellite task satisfaction rate reflects the low-orbit measurement and control task satisfaction degree, the statistical data are defined as the ratio of the total number of subtasks met by the low-orbit satellite measurement and control task to the total number of required subtasks in a scheduling period according to task completion conditions, and a quantization formula is as follows:
2) Medium and high rail duty ratio
The medium and high orbit task satisfaction rate reflects the medium and high orbit measurement and control task satisfaction degree, is defined as the ratio of the total number of subtasks met by the medium and high orbit satellite measurement and control task to the total number of required subtasks in a scheduling period according to the statistical data of task completion conditions, and has the following quantization formula:
3) Utilization of resources of the whole network
The utilization rate of the resources in the whole network reflects the overall utilization degree of the resources in the whole network, and is defined as the ratio of the total duration of the task arc sections allocated to the resources in the whole network in a scheduling period to the total duration capable of being provided according to the statistical data of the utilization condition of the resources, and the quantitative formula is as follows:
4) Degree of balance in resource utilization
The resource utilization equilibrium reflects the discrete degree of each resource utilization rate, and is defined as the standard deviation of each resource utilization rate in a scheduling period according to the resource utilization condition information, and the quantization formula is as follows:
wherein x is i Indicating the resource utilization rate of the ith resource, N indicating the number of resources and the average resource utilization rate being E x 。
5) Average fragmentation rate of resources in the whole network
The average fragmentation rate of the resources in the whole network reflects the fragmentation degree of each resource which can not be reused, and is defined as the average value of the fragmentation rate of each resource in a scheduling period according to the resource utilization condition information, wherein the fragmentation rate of the resources is defined as the ratio of the fragment time length of equipment to the available time length of the equipment in the scheduling period, and the quantization formula is as follows:
6) Model runtime
The model run time reflects the one-time resource scheduling model run timeliness and is defined as the duration from the model startup run to the generation of all plans.
In another embodiment, for step 103, the piecewise linear normalization function includes piecewise linear normalization functions of six indexes, namely low-orbit task satisfaction rate, medium-orbit task satisfaction rate, full-network resource utilization rate, resource utilization balance, resource average fragmentation rate and model runtime.
The piecewise linear normalization function design of the low-rail task satisfaction rate and the medium-high rail task satisfaction rate is shown in fig. 3, and shows that when the low-rail task satisfaction rate or the medium-high rail task satisfaction rate is greater than d0, the benefit is increased to 1 linearly; when less than d0, the benefit is 0. For the low-rail task satisfaction rate and the medium-high rail task satisfaction rate, d0 may take different values. If d0=0.5, then its normalization function can be expressed as:
x represents the low-orbit satellite mission satisfaction rate or the medium-high orbit mission satisfaction rate, y 1 Represents a normalized value thereof;
the design of the piecewise linear normalization function of the resource utilization rate of the whole network is shown in fig. 4, which shows that the best benefit is achieved when the overall resource utilization rate is between d2 and d 3; when d3 is greater or d2 to d1 is less, the benefit is linearly reduced to 0.1; when less than d1, the benefit is 0. If d1=0.4, d2=0.7, and d3=0.8, the normalization function can be expressed as:
x denotes the total network resource utilization, y 2 Represents a normalized value thereof;
the piecewise linear normalization function design of the resource utilization balance degree, the resource average fragment rate and the model operation time is shown in fig. 5, and represents that the best benefit is achieved when the index value is less than d 4; when between d4 and d5, the benefit decreases linearly to 0.1; when smaller than d5, the benefit is 0. For the resource utilization balance degree, the resource average fragment rate and the model running time, d4 and d5 can respectively take different dimension values.
If d4=0.05 and d5=0.2 are set for the resource utilization balance, the normalization function can be expressed as:
x denotes the resource utilization balance, y 3 Represents a normalized value thereof;
for the average fragmentation rate of the resource, d4=10%, d5=50%, the normalization function can be expressed as:
x denotes the average fragmentation rate of the resource, y 4 Represents a normalized value thereof;
for the model runtime, d4=10 (minutes) and d5=50 (minutes) are set, and then its normalization function can be expressed as:
x denotes the model runtime, y 5 Representing its normalized value.
In a next embodiment, for step 104, determining the weight of each index in the evaluation index system by a hierarchical analysis method includes:
401: and constructing a judgment matrix on the hierarchical structure of the evaluation index system.
Starting from the third layer of the hierarchical structure, comparing the indexes of the same layer subordinate to the second layer by using a relative comparison method and a 1-9 criterion factor until reaching the first layer; finally, an interpretation matrix of two indexes of low-rail task satisfaction rate and medium-rail task satisfaction rate, an interpretation matrix of three indexes of full-network resource utilization rate, resource utilization balance and resource average fragment rate and an interpretation matrix of three second-layer indexes of task satisfaction, resource utilization and timeliness are obtained.
402: and calculating the weight vector of the judgment matrix, and carrying out consistency check on the judgment matrix.
The consistency of the judgment matrix G is checked, and the calculation formula is
Wherein λ is max The maximum eigenvalue of the matrix G, n the dimension of the matrix G, and RI the average random consistency index. If the calculated result CR < 0.1, then the consistency level of G is acceptable, otherwise G needs to be modified to meet the consistency check.
403: and solving and determining the weight of each layer index by adopting a characteristic value method according to the weight vector.
In another embodiment, for step 105, the method for comprehensively evaluating the performance of the space flight measurement and control resource scheduling model through linear weighting according to the weight of each index in the evaluation index system includes:
501: and obtaining a second-layer index value by adopting an arithmetic weighted average method according to the third-layer index weight and the index value of the evaluation index system.
502: and obtaining the overall performance of the space measurement and control resource scheduling model by adopting an arithmetic weighted average method according to the second-layer index weight and the index value of the evaluation index system.
The invention also provides a system for evaluating the performance of the space measurement and control resource scheduling model, which comprises the following steps:
the data acquisition module is used for determining performance statistical data of the space measurement and control resource scheduling model; the model performance statistical data comprise task completion conditions, resource utilization conditions and model operation time;
the system construction module is used for constructing a performance evaluation index system of the space measurement and control resource scheduling model according to the model performance statistical data; the evaluation index system comprises a first layer, a second layer and a third layer; designing a piecewise linear normalization function of the third layer according to the evaluation index system, and performing normalization processing on the third layer by using the piecewise linear normalization function;
the weight analysis module is used for determining the weight of each index in the evaluation index system in a hierarchical analysis mode;
and the evaluation module is used for comprehensively evaluating the performance of the space measurement and control resource scheduling model through linear weighting according to the weight of each index in the evaluation index system.
The invention further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.
The invention also proposes a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method described above.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all modifications and equivalents of the present invention, which are made by the contents of the present specification and the accompanying drawings, or directly/indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A performance evaluation method for a space flight measurement and control resource scheduling model is characterized by comprising the following steps:
determining performance statistical data of a space measurement and control resource scheduling model; the model performance statistical data comprises task completion conditions, resource utilization conditions and model running time;
constructing a performance evaluation index system of the space measurement and control resource scheduling model according to the model performance statistical data; the evaluation index system comprises a first layer, a second layer and a third layer;
designing a piecewise linear normalization function of the third layer according to the evaluation index system, and performing normalization processing on the third layer by using the piecewise linear normalization function;
determining the weight of each index in the evaluation index system in a hierarchical analysis mode;
and comprehensively evaluating the performance of the space measurement and control resource scheduling model through linear weighting according to the weight of each index in the evaluation index system.
2. The model performance evaluation method of claim 1, wherein the task completion condition is a task completion condition of each low-earth orbit satellite measurement and control requirement and each medium-high earth orbit satellite measurement and control requirement, and the statistical data includes a task number of each low-earth orbit satellite measurement and control requirement, a task number of each medium-high earth orbit satellite measurement and control requirement, and a task number of each medium-high earth orbit satellite measurement and control requirement;
the resource utilization condition refers to the task allocation condition of each resource, and the statistical data comprises the available time length of each resource, the occupied time length of each resource task and the time length of each resource fragment.
3. The model performance evaluation method of claim 1, wherein the first layer is an aerospace measurement and control resource scheduling model overall performance; the second layer is a criterion layer and comprises task satisfaction, resource utilization and timeliness; the third layer is an index layer and comprises a low-orbit task satisfaction rate, a medium-orbit task satisfaction rate, a high-orbit task satisfaction rate, a whole network resource utilization rate, resource utilization balance, a resource average fragmentation rate and model operation time.
4. The model performance evaluation method according to any one of claims 1 to 3, wherein the correspondence relationship between the second layer and the third layer is as follows:
the task satisfaction is used for measuring the satisfaction degree of the resource scheduling model generation result on the measurement and control task requirements of each satellite and is represented by two indexes, namely low-orbit task satisfaction rate and medium-high orbit task satisfaction rate;
the resource utilization is used for measuring the utilization degree of the resource scheduling model generation result to each resource and is represented by the utilization rate of the resources of the whole network, the utilization balance of the resources and the average fragment rate of the resources;
the timeliness criterion is used for measuring the time effect of the resource scheduling model and is directly characterized by the model running time.
5. The model performance evaluation method of claim 1, wherein the piecewise linear normalization function comprises a piecewise linear normalization function of six indexes, namely low-rail task satisfaction rate, medium-rail task satisfaction rate, full-network resource utilization rate, resource utilization balance, resource average fragmentation rate and model running time.
6. The model performance evaluation method of claim 1, wherein determining the weight of each index in the evaluation index system by a hierarchical analysis comprises:
constructing a judgment matrix on the hierarchical structure of the evaluation index system;
calculating a weight vector of a judgment matrix, and carrying out consistency check on the judgment matrix;
and solving and determining the weight of each layer index by adopting a characteristic value method according to the weight vector.
7. The model performance evaluation method of claim 1, wherein the comprehensive evaluation of the performance of the space flight measurement and control resource scheduling model by linear weighting according to the weight of each index in the evaluation index system comprises:
obtaining a second-layer index value by adopting an arithmetic weighted average method according to the third-layer index weight and the index value of the evaluation index system;
and obtaining the overall performance of the space measurement and control resource scheduling model by adopting an arithmetic weighted average method according to the index weight and the index value of the second layer of the evaluation index system.
8. A performance evaluation system of a space flight measurement and control resource scheduling model is characterized by comprising:
the data acquisition module is used for determining performance statistical data of the space measurement and control resource scheduling model; the model performance statistical data comprises task completion conditions, resource utilization conditions and model running time;
the system construction module is used for constructing a performance evaluation index system of the space measurement and control resource scheduling model according to the model performance statistical data; the evaluation index system comprises a first layer, a second layer and a third layer; designing a piecewise linear normalization function of the third layer according to the evaluation index system, and performing normalization processing on the third layer by using the piecewise linear normalization function;
the weight analysis module is used for determining the weight of each index in the evaluation index system in a hierarchical analysis mode;
and the evaluation module is used for comprehensively evaluating the performance of the space measurement and control resource scheduling model through linear weighting according to the weight of each index in the evaluation index system.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of the method according to any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211501252.3A CN115801601A (en) | 2022-11-28 | 2022-11-28 | Performance evaluation method for space measurement and control resource scheduling algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211501252.3A CN115801601A (en) | 2022-11-28 | 2022-11-28 | Performance evaluation method for space measurement and control resource scheduling algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115801601A true CN115801601A (en) | 2023-03-14 |
Family
ID=85442151
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211501252.3A Pending CN115801601A (en) | 2022-11-28 | 2022-11-28 | Performance evaluation method for space measurement and control resource scheduling algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115801601A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116011889A (en) * | 2023-03-22 | 2023-04-25 | 中国人民解放军国防科技大学 | Multi-satellite measurement and control plan efficiency evaluation method, system and device |
| CN116011891A (en) * | 2023-03-24 | 2023-04-25 | 中国西安卫星测控中心 | Space measurement and control resource utilization effect determining method based on time classification |
-
2022
- 2022-11-28 CN CN202211501252.3A patent/CN115801601A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116011889A (en) * | 2023-03-22 | 2023-04-25 | 中国人民解放军国防科技大学 | Multi-satellite measurement and control plan efficiency evaluation method, system and device |
| CN116011891A (en) * | 2023-03-24 | 2023-04-25 | 中国西安卫星测控中心 | Space measurement and control resource utilization effect determining method based on time classification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115801601A (en) | Performance evaluation method for space measurement and control resource scheduling algorithm | |
| Dupačová et al. | Scenario reduction in stochastic programming | |
| González et al. | Adaptive fault tolerance and graceful degradation under dynamic hard real-time scheduling | |
| CN115766483A (en) | Method for evaluating service efficiency of measurement and control data transmission resource of space measurement and control network | |
| Dillon et al. | Programmatic risk analysis for critical engineering systems under tight resource constraints | |
| CN105718364A (en) | Dynamic assessment method for ability of computation resource in cloud computing platform | |
| CN113037877A (en) | Optimization method for time-space data and resource scheduling under cloud edge architecture | |
| Zhan et al. | An adaptive parallel learning dependent Kriging model for small failure probability problems | |
| CN115168027A (en) | Calculation power resource measurement method based on deep reinforcement learning | |
| CN111200283B (en) | Multi-microgrid system optimization control method | |
| CN115564152A (en) | Carbon emission prediction method and device based on STIRPAT model | |
| Yang et al. | An accelerated simulation approach for multistate system mission reliability and success probability under complex mission | |
| CN115529249B (en) | Task demand-oriented spaceflight measurement and control data transmission resource configuration evaluation method | |
| CN114816750B (en) | Big data management task operation method | |
| CN116307709A (en) | Comprehensive assessment method and system for flood control capacity of transformer substation based on information gain fusion | |
| CN112070129A (en) | Ground settlement risk identification method, device and system | |
| CN113238873A (en) | Method for optimizing and configuring spacecraft resources | |
| CN112257233A (en) | Elastic power grid resilience evaluation method and device, computer equipment and medium | |
| Birje et al. | Economical job scheduling in wireless grid | |
| Möding | Analyze System Scalability in R with the Universal Scalability Law | |
| Fiondella et al. | Importance Measures for a Modular Software System (Short Paper) | |
| Ewart et al. | Enhancing nss system engineering analysis through value-centric design methodology | |
| CN116225708A (en) | GPU resource scheduling method and device | |
| CN116594855A (en) | Virtual machine load prediction method based on missing value filling | |
| Schopf et al. | Using predicted variance for conservative scheduling on shared resources |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |