CN102123053A - Method for analyzing performance of multi-class closed fork-join queuing network based on horizontal decomposition - Google Patents
Method for analyzing performance of multi-class closed fork-join queuing network based on horizontal decomposition Download PDFInfo
- Publication number
- CN102123053A CN102123053A CN2011100801557A CN201110080155A CN102123053A CN 102123053 A CN102123053 A CN 102123053A CN 2011100801557 A CN2011100801557 A CN 2011100801557A CN 201110080155 A CN201110080155 A CN 201110080155A CN 102123053 A CN102123053 A CN 102123053A
- Authority
- CN
- China
- Prior art keywords
- request
- model
- service centre
- closed
- network
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000000354 decomposition reaction Methods 0.000 title claims abstract description 21
- 230000004044 response Effects 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 125000002015 acyclic group Chemical group 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 abstract description 10
- 238000011156 evaluation Methods 0.000 description 7
- 230000015572 biosynthetic process Effects 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a method for analyzing performance of a multi-class closed fork-join queuing network based on horizontal decomposition. According to the method, each class of model including fork-join operation in the models is subjected to horizontal decomposition so that a computer can implement rapid and accurate analysis on the performance of the queuing network models to obtain analyzable parameters of actual system performance, thereby improving the efficiency of the computer in analyzing the system performance.
Description
Technical field
The present invention relates to queueing network performance evaluation field, mainly is the closed bifurcated of a kind of multiclass based on horizontal decomposition-compile queueing network's method for analyzing performance.
Background technology
Queuing network (Queueing Network) model is a kind of system performance analysis method of classics, it describes a software and hardware resources with a service centre (Service Center), and whole system can be regarded the network that several service centres form according to certain composition of relations as.Service centre can be divided into two types of formation type and time lagged types: formation type service centre is made up of a formation and several servers, and server is used for executable operations, and formation then is used for buffer memory and waits for the request of serving; And time lagged type service centre is mainly used in the simulation delay operation.Network of queues's model can be divided into open model and closed type model again according to the loadtype difference.
Queueing network has portfolio effect preferably between complexity and accuracy, be widely used in the performance evaluation of various computer software and hardware system.Yet along with the appearance of technology such as parallel computation, Distributed Calculation, simple queueing network can't be applicable to the performance evaluation of this type of scale complex system.A kind of queueing network that comprises bifurcated-compile (Fork-Join) operation is widely used in the performance evaluation of systems such as parallel computation, Distributed Calculation and workflow management.Bifurcated-integration operations can be used to describe the parallel processing scene: a request (or being called task) will be broken down into the plurality of sub task after arriving the bifurcated running node, and these subtasks can be by different service centre's parallel processings; And after the integration operations node must wait for that relevant subtask is all complete, their result is aggregated into a new request send to next service centre.Bifurcated-integration operations makes such queueing network can't use the mode of product form (Product-Form) to calculate, thereby has increased the difficulty of such model analysis, particularly for the network of closed type.
At present, about the exact algorithm of bifurcated-compile queueing network only based on the analytical method of Markov chain (Markov Chains), but such algorithm only is applicable to the model that scale is less.Therefore, adopt approximate analytical method usually for large-scale bifurcated-compile queueing network.And most methods all is to utilize a kind of level to decompose the method for (Hierarchical Decomposition).This method at first resolves into multi-level sub-network with large-scale queueing network, and each sub-network is represented bottom-up then each sub-network model of finding the solution respectively with the relevant service centre of a load in the layer network thereon.If one comprises
NThe closed bifurcated of single class of individual request-compile queueing network to be divided into by the level decomposition method
LLayer, every layer comprises 1 sub-network, then need find the solution for each sub-network
NInferior (request number from 1 to
NSituation), and whole network needs to find the solution at least
N L Individual closed queuing network model.Therefore, use the analytical method of decomposing to have higher computation complexity for large-scale bifurcated-compile queueing network based on level.
For example, bifurcated-(Business Process Management when BPM) system carries out modeling, needs to consider concurrently deployed a plurality of flow processs usually for BPM to compile queueing network when using.Therefore, when carrying out performance evaluation for the software systems of the type, bifurcated-compiling queueing network carries out system performance analysis to need to use multiclass (Multi-Class).But because to find the solution complexity higher, in the prior art computer substantially can only at single type (Single-Class) bifurcated-compiling queueing network carries out analytical calculation, still can't be to the closed bifurcated of multiclass-compile queueing network's performance evaluation.
Summary of the invention
The present invention is for solving the existing in prior technology defective, the closed bifurcated of a kind of multiclass based on horizontal decomposition (Horizontal Decomposition)-compile queueing network's method for analyzing performance has been proposed, make to calculate function by quick Accurate Analysis, but and then obtain the analytical parameters of actual system behavior queueing network's performance.
To achieve these goals, the present invention adopts following technical scheme:
The closed bifurcated of the multiclass of horizontal decomposition-compile the queuing network method for analyzing performance may further comprise the steps:
1) in computer the system that comprises multiclass request and bifurcated-integration operations is set up multiclass closed queuing network model, wherein corresponding service centre of each computational resource in described model analyzes two required input parameters of this model and is respectively the request number
With the service time D of each i of service centre at different request c
C, i
Described C is request kind sum, described N
cBe the number of request c, described request number
Load scale according to described system reality is set D service time of described service centre
C, iFrom the historical record of corresponding computational resource, obtain;
2) described computer carries out horizontal decomposition to the model that the closed bifurcated of described multiclass-the compile every class in the queueing network comprises bifurcated-integration operations, thereby described computer obtains several trunks and the product type hybrid queueing network of corresponding branch with it thereof, simultaneously, described computer is determined the dependence of this mixing queueing network;
3) mix queueing network described computer determining step 2), if described mixing queueing network belongs to acyclic dependence, then according to the rightabout of dependence solving model one by one; Otherwise, use the recurrence convergence algorithm to find the solution described circulation and rely on model;
4) described computer is according to step 2) response time of calculating each service centre of gained, recomputate closed bifurcated of described each single class-compile in the queueing network trunk and each the service centre's response time in each branch;
5) determining step 4) result of calculation, if in step 2) in all trunks of selecting all have the longest response time, then the selection before the explanation is correct, finds the solution flow process and finishes; Otherwise the branch that the response time is the longest is chosen as trunk, and decomposes original every class model again, returns step 3) then and re-executes, and the trunk of selecting up to every class model all has the longest response time.
As possibility, open model and closed model are alternately to appear to rely on the ring in the described circulation dependence model; Described open model can calculate with following formula:
（1）
Described
Be request c correspondence system throughput,
Be the arrival rate of request c,
Be the resource utilization of request c at the i of service centre;
Described closed model can calculate with following formula:
Described
Be after request c-1 is converted into request c, request c service time of the i of service centre,
Be request c the average queue length of the i of service centre,
Be request c arrive constantly queue length of the i of service centre,
Be request c response time of the i of service centre,
It is the blanking time that sends request c.
As possibility, described circulation relies on mixing queueing network and can be expressed as
Described function
f o Represent described formula (1).With
f c Represent described formula (2).
As possibility, described circulation relies on finding the solution of queueing network of mixing and may further comprise the steps:
1) described computer is the average queue length of the service centre of described each closed model
An initial value is provided
2) described computer is found the solution according to described formula (3) according to the initial value that provides, and obtains the response time of each service centre and the throughput of every class model;
3) described computer is according to step 2) result of calculation, recomputate the average queue length of each service centre
4) described computer is judged institute's result calculated, if all
With
Relative error all count τ less than the acceptable error that the user sets, then stop to calculate; Otherwise, use
Return step 2) recomputate, up to the relative error of all average queue lengths all less than τ.
The effect that the present invention is useful is:
1) computer passes through horizontal decomposition, the closed bifurcated of multiclass-compile queueing network can be resolved into the mixing queueing network of closed and open model composition such as several product types, thereby solved in the prior art, for calculating the closed bifurcated of the quick accurate Calculation multiclass of function-compile queueing network a kind of feasible method for analyzing performance is provided, improved the efficient of computer to system performance analysis.
2) for mixing queueing network with acyclic dependence, can be according to the rightabout of dependence solving model one by one.
3) for mixing queueing network with circulation dependence, a kind of method of recurrence convergence has been proposed, can find the solution this class model effectively.
Description of drawings
The mixing queueing network example of the acyclic dependence of Fig. 1;
The mixing queueing network example that Fig. 2 circulates and relies on;
Fig. 3 is based on the closed bifurcated of the multiclass of horizontal decomposition-compile queueing network to find the solution flow process;
Fig. 4 circulates and relies on the topological structure that mixes queueing network;
Fig. 5 circulates and relies on the flow process of finding the solution of mixing queueing network.
Embodiment
The invention will be described further below in conjunction with drawings and Examples:
The present invention is directed to the closed bifurcated of multiclass-compile queueing network, the product type queueing network of a closure and some openings is resolved in the non-product type queueing network that every class is comprised bifurcated-closed procedure by computer usage level decomposition method.The horizontal decomposition method is with bifurcated-parallel processing between compiling
N B The subtask be divided into a trunk and
Individual branch, wherein definite method of trunk is that average queue length for each service centre (for example provides a rational initial value
,
NBe the sum of asking in closed queuing network's model,
KSum for service centre in closed queuing network's model), thereby estimate response time (Response Time) of each subtask, and the subtask execution route that the response time is the longest is set at trunk.
The closed bifurcated of multiclass-compile queueing network can obtain one group of mixing queueing network with dependence by horizontal decomposition.The reason that produces dependence has two: one is the horizontal decomposition method, and it requires open model to use the throughput of closed model as initial conditions (request arriving rate); Another is the mixed model algorithm, and this algorithm uses the utilance of service centre in the open model to amplify the service time of service centre in the closed model, thereby can shield the influence of open model to closed model.According to the structure of dependence, the mixing queueing network that obtains after the horizontal decomposition can be divided into two types: acyclic dependence and circulation rely on.
Fig. 1 is the example of an acyclic dependence mixed model, and this mixed model is by one two class C
1And C
2Closed bifurcated-compile queueing network through horizontal decomposition comprises 2 closed model C
1, C
22With 1 open model C
21Wherein, C
21Need C
22Throughput as initial conditions, therefore, C
21Rely on C
22In addition, because C1 and C
2Comprise the same A of service centre jointly, found the solution C
22Before need to obtain C
1The utilance of middle A, i.e. C
22Depend on C
1
Fig. 2 is the example that a circulation relies on mixed model.This mixed model is by one two class C
3And C
4Closed bifurcated-compile queueing network through horizontal decomposition comprises 2 closed model C
31, C
32With 2 open model C
42, C
41Wherein, C
3And C
4All comprise bifurcated-integration operations, and all comprised B of service centre and C jointly.Because above-mentioned dependence produces, this mixed model has comprised one and has relied on circulation, i.e. C
31Rely on C
41, C
41Rely on C
42, C
42Rely on C
32, C
32Rely on C again
31
Fig. 3 has described based on the closed bifurcated of the multiclass of horizontal decomposition-compile queueing network to find the solution flow process:
1) in computer the system that comprises multiclass request and bifurcated-integration operations is set up multiclass closed queuing network model, wherein corresponding service centre of each computational resource in described model analyzes two required input parameters of this model and is respectively the request number
With the service time Dc of each i of service centre at different request c, i;
Described C is the number of request c for request kind sum, described Nc, the described request number
Load scale according to described system reality is set, Dc service time of described service centre, and i obtains from the historical record of corresponding computational resource;
2) described computer carries out horizontal decomposition to the model that the closed bifurcated of described multiclass-the compile every class in the queueing network comprises bifurcated-integration operations, thereby described computer obtains several trunks and the product type hybrid queueing network of corresponding branch with it thereof, simultaneously, described computer is determined the dependence of this mixing queueing network;
6) mix queueing network described computer determining step 2), if described mixing queueing network belongs to acyclic dependence, then according to the rightabout of dependence solving model one by one, method for solving is seen (Gunter Bolch in detail, Stefan Greiner, Hermann de Meer, and Kishor S. Trivedi. Queueing Networks and Markov Chains:Modeling and Performance Evaluation with Computer Science Applications, Second Edition. Wiley-Interscience, 2006, pp.422-427); Otherwise, use the recurrence convergence algorithm to find the solution described circulation and rely on model;
7) described computer is according to step 2) response time of calculating each service centre of gained, recomputate closed bifurcated of described each single class-compile in the queueing network trunk and each the service centre's response time in each branch;
8) determining step 4) result of calculation, if in step 2) in all trunks of selecting all have the longest response time, then the selection before the explanation is correct, finds the solution flow process and finishes; Otherwise respectively that the response time is the longest branch is chosen as trunk, and decomposes original every class model again, returns step 3) then and re-executes, and the trunk of selecting up to every class model all has the longest response time.
By dependence being formed the analysis of reason, the dependence of can finding to circulate mixes queueing network and has the topological result of Fig. 4: open model and closed model are alternately to appear to rely on the ring.Therefore, the mode of these models according to Fig. 4 can be sorted, promptly open model is positioned at odd positions for example 1, and 2n-1, closed model are positioned at even number position for example 2,2n.For open model, can use formula (1) to calculate:
Wherein,
Be the system throughput of request c correspondence,
Be the arrival rate of request c,
Be the resource utilization of request c at the i of service centre.
And closed model can use formula (2) to calculate:
Wherein,
Be that c was in the service time of the i of service centre in request after request c-1 was converted into request c,
Be the average queue length of request c at the i of service centre,
Be that request c arrives the i of service centre queue length constantly,
Be to ask c in the response time of the i of service centre,
It is the blanking time that sends request c.
For easy, we use function
f o Representation formula (1).With
f c Representation formula (2).Therefore, circulation dependence mixing queueing network can be expressed as:
Fig. 5 has described circulation and has relied on the flow process of finding the solution of mixing queueing network.Because in the equation group (3)
Be unknown number, we adopt a kind of recurrence convergence algorithm to find the solution, and concrete steps are as follows:
1) described computer is the average queue length of the service centre of described each closed model
An initial value is provided
2) described computer is found the solution according to described formula (3) according to the initial value that provides, and obtains the response time of each service centre and the throughput of every class model;
3) described computer is according to step 2) result of calculation, recomputate the average queue length of each service centre
4) described computer is judged institute's result calculated, if all
With
Relative error all count τ less than the acceptable error that the user sets, then stop to calculate; Otherwise, use
Return step 2) recomputate, up to the relative error of all average queue lengths all less than τ.
The above only is a preferred implementation of the present invention; should be pointed out that for those skilled in the art, without departing from the inventive concept of the premise; can also make some improvements and modifications, these improvements and modifications also should be considered within the scope of protection of the present invention.
Claims (4)
1. the closed bifurcated of the multiclass of horizontal decomposition-compile the queuing network method for analyzing performance is characterized in that may further comprise the steps:
1) in computer the system that comprises multiclass request and bifurcated-integration operations is set up multiclass closed queuing network model, wherein corresponding service centre of each computational resource in described model analyzes two required input parameters of this model and is respectively the request number
With the service time Dc of each i of service centre at different request c, i;
Described C is the number of request c for request kind sum, described Nc, the described request number
Load scale according to described system reality is set, Dc service time of described service centre, and i obtains from the historical record of corresponding computational resource;
2) described computer carries out horizontal decomposition to the model that the closed bifurcated of described multiclass-the compile every class in the queueing network comprises bifurcated-integration operations, thereby described computer obtains several trunks and the product type hybrid queueing network of corresponding branch with it thereof, simultaneously, described computer is determined the dependence of this mixing queueing network;
Described computer determining step 2) mixes queueing network described in, if described mixing queueing network belongs to acyclic dependence, then according to the rightabout of dependence solving model one by one; Otherwise, use the recurrence convergence algorithm to find the solution described circulation and rely on model;
Described computer is according to step 2) response time of calculating each service centre of gained, recomputate closed bifurcated of described each single class-compile in the queueing network trunk and each the service centre's response time in each branch;
Determining step 4) if result of calculation is in step 2) in all trunks of selecting all have the longest response time, then the selection before the explanation is correct, finds the solution flow process and finishes; Otherwise respectively that the response time is the longest branch is chosen as trunk, and decomposes original every class model again, returns step 3) then and re-executes, and the trunk of selecting up to every class model all has the longest response time.
2. the closed bifurcated of the multiclass of horizontal decomposition according to claim 1-compile the queuing network method for analyzing performance is characterized in that, described circulation relies on that open model and closed model are alternately to appear to rely on the ring in the model; Described open model can calculate with following formula:
Described
Be request c correspondence system throughput,
Be the request c arrival rate,
Be the resource utilization of request c at the i of service centre;
Described closed model can calculate with following formula:
（2）
Described
Be after request c-1 is converted into request c, request c service time of the i of service centre,
Be request c the average queue length of the i of service centre,
Be request c arrive constantly queue length of the i of service centre,
Be request c response time of the i of service centre,
It is the blanking time that sends request c.
3. according to the closed bifurcated of the multiclass of any described horizontal decomposition of claim 2-compile the queuing network method for analyzing performance, it is characterized in that described circulation relies on and mixes queueing network and can be expressed as
Described function
f o Represent described formula (1), use
f c Represent described formula (2).
4. according to the closed bifurcated of the multiclass of any described horizontal decomposition of claim 1 ~ 3-compile the queuing network method for analyzing performance, it is characterized in that described circulation relies on and mixes finding the solution of queueing network and may further comprise the steps:
1) described computer is the average queue length of the service centre of described each closed model
An initial value is provided
2) described computer is found the solution according to described formula (3) according to the initial value that provides, and obtains the response time of each service centre and the throughput of every class model;
3) described computer is according to step 2) result of calculation, recomputate the average queue length of each service centre
4) described computer is judged institute's result calculated, if all
With
Relative error all count τ less than the acceptable error that the user sets, then stop to calculate; Otherwise, use
Return step 2) recomputate, up to the relative error of all average queue lengths all less than τ.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110080155.7A CN102123053B (en) | 2011-03-31 | 2011-03-31 | Method for analyzing performance of multi-class closed fork-join queuing network based on horizontal decomposition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110080155.7A CN102123053B (en) | 2011-03-31 | 2011-03-31 | Method for analyzing performance of multi-class closed fork-join queuing network based on horizontal decomposition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102123053A true CN102123053A (en) | 2011-07-13 |
| CN102123053B CN102123053B (en) | 2014-01-01 |
Family
ID=44251514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110080155.7A Active CN102123053B (en) | 2011-03-31 | 2011-03-31 | Method for analyzing performance of multi-class closed fork-join queuing network based on horizontal decomposition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102123053B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927232A (en) * | 2014-04-15 | 2014-07-16 | 广东电网公司信息中心 | System processing method |
| CN106953756A (en) * | 2017-03-17 | 2017-07-14 | 腾讯科技（深圳）有限公司 | The simulation time-delay method and server of a kind of business datum |
| CN112579293A (en) * | 2020-12-24 | 2021-03-30 | 中国航空工业集团公司西安航空计算技术研究所 | Comprehensive verification method of distributed computing system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110841A (en) * | 2007-08-24 | 2008-01-23 | 清华大学 | Mixed strategy method for optimizing aggregative indicator under service oriented architecture SOA |
| CN101557608A (en) * | 2009-05-14 | 2009-10-14 | 北京航空航天大学 | Node identity protection method of mobile wireless sensor network on basis of message time delay condition |
-
2011
- 2011-03-31 CN CN201110080155.7A patent/CN102123053B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110841A (en) * | 2007-08-24 | 2008-01-23 | 清华大学 | Mixed strategy method for optimizing aggregative indicator under service oriented architecture SOA |
| CN101557608A (en) * | 2009-05-14 | 2009-10-14 | 北京航空航天大学 | Node identity protection method of mobile wireless sensor network on basis of message time delay condition |
Non-Patent Citations (3)
| Title |
|---|
| F.BASKETT 等: "《open,closed,and mixed networks of queues with different classes of customers》", 《JOURNAL OF THE ASSCIATION FOR COMPUTING MACHINERY》, vol. 22, no. 2, 30 April 1975 (1975-04-30), pages 248 - 257 * |
| GUNTER BOLCH 等: "《Queueing Networks and Markov Chains:Modeling and Performance Evaluation with Computer Science Applications》", 14 April 2006, article "Approximation Algorithms for Product-Form Networks", pages: 421-457 * |
| SETIA,S.K.等: "《Analysis of Processor Allocation in Multiprogrammed, Distributed-Memory Parallel Processing Systems》", 《PARALLEL AND DISTRIBUTED SYSTEMS, IEEE TRANSACTIONS ON》, vol. 5, no. 4, 30 April 1994 (1994-04-30), pages 401 - 420 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927232A (en) * | 2014-04-15 | 2014-07-16 | 广东电网公司信息中心 | System processing method |
| CN103927232B (en) * | 2014-04-15 | 2017-08-04 | 广东电网有限责任公司信息中心 | System processing method |
| CN106953756A (en) * | 2017-03-17 | 2017-07-14 | 腾讯科技（深圳）有限公司 | The simulation time-delay method and server of a kind of business datum |
| CN106953756B (en) * | 2017-03-17 | 2020-04-07 | 腾讯科技（深圳）有限公司 | Simulation delay method of service data and server |
| CN112579293A (en) * | 2020-12-24 | 2021-03-30 | 中国航空工业集团公司西安航空计算技术研究所 | Comprehensive verification method of distributed computing system |
| CN112579293B (en) * | 2020-12-24 | 2023-03-14 | 中国航空工业集团公司西安航空计算技术研究所 | Comprehensive verification method of distributed computing system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102123053B (en) | 2014-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Heidari et al. | Scheduling in multiprocessor system using genetic algorithm | |
| Zhang et al. | Dynamic DNN decomposition for lossless synergistic inference | |
| Bellettini et al. | Distributed CTL model checking in the cloud | |
| Filelis-Papadopoulos et al. | Towards simulation and optimization of cache placement on large virtual content distribution networks | |
| Thomas et al. | Mean value analysis for a class of PEPA models | |
| CN102123053A (en) | Method for analyzing performance of multi-class closed fork-join queuing network based on horizontal decomposition | |
| CN108768857B (en) | Virtual route forwarding method, device and system | |
| Liu et al. | Analysis of integration models for service composition | |
| CN104346220A (en) | Task scheduling method and system | |
| CN106936905A (en) | The dispatching method and its scheduling system of the Nova component virtual machines based on openstack | |
| George et al. | Asymptotic analysis of closed queueing networks and its implications to achievable service levels | |
| CN102158357B (en) | Method for analyzing performances of single closed fork-join queuing network based on horizontal decomposition | |
| CN106874215B (en) | Serialized storage optimization method based on Spark operator | |
| Liu et al. | A parallel matching algorithm based on order relation for HLA data distribution management | |
| Gu et al. | A reliable task assignment strategy for spatial crowdsourcing in big data environment | |
| Hou et al. | A distributed deployment algorithm of process fragments with uncertain traffic matrix | |
| Cheng et al. | GSLAC: A general scalable and low-overhead alert correlation method | |
| Luo et al. | Hardware/software partitioning for heterogeneous multicore SoC using genetic algorithm | |
| Duan et al. | Accelerating DAG-Style Job Execution via Optimizing Resource Pipeline Scheduling | |
| Wang et al. | A novel method for virtual network embedding with incentive convergence mechanism | |
| Abdelli et al. | Time Petri Nets for performance evaluation of composite web services architectures | |
| Peng et al. | Improving Performance of Batch Point-to-Point Communications by Active Contention Reduction Through Congestion-Avoiding Message Scheduling | |
| Wang et al. | Vce-pso: Virtual cloud embedding through a meta-heuristic approach | |
| Nacer et al. | Binary decision diagram based generation algorithm for large scale graph distribution | |
| Shah et al. | Load Balancing in Distributed System Using Genetic Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |