CN115174403A - Resource scheduling and routing management method for multi-mode communication network in low-carbon park - Google Patents
Resource scheduling and routing management method for multi-mode communication network in low-carbon park Download PDFInfo
- Publication number
- CN115174403A CN115174403A CN202210775986.4A CN202210775986A CN115174403A CN 115174403 A CN115174403 A CN 115174403A CN 202210775986 A CN202210775986 A CN 202210775986A CN 115174403 A CN115174403 A CN 115174403A
- Authority
- CN
- China
- Prior art keywords
- embedding
- vnf
- flow
- server
- scheduling
- 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
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 60
- 238000004891 communication Methods 0.000 title claims abstract description 53
- 238000007726 management method Methods 0.000 title claims description 65
- 238000005457 optimization Methods 0.000 claims abstract description 75
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 36
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 24
- 230000008447 perception Effects 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000007774 longterm Effects 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 230000009471 action Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 230000033228 biological regulation Effects 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 6
- 238000011217 control strategy Methods 0.000 claims description 2
- 230000006641 stabilisation Effects 0.000 claims description 2
- 238000011105 stabilization Methods 0.000 claims description 2
- 229910052739 hydrogen Inorganic materials 0.000 claims 1
- 239000001257 hydrogen Substances 0.000 claims 1
- 125000004435 hydrogen atom Chemical class [H]* 0.000 claims 1
- 239000000126 substance Substances 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 3
- 238000009826 distribution Methods 0.000 abstract description 3
- 230000008878 coupling Effects 0.000 abstract description 2
- 238000010168 coupling process Methods 0.000 abstract description 2
- 238000005859 coupling reaction Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 7
- 230000004048 modification Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000009466 transformation Effects 0.000 description 3
- 101100460704 Aspergillus sp. (strain MF297-2) notI gene Proteins 0.000 description 2
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 241000764238 Isis Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- 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
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/02—Topology update or discovery
- H04L45/08—Learning-based routing, e.g. using neural networks or artificial intelligence
-
- 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)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a method for resource scheduling and route management of a multi-modal communication network in a low-carbon park, belonging to the technical field of communication. The VNF embedding and flow scheduling combined optimization algorithm provided by the invention utilizes Lyapunov optimization to solve the problem of coupling of VNF embedding and flow scheduling, optimizes a long-time-scale embedding strategy and short-time-scale flow scheduling, realizes flexible scheduling and route management of multi-modal communication network resources, and guarantees differentiated QoS (quality of service) requirements of energy management services; by establishing the matching problem between the server and the VNF, the external problem is solved by using an exchange matching theory, and an embedding strategy with stable exchange is obtained by continuously exchanging an embedding scheme among streams, so that the embedding cost is reduced, and the efficient utilization of multi-mode communication network resources is realized; the method has the advantages that under the condition that incomplete information is caused by diversified regional characteristics and complex power distribution and utilization environments of the park, the routing strategy is optimized through Q learning and backpressure perception, network throughput is improved, and low-carbon operation of energy management services such as carbon footprint monitoring is supported.
Description
Technical Field
The invention relates to a resource scheduling and routing management method for a multi-mode communication network in a low-carbon park, and belongs to the technical field of communication.
Background
The park is an industrial park with informationization and intelligentization characteristics realized by new-generation information technology means such as 'cloud moving intelligence'. The development of low-carbon operation construction of park energy management services is an important ring for assisting 3060 double-carbon target realization and propelling novel power system construction. The energy management service of the low-carbon park is flexible and various, such as flexible load regulation, electric power spot market, carbon footprint monitoring and the like, and the requirements of each service application on time delay, bandwidth, throughput, reliability and the like are different. Therefore, there is a need for flexible scheduling of communication network resources based on differentiated energy management business needs. However, the traditional communication network is closed and rigid, and software and hardware are highly coupled, so that the requirements of low-carbon park energy management services cannot be met. By utilizing Network Function Virtualization (NFV), multi-dimensional physical resources such as a low-carbon park 5G, an optical fiber, an AC/DC carrier wave, a WLAN communication link, a multi-modal communication edge computing gateway and a server are virtualized, and by combining the advantage of separation of control and forwarding of a Software Defined Network (SDN), centralized management and flexible scheduling of multi-modal communication Network resources are realized. In addition, due to the diversified regional characteristics and the complex power distribution and utilization environment of the low-carbon park, the channel transmission state information is unpredictable, so that the routing management under the incomplete information needs to be realized by combining an advanced artificial intelligence technology, and the requirement of Quality of Service (QoS) differentiation of the low-carbon park energy management Service is met.
Based on the NFV technology, the low-carbon park energy management Service is identified by a Service Function Chain (SFC). The SFC is composed of a group of Virtual Network Functions (VNFs) in a specific order, and the data stream must traverse all VNFs, that is, software running on a server, so as to provide a service for a specific energy management service in the low-carbon campus. The invention considers multi-mode communication network resource scheduling and routing management supporting low-carbon park energy management services, and mainly focuses on two core problems of VNF embedding and flow scheduling. VNF embedding decides how to efficiently embed VNFs on servers to reduce the embedding cost. The stream scheduling means that adaptive routing selection is realized through routing management on the basis that a VNF is embedded in a server, the admitted data volume is determined, a suitable next-hop server is selected, and the throughput maximization is realized while a Service Level Agreement (SLA) is satisfied. However, the joint optimization of VNF embedding and flow scheduling still faces some challenges, and first, the campus low-carbon service has differentiated QoS requirements in terms of throughput and VNF embedding cost; secondly, VNF embedding strategies and flow scheduling strategies are mutually coupled under different time scales, and the VNF embedding strategies among different flows influence each other to cause externality, so that the solution of the joint optimization problem is very complex; finally, due to the unpredictability of the information in practical application, the flow scheduling optimization needs to be performed under incomplete information.
Therefore, a multimodal communication network resource scheduling and routing management method capable of performing joint optimization on VNF embedding and flow scheduling is urgently needed to be designed, so that embedding cost is greatly reduced while throughput is maximized, and differentiated QoS requirements of low-carbon park energy management services are met.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a resource scheduling and routing management method for a multimodal communication network in a low-carbon park.
The invention discloses a resource scheduling and routing management method for a multi-modal communication network in a low-carbon park, which comprises the following specific management steps of:
the method comprises the steps that a VNF embedding and flow scheduling process in a pre-constructed architecture model is modeled into a VNF embedding model and a flow scheduling model based on a multi-time scale model, wherein the embedding from a VNF to a data plane server under a set time period is established into the VNF embedding model, and the route from a flow of a source server to a destination server under a time slot is established into the flow scheduling model;
establishing a VNF embedding and flow scheduling joint optimization problem model based on the VNF embedding model and the flow scheduling model, and constraining network performance;
based on the result of constraining the network performance, describing a VNF embedding and flow scheduling joint optimization problem model as a weighted difference of the maximized network throughput and the VNF embedding cost; and
converting the lyapunov optimization into a VNF embedding strategy optimization problem of a set time period and a time slot scale flow scheduling optimization problem;
VNF embedding strategy optimization under a set time period is carried out through exchanging a matched VNF embedding algorithm, flow scheduling optimization of the time slot is carried out through admission control under the time slot and a backpressure perception routing selection algorithm based on Q learning, and resource scheduling and routing management of the low-carbon park multi-mode communication network are carried out.
Further, the pre-constructed architecture model comprises a data plane, a control plane and an application plane; wherein:
on a data plane, multi-modal heterogeneous communication network resources are abstracted into a uniform virtual resource pool, the virtual resource pool comprises communication, calculation and storage virtual resources, the deployment virtual resources support different VNFs, and the VNFs are arranged in a specific sequence to form an SFC;
in a control plane, the SDN controller utilizes a resource scheduling component to carry out VNF embedding and utilizes a route management component to carry out flow scheduling to realize route management optimization; wherein the VNF embedding is to embed VNFs of the SFC in a server to support a plurality of low carbon services; the flow scheduling refers to selecting a proper path for the flow from the source server to transmit to the destination server on the basis of embedding the VNF;
on the application plane, the low-carbon intelligent park energy management service comprises the following steps: carbon footprint monitoring, electric power spot market, flexible load regulation.
Further the VNF embedding model is: embedding an indicator variable in the h-th time period VNF
Wherein the subscript
Represents the nth processing server; upper label
The kth VNF representing SFC;
the flow scheduling model is as follows: stream f queue backlog at server n with t-th slot embedded in VNFk
The update expression is as follows:
wherein, the first and the second end of the pipe are connected with each other,
and
denoted as flow f queue backlog at server n embedding VNFk for t and t +1 time slots respectively,
selecting an indicator variable for the flow f route;
for the set of servers embedded in VNFk +1,
is a server set embedded in VNFk-1;
it is the t-th time slot that is processed by server n and transmitted to the set
The data volume of the server in (1);
is the t-th slot to be aggregated
The amount of data transmitted by the server n to the server n;
is admitted data.
Further, the establishing of the VNF embedding and flow scheduling joint optimization problem model to constrain network performance includes:
constraints of streaming, for origin server
Admission data of flow f
The constraints are:
wherein
Presentation server
Up, the amount of data that flow f arrives; at the same time, only VNFk +1 is embedded in server j,
can be transmitted to server j, where
Embedding an indicator variable for the VNF;
the resource constraint, the amount of data transmitted via the link (n, j) in the t-th slot is subject to the link capacity L n,j (t) and calculation of the Capacity C n (t) constraint, whose formula is:
wherein
Represents the unit complexity of processing the flow f data by the VNFk; τ is the duration of one slot;
a queue backlog constraint, representing a long-term queue backlog constraint as:
wherein
Is the flow f queue backlog at server n where the t-th slot is embedded in the VNFk;
throughput constraint, average throughput of flow f r f The constraint is expressed as:
wherein
And
the minimum throughput and the maximum throughput of flow f are indicated separately.
Further, based on the result of constraining the network performance, the VNF embedding and flow scheduling joint optimization problem model is described as a method of maximizing the weighted difference between the network throughput and the VNF embedding cost, which is as follows:
the optimization problem P1 is a maximized weighted cumulative utility function, and the formula is as follows:
C 3 (2), (3), (4), and (5)
Wherein
Beta and lambda represent the weights of throughput and embedding cost respectively,
it is shown that the VNF embeds an indication variable,
admission data representing a flow f on a server n, e k (h) Represents the embedding cost of VNFk; y (h), r (t), and x (t) each represents k
In which
Selecting an indicator variable for the flow f route; constraint C 1 Representing server selection constraints; constraint C 2 Representing a VNF embedding constraint;
c3 has the formula (2) of
Formula (3) is
Formula (4) is
Formula (5) is
Wherein
Presentation server
Up, the amount of data that flow f arrives;
is the amount of data transmitted via the link (n, j) for the t-th time slot; l is a radical of an alcohol n,j (t) and C n (t) represents the link capacity of the link (n, j) and the server n calculated capacity, respectively;
represents the unit complexity of processing the flow f data by the VNFk; τ is the duration of one slot;
is the flow f queue backlog at server n where the t-th slot is embedded in the VNFk;
and
respectively representing the minimum throughput and the maximum throughput of the flow f; r is f Is the average throughput of flow f.
Further, the specific steps of converting the lyapunov optimization into the VNF embedding strategy optimization problem of the time slot and the stream scheduling optimization problem of the time slot scale are as follows:
converting long-term queue stability constraint into a virtual queue by using a virtual queue principle, and rewriting an optimization problem P1 as follows:
s.t.C 1 ,C 2
C 4 (2) and (3)
C 5 :Y f (t) and Z f (t) average Rate stabilization
Wherein the formula (2) in C4 is
Formula (3) is
In C5
Wherein W is a weighted cumulative utility function;
presentation server
Up, the amount of data that flow f arrives;
admission data representing a flow f on a server n;
is the amount of data transmitted via the link (n, j) for the t-th time slot; l is n,j (t) and C n (t) represents the link capacity of the link (n, j) and the server n calculated capacity, respectively;
represents the unit complexity of processing the flow f data by the VNFk; τ is the duration of one slot; y is f (t) and Z f (t) is a virtual queue;
admission data representing flow f;
based on lyapunov optimization, P1.1 translates to an upper bound of minimized drift minus reward, expressed as:
wherein
V is a non-negative weighting parameter of the utility function; Θ (t) = [ Q (t), Y (t), Z (t)]In which
And
in order to be a virtual queue vector, the virtual queue vector,
is a queue vector;
is lyapunov drift, in which
Is the lyapunov function.
Further, the method for optimizing the VNF embedding policy in the time period by exchanging the matched VNF embedding algorithm includes:
by solving the VNF embedding sub-problem SP1 in the set time period, specific embedding positions of K VNFs on N servers are determined, and the formula is as follows:
s.t.C 2
where y (h) is the VNF embedding policy for the h time period;
based on SP1, the utility function of flow f is:
wherein V is a non-negative weighting parameter of the utility function; β and λ represent the weights of throughput and embedding cost, respectively;
representing a VNF embedded indicator variable; e.g. of the type k (h) Represents the embedding cost of VNFk;
selecting an indicator variable for the flow f route;
the embedding condition of the h time period;
are respectively as
L n,j (t),C n (t) an empirical value of (t),
is admitted data;
is the queue backlog of the t-th time slot under the given embedding strategy;
wherein
Presentation server
Up, the amount of data that flow f arrives; l is a radical of an alcohol n,j (t) and C n (t) represents the link capacity of the link (n, j) and the server n calculated capacity, respectively;
calculating utility values according to a formula, and arranging and establishing a preference list according to a descending order; the provided exchange matching-based VNF embedding algorithm for the set time period comprises the following specific processes:
given satisfaction of constraint C 2 Embedding strategy of
Calculating the utility of the flow;
in each iteration, all servers randomly select one server
And another subset
If it is not
The number of servers in is greater than 1, i.e.
Then the server n Leave from
Adding into
Forming new embedding strategies
Then, the utility of the flow is recalculated; if it is not
Is that
Exchange matching of the original embedding strategy
Instead of using
Otherwise
Keeping the same;
according to
Then
Otherwise
In principle, will
Conversion to y * (h)。
Further, the admission control method comprises:
determine slot admission control sub-problem SP2:
s.t.C 6 :(2)
wherein the formula (2) in C6 is
V is a non-negative weighting parameter of the utility function; β is the throughput weight; y is f (t) and Z f (t) is a virtual queue;
backlogging the t-th time slot queue;
admission data representing a flow f on a server n;
presentation server
Up, the amount of data that flow f arrives;
using an admission control method to resolve SP2, denoted as
Further, the backpressure sensing routing algorithm based on Q learning specifically includes the following steps:
determining a time slot routing sub-problem SP3, determining an optimal next hop server:
C 7 :(3)
wherein the formula (3) in C7 is
Is the flow f queue backlog at server n where the t-th slot is embedded in the VNFk;
is the amount of data transmitted via the link (n, j) for the t-th time slot;
selecting an indication variable for the flow f route; x (t) is a routing strategy;
the SP2 is solved by adopting Q learning, and the backpressure sensing routing algorithm based on the Q learning is provided, and the specific flow is as follows:
initialize Q value, set Q (S) n (t),a n (t))＝0；
At the beginning of the tth time slot, each server selects actions according to an epsilon greedy strategy; server j will select B n (t) the largest server n rejects others, and server selection conflicts are resolved; all servers update the reward and queue information and go to the next state S n (t + 1); and updating the Q value;
according to a n (t) = j then
Otherwise
Will be { a } n (t) } conversion to x * (t)；
Wherein the state is
Acting as
The reward is
Q value Q (S) n (t),a n (t)) estimating the state S for the server n (t) selecting action a n (t) as a function of the value of (t).
Further, the algorithm for jointly optimizing VNF embedding and flow scheduling is as follows:
initializing queue backlog of all queues, and VNF embedding, admission control and routing strategy indication functions;
in each set time period, obtaining an optimal VNF embedding strategy y (t) by the VNFs according to a VNF embedding algorithm based on exchange matching in the set time period;
and in each time slot, each source server acquires an optimal admission control strategy r (t) according to a formula, and the source server and the processing server acquire an optimal routing strategy x (t) according to a backpressure perception routing algorithm based on Q learning.
A resource scheduling and routing management device for a multimodal communication network in a low-carbon park specifically comprises:
a modeling module: the flow scheduling method comprises the steps of modeling VNF embedding and flow scheduling processes in a pre-constructed architecture model into a VNF embedding model and a flow scheduling model based on a multi-time scale model, wherein the embedding from a VNF to a data plane server under a time period is established into the VNF embedding model, and the route from a flow of a source server to a destination server under a time slot is established into the flow scheduling model;
a constraint module: the VNF embedding model and the flow scheduling model are used for establishing a VNF embedding and flow scheduling joint optimization problem model and constraining network performance;
a conversion module: the method comprises the steps of utilizing the constraint to jointly optimize a problem model of VNF embedding and flow scheduling, and describing the problem model as the weighted difference of the maximized network throughput and the VNF embedding cost; and
utilizing the Lyapunov optimization to convert the time period VNF embedding strategy optimization problem and the time slot scale flow scheduling optimization problem into time slot optimization problem;
VNF embedding strategies are optimized in a time period through exchanging and matching VNF embedding algorithms, flow scheduling optimization of the time slot is performed through admission control in the time slot and a backpressure perception routing selection algorithm based on Q learning, and resource scheduling and routing management of the low-carbon park multi-mode communication network are achieved.
Further, the modeling module includes:
the system comprises a data plane, a control plane and an application plane; wherein:
on a data plane, multi-modal heterogeneous communication network resources are abstracted into a uniform virtual resource pool, the virtual resource pool comprises communication, calculation and storage virtual resources, different VNFs are supported by deploying the virtual resources, and the VNFs are arranged in a specific sequence to form an SFC;
in a control plane, an SDN controller utilizes a resource scheduling component to carry out VNF embedding and utilizes a route management component to carry out flow scheduling to realize route management optimization; wherein the VNF embedding is to embed VNFs of the SFC in a server to support a plurality of low carbon services; the flow scheduling refers to selecting a proper path for the flow from the source server to transmit to the destination server on the basis of embedding the VNF;
on the application plane, the low-carbon intelligent park energy management service comprises the following steps: carbon footprint monitoring, electric power spot market, flexible load regulation.
Further, the constraint model is used for the constraint of the constraint model for streaming, and the source server
Admission data of flow f
The constraints are:
wherein
Presentation server
Up, the amount of data that flow f arrives; at the same time, only VNFk +1 is embedded in server j,
can be transmitted to server j, where
Embedding an indicator variable for the VNF;
the resource constraint, the amount of data transmitted via the link (n, j) in the t-th slot is subject to the link capacity L n,j (t) and calculation of the Capacity C n (t) constraint, whose formula is:
wherein
Represents the unit complexity of processing the flow f data by the VNFk; τ is the duration of one slot;
a queue backlog constraint, representing a long-term queue backlog constraint as:
wherein
Is the flow f queue backlog at server n where the t-th slot is embedded in the VNFk;
throughput constraint, average throughput of flow f r f The constraints are expressed as:
wherein
And
the minimum throughput and the maximum throughput of flow f are indicated separately.
By the scheme, the invention at least has the following advantages:
(1) The VNF embedding and flow scheduling combined optimization algorithm VEFS provided by the invention utilizes Lyapunov optimization to solve the problem of coupling of VNF embedding and flow scheduling, optimizes a long-time-scale VNF embedding strategy and a short-time-scale flow scheduling, realizes flexible scheduling and routing management of multi-modal communication network resources, and guarantees differentiated QoS (quality of service) requirements of energy management services.
(2) The exchange matching-based long-time-scale VNF embedding algorithm provided by the invention solves the external problem by establishing the matching problem of the server and the VNF and utilizing the exchange matching theory, obtains an embedding strategy with stable exchange by continuously exchanging the embedding scheme among streams, reduces the embedding cost overhead and realizes the high-efficiency utilization of multi-mode communication network resources.
(3) The backpressure sensing routing algorithm based on Q learning provided by the invention can optimize the routing strategy through Q learning and backpressure sensing under the condition that information is incomplete due to diversified regional characteristics and complex power distribution and utilization environments in a park, thereby improving the network throughput and supporting low-carbon operation of energy management services such as carbon footprint monitoring and the like.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical solutions of the present invention more clearly understood and to implement them in accordance with the contents of the description, the following detailed description is given with reference to the preferred embodiments of the present invention and the accompanying drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate a certain embodiment of the present invention, and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic diagram of a low-carbon smart campus multi-modal communication network resource scheduling and routing management architecture based on SDN/NFV according to the present invention;
fig. 2 is a schematic diagram of the slot model of the present invention.
Detailed Description
The following detailed description of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
The whole technical scheme of the invention mainly comprises five steps: (1) constructing a system model framework; (2) refining a model; (3) proposing VNF embedding and flow scheduling constraint and optimization problems; (4) transformation of optimization problems based on Lyapunov; (5) A multi-mode communication network resource scheduling and routing management method is provided. . The concrete introduction is as follows:
1. building a system model framework
The invention constructs a low-carbon park multi-modal communication network resource scheduling and routing management architecture based on SDN/NFV, and as shown in figure 1, the low-carbon park multi-modal communication network resource scheduling and routing management architecture comprises a data plane, a control plane and an application plane. The data plane comprises multi-mode heterogeneous communication network resources, namely 'source load storage' terminal resources such as photovoltaic panels, air conditioners and user energy storage, communication resources such as WLAN, 5G/6G, optical fibers and Power Line Carriers (PLC), resource servers and the like, and the multi-mode heterogeneous communication network resources are abstracted into a uniform virtual resource pool based on NFV technology and comprise communication, calculation and storage virtual resources. By flexibly deploying virtual resources to support SFC, the SFC is composed of diversified VNFs arranged according to a specific sequence and is used for identifying various low-carbon park energy management services. The control plane is composed of an SDN controller, the SDN controller comprises a resource scheduling component and a route management component, the resource scheduling component and the route management component are respectively used for coordinating VNF embedding and configuring flow scheduling, the control plane SDN controller utilizes the resource scheduling component to conduct VNF embedding so as to achieve network resource scheduling optimization aiming at different low-carbon intelligent park energy management service differentiated service quality requirements of the application plane, the route management component is utilized to conduct flow scheduling so as to achieve route management optimization, and the application plane is supported to comprise park management services such as carbon footprint monitoring, electric power spot market, flexible load regulation and the like to run at low carbon.
2. Refinement of models
(1) Multi-time scale time slot model
The present invention employs a multi-time scale time slot model, as shown in fig. 2, to optimize VNF embedding policies under long time scales (time periods), and to optimize stream scheduling policies under short time scales (time slots), wherein the stream scheduling policies are implemented by optimizing admission control and routing. The invention divides the whole optimization time into T A set of time slots
Where each slot is of length tau. Secondly, will T One time slot being equally divided into H Time period, set
Representation in which each time segment is of length T 0 I.e. T = T 0 H. The h-th time period is represented as
(2) VNF embedding model
The present invention describes the underlying physical network as an undirected graph
Wherein
Representing a set of N processing servers, N D Representing the destination server and epsilon the set of links. The set of origin servers is denoted N S And is and
in each SFC consists of K A set of VNFs
Define VNF embed indication variable as
When in use
Time indicates successful embedding of VNFk into server n in h time period, otherwise
The present invention can only support one VNF embedding at most per server per time period.
(3) Flow scheduling model
On the basis that VNF is embedded into a bottom-layer server, flow scheduling optimization is carried out, and for a server n embedded with VNFk, the method defines
For embedding VNF k+1 The set of servers of (a) is,
for embedding VNF k-1 The server set of (2). In the first place t And in each time slot, processing the flow from the source server through the routing sequence of VNF 1-K by flow scheduling optimization, and finally reaching the destination server. Define a set of streams as
The routing indicator variable defining flow f is
When the temperature is higher than the set temperature
When the data of flow f is embedded by the VNF at the t-th time slot k Server of n Is transmitted to a server
Otherwise
In the first place t At the end of one time slot, in VNF k Will be stored in the server n The buffer is modeled as a queue, the queue backlog of which
The evolution is as follows:
wherein
Is shown in t Time slot by embedded VNF k Server of n Transport to embedded VNF k+1 Server of
The amount of data of (a).
Indicating by the server at the t-th time slot n Processed and transmitted to the collection
The data volume of the server in (1).
Indicates that the data is collected in the t-th time slot
Is transmitted to the server n Wherein when k =1, the value is 0 。
3.VNF embedding and proposing flow scheduling constraint and optimization problem
(1) VNF embedding and flow scheduling constraints
1) And (3) stream transmission constraint: for source server
Admission data for flow f
Data that cannot be higher than arrival
Namely:
at the same time, only VNFk +1 is embedded in server j,
namely, it is
Can be transmitted to server j.
2) Resource constraint: in the t-th time slot, the amount of data transmitted via the link (n, j) is subject to the link capacity L n,j (t) and calculation of the Capacity C n (t) constraint, whose formula is:
wherein
Indicating the unit complexity of processing the flow f data by the VNFk.
3) Network performance constraints: to ensure the stability of the network, the long-term queue backlog constraint should be satisfied:
average throughput r of flow f to satisfy SLA f Maximum throughput should be met
And minimum throughput
Constraints, namely:
(2) Optimization problem proposition
The invention solves the optimization problems as follows: under multiple time scales, by jointly optimizing VNF embedding and flow scheduling, the VNF embedding cost is reduced while the network throughput is maximized, and a weighted cumulative utility function is defined as
Where β and λ represent the weights of throughput and embedding cost, respectively, e k (t) represents the embedding cost of the VNFk. Thus, the optimization problem P1 is a maximized weighted cumulative utility function, which is formulated as:
wherein y (h), r (t), and x (t) respectively represent
A collection of (a). Constraint C 1 The server selection constraint is expressed, namely each server can only select one next-hop server to process the task in each time slot; constraint C 2 VNF embedded constraints are expressed, i.e. each VNF can be embedded on only one server per time period.
4. Transformation and algorithm design of optimization problem
(1) Transformation of optimization problem
The optimization problem P1 is a long-term random mixed integer nonlinear programming problem and is difficult to directly solve. Therefore, the invention is based on the virtual queue principle, and converts the long-term queue stability constraint (5) into a virtual queue, and the formula is as follows:
wherein
If Y is f (t + 1) and Z f (t + 1) is that the average rate is stable, then constraint (5) is satisfied automatically, and therefore optimization problem P1 can be rewritten as:
definition of
And
is a virtual queue vector. Definitions Θ (t) = [ Q (t), Y (t), Z (t)]The lyapunov function is expressed as:
the conditional lyapunov drift for a single slot is defined as:
thus, P1.1 may translate into an upper bound for minimizing drift minus reward, which is expressed as:
wherein
V is a non-negative weighting parameter of the utility function.
Thus, P1.1 is equivalent to satisfying constraint C 1 、C 2 、C 4 Maximum under the condition of Γ . Will further maximize Γ The problem is transformed into three sub-problems, namely a large time scale VNF embedding sub-problem SP1, a short time scale admission control sub-problem SP2, a routing sub-problem SP3.
VNF embedding and flow scheduling joint optimization algorithm
(1) Exchange matching based long-time scale VNF embedding optimization
Determining by solving a Large time-Scale VNF embedder sub-problem SP1 K The specific embedded positions of the VNFs on the N servers are expressed as:
due to the fact that
L n,j (t),C n (t) dynamically changing and unknown, and therefore, using their empirical values
Wherein
Can be calculated as:
therefore, the same principle can be obtained
Based on equation (3), an empirical value for the amount of data transmitted via link (n, j) can be further determined
The invention utilizes the matching theory to solve the problem that SP1, stream and embedding strategies are both matched parties. An embedding policy defining the h-th time period as
Wherein
Representing VNF k embeddingA collection of servers. If it is not
Then
Based on SP1, we define the utility function of flow f as
Wherein
Is the data that is admitted to be,
is the queue backlog for the t-th slot under a given embedding policy, which can be derived from short timescale admission control and routing in the following sections.
The flow calculates utility values according to equation (15) and builds favorites lists in descending order. Since different embedding strategies may affect the routing of flows and their utility, i.e. VNF embedding is extrinsic, this problem is solved with switch matching. Exchange matching refers to embedding policies given
Next, if the VNF embedded on server n changes, the original embedding policy
Will be composed of new embedding strategy
And (4) substitution. If it is used
Then define
Is composed of
One exchange of (2) matches.
The invention provides a long-time scale VNF embedding algorithm based on exchange matching, which comprises the following specific processes:
1) Initialization: giving satisfaction of constraint C 2 Embedding strategy of
The utility of the flow is calculated.
2) Exchange matching: in each iteration, all servers randomly select one server
And another subset
If it is not
The number of servers in is greater than 1, i.e.
Server n leaves
Adding into
Forming new embedding strategies
Then, the utility of the flow is recalculated. If it is not
Is that
Exchange matching of (2) the original embedding strategy
Is replaced by
Otherwise
Remain unchanged.
3) VNF embedding: according to
Then
Otherwise
In principle, will
Conversion to y * (h)。
(2) Admission control and Q learning-based backpressure-aware routing algorithm
By solving the short timescale admission control sub-problem SP2, admission data for flow f is determined to keep the queue stable, the formula of which is:
the strategy based on the queue backlog threshold is utilized to solve the optimization problem SP2 and complete the admission control decision
Expressed as:
to determine the optimal next-hop server, the short timescale routing sub-problem SP3 can be expressed as:
based on Markov Decision Process (MDP), the following definition 1) states are given: the network state is defined as a function of throughput and queue information, i.e.
2) The actions are as follows: server n next hop server selects an action space of
3) Reward: for a server n embedded in a VNFk whose potential next hop server queue backlog should be taken into account, SP3 is rewritten to an optimized reward
4) Definition of Q value
Estimating state S for a server n (t) selecting action a n (t) where ψ is the learning rate and γ is the attenuation coefficient.
The invention provides a backpressure perception routing algorithm based on Q learning, which comprises the following specific processes:
1) Initialization: q (S) n (t),a n (t))＝0。
2) Learning: in the first place t At the beginning of each time slot, each server selects an action according to an epsilon greedy strategy. If multiple servers select the same server j, server j will select B n (t) the largest server n and rejects others. All servers then update the reward and queue information and move to the next state S n (t + 1). Finally, the Q value is updated.
3) And (3) routing selection: according to a n (t) = j then
Otherwise
Will be { a } n (t) } conversion to x * (t)。
(3) VNF embedding and flow scheduling joint optimization algorithm
A VNF Embedding and Flow Scheduling (VEFS) joint optimization algorithm provides a flexible solution to the problem of multi-time scale VNF Embedding and Flow Scheduling, and the VEFS algorithm can optimize admission control and routing policies of a small time scale on the basis of a large time scale VNF Embedding result, and is specifically introduced as follows:
1) Initialization: initializing queue backlogs of all queues, and indicating functions of VNF embedding, admission control, routing strategies and the like.
2) VNF embedding: in each time period, the VNFs obtains an optimal VNF embedding policy y (t) according to a large-time-scale VNF embedding algorithm based on exchange matching.
3) Admission control and routing: at each time slot, each source server obtains an optimal admission control policy r (t) according to formula (17), and the source server and the processing server obtain an optimal routing policy x (t) according to a backpressure-aware routing algorithm based on Q learning.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and it should be noted that, for those skilled in the art, many modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein. The scheme in the embodiment of the application can be implemented by adopting various computer languages, such as object-oriented programming language Java and transliterated scripting language JavaScript.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the present application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (13)
1. A resource scheduling and routing management method for a multi-mode communication network in a low-carbon park is characterized by comprising the following specific management steps:
the method comprises the steps that a VNF embedding and flow scheduling process in a pre-constructed architecture model is modeled into a VNF embedding model and a flow scheduling model based on a multi-time scale model, wherein the embedding from a VNF to a data plane server under a set time period is established into the VNF embedding model, and the route from a flow of a source server to a destination server under the time period is established into the flow scheduling model;
based on the VNF embedding model and the flow scheduling model, a VNF embedding and flow scheduling combined optimization problem model is established, and network performance is restrained;
based on the result of constraining the network performance, describing a VNF embedding and flow scheduling joint optimization problem model as a weighted difference of the maximized network throughput and the VNF embedding cost; and
converting the lyapunov optimization into a VNF embedding strategy optimization problem of a set time period and a time slot scale flow scheduling optimization problem;
VNF embedding strategy optimization under a set time period is carried out through a VNF embedding algorithm matched with exchange, flow scheduling optimization of time slots is carried out through admission control under the time slots and a backpressure perception routing selection algorithm based on Q learning, and resource scheduling and routing management of the low-carbon park multi-mode communication network are carried out.
2. The method for resource scheduling and routing management of the multimodal communication network of the low carbon park as claimed in claim 1, wherein: the pre-constructed architecture model comprises a data plane, a control plane and an application plane; wherein:
on a data plane, multi-modal heterogeneous communication network resources are abstracted into a uniform virtual resource pool, the virtual resource pool comprises communication, calculation and storage virtual resources, the deployment virtual resources support different VNFs, and the VNFs are arranged in a specific sequence to form an SFC;
in a control plane, an SDN controller utilizes a resource scheduling component to carry out VNF embedding and utilizes a route management component to carry out flow scheduling to realize route management optimization; wherein the VNF embedding is to embed VNFs of the SFC in a server to support a plurality of low carbon services; the flow scheduling refers to that on the basis of embedding the VNF, a proper path is selected for a flow from a source server to be transmitted to a destination server;
on the application plane, the low-carbon intelligent park energy management service comprises the following steps: carbon footprint monitoring, electric power spot market, flexible load regulation.
3. The method for resource scheduling and routing management of the multi-modal communication network of the low carbon park as recited in claim 1, wherein:
the VNF embedding model is: embedding an indicator variable for the h-th time period VNF
Wherein the subscript
Represents the nth processing server; upper label
The kth VNF representing SFC;
the flow scheduling model is as follows: flow f queue backlog at server n with t-th slot embedded in VNFk
The update expression is as follows:
wherein the content of the first and second substances,
and
denoted as flow f queue backlog at server n of the embedding VNFk for t and t +1 th time slot respectively,
selecting an indication variable for the flow f route;
for the set of servers embedded in VNFk +1,
is a server set embedded in VNFk-1;
it is the t-th time slot that is processed by server n and transmitted to the set
The data volume of the server in (1);
is the t-th slot to be aggregated
The amount of data transmitted by the server n to the server n;
is admitted toAnd (4) data.
4. The method for resource scheduling and routing management of the multimodal communication network of the low carbon park as claimed in claim 1, wherein: the establishing of the VNF embedding and flow scheduling joint optimization problem model for restricting the network performance comprises the following steps:
constraints of streaming, for origin server
Admission data of flow f
The constraints are:
wherein
Presentation server
Up, the amount of data that flow f arrives; at the same time, only VNFk +1 is embedded in server j,
can be transmitted to server j, where
Embedding an indicator variable for the VNF;
the resource constraint, the amount of data transmitted via the link (n, j) in the t-th slot is subject to the link capacity L n,j (t) and calculation of the Capacity C n (t) constraint, whose formula is:
wherein
Represents the unit complexity of processing the flow f data by the VNFk; τ is the duration of one slot;
a queue backlog constraint, representing a long-term queue backlog constraint as:
wherein
Is the flow f queue backlog at server n where the t-th slot is embedded in the VNFk;
throughput constraint, average throughput of flow f r f The constraint is expressed as:
wherein
And
the minimum throughput and the maximum throughput of flow f are indicated separately.
5. The method for resource scheduling and routing management of the multimodal communication network of the low carbon park as claimed in claim 1, wherein: based on the result of constraining network performance, a method for describing a problem model of VNF embedding and flow scheduling joint optimization as a weighted difference that maximizes network throughput and VNF embedding cost is as follows:
the optimization problem P1 is a maximized weighted cumulative utility function, and the formula is as follows:
P1:
C 3 (2), (3), (4), and (5)
Wherein
Beta and lambda represent the weights of throughput and embedding cost respectively,
it is shown that the VNF embeds an indication variable,
admission data representing a flow f on a server n, e k (h) Represents the embedding cost of VNFk; y (h), r (t), and x (t) each represents k
In which
Selecting an indicator variable for the flow f route; constraint C 1 Representing server selection constraints;constraint C 2 Representing VNF embedding constraints;
c3 is represented by the formula (2)
Formula (3) is
Formula (4) is
Formula (5) is
Wherein
Presentation server
Up, the amount of data that flow f arrives;
is the amount of data transmitted via the link (n, j) for the t-th time slot; l is n,j (t) and C n (t) represents the link capacity of the link (n, j) and the server n calculated capacity, respectively;
represents the unit complexity of processing the flow f data by the VNFk; τ is the duration of one slot;
is the flow f queue backlog at server n where the t-th slot is embedded in the VNFk;
and
respectively representing the minimum throughput and the maximum throughput of the flow f; r is a radical of hydrogen f Is the average throughput of flow f.
6. The method for resource scheduling and routing management of the multi-modal communication network of the low carbon park as recited in claim 1, wherein: the method for converting the time-slot VNF embedding strategy optimization problem into the time-slot flow scheduling optimization problem by utilizing the Lyapunov optimization comprises the following specific steps of:
by using the virtual queue principle, the long-term queue stability constraint is converted into a virtual queue, and the optimization problem P1 is rewritten as follows:
P1.1:
s.t.C 1 ,C 2
C 4 first (2) and second (3)
C 5 :Y f (t) and Z f (t) average Rate stabilization
Wherein the formula (2) in C4 is
Formula (3) is
In C5
Wherein W is a weighted cumulative utility function;
presentation server
Up, the amount of data that flow f arrives;
admission data representing a flow f on a server n;
is the amount of data transmitted via the link (n, j) for the t-th time slot; l is n,j (t) and C n (t) represents the link capacity of the link (n, j) and the server n calculated capacity, respectively;
represents the unit complexity of processing the flow f data by the VNFk; τ is the duration of one slot; y is f (t) and Z f (t) is a virtual queue;
admission data representing flow f;
based on lyapunov optimization, P1.1 translates into an upper bound for minimizing drift minus reward, expressed as:
wherein
V is a non-negative weighting parameter of the utility function; Θ (t) = [ Q (t), Y (t), Z (t)]Wherein
And
in order to be a virtual queue vector, the virtual queue vector,
is a queue vector;
is lyapunov drift, in which
Is the lyapunov function.
7. The method for resource scheduling and routing management of the multimodal communication network of the low carbon park as claimed in claim 1, wherein: the method for optimizing the VNF embedding strategy in the time period by exchanging the matched VNF embedding algorithm comprises the following steps:
by solving the VNF embedding sub-problem SP1 in the set time period, specific embedding positions of K VNFs on N servers are determined, and the formula is as follows:
SP1:
s.t.C 2
where y (h) is the VNF embedding policy for the h time period;
based on SP1, the utility function of flow f is:
wherein V is a non-negative weighting parameter of the utility function; β and λ represent the weights of throughput and embedding cost, respectively;
representing a VNF embedded indicator variable; e.g. of the type k (h) Represents the embedding cost of VNFk;
selecting an indication variable for the flow f route;
the embedding condition of the h time slot;
are respectively as
L n,j (t),C n (t) an empirical value of (t),
is admitted data;
is the queue backlog of the t-th slot under the given embedding strategy;
wherein
Presentation server
Up, the amount of data that flow f arrives; l is n,j (t) and C n (t) represents the link capacity of the link (n, j) and the server n calculated capacity, respectively;
calculating utility values according to a formula, and arranging and establishing a preference list according to a descending order; the provided exchange matching-based VNF embedding algorithm for the set time period comprises the following specific processes:
giving satisfaction of constraint C 2 Embedding strategy of
Calculating the utility of the flow;
in each iteration, all servers randomly select one server
And another subset
If it is used
The number of servers in is greater than 1, i.e.
Server n leaves
Adding into
Forming new embedding strategies
Then, the utility of the flow is recalculated; if it is used
Is that
Exchange matching of the original embedding strategy
Is replaced by
Otherwise
Keeping the original shape;
according to
Then the
Otherwise
In principle, will
Conversion to y * (h)。
8. The method for resource scheduling and routing management of the multimodal communication network of the low carbon park as claimed in claim 1, wherein: the admission control method comprises the following steps:
determine slot admission control sub-problem SP2:
SP2:
s.t.C 6 :(2)
wherein the formula (2) in C6 is
V is a non-negative weighting parameter of the utility function; β is the throughput weight; y is f (t) and Z f (t) is a virtual queue;
backlogging the t-th time slot queue;
admission data representing a flow f on a server n;
presentation server
Up, the amount of data that flow f arrives;
using the admission control method, the solution SP2 is denoted as
9. The method for resource scheduling and routing management of the multimodal communication network of the low carbon park as claimed in claim 1, wherein: the backpressure perception routing algorithm based on Q learning comprises the following specific processes:
determining a time slot routing sub-problem SP3, determining an optimal next hop server:
SP3:
C 7 :(3)
wherein the formula (3) in C7 is
Is the flow f queue backlog at server n of the t-th slot embedding VNFk;
is the amount of data transmitted via the link (n, j) for the t-th time slot;
selecting an indication variable for the flow f route; x (t) is a routing strategy;
the SP2 is solved by adopting Q learning, and the backpressure sensing routing algorithm based on the Q learning comprises the following specific processes:
initializing Q value, setting Q (S) n (t),a n (t))＝0；
At the beginning of the tth time slot, each server selects an action according to an epsilon greedy strategy; server j will select B n (t) the largest server n rejects others, and server selection conflicts are resolved; all servers update the reward and queue information and go to the next state S n (t + 1); and updating the Q value;
according to a n (t) = j then
Otherwise
Will be { a } n (t) } conversion to x * (t)；
Wherein the state is
Acting as
The reward is
Q value Q (S) n (t),a n (t)) estimate the state S for the server n (t) selecting action a n (t) as a function of the value of (t).
10. The method for resource scheduling and routing management in a multi-modal communication network of a low carbon campus of claim 7, wherein: the algorithm of the VNF embedding and flow scheduling joint optimization is as follows:
initializing queue backlog of all queues, and VNF embedding, admission control and routing strategy indication functions;
in each set time period, obtaining an optimal VNF embedding strategy y (t) by the VNFs according to a VNF embedding algorithm based on exchange matching in the set time period;
and in each time slot, each source server acquires an optimal admission control strategy r (t) according to a formula, and the source server and the processing server acquire an optimal routing strategy x (t) according to a backpressure perception routing algorithm based on Q learning.
11. A resource scheduling and routing management device for a multi-mode communication network in a low-carbon park is characterized by specifically comprising the following steps:
a modeling module: the flow scheduling method comprises the steps of modeling a VNF embedding and flow scheduling process in a pre-constructed architecture model into a VNF embedding model and a flow scheduling model based on a multi-time scale model, wherein the embedding from a VNF to a data plane server under a time period is established as the VNF embedding model, and the route from a flow of a source server to a destination server under the time period is established as the flow scheduling model;
a constraint module: the VNF embedding model and the flow scheduling model are used for establishing a VNF embedding and flow scheduling joint optimization problem model and constraining network performance;
a conversion module: the method comprises the steps of utilizing the constraint to jointly optimize a problem model of VNF embedding and flow scheduling, and describing the problem model as the weighted difference of the maximized network throughput and the VNF embedding cost; and
utilizing the Lyapunov optimization to convert the time period VNF embedding strategy optimization problem and the time slot scale flow scheduling optimization problem into time slot optimization problem;
VNF embedding strategies are optimized in a time period through exchanging and matching VNF embedding algorithms, flow scheduling optimization of the time slot is performed through admission control in the time slot and a backpressure perception routing selection algorithm based on Q learning, and resource scheduling and routing management of the low-carbon park multi-mode communication network are achieved.
12. The resource scheduling and routing management device for the multimodal communication network in the low carbon park as claimed in claim 11, wherein:
the modeling module includes:
the system comprises a data plane, a control plane and an application plane; wherein:
on a data plane, multi-modal heterogeneous communication network resources are abstracted into a unified virtual resource pool, the virtual resource pool comprises communication, calculation and storage virtual resources, different VNFs are supported by deploying the virtual resources, and the VNFs are arranged in a specific sequence to form an SFC;
in a control plane, the SDN controller utilizes a resource scheduling component to carry out VNF embedding and utilizes a route management component to carry out flow scheduling to realize route management optimization; wherein the VNF embedding is to embed VNFs of the SFC in a server to support a plurality of low carbon services; the flow scheduling refers to that on the basis of embedding the VNF, a proper path is selected for a flow from a source server to be transmitted to a destination server;
on the application plane, the low-carbon intelligent park energy management service comprises the following steps: carbon footprint monitoring, electric power spot market, flexible load regulation.
13. The resource scheduling and routing management device for the multimodal communication network of the low carbon park as claimed in claim 12, wherein: the constraint model is used for the constraint of streaming, and is used for the source server
Admission data of flow f
The constraints are:
wherein
Presentation server
Up, the amount of data that flow f arrives; at the same time, only VNFk +1 is embedded in server j,
can be transmitted to server j, where
Embedding an indication variable for the VNF;
the resource constraint, the amount of data transmitted via the link (n, j) in the t-th slot is subject to the link capacity L n,j (t) and calculation of the Capacity C n (t) constraint, whose formula is:
wherein
Represents the unit complexity of processing the flow f data by the VNFk; τ is the duration of one slot;
a queue backlog constraint, representing a long-term queue backlog constraint as:
wherein
Is the flow f queue backlog at server n where the t-th slot is embedded in the VNFk;
throughput constraint, average throughput of flow f r f The constraint is expressed as:
wherein
And
respectively representing the minimum throughput and the maximum throughput of flow f.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210775986.4A CN115174403B (en) | 2022-07-02 | 2022-07-02 | Method and device for resource scheduling and route management of multi-mode communication network in low-carbon park |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210775986.4A CN115174403B (en) | 2022-07-02 | 2022-07-02 | Method and device for resource scheduling and route management of multi-mode communication network in low-carbon park |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115174403A true CN115174403A (en) | 2022-10-11 |
| CN115174403B CN115174403B (en) | 2024-03-12 |
Family
ID=83488569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210775986.4A Active CN115174403B (en) | 2022-07-02 | 2022-07-02 | Method and device for resource scheduling and route management of multi-mode communication network in low-carbon park |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115174403B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015157947A1 (en) * | 2014-04-16 | 2015-10-22 | 华为技术有限公司 | Software defined network based networking method and device |
| CN105847151A (en) * | 2016-05-25 | 2016-08-10 | 安徽大学 | Multi-constrained QoS (Quality of Service) routing strategy designing method for software defined network |
| EP3058464A1 (en) * | 2013-12-06 | 2016-08-24 | Huawei Technologies Co., Ltd. | Method and controller for chaining applications in a software defined network |
| WO2016188548A1 (en) * | 2015-05-22 | 2016-12-01 | Huawei Technologies Co., Ltd. | Telecommunication network with automated control and data plane instantiation |
| CN108206780A (en) * | 2016-12-19 | 2018-06-26 | 中国电信股份有限公司 | Flow scheduling strategy report method, autonomy field system and SDN network system |
| US20180227225A1 (en) * | 2015-07-28 | 2018-08-09 | Phicomm (Shanghai) Co., Ltd. | Sdn-based qos-supported communication tunnel establishment method and system |
| CN109618312A (en) * | 2019-01-18 | 2019-04-12 | 华北电力大学 | A kind of low complex degree online resource distribution optimization algorithm towards D2D junction network |
| CN110765595A (en) * | 2019-10-10 | 2020-02-07 | 内蒙古农业大学 | SDN data center network flow scheduling algorithm based on multi-layer virtual topology energy saving |
| CN111475252A (en) * | 2020-03-06 | 2020-07-31 | 重庆邮电大学 | Virtual network function deployment optimization algorithm based on deep reinforcement learning |
| CN112787943A (en) * | 2019-11-08 | 2021-05-11 | 中兴通讯股份有限公司 | Traffic scheduling method and device and computer readable storage medium |
| CN114501355A (en) * | 2022-03-16 | 2022-05-13 | 华北电力大学 | Privacy capacity guaranteeing system and method suitable for electric carbon information conversion of park |
-
2022
- 2022-07-02 CN CN202210775986.4A patent/CN115174403B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3058464A1 (en) * | 2013-12-06 | 2016-08-24 | Huawei Technologies Co., Ltd. | Method and controller for chaining applications in a software defined network |
| WO2015157947A1 (en) * | 2014-04-16 | 2015-10-22 | 华为技术有限公司 | Software defined network based networking method and device |
| WO2016188548A1 (en) * | 2015-05-22 | 2016-12-01 | Huawei Technologies Co., Ltd. | Telecommunication network with automated control and data plane instantiation |
| US20180227225A1 (en) * | 2015-07-28 | 2018-08-09 | Phicomm (Shanghai) Co., Ltd. | Sdn-based qos-supported communication tunnel establishment method and system |
| CN105847151A (en) * | 2016-05-25 | 2016-08-10 | 安徽大学 | Multi-constrained QoS (Quality of Service) routing strategy designing method for software defined network |
| CN108206780A (en) * | 2016-12-19 | 2018-06-26 | 中国电信股份有限公司 | Flow scheduling strategy report method, autonomy field system and SDN network system |
| CN109618312A (en) * | 2019-01-18 | 2019-04-12 | 华北电力大学 | A kind of low complex degree online resource distribution optimization algorithm towards D2D junction network |
| CN110765595A (en) * | 2019-10-10 | 2020-02-07 | 内蒙古农业大学 | SDN data center network flow scheduling algorithm based on multi-layer virtual topology energy saving |
| US20210111994A1 (en) * | 2019-10-10 | 2021-04-15 | Inner Mongolia Agricultural University | Energy-efficient traffic scheduling algorithm for sdn data center network based on multi-layer virtual topology |
| CN112787943A (en) * | 2019-11-08 | 2021-05-11 | 中兴通讯股份有限公司 | Traffic scheduling method and device and computer readable storage medium |
| CN111475252A (en) * | 2020-03-06 | 2020-07-31 | 重庆邮电大学 | Virtual network function deployment optimization algorithm based on deep reinforcement learning |
| CN114501355A (en) * | 2022-03-16 | 2022-05-13 | 华北电力大学 | Privacy capacity guaranteeing system and method suitable for electric carbon information conversion of park |
Non-Patent Citations (3)
| Title |
|---|
| JIA M: "《Routing cost minimization and throughput maximization of NFV-enables unicasting in software-defined networks》", 《IEEE TRANSACTION》 * |
| 严亮亮: "面向轻量云的嵌入式系统容器化资源管理技术研究", 《中国优秀硕士学位论文全文数据库》 * |
| 姚毅夫: "虚拟网络中功能节点部署和流调度研究", 《中国优秀硕士学位论文全文数据库》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115174403B (en) | 2024-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hussein et al. | Efficient task offloading for IoT-based applications in fog computing using ant colony optimization | |
| Qi et al. | Knowledge-driven service offloading decision for vehicular edge computing: A deep reinforcement learning approach | |
| WO2023004898A1 (en) | Delay deterministic transmission method based on route scheduling and joint optimization | |
| Wang et al. | Drl-sfcp: Adaptive service function chains placement with deep reinforcement learning | |
| CN115033359A (en) | Internet of things agent multi-task scheduling method and system based on time delay control | |
| US20230145097A1 (en) | Autonomous traffic (self-driving) network with traffic classes and passive and active learning | |
| CN113781002B (en) | Low-cost workflow application migration method based on agent model and multiple group optimization in cloud edge cooperative network | |
| Qi et al. | Vehicular edge computing via deep reinforcement learning | |
| Xie et al. | Workflow scheduling in serverless edge computing for the industrial internet of things: A learning approach | |
| Zhang et al. | Employ AI to improve AI services: Q-learning based holistic traffic control for distributed co-inference in deep learning | |
| CN115174403B (en) | Method and device for resource scheduling and route management of multi-mode communication network in low-carbon park | |
| Chen et al. | Traffic engineering based on deep reinforcement learning in hybrid IP/SR network | |
| Chu et al. | Reinforcement learning based multi-access control with energy harvesting | |
| Hsieh et al. | Deep reinforcement learning-based task assignment for cooperative mobile edge computing | |
| CN113127167B (en) | Heterogeneous resource intelligent parallel scheduling method based on improved genetic algorithm | |
| Bekhit et al. | Multi-objective VNF Placement Optimization with NSGA-III | |
| CN114785692A (en) | Virtual power plant aggregation regulation and control communication network flow balancing method and device | |
| Liu et al. | Multi-objective robust workflow offloading in edge-to-cloud continuum | |
| CN114375050A (en) | Digital twin-assisted 5G power distribution network resource scheduling method | |
| CN113676955A (en) | Virtual network function universal migration method under 5G/B5G environment | |
| Gong et al. | IMAP-GCG: Edge Container Resource Scheduling and Configuration Method Based on Improved MAPPO and GCN-GRU | |
| CN115361726B (en) | Intelligent access control method and system for network slice | |
| Qian et al. | A Reinforcement Learning-based Orchestrator for Edge Computing Resource Allocation in Mobile Augmented Reality Systems | |
| CN114285880B (en) | Intelligent method for lightweight equipment of Internet of things based on enhanced twinning | |
| CN114710439B (en) | Network energy consumption and throughput joint optimization routing method based on deep reinforcement learning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |