CN117278557B - Wide area deterministic algorithm network scheduling method, system, device and medium based on double-layer planning - Google Patents
Wide area deterministic algorithm network scheduling method, system, device and medium based on double-layer planning Download PDFInfo
- Publication number
- CN117278557B CN117278557B CN202311227412.4A CN202311227412A CN117278557B CN 117278557 B CN117278557 B CN 117278557B CN 202311227412 A CN202311227412 A CN 202311227412A CN 117278557 B CN117278557 B CN 117278557B
- Authority
- CN
- China
- Prior art keywords
- constraint
- representing
- request
- node
- layer
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000004364 calculation method Methods 0.000 claims abstract description 36
- 238000005457 optimization Methods 0.000 claims abstract description 35
- 230000005540 biological transmission Effects 0.000 claims abstract description 23
- 239000010410 layer Substances 0.000 claims description 49
- 239000002355 dual-layer Substances 0.000 claims description 7
- 238000004891 communication Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 239000002356 single layer Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/52—Queue scheduling by attributing bandwidth to queues
- H04L47/522—Dynamic queue service slot or variable bandwidth allocation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/56—Queue scheduling implementing delay-aware scheduling
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/63—Routing a service request depending on the request content or context
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a wide area deterministic algorithm network scheduling method, a wide area deterministic algorithm network scheduling system and a wide area deterministic algorithm network scheduling medium based on double-layer planning, and belongs to the technical field of deterministic algorithm networks. And constructing an optimal computational network scheduling model by using a double-layer planning method of mathematical planning, taking the throughput of the maximized computational power request as an upper-layer target and the time delay of the minimized computational power request as a lower-layer target. The built double-layer optimization scheduling model comprises four parts, namely constant, variable, constraint condition and optimization target. The constant enumerates the input of the model, including computing power network topology, node pair path set, request to be served, etc.; variables are the output of the model, including the selected computing nodes, the selected transmission paths, the planned hop-by-hop transmission time slots, etc., for each request; constraint conditions give equality or inequality constraints which are required to be met by the variables, including path constraints, calculation force constraints and time delay constraints; the optimization objectives are to maximize throughput of the power requests and minimize latency of the power requests, respectively.
Description
Technical Field
The invention relates to a wide area deterministic algorithm network scheduling method, a wide area deterministic algorithm network scheduling system and a wide area deterministic algorithm network scheduling medium based on double-layer planning, and belongs to the technical field of deterministic algorithm networks.
Background
Conventional IP networks provide service in a best effort manner and fail to provide "on-time, accurate" data transmission services. However, with the advent of cloud computing and 5G/B5G technology, the emerging applications of virtual/enhanced reality, smart grids, remote industrial control, etc. require networks that can provide deterministic quality of service. On the other hand, emerging applications are accompanied by mass data generation, the data processing needs strong computing power and wide coverage and high-quality network connection of cloud, side and end coordination, and the computing power application not only needs computing power and deterministic network, but also needs to schedule computing tasks to proper computing power nodes through the deterministic network.
The first prior art is: the periodic cyclic queuing forwarding (CYCLIC SPECIFIED Queuing and Forwarding, CSQF) is an important foreground technology for guaranteeing deterministic delay and jitter, CSQF adopts a dedicated queue on a node for forwarding deterministic traffic, requires frequency synchronization among forwarding nodes, defines a scheduling period mapping relation among nodes, allows forwarding queuing delay, and improves expandability and flexibility of deterministic flow in wide-area scheduling.
And the second prior art is as follows: in the aspect of deterministic scheduling, most of work researches on the implementation of a local deterministic scheduling technology, in the aspect of wide-area deterministic scheduling, krolikowski and the like research on scheduling problems based on the CSQF technology, a single-layer single-target integer linear programming model is established, and a deterministic flow admission algorithm based on column generation and dynamic programming is designed to maximize the throughput of deterministic flows.
The third prior art is: the research of the computing power network has become a hot spot in the academia and industry, and one of the problems is the cooperative scheduling of computing power resources and network resources. Han et al propose a gain-based computational power aware computational power network bandwidth allocation method that uses user quality of service as a gain metric while solving the problem of computational power scheduling and network routing to maximize the gain metric value.
One disadvantage of the prior art is that: CSQF only propose a scheduling mechanism for deterministic flows, but a scheme for calculating flow forwarding paths, forwarding slots is not designed for each deterministic flow, i.e. an implementation of a scheduling mechanism for a given deterministic flow in the network is lacking.
Two disadvantages of the prior art: the scheduling problem of deterministic flows is studied based on different scheduling techniques, the research work based on CSQF techniques is very little, and only the scheduling of network resources is considered, and computational scheduling is not involved.
Three disadvantages of the prior art: most of the resource scheduling schemes consider either only computational resources or only network resources, and a small part of the resource scheduling schemes consider both resources at the same time, but do not consider the deterministic demands of computational applications, and the proposed resource scheduling schemes cannot solve the deterministic scheduling problem.
Disclosure of Invention
The invention aims to provide a wide area deterministic algorithm network scheduling method, a wide area deterministic algorithm network scheduling system and a wide area deterministic algorithm network scheduling medium based on double-layer planning, which solve the scheduling problem of algorithm application in a wide area deterministic network and guide the realization of optimal scheduling of algorithm application.
The invention aims to achieve the aim, and the aim is achieved by the following technical scheme:
and acquiring network topology information and calculation service request information, and calculating a feasible path set between the network node pairs according to the network topology information.
And inputting the network topology information, the node pair feasible path set and the computing power service request information into a double-layer planning model. The double-layer planning model comprises an upper-layer optimization target, a lower-layer optimization target and constraint conditions, wherein the upper-layer optimization target is used for maximizing throughput of a computing power service request, and the lower-layer optimization target is used for minimizing average time delay of the computing power service.
And solving through a double-layer planning model to obtain the planning results of the power calculation nodes, the transmission paths and the hop-by-hop transmission time slots of each power calculation service request.
And carrying out calculation network scheduling according to the planning result, and serving the calculation service request.
The network topology information includes: a network node set, a network link set, a node set capable of providing computing power, a computing power size capable of being provided by a computing power node, a transmission bandwidth capable of being provided by a link, a propagation delay of the link, a forwarding time slot size, and a super period size in units of forwarding time slots.
The power calculation service request information includes: the source node of the request, the length of the data packet of the request, the number of data packets of the request in the forwarding time slot, the calculation power requirement of the request, and the maximum acceptable end-to-end time delay of the request.
Preferably, the maximizing throughput of the power service requestThe specific formula is as follows:
，
wherein, Representing request/>Packet size,/>Representing request/>In time slot/>Data packet number,/>Representing super period in units of forwarding time slots,/>Representing request/>Whether to use path/>A value of 1 indicates yes, a value of 0 indicates no,Representing all request sets,/>Representing the total set of paths.
Average time delay of the minimized computing power serviceThe specific formula is as follows:
，
wherein, Representing link/>Propagation delay of/>Representing the size of the forwarding slot,/>Indicating the total number of requests,Representing request/>In the path/>(1 /)Slot offset at the time of forwarding on the link.
Preferably, the constraint condition includes a computing force node selection constraint, a path selection constraint, a time slot offset constraint, a time delay constraint, a forwarding time slot constraint and a link bandwidth constraint.
Preferably, the computing force node selection constraint includes:
Node uniqueness constraint: ，
Node calculation force size constraint: ，
wherein, Representing request/>Calculated force demand,/>Representing the computational effort node/>The available calculation force,/>Representing request/>Whether to select the computing force node/>For the destination node, a value of 1 indicates yes, and a value of 0 indicates no,/>Representing a set of all computing nodes.
The path selection constraint includes:
at most one path constraint: ，
Link identification constraints: ，
wherein, Representing request/>Whether or not to use a link/>A value of 1 indicates yes, a value of 0 indicates no,/>Representing the set of paths from node s to node d.
The time slot offset constraint is that
，
Wherein,Representing link/>Deterministic queue number,/>Is constant.
The time delay constraint is as follows:
，
wherein, For flow/>Acceptable maximum end-to-end delay,/>For forwarding the size of the time slot.
The forwarding slot constraints include:
slot uniqueness constraint:
，
time slot allocation constraints:
，
，
wherein, Representing request/>Belonging to time slot/>Traffic in path/>Link/>Whether or not to use time slot/>。
The link bandwidth constraint includes:
request data volume constraint:
，
bandwidth capacity constraint:
，
wherein, Representing link/>Is/are provided with the available transmission bandwidthRepresenting request/>Belonging to time slot/>Traffic in path/>Link/>Time slots of upper usage/>Is a number of packets of data.
Preferably, the time slot offset constraint and the time delay constraint are includedThe value is three or more orders of magnitude higher than the other parameter values.
The invention has the advantages that: aiming at the scene that the computing power application needs deterministic transmission service, the scheduling problem of the computing power application in a wide area deterministic network is solved, and the optimal scheduling of the computing power application is guided to be realized. Selecting a proper node capable of providing computing power for the computing power service, selecting a proper transmission path from a source to the computing node for the computing power service, planning hop-by-hop transmission time slots for the computing power service along the transmission path, and mutually coupling and influencing three sub-problems.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
Fig. 1 is a schematic diagram of a CSQF-based slot plan according to the present invention.
FIG. 2 is a schematic diagram of routing and computing node selection for a computing application of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
The wide area deterministic algorithm network scheduling method based on double-layer planning is realized by the following technical scheme:
and inputting the network topology information, the node pair feasible path set and the computing power service request information into a double-layer planning model.
The network topology information includes: a network node set, a network link set, a node set capable of providing computing power, a computing power size capable of being provided by a computing power node, a transmission bandwidth capable of being provided by a link, a propagation delay of the link, a forwarding time slot size, and a super period size in units of forwarding time slots.
The power calculation service request information includes: the source node of the request, the length of the data packet of the request, the number of data packets of the request in the forwarding time slot, the calculation power requirement of the request, and the maximum acceptable end-to-end time delay of the request.
The double-layer planning model comprises an upper-layer optimization target, a lower-layer optimization target and constraint conditions, wherein the upper-layer optimization target is used for maximizing throughput of a computing power service request, and the lower-layer optimization target is used for minimizing average time delay of the computing power service.
Throughput of the maximized power service requestThe specific formula is as follows:
，
wherein, Representing request/>Packet size,/>Representing request/>In time slot/>Data packet number,/>Representing super period in units of forwarding time slots,/>Representing request/>Whether to use path/>A value of 1 indicates yes, a value of 0 indicates no,Representing all request sets,/>Representing the total set of paths.
Average time delay of the minimized computing power serviceThe specific formula is as follows:
，
wherein, Representing link/>Propagation delay of/>Representing the size of the forwarding slot,/>Indicating the total number of requests,Representing request/>In the path/>(1 /)Slot offset at the time of forwarding on the link.
The constraint conditions comprise a computing force node selection constraint, a path selection constraint, a time slot offset constraint, a time delay constraint, a forwarding time slot constraint and a link bandwidth constraint.
The computing force node selection constraint includes:
Node uniqueness constraint: ，
Node calculation force size constraint: ，
wherein, Representing request/>Calculated force demand,/>Representing the computational effort node/>The available calculation force,/>Representing request/>Whether to select the computing force node/>For the destination node, a value of 1 indicates yes, and a value of 0 indicates no,/>Representing a set of all computing nodes.
The path selection constraint includes:
at most one path constraint: ，
Link identification constraints: ，
wherein, Representing request/>Whether or not to use a link/>A value of 1 indicates yes, a value of 0 indicates no,/>Representing the set of paths from node s to node d.
The time slot offset constraint is that
，
Wherein,Representing link/>Deterministic queue number,/>Is constant.
The time delay constraint is as follows:
，
wherein, For flow/>Acceptable maximum end-to-end delay,/>For forwarding the size of the time slot. /(I)The value is three or more orders of magnitude higher than the other parameter values
The forwarding slot constraints include:
slot uniqueness constraint:
，
time slot allocation constraints:
，
，
wherein, Representing request/>Belonging to time slot/>Traffic in path/>Link/>Whether or not to use time slot/>。
The link bandwidth constraint includes:
request data volume constraint:
，
bandwidth capacity constraint:
，
wherein, Representing link/>Is/are provided with the available transmission bandwidthRepresenting request/>Belonging to time slot/>Traffic in path/>Link/>Time slots of upper usage/>Is a number of packets of data.
And solving through a double-layer planning model to obtain the planning results of the power calculation nodes, the transmission paths and the hop-by-hop transmission time slots of each power calculation service request.
And carrying out calculation network scheduling according to the planning result, and serving the calculation service request.
Example 2
The embodiment of the disclosure provides a wide area deterministic algorithm scheduling system based on double-layer planning, which is characterized by comprising:
and a data acquisition module. And acquiring network topology information and calculation service request information, and calculating a feasible path set between the network node pairs according to the network topology information.
And planning a scheduling module. And inputting the network topology information, the node pair feasible path set and the computing power service request information into a double-layer planning model. The double-layer planning model comprises an upper-layer optimization target, a lower-layer optimization target and constraint conditions, wherein the upper-layer optimization target is used for maximizing throughput of a computing power service request, and the lower-layer optimization target is used for minimizing average time delay of the computing power service.
And solving through a double-layer planning model to obtain the planning results of the power calculation nodes, the transmission paths and the hop-by-hop transmission time slots of each power calculation service request.
And carrying out calculation network scheduling according to the planning result, and serving the calculation service request.
Embodiments of the present disclosure provide a wide area deterministic algorithm scheduling device based on dual layer planning, including a processor (processor) and a memory (memory). Optionally, the apparatus may further comprise a communication interface (Communication Interface) and a bus. The processor, the communication interface and the memory can complete communication with each other through the bus. The communication interface may be used for information transfer. The processor may invoke logic instructions in memory to perform the wide area deterministic algorithm scheduling method based on dual layer planning of the above embodiments.
Further, the logic instructions in the memory described above may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product.
The memory is used as a computer readable storage medium for storing a software program, a computer executable program, and program instructions/modules corresponding to the methods in the embodiments of the present disclosure. The processor executes the program instructions/modules stored in the memory to perform the functional application and data processing, i.e., implement the wide area deterministic algorithm scheduling method based on the two-layer programming in the above embodiments.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function. The storage data area may store data created according to the use of the terminal device, etc. Further, the memory may include a high-speed random access memory, and may also include a nonvolatile memory.
Embodiments of the present disclosure provide a computer readable storage medium storing computer executable instructions configured to perform the above-described wide area deterministic algorithm scheduling method based on dual layer planning.
The computer readable storage medium may be a transitory computer readable storage medium or a non-transitory computer readable storage medium.
Embodiments of the present disclosure may be embodied in a software product stored on a storage medium, including one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of a method according to embodiments of the present disclosure. And the aforementioned storage medium may be a non-transitory storage medium including: a plurality of media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or a transitory storage medium.
Example 3
To verify the superiority of the solution proposed by this patent, we combine this two-layer optimization model with a single-layer optimization model (hereinafter referred to as throughput optimization model) composed of the upper-layer optimization objective of claim 3, the constraints of claims 4-8, a single-layer optimization model (hereinafter referred to as optimal delay optimization model) composed of the lower-layer optimization objective of claim 4, the constraints of claims 4-8, and the linear combinations of claims 3 and 4 (i.e.) Comparison of joint optimization models (hereinafter referred to as joint optimization models) constructed by the constraints of claims 4-8. When the number of the computing power service requests is 10 and 20 respectively, the comparison results of the four models in terms of total throughput, average time delay and solving time are shown in the following table one:
Table 1 model comparison results
As can be seen from the table, the throughput optimization model can obtain the optimal throughput but the average delay is larger, and the delay optimization model can obtain the shortest average delay but the throughput is the lowest. Compared with the throughput optimal model and the time delay optimal model, the joint optimal model and the double-layer planning model can better balance throughput and average time delay, and the double-layer planning model can better balance throughput and average time delay compared with the joint optimal model. Although the adjustment of the coefficient constants α, β of the joint optimization model may achieve the effect of the dual-layer planning model, a complex parameter adjustment operation is required, and the dual-layer planning model is adopted to avoid the complex operation. In terms of solving time, the solving time of the first three models is lower than that of the double-layer planning model, but the difference between solving time can be reduced by adopting a higher-performance solving server.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. The wide area deterministic algorithm network scheduling method based on double-layer planning is characterized by comprising the following steps of:
Acquiring network topology information and calculation service request information, and calculating a feasible path set between network node pairs according to the network topology information;
Inputting network topology information, node pair feasible path sets and calculation service request information into a double-layer planning model; the double-layer planning model comprises an upper-layer optimization target, a lower-layer optimization target and constraint conditions, wherein the upper-layer optimization target is used for maximizing throughput of a computing power service request, and the lower-layer optimization target is used for minimizing average time delay of the computing power service;
solving through a double-layer planning model to obtain planning results of computing nodes, transmission paths and hop-by-hop transmission time slots of each computing service request;
According to the planning result, carrying out calculation network scheduling and serving calculation service requests;
The network topology information includes: the method comprises the steps of a network node set, a network link set, a node set capable of providing computing power, the computing power size capable of being provided by a computing power node, the transmission bandwidth capable of being provided by a link, the propagation delay of the link, the forwarding time slot size and the super period size taking the forwarding time slot as a unit;
The power calculation service request information includes: the method comprises the steps of requesting a source node, requesting a data packet length, requesting the number of the data packets in a forwarding time slot, requesting calculation power demand, and requesting acceptable maximum end-to-end time delay;
throughput of the maximized power service request The specific formula is as follows:
，
wherein, Representing request/>Packet size,/>Representing request/>In time slot/>Data packet number,/>Representing super period in units of forwarding time slots,/>Representing request/>Whether to use path/>A value of 1 indicates yes, a value of 0 indicates no,/>Representing a request set,/>Representing a set of total paths; /(I)Representing link/>Number of deterministic queues;
average time delay of the minimized computing power service The specific formula is as follows:
，
wherein, Representing link/>Propagation delay of/>Representing the size of the forwarding slot,/>Representing the total number of requests,/>Representing request/>In the path/>(1 /)Time slot offset during forwarding on a link;
The constraint conditions comprise a calculation node selection constraint, a path selection constraint, a time slot offset constraint, a time delay constraint, a forwarding time slot constraint and a link bandwidth constraint;
the computing force node selection constraint includes:
Node uniqueness constraint: ，
Node calculation force size constraint: ，
wherein, Representing request/>Calculated force demand,/>Representing the computational effort node/>The available calculation force,/>Representing request/>Whether to select the computing force node/>For the destination node, a value of 1 indicates yes, and a value of 0 indicates no,/>Representing a set of all available nodes that can provide computing power;
The path selection constraint includes:
at most one path constraint: ，
Link identification constraints: ，
wherein, Representing request/>Whether or not to use a link/>A value of 1 indicates yes, a value of 0 indicates no,/>Representing nodes/>To node/>Is a set of paths;
The time slot offset constraint is that
，
Wherein,Is a constant;
The time delay constraint is as follows:
，
wherein, For flow/>Acceptable maximum end-to-end delay,/>The size of the forwarding slot;
The forwarding slot constraints include:
slot uniqueness constraint:
，
time slot allocation constraints:
，
，
wherein, Representing request/>Belonging to time slot/>Traffic in path/>Link/>Whether or not to use time slot/>；
The link bandwidth constraint includes:
request data volume constraint:
，
bandwidth capacity constraint:
，
wherein, Representing link/>Is/are provided with the available transmission bandwidthRepresenting request/>Belonging to time slot/>Traffic in path/>Link/>Time slots of upper usage/>Is the number of data packets;
in time slot offset constraint and time delay constraint The value is three or more orders of magnitude higher than the other parameter values.
2. A wide area deterministic algorithm scheduling system based on two-tier planning for performing the method of claim 1, comprising:
a data acquisition module; acquiring network topology information and calculation service request information, and calculating a feasible path set between network node pairs according to the network topology information;
Planning a scheduling module; inputting network topology information, node pair feasible path sets and calculation service request information into a double-layer planning model; the double-layer planning model comprises an upper-layer optimization target, a lower-layer optimization target and constraint conditions, wherein the upper-layer optimization target is used for maximizing throughput of a computing power service request, and the lower-layer optimization target is used for minimizing average time delay of the computing power service;
solving through a double-layer planning model to obtain planning results of computing nodes, transmission paths and hop-by-hop transmission time slots of each computing service request;
And carrying out calculation network scheduling according to the planning result, and serving the calculation service request.
3. A dual layer programming based wide area deterministic algorithm scheduling apparatus comprising a processor and a memory storing program instructions, wherein the processor is configured to perform the dual layer programming based wide area deterministic algorithm scheduling method in accordance with claim 1 when the program instructions are executed.
4. A storage medium storing program instructions which, when executed, perform the wide area deterministic algorithm scheduling method based on two-layer planning according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311227412.4A CN117278557B (en) | 2023-09-22 | 2023-09-22 | Wide area deterministic algorithm network scheduling method, system, device and medium based on double-layer planning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311227412.4A CN117278557B (en) | 2023-09-22 | 2023-09-22 | Wide area deterministic algorithm network scheduling method, system, device and medium based on double-layer planning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117278557A CN117278557A (en) | 2023-12-22 |
| CN117278557B true CN117278557B (en) | 2024-05-17 |
Family
ID=89213793
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311227412.4A Active CN117278557B (en) | 2023-09-22 | 2023-09-22 | Wide area deterministic algorithm network scheduling method, system, device and medium based on double-layer planning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117278557B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101677289A (en) * | 2008-09-17 | 2010-03-24 | 华为技术有限公司 | Method and device for optimizing route |
| CN104219190A (en) * | 2014-09-04 | 2014-12-17 | 西安电子科技大学 | Component channel and power distribution method for cognition OFDM (orthogonal frequency division multiplexing) system |
| US9184999B1 (en) * | 2013-03-15 | 2015-11-10 | Google Inc. | Logical topology in a dynamic data center network |
| CN112565272A (en) * | 2020-12-09 | 2021-03-26 | 中国人民解放军国防科技大学 | Method and device for blocking minimum Steiner tree of double-layer network and computer equipment |
-
2023
- 2023-09-22 CN CN202311227412.4A patent/CN117278557B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101677289A (en) * | 2008-09-17 | 2010-03-24 | 华为技术有限公司 | Method and device for optimizing route |
| US9184999B1 (en) * | 2013-03-15 | 2015-11-10 | Google Inc. | Logical topology in a dynamic data center network |
| CN104219190A (en) * | 2014-09-04 | 2014-12-17 | 西安电子科技大学 | Component channel and power distribution method for cognition OFDM (orthogonal frequency division multiplexing) system |
| CN112565272A (en) * | 2020-12-09 | 2021-03-26 | 中国人民解放军国防科技大学 | Method and device for blocking minimum Steiner tree of double-layer network and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117278557A (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hussein et al. | Efficient task offloading for IoT-based applications in fog computing using ant colony optimization | |
| EP3090517B1 (en) | Inter-domain sdn traffic engineering | |
| JP5324637B2 (en) | Dynamic flowlet scheduling system, flow scheduling method, and flow scheduling program | |
| Grosu et al. | Noncooperative load balancing in distributed systems | |
| JP6301509B2 (en) | System and method for providing on-site service | |
| WO2017143984A1 (en) | Method and apparatus for dynamic backhaul resource allocation in a radio access network | |
| WO2021003422A1 (en) | Network and method for servicing a computation request | |
| Wu et al. | Queue-length stability of maximal greedy schedules in wireless networks | |
| Abdellatif et al. | Intelligent-slicing: an AI-assisted network slicing framework for 5G-and-Beyond networks | |
| CN117278557B (en) | Wide area deterministic algorithm network scheduling method, system, device and medium based on double-layer planning | |
| US10182433B2 (en) | System and method for overlapping rate region zoning | |
| CN112867088A (en) | Dynamic adjustment method and system for cloud-edge-end communication architecture | |
| CN105917621B (en) | Method and system for data routing | |
| Yang et al. | A game-theoretic approach to stable routing in max-min fair networks | |
| Satyananda et al. | A multi-objective QoS optimization with fuzzy based parameter setting for real-time multicasting | |
| Wang et al. | Adaptive flow rate control for network utility maximization subject to QoS constraints in wireless multi-hop networks | |
| Parag et al. | Value-aware resource allocation for service guarantees in networks | |
| Liu et al. | Ppo-based reliable concurrent transmission control for telemedicine real-time services | |
| CN109450809B (en) | Data center scheduling system and method | |
| Thi et al. | A rate allocation framework for multi-class services in software-defined networks | |
| Elbey et al. | Review on Reinforcement Learning-based approaches for Service Function Chain deployment in 5G networks | |
| López et al. | Priority flow admission and routing in sdn: Exact and heuristic approaches | |
| CN117221126B (en) | Network collaboration flow-oriented route scheduling method and system | |
| Schmidt et al. | Scalable bandwidth optimization in advance reservation networks | |
| Paschos et al. | In-Network Congestion Control<? Pub _newline=""?> for Multirate Multicast |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Ma Zhongjun Inventor after: Shen Yanbin Inventor after: Tao Gaofeng Inventor before: Zhu Jing Inventor before: Tao Gaofeng Inventor before: Ma Zhongjun Inventor before: Shen Yanbin |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |