阅读说明：本技术 云边协同网络中时延和频谱占用联合优化方法及系统 (Combined optimization method and system for time delay and frequency spectrum occupation in cloud edge cooperative network ) 是由 陈伯文 刘玲 梁瑞鑫 王守翠 陈琪 沈纲祥 高明义 邵卫东 陈虹 于 2021-08-24 设计创作，主要内容包括：本发明涉及一种云边协同网络中时延和频谱占用联合优化方法及系统,包括：初始化云边协同网络,生成一组用户请求；建立以用户请求平均端到端的最低时延和最小占用频谱隙的目标函数；基于所述目标函数,在处理每个用户请求的过程中,依次判断是否满足节点及路径选择唯一性约束、移动边缘计算服务器负载约束、频谱资源占用及唯一性约束、频谱连续性约束以及频谱一致性约束,若均满足,则用户请求处理成功,进入步骤S4；若有任意一项不满足,则用户请求处理失败；计算用户请求平均端到端时延和频谱资源占用率。本发明有利于提高了频谱资源的利用率以及提升用户服务质量。(The invention relates to a time delay and frequency spectrum occupation combined optimization method and a system in a cloud edge cooperative network, which comprises the following steps: initializing a cloud edge collaborative network, and generating a group of user requests; establishing an objective function of the minimum end-to-end time delay and the minimum occupied frequency spectrum slot which are averaged by the user request; based on the objective function, in the process of processing each user request, whether node and path selection uniqueness constraint, mobile edge computing server load constraint, spectrum resource occupation and uniqueness constraint, spectrum continuity constraint and spectrum consistency constraint are met or not is sequentially judged, if yes, the user request is successfully processed, and the process enters step S4; if any item is not satisfied, the user request processing fails; and calculating the average end-to-end time delay and the spectrum resource occupancy rate of the user request. The invention is beneficial to improving the utilization rate of frequency spectrum resources and improving the service quality of users.)

1. A joint optimization method for time delay and frequency spectrum occupation in a cloud edge cooperative network is characterized by comprising the following steps:

step S1: initializing a cloud edge collaborative network, and generating a group of user requests;

step S2: establishing an objective function of the minimum end-to-end time delay and the minimum occupied frequency spectrum slot which are averaged by the user request;

step S3: based on the objective function, in the process of processing each user request, whether node and path selection uniqueness constraint, mobile edge computing server load constraint, spectrum resource occupation and uniqueness constraint, spectrum continuity constraint and spectrum consistency constraint are met or not is sequentially judged, if yes, the user request is successfully processed, and the process enters step S4; if any item is not satisfied, the user request processing fails;

step S4: and calculating the average end-to-end time delay and the spectrum resource occupancy rate of the user request.

2. The joint optimization method for time delay and spectrum occupation in the cloud-edge cooperative network according to claim 1, characterized in that: when the cloud edge collaborative network is initialized, the computing resources of the edge computing server are initialized, and the spectrum flexible optical network is initialized.

3. The joint optimization method for time delay and spectrum occupation in the cloud-edge cooperative network according to claim 1, characterized in that: the objective function includes a primary optimization objective and a secondary optimization objective.

4. The joint optimization method for time delay and spectrum occupation in the cloud-edge cooperative network according to claim 1 or 3, characterized in that: the formula of the objective function is:wherein | CR | represents the total number of user requests, and CR is a set of user requests;is a binary variable, if a user request (u, s) is processed at an MEC server node E and the user request is transmitted through a kth path, E represents a group of MEC server sets, the value of the binary variable is 1, otherwise the value is 0; r_(u,s)Represents the number of computational resources required for the transmission of the user request (u, s); m_eComputing resource capacity for MEC server node e;indicating the distance between the links (k, l) of the user request (u, s) transmitted from node s to MEC server node e via the kth working pathK represents KA set of strip paths; c represents the transmission rate of the subscriber request over the fibre link set at 3 x 10⁵km/s；y_(u,s)The binary variable is a binary variable, if the user request (u, s) is migrated to the second layer, namely the MEC server node e processing of the cloud area, the value of the binary variable is 1, otherwise, the value is 0; tau is the extra switching delay of the user request transmitted to the cloud area through the switch, alpha and beta are parameters,is a binary variable, the user request (u, s) is input to the MEC server node e and the spectrum gap of the link (k, l) number f is occupied, the value of the binary variable is 1, otherwise the value is 0.

5. The joint optimization method for time delay and spectrum occupation in the cloud-edge cooperative network according to claim 4, wherein: the node and path selection uniqueness constraint is as follows:

wherein the content of the first and second substances,is a binary variable whose value is 1 if the user request (u, s) is processed at the MEC server node e and transmitted over the kth path, otherwise it is 0, y_(u,s)And for the binary variable, if the user request (u, s) is migrated to the second layer, namely the MEC server node e processing of the cloud area, the value of the binary variable is 1, otherwise, the value is 0.

6. The joint optimization method for time delay and spectrum occupation in the cloud-edge cooperative network according to claim 4, wherein: the MEC server load constraint is: wherein R is_(u,s)Representing the number of computational resources required for the transmission of a user request (u, s),represents the maximum load, V, of the server_eRepresenting the maximum computing resource capacity of the MEC server node e.

7. The joint optimization method for time delay and spectrum occupation in the cloud-edge cooperative network according to claim 4, wherein: the spectrum resource occupation and uniqueness constraint is as follows:

wherein, | F_(k,l)I represents the maximum number of spectrum slots on the link (k, l), assuming that the maximum number of spectrum slots that can be provided by each link is the same,the kth working path representing the transmission of a user request (u, s) from node s to MEC server node e is via optical fiber links (k, l), F_(u,s)Indicating the number of spectral slots required for a user to request (u, s) transmission.

8. The joint optimization method for time delay and spectrum occupation in the cloud-edge cooperative network according to claim 7, wherein: the spectral continuity constraint is:

θ＝|F_(k,l)lx L; where θ represents the total number of spectrum for the entire network, equal to the product of the total number of links and the capacity of the link spectrum slots.

9. The joint optimization method for time delay and spectrum occupation in the cloud-edge cooperative network according to claim 4, wherein: the spectral conformance constraint is:wherein, F_(u,s)Indicating the number of spectral slots required for a user to request (u, s) transmission.

10. A joint optimization system for time delay and spectrum occupation in a cloud edge collaborative network is characterized by comprising the following steps:

the initialization module is used for initializing the cloud edge collaborative network and generating a group of user requests;

the modeling module is used for establishing an objective function of the minimum end-to-end time delay and the minimum occupied frequency spectrum slot which are averagely requested by the user;

a judging module, configured to sequentially judge whether node and path selection uniqueness constraints, mobile edge computing server load constraints, spectrum resource occupation and uniqueness constraints, spectrum continuity constraints, and spectrum consistency constraints are met in the process of processing each user request based on the objective function, and if yes, the user request is successfully processed, and then the process proceeds to step S4; if any item is not satisfied, the user request processing fails;

and the calculation module is used for calculating the average end-to-end time delay of the user request and the spectrum resource occupancy rate.

Technical Field

The invention relates to the technical field of cloud-edge cooperative network optimization, in particular to a method and a system for jointly optimizing time delay and frequency spectrum occupation in a cloud-edge cooperative network.

Background

In recent years, with the rapid development of the internet of things, a large number of emerging application program scenes such as face recognition, smart cities, intelligent traffic systems, virtual reality technologies (VR) and the like are produced. As these application scenarios may lead to higher bandwidth rates, more network connections and lower latency for the user, the data size and service requests that the core network needs to process per unit time grows exponentially. Therefore, with the increase of network traffic borne by the mobile device and the internet of things device, the centralized processing mode adopted by the cloud computing is far away from the terminal device, so that the daily requirements of users cannot be met, and for a computing service with high performance requirements such as time delay and energy consumption, the mode can cause problems such as high time delay and network congestion.

For these problems, the European Telecommunications Standards Institute (ETSI) proposes Mobile Edge Computing (MEC) by fusing Edge Computing to the architecture of a Mobile network. The MEC is a novel computing model for offloading computing tasks of the mobile terminal to the edge of the network, and performing computing and storing on the edge of the network. MEC is considered to be a key element of cellular base station model modernization evolution and 5G technology development. The MEC introduces computing and storage resources to the edge of the mobile network, computing time delay and energy consumption of terminal equipment are reduced, user experience quality of mobile internet application is improved, and high load of a cloud computing center is reduced. Meanwhile, the MEC also needs to be supported by a computation offloading technology, which is a technology for uploading computation data of the terminal device to the cloud and performing a series of computation processes. In the information era of everything interconnection, in order to realize the situations of low data transmission delay, low server energy consumption and high mobile terminal resource storage, complex computing tasks need to be offloaded to a network edge server for computing processing.

In order to better combine the advantages of cloud computing and edge computing, cloud edge collaboration becomes a new research trend as a novel computing mode. With the increase of data-intensive applications and computing-intensive applications, the cloud computing needs to be implemented by utilizing the strong computing power of cloud computing and the response characteristics of communication resources and edge computing short-time transmission, and corresponding application requests need to be completed. By means of cooperative work and various growth of the two, the value of edge computing and cloud computing cooperation is maximized, and therefore performance of the application program is effectively improved. At present, most of research aiming at cloud-side collaboration focuses on application scenarios in a plurality of fields such as internet of things, industrial internet, intelligent transportation, security monitoring and the like, and the main purposes are to reduce time delay, reduce energy consumption, improve user experience quality and the like.

Currently, there are two main resource offloading methods: off-loading to the cloud and off-loading to the edge. The unloading to the cloud end allows a user to unload the calculation-intensive tasks to a cloud server with powerful resources for processing; offloading to the edge end is deploying cloud services at the edge of the network. The delay-sensitive application cannot be well processed due to the long transmission distance when the application is unloaded to the cloud, and the factors such as computing resources, storage resources, energy consumption and delay also need to be considered when the application is unloaded to the edge, so how to unload the service and which end to unload to become a current research hotspot.

Disclosure of Invention

Therefore, the technical problem to be solved by the present invention is to overcome the problem of high end-to-end time delay requested by a user and high occupancy rate of spectrum resources in the prior art, so as to provide a method and a system for jointly optimizing time delay and spectrum occupancy in a cloud-edge cooperative network, which effectively reduce the end-to-end time delay requested by the user and the occupancy rate of spectrum resources.

In order to solve the technical problem, the invention provides a combined optimization method for time delay and frequency spectrum occupation in a cloud edge cooperative network, which comprises the following steps: initializing a cloud edge collaborative network, and generating a group of user requests; establishing an objective function of the minimum end-to-end time delay and the minimum occupied frequency spectrum slot which are averaged by the user request; based on the objective function, in the process of processing each user request, whether node and path selection uniqueness constraint, mobile edge computing server load constraint, spectrum resource occupation and uniqueness constraint, spectrum continuity constraint and spectrum consistency constraint are met or not is sequentially judged, if yes, the user request is successfully processed, and the process enters step S4; if any item is not satisfied, the user request processing fails; and calculating the average end-to-end time delay and the spectrum resource occupancy rate of the user request.

In an embodiment of the present invention, when initializing the cloud edge collaborative network, the computing resources of the edge computing server are initialized, and the spectrum flexible optical network is initialized.

In one embodiment of the invention, the objective function comprises a primary optimization objective and a secondary optimization objective.

In one embodiment of the present invention, the formula of the objective function is:wherein | CR | represents the total number of user requests, and CR is a set of user requests;is a binary variable, if a user request (u, s) is processed at an MEC server node E and the user request is transmitted through a kth path, E represents a group of MEC server sets, the value of the binary variable is 1, otherwise the value is 0; r_(u,s)Represents the number of computational resources required for the transmission of the user request (u, s); m_eComputing resource capacity for MEC server node e;indicating the distance between the links (k, l) of the user request (u, s) transmitted from node s to MEC server node e via the kth working path K represents a set of K paths; c represents the transmission rate of the subscriber request over the fibre link set at 3 x 10⁵km/s；y_(u,s)The binary variable is a binary variable, if the user request (u, s) is migrated to the second layer, namely the MEC server node e processing of the cloud area, the value of the binary variable is 1, otherwise, the value is 0; tau is the extra switching delay of the user request transmitted to the cloud area through the switch, alpha and beta are parameters,is a binary variable, the user request (u, s) is input to the MEC server node e and the spectrum gap of the link (k, l) number f is occupied, the value of the binary variable is 1, otherwise the value is 0.

In one embodiment of the present invention, the node and path selection uniqueness constraint is:whereinIs a binary variable whose value is 1 if the user request (u, s) is processed at the MEC server node e and transmitted over the kth path, otherwise it is 0, y_(u,s)And for the binary variable, if the user request (u, s) is migrated to the second layer, namely the MEC server node e processing of the cloud area, the value of the binary variable is 1, otherwise, the value is 0.

In one embodiment of the present invention, the MEC server load constraint is:wherein R is_(u,s)Representing the number of computational resources required for the transmission of a user request (u, s),represents the maximum load, V, of the server_eRepresenting the maximum computing resource capacity of the MEC server node e.

In an embodiment of the present invention, the spectrum resource occupation and uniqueness constraint is:

wherein, | F_(k,l)I represents the maximum number of spectrum slots on the link (k, l), assuming that the maximum number of spectrum slots that can be provided by each link is the same,the kth working path representing the transmission of a user request (u, s) from node s to MEC server node e is via optical fiber links (k, l), F_(u,s)Indicating the number of spectral slots required for a user to request (u, s) transmission.

In one embodiment of the invention, the spectral continuity constraint is:

θ＝|F_(k,l)|×|L|；

where θ represents the total number of spectrum for the entire network, equal to the product of the total number of links and the capacity of the link spectrum slots.

In one embodiment of the present invention, the spectrum consistency constraint is:wherein, F_(u,s)Indicating the number of spectral slots required for a user to request (u, s) transmission.

The invention also provides a combined optimization method of time delay and frequency spectrum occupation in the cloud edge cooperative network, which comprises the following steps: the initialization module is used for initializing the cloud edge collaborative network and generating a group of user requests; the modeling module is used for establishing an objective function of the minimum end-to-end time delay and the minimum occupied frequency spectrum slot which are averagely requested by the user; a judging module, configured to sequentially judge whether node and path selection uniqueness constraints, mobile edge computing server load constraints, spectrum resource occupation and uniqueness constraints, spectrum continuity constraints, and spectrum consistency constraints are met in the process of processing each user request based on the objective function, and if yes, the user request is successfully processed, and then the process proceeds to step S4; if any item is not satisfied, the user request processing fails; and the calculation module is used for calculating the average end-to-end time delay of the user request and the spectrum resource occupancy rate.

Compared with the prior art, the technical scheme of the invention has the following advantages:

the invention discloses a time delay and frequency spectrum occupation combined optimization method and system in a cloud edge cooperative network, and mainly solves the problem of how to select a proper MEC server to process a user request in the cloud edge cooperative network. The cloud computing is combined with the edge computing, and a cloud-edge cooperative network is provided as an effective way for processing services. The invention provides an end-to-end time delay and spectrum resource occupation evaluation mechanism, then a combined optimization method taking the minimum user request average end-to-end time delay and the minimum occupied spectrum slot as objective functions is established according to the mechanism, and a resource allocation method of computing unloading, routing selection and spectrum allocation of a cloud-edge cooperative network is realized by an integer linear programming method. A group of user request sets are generated in a static cloud edge cooperative network, corresponding computing resources and spectrum resource requirements are set, and then an optimization target method with the lowest end-to-end time delay and spectrum occupation is established according to constraint conditions and an optimization target, so that the optimal MEC server is found for all user requests to process and distribute resources.

The invention can select the optimal MEC server to process the user request, thereby greatly reducing the data processing delay and the data transmission delay generated by processing the user request and further improving the user service quality; meanwhile, the shortest working path is searched for each user request, the waste of frequency spectrum resources in the network is reduced, and the utilization rate of the frequency spectrum resources is greatly improved.

Drawings

In order that the present disclosure may be more readily and clearly understood, reference is now made to the following detailed description of the embodiments of the present disclosure taken in conjunction with the accompanying drawings, in which

FIG. 1 is a flowchart of a joint optimization method of time delay and spectrum occupation in a cloud-edge cooperative network according to the present invention;

FIG. 2 is a six node network topology of the present invention;

fig. 3 is a schematic view of service processing in the cloud-edge collaborative network according to the present invention.

Detailed Description

Example one

As shown in fig. 1, the present embodiment provides a method for jointly optimizing time delay and spectrum occupancy in a cloud-edge cooperative network, including: step S1: initializing a cloud edge collaborative network, and generating a group of user requests; step S2: establishing an objective function of the minimum end-to-end time delay and the minimum occupied frequency spectrum slot which are averaged by the user request; step S3: based on the objective function, in the process of processing each user request, whether node and path selection uniqueness constraint, mobile edge computing server load constraint, spectrum resource occupation and uniqueness constraint, spectrum continuity constraint and spectrum consistency constraint are met or not is sequentially judged, if yes, the user request is successfully processed, and the process enters step S4; if any item is not satisfied, the user request processing fails; step S4: and calculating the average end-to-end time delay and the spectrum resource occupancy rate of the user request.

In the method for jointly optimizing time delay and spectrum occupation in a cloud-edge collaborative network according to this embodiment, in step S1, the cloud-edge collaborative network is initialized to generate a group of user requests, thereby facilitating establishment of an objective function; in step S2, an objective function of minimum end-to-end delay and minimum occupied spectrum slot requested by the user is established, which is favorable for implementing an optimization scheme with minimum delay and spectrum occupied as targets; in the step S3, based on the objective function, in the process of processing each user request, sequentially determining whether node and path selection uniqueness constraint, mobile edge computing server load constraint, spectrum resource occupation and uniqueness constraint, spectrum continuity constraint and spectrum consistency constraint are satisfied, if both are satisfied, the user request processing is successful, and entering step S4; if any item is not satisfied, the user request processing fails, which is beneficial to realizing resource allocation of computation unloading, routing selection and spectrum allocation of the cloud-edge cooperative network and reducing the end-to-end time delay of the user request and the occupancy rate of the spectrum resource; in the step S4, the average end-to-end time delay and the spectrum resource occupancy rate of the user request are calculated, so as to find the optimal MEC server for processing and allocating resources for all the user requests, the optimal MEC server can be selected to process the user requests, and the data processing time delay and the data transmission time delay generated by processing the user requests are greatly reduced, thereby improving the user service quality; meanwhile, the shortest working path is searched for each user request, the waste of frequency spectrum resources in the network is reduced, and the utilization rate of the frequency spectrum resources is greatly improved.

In the invention, the end-to-end time delay of the user request in the cloud edge cooperative network mainly comprises network transmission time delay and computing resource time delay. The network transmission delay refers to the shortest path length between the service area of the user and the edge calculation server, and is calculated by the accumulated delay of the link delay; the computing resource latency is related to the computing resource requirements of each user and the computing power of the edge computing server. The invention mainly considers three end-to-end time delays for processing user request conditions, namely local processing, unloading to other areas connected with the switch and unloading to cloud areas connected with the switch. The average end-to-end delay requested by the user is as follows:

wherein | CR | represents the total number of user requests, and CR is a set of user requests;is a binary variable, if a user request (u, s) is processed at an MEC server node E and the user request is transmitted through a kth path, E represents a group of MEC server sets, the value of the binary variable is 1, otherwise the value is 0; r_(u,s)Represents the number of computational resources required for the transmission of the user request (u, s); m_eComputing resource capacity for MEC server node e;representing the distance between links (K, l) of a user request (u, s) transmitted from the node s to the MEC server node e through the kth working path, wherein K represents a set of K paths; c represents the transmission rate of the subscriber request over the fibre link set at 3 x 10⁵km/s；y_(u,s)The binary variable is a binary variable, if the user request (u, s) is migrated to the second layer, namely the MEC server node e processing of the cloud area, the value of the binary variable is 1, otherwise, the value is 0; τ is the extra switching delay for a user request to travel through the switch to the cloud area.

The spectrum resource occupancy rate is the ratio of the total number of spectrum slots occupied by the working paths requested by all users divided by the spectrum slots of all links, and the specific calculation formula is as follows:

wherein, F_(u,s)Representing the spectrum resource requirement of a user request u, the CR is a group of user request sets, and the LN and the SN respectively represent the total number of links and the spectrum resource capacity of each link.

In order to solve the problem of how to select a proper server to process services in the cloud edge collaborative network, the invention provides an integer linear programming method on the basis of the time delay and spectrum occupation evaluation mechanism, namely, an optimization scheme aiming at the lowest time delay and spectrum occupation is realized in a static network.

In step S1, when initializing the cloud edge coordination network, the computing resources of the edge computing server are initialized, and the spectrum flexible optical network is initialized. In a cloud-edge collaborative network G (CR, E), where CR ═ {1,2, …, (u, s), … } represents a set of user requests, and E ═ 1,2, …, E, … represents a set of edge compute server nodes. Each user request CR (u, s) is ∈ CR, u denotes the number of user requests, and s denotes the source node that generated the user request.

In the step S2, when an objective function of minimum end-to-end delay and minimum occupied spectrum slot requested by a user is established, because the present invention mainly solves the problem of how to select a suitable edge computing server to process services in the cloud-edge collaborative network, the objective function of joint optimization minimizes the average end-to-end delay and the spectrum resource occupancy rate requested by the user in the cloud-edge collaborative network, that is, the objective function is composed of a primary optimization objective and a secondary optimization objective, and the weight of the optimization objective can be changed by adjusting the sizes of parameters α and β (α is greater than or equal to 0 and β is less than or equal to 1), thereby achieving different optimization objectives. When α ═ 1 and β ═ 0, the optimization objective becomes the minimum to achieve average end-to-end delay in the network; when alpha is 0 and beta is 1, the optimization target is used for optimizing the occupancy rate of the spectrum resources in the network, and the optimization of the spectrum utilization in the network is realized.

The optimization objective function may be represented by the following sub-formula:

minimization

The target G of the integer linear programming model is to minimize the average end-to-end delay and the number of occupied spectrum slots in the cloud-edge cooperative network. In formula (3), the first part represents the average end-to-end delay requested by the user, and the specific evaluation method is as shown in formula (1), and the processing delay and the transmission delay of the user are reduced by optimally selecting a proper server; the second part represents the total number of the frequency spectrum slots occupied in the cloud edge cooperative network through optimizationTo reduce the number of spectrum slots occupied by connection requests,is a binary variable, the user request (u, s) is transmitted to the MEC server node e and the spectrum slot with number f on the link (k, l) is occupied, the value of the binary variable is 1, otherwise the value is 0.

In step S3, based on the objective function, a constraint condition that satisfies an objective function optimization method is established.

When allocating reasonable MEC server processing to a user request, the nodes and links need to satisfy the following conditions:

the node and path selection uniqueness constraint is as follows:

wherein the content of the first and second substances,is a binary variable, two if the user request (u, s) is processed at MEC server node e and transmitted over the kth pathThe value of the binary variable is 1, otherwise the value is 0. y is_(u,s)And for the binary variable, if the user request (u, s) is migrated to the second layer, namely the MEC server node e processing of the cloud area, the value of the binary variable is 1, otherwise, the value is 0. Equations (4) and (5) ensure that a user request can only be processed by one server, and each user request selects one of k working paths to transmit the user request.

The mobile edge computing server load constraint is:

r in formula (6)_(u,s)Representing the number of computational resources required for the transmission of a user request (u, s),representing the maximum load of the server. V in formula (7)_eRepresenting the maximum computing resource capacity of the MEC server node e. Equations (6) and (7) ensure that the total amount of computing resources of user requests handled by each MEC server node cannot exceed the maximum load of the MEC node, and that the maximum load of the MEC node cannot exceed the computing resource capacity of the node.

The spectrum resource occupation and uniqueness constraint is as follows:

wherein, | F_(k,l)I represents the maximum number of spectrum slots on the link (k, l), assuming that the maximum number of spectrum slots that can be provided by each link is the same,the kth working path representing the transmission of a user request (u, s) from node s to MEC server node e is via optical fiber links (k, l), F_(u,s)Indicating the number of spectral slots required for a user to request (u, s) transmission. Equation (8) ensures that the number of spectrum slots occupied by each fiber link cannot exceed the total number of spectrum slots for that link. Equations (9) and (10) ensure that the number of spectrum slots occupied by a user request (u, s) transmitted to the MEC server node over the optical fiber link (k, l) is equal to the number of spectrum slots required by the user request, and that the spectrum slot f of each link can only be occupied by one user request.

The spectral continuity constraint is:

θ＝|F_(k,l)|×|L| (13)

where θ represents the total number of spectrum of the entire network, equal to the product of the total number of links and the capacity of the link spectrum slot, as shown in equation (13). The spectrum slots allocated per fiber link must be contiguous over the active path. In formula (11), ifAnd isAll spectral slots with index values higher than f +1 do not allocate spectral resources on the fiber link (k, l). In the formula (12), ifThen no spectral gaps with index values below f will be allocated to the fiber link (k, l). Equations (11) and (12) ensure the constraint of spectral continuity.

The spectral conformance constraint is:

the constraint (14) ensures the consistency of the spectrum resources, i.e. the number of spectrum slots occupied by each link through which the working path passes is the same for each user request.

Through the constraint conditions, a resource allocation method based on computation unloading, routing selection and spectrum allocation of the cloud edge collaborative network can be found out, and therefore the integral linear programming combined optimization objective function is achieved.

In order to further understand the optimization method proposed in the present invention, the following detailed description of the specific implementation method of the present invention is provided in conjunction with the relevant examples, and the specific example steps are as follows:

taking the network topology shown in fig. 2 as an example, the network is a cloud edge cooperative network with 6 nodes and 8 links, where MEC server nodes e are represented by circles and numbered as 0, 1,2, 3, 4, and 5, where the cloud server node is node number 0. The numbers inside the dashed circles next to the nodes represent the computing resource capacity that the server has. The nodes are connected by optical fibre links, each of which is bi-directional, the numbers on the links representing the length of the link (in km). Here, each link is set to contain 20 spectrum slot resources.

Generating a set of user request sets CR ═ CR in a cloud-edge collaborative network₁(0,5),CR₂(1,1) }, the computing resource and spectrum resource requirements requested by the user are R respectively_(0,5)＝5、R_(1,1)＝4、F_(0,5)2 and F_(1,1)＝3。

The minimum user request average end-to-end time delay and the minimum occupied spectrum slot proposed in the invention are established and executed as objective functions, and refer to formula (3).

And establishing and executing constraint conditions of the combined optimization method based on time delay and spectrum occupation in the cloud edge cooperative network. In the process of processing each user request, node and path selection uniqueness constraint conditions need to be met, referring to formula 4 and formula 5, MEC server load constraint conditions, referring to formula 6 and formula 7, spectrum resource occupation and uniqueness constraint conditions, referring to formula 8 to formula 10, spectrum continuity constraint conditions, referring to formula 11 to formula 13, spectrum consistency constraint, and referring to formula 14.

Through the steps, the CR can be requested for the user in the cloud edge cooperative network based on the target condition₁(0,5) and CR₂And (1,1) allocating corresponding servers and spectrum resources. In order to achieve the goals of average end-to-end delay of the minimum user request and minimum occupied frequency spectrum slot, the invention considers the delay and the frequency spectrum slot when selecting the server node to process the user request. As shown in fig. 3, a grid on the link represents a spectrum slot, a red grid represents that the spectrum slot is occupied, and a white grid represents that the spectrum slot is in a free state, i.e. can be used to allocate spectrum resources. Requesting CR from user according to the above constraint and objective function₁(0,5) to the node 4 for processing, the user requests CR₂(1,1) to node 3 for processing, the corresponding working path spectral slot is changed to green. As can be seen from fig. 3, the above constraints can be satisfied, and the number of hops of the working path is only one hop, and both the spectrum resource occupation and the time delay are relatively low.

Example two

Based on the same inventive concept, the embodiment provides a combined optimization system for time delay and spectrum occupation in a cloud-side cooperative network, and the principle of solving the problem is similar to the combined optimization method for time delay and spectrum occupation in the cloud-side cooperative network, and repeated parts are not described again.

The embodiment provides a system for jointly optimizing time delay and spectrum occupation in a cloud-edge collaborative network, which includes:

the initialization module is used for initializing the cloud edge collaborative network and generating a group of user requests;

the modeling module is used for establishing an objective function of the minimum end-to-end time delay and the minimum occupied frequency spectrum slot which are averagely requested by the user;

a judging module, configured to sequentially judge whether node and path selection uniqueness constraints, mobile edge computing server load constraints, spectrum resource occupation and uniqueness constraints, spectrum continuity constraints, and spectrum consistency constraints are met in the process of processing each user request based on the objective function, and if yes, the user request is successfully processed, and then the process proceeds to step S4; if any item is not satisfied, the user request processing fails;

and the calculation module is used for calculating the average end-to-end time delay of the user request and the spectrum resource occupancy rate.

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 the like) having computer-usable program code embodied therein.

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.

It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.