Service and quality aware slice orchestration

Abstract

Network slice orchestration includes deploying both a performance monitor and a slice orchestrator in a core network of a host cellular telecommunications network and defining network slices therein, each with a different set of network resources accessible by different application instances executing at an edge portion of the host cellular telecommunications network. Thereafter, performance data is received from the performance monitor in respect to a particular mobile device accessing a corresponding application instance through an assigned network slice. The slice orchestrator then determines a mismatch in the performance data with respect to an expected performance for the application instance. Finally, in response to the determined mismatch, the slice orchestrator selects a different network slice and re-assigns the application instance to the different network slice.

Description

SERVICE AND QUALITY AWARE SLICE ORCHESTRATIONBACKGROUND OF THE INVENTION

[0001] Field of the Invention

[0002] The present invention relates to the field of network resource allocation in a communications network and more particularly to network slice provisioning.

[0003] Description of the Related Art

[0004] The software defined network (SDN) is a technology that separates the control plane management of different connected network devices, from the underlying data plane that forwards network traffic to the devices. In this regard, an SDN architecture features software-defined controllers abstracted from the underlying network hardware, while offering intent-based or policy-based management of the network as a whole. This results in a network that is better aligned with the needs of application workloads through automated provisioning, programmatic network management, pervasive application- oriented visibility, and where needed, direct integration with cloud orchestration platforms.

[0005] The separation of the control from the data plane in a network architecture remains the paramount feature of the SDN. Yet, SDN is more in that the SDN has a centralized or distributed intelligent entity that enjoys an entire view of the network, so as to make routing and switching decisions based on that view. In comparison, legacy network routers and switches only know of neighboring network gear. However, with aproperly configured SDN environment, that central entity can control everything, from easily changing policies to simplifying configuration and automation across the enterprise. As can be seen, the principle of the SDN can find wide applications not just in connection with the management of a computer communications network, but also in the implementation and management of a cellular telecommunications network incorporating a computer communications network. As to the latter, the SDN forms an integral part in the emerging next generation cellular telephony space.

[0006] Some have referred to "network slicing" as the key ingredient of the next generation cellular telephony space, enabling the full potential of the next generation architecture to be realized. Of particular importance, network slicing adds an extra dimension to the resource allocation domain by allowing multiple logical networks to simultaneously run on top of a shared physical network infrastructure. As such, network slicing becomes integral to the next generation architecture by creating end-to-end virtual networks that include both networking and storage functions. Operators of a next generation telecommunications network then can effectively manage diverse use cases with differing throughput, latency and availability demands by partitioning network resources to multiple users or “tenants”.

[0007] With strategically tuned network slicing and the optimized allocation of resources, known as "virtual network function" (VNF) instances, the cost of operating an SDN architected network can be optimized. Presently, the allocation of VNF instances within particular network slices is based upon pre-provisioning and static configurationwithout allowing external applications or services to interact with network functions. For example, current mobile network cores include network functions, such as the Network Slice Selection Function (NSSF) and the Policy Control Function (PCF), to deploy and manage network slices upon request of the mobile devices’ assignment by the mobile operator. The NSSF as a core functionality of the modern cellular telecommunications network is limited, however, as (i) the NSSF manages network selection information only based on tracking area, (ii) interaction with Network Data Analytics Function (NWDAF) is not supported yet in commercial solutions and it is essential for collecting real-time monitoring data from the radio and core, and (iii) the NSSF has limited support for roaming scenarios including cross-border / cross-MNO interactions).

[0008] To be sure, in the conventional network core, network resources are statically allocated by the operator to the different slices. That is to say, at the time of bootstrap of the SDN in the cellular telecommunications network, all available network slices are predefined and instantiated, each with a specific endpoint address within the SDN. Thereafter, the core network of the SDN assigns different application instances providing application services to user equipment on the cellular telecommunications network based upon the perceived resource requirements of those application instance. Importantly, once those network slices are created in the SDN, there is no possibility to dynamically rearrange the available network slices based on available static network resources. As a result, an error in the estimation of resource needs of the different application instances will result in the sub-optimal performance of those different application instances.BRIEF SUMMARY OF THE INVENTION

[0009] Embodiments of the present invention address technical deficiencies of the art in respect to network slicing. To that end, embodiments of the present invention provide for a novel and non-obvious method for network slice orchestration in a cellular telecommunications network according to the dynamically determined needs of application instances already assigned to existing network slices in the cellular telecommunications network. Embodiments of the present invention also provide for a novel and non-obvious computing device adapted to perform the foregoing method. Finally, embodiments of the present invention provide for a novel and non-obvious data processing system incorporating the foregoing device in order to perform the foregoing method.

[0010] EXEMPLARY EMBODIMENT # 1

[0011] In one embodiment of the disclosure, a network slice orchestration method includes deploying both a performance monitor and a slice orchestrator in a core network of a host cellular telecommunications network and defining network slices in the host cellular telecommunications network, each with a different set of network resources accessible by different application instances of different applications, with the application instances executing at an edge portion of the host cellular telecommunications network. The method additionally includes receiving, from the performance monitor, performance data in respect to a particular mobile device accessing a corresponding one of the different application instances through an assigned one of the network slices. The method yet further includes determining in the slice orchestrator a mismatch in theperformance data with respect to an expected performance for the one of the different application instances. Finally, the method includes responding to the determined mismatch by selecting in the slice orchestrator a different one of the network slices and re-assigning by the slice orchestrator the one of the different application instances to the selected different one of the network slices.

[0012] In one aspect of the embodiment, application performance requirements may be stored for different ones of the applications. For example, the performance requirements can include a specified latency value or range of values, a specified bandwidth or range of bandwidth, or a specified reliability or range of reliability. In this way, the mismatch may be determined in response to the performance data failing the stored application performance requirements for the one of the application instances.

[0013] In another aspect of the embodiment, a rule is retrieved into the slice orchestrator. The rule can map application performance requirements to specific ones of the network slices. As such, the selection can include applying the rule to performance requirements of the one of the application instances in order to identify the alternative one of the network slices mapped to performance requirements of an application corresponding to the one of the application instances.

[0014] In yet another aspect of the embodiment, each of the different application instances are assigned to different subscription tiers corresponding to different reassignment priorities. Consequently, the method may additionally include identifying multiple different ones of the different applications instances requiring re-assignment tothe selected different one of the network slices. Then, the re-assignment may be prioritized by the slice orchestrator to the different one of the network slices based upon a highest one of the priorities associated with respective ones of the different subscription tiers of the multiple different ones of the different applications.

[0015] In even yet another aspect of the embodiment, the edge portion of the host cellular telecommunications network is adjacent to a different edge portion of a different cellular telecommunications network. As such, the method additionally includes populating, in memory accessible by the core network, a data structure encapsulating the performance data in respect to the particular mobile device accessing the corresponding one of the different application instances through the assigned one of the network slices. Thereafter, the data structure may be transmitted to the different edge portion for use by the different edge portion in assigning a counterpart instance of the of the corresponding one of the application instances to a suitable network slice executing at the different edge portion providing an expected performance matching the performance data encapsulated in the data structure.

[0016] EXEMPLARY EMBODIMENT #2

[0017] In another embodiment of the disclosure, a computing device is provided that includes a non-transitory computer readable storage medium. The storage medium has stored thereon program instructions which are executable by at least one processing core of a processing unit so as to cause the processing unit to perform network slice orchestration. Specifically, the program instructions cause the processing core to define a set of network slices extending to an edge portion of a host cellular telecommunications network, each with a different slice configuration to produce different performance metrics in operation. The program instructions additionally cause the processing core to bootstrap a core network extending to the edge portion of the host cellular telecommunications network with the set of network slices in a pool of available slices, and to assign each of the slices to a specific endpoint address.

[0018] Thereafter, the program instructions cause the processing core to load into memory a list of the slices and the different performance metrics, to determine slice performance requirements for each corresponding one of different application instances of respectively different applications executing at edge locations of the cellular data communications networks, and to assign each corresponding one of the different application instances to the specific endpoint address of a matching one of the slices in the pool. More particularly, the assignment is based upon the determined slice performance requirements of the corresponding one of the respectively different applications and the different performance metrics of the matched one of the slices. Inthis regard, the performance requirements and performance metrics can include those values and ranges of values for latency, bandwidth and reliability.

[0019] Finally, the program instructions cause the processing core to performance monitor each of the different applications. In consequence of the performance monitoring, the program instructions cause the processing core to respond to a determination that the determined slice performance requirements of a monitored application instance for the matched one of the slices differs by a threshold value from the performance metrics produced by the performance monitoring. The response specifically includes matching the monitored application instance to a different one of the slices with values of the different performance metrics that are within the threshold value of the observed performance metrics. The response further includes re-assigning the monitored application instances to the endpoint address of the different one of the slices. Optionally, both the assignment and re-assignment are performed by a core service of the host cellular telecommunications network.

[0020] EXEMPLARY EMBODIMENT #3

[0021] In yet another embodiment of the disclosure, a data processing system is adapted for network slice orchestration in a mobile communications network. The system includes a host computing platform disposed within a central unit (CU) of a cellular telecommunications network. The CU includes a communicative coupling to a multiplicity of different distributed units (DUs). The platform includes one or more computers, each with memory and at least one processor. An SDN is established in thehost computing platform. As well, a core network is defined within the SDN so as to control both data and also control plane operations within the CU. Multiple different network slices are defined across the core network, each including a different set of network resources accessible by different application instances of different applications delivering application services to different user equipment (UE) coupled to the DUs. Finally, a performance monitor executes in the core network, collecting performance data for the instances of the application executing within respective ones of the different network slices.

[0022] Importantly, the system includes a slice orchestrator. The orchestrator includes computer program instructions enabled while executing in the host computing platform to perform network slice orchestration. Specifically, the program instructions receive, from the performance monitor, performance data in respect to the UE accessing a corresponding one of the different application instances through an assigned one of the network slices. The program instructions then determine a mismatch in the performance data with respect to an expected performance for the one of the different application instances. Finally, program instructions respond to the determined mismatch by selecting a different one of the network slices and re-assigning the one of the different application instances to the selected different one of the network slices.

[0023] In this way, the technical deficiencies of static network slice allocation are overcome owing to the configuration of multiple different network slices in a pool at the time of bootstrap of the SDN, and the dynamic re-assignment of a particular applicationinstance from one of the slices in the pool to another in response to a determination that the performance of an assigned one of the network slices for a particular application instance as determined by the performance monitor falls outside the pre-determined range of acceptable performance for the particular application instance.

[0024] Additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The aspects of the invention will be realized and attained by means of the elements and combinations particularly pointed out in the appended claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0025] The accompanying drawings, which are incorporated in and constitute part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention. The embodiments illustrated herein are presently preferred, it being understood, however, that the invention is not limited to the precise arrangements and instrumentalities shown, wherein:

[0026] Figure 1 is a pictorial illustration reflecting different aspects of a process of network slice orchestration in a mobile communications network;

[0027] Figure 2 is a block diagram depicting a data processing system adapted to perform one of the aspects of the process of Figure 1 ; and,

[0028] Figure 3 is a flow chart illustrating one of the aspects of the process of Figure 1. DETAILED DESCRIPTION OF THE INVENTION

[0029] Embodiments of the invention provide for network slice orchestration in a mobile communications network. In accordance with an embodiment of the invention, the core network of an SDN of a cellular telecommunications network bootstraps with a pre-defined set of network slices in a pool of slices, each of the slices having a different resource configuration so as to provide different levels of performance in terms of latency, bandwidth and reliability. Following bootstrap, different application instances instantiate at the edge of the core network, each being assigned to a corresponding one of the slices based upon the performance requirements of each one of the instances. A performance monitor then monitors the performance of each application instance executing within a respectively assigned one of the slices. To the extent that an application instance demonstrates performance outside of a threshold range of the performance requirements of the instance, the instance is then re-assigned to a different one of the slices configured in a manner more likely to meet the performance requirements of the application instance.

[0030] In illustration of one aspect of the embodiment, Figure 1 pictorially shows a process of network slice orchestration in a mobile communications network. As shown in Figure 1, an SDN 120 including application plane 120A and control plane 120B, include a core network 130 defined at the moment of bootstrap to include different network slices 110, each defined differently according to an arrangement of VNF instances 100 of different VNFs 150 defined for the SDN 120. Following bootstrap, different application instances 140 in the application plan 120A executing at an edge of the SDN 120 are assigned to respectively different ones of the network slices 110 according to the performance requirements 170 known for each of the applications instance 140 so that the VNF instances 100 of an assigned one of the network slices 110 is suited to support the performance requirements 170 of an assigned one of the application instances 140.

[0031] During the course of execution of each of the application instances 140, a performance monitor 190 monitors the performance of each executing one of the application instances 140 in order to acquire performance data 180 for the different network slices 110 to which the application instances 140 are assigned. A slice orchestrator 160, upon determining from the performance data 180 that an identifiable one of the application instances 140 demonstrates an application performance falling out of range from the associated performance requirements, dynamically re-assigns the identifiable one of the application instances 140 to a different one of the network slices 110 having an arrangement of VNF instances 100 known to be able to secure applicationperformance within the range of the performance requirements 170 of the identifiable one of the application instances 140.

[0032] The process described in connection with Figure 1 may be specifically embodied in an SDN architected telecommunications network data processing system. In further illustration, Figure 2 schematically shows an SDN architected mobile communications network data processing system adapted for network slice orchestration in a mobile communications network. The system includes a C-RAN 230A implemented in the control plane of an SDN. The C-RAN 230A includes a host computing platform 240 that includes one or more computers 210 each with memory 220 A and one or more processors 220B. Multiple different centralized units (CUs) 250 for respective network slices 270 are defined in the memory 220 A, each including one or more infrastructure resources 200, namely VNF instances 260 of different VNFs 200, accessible by different mobile application instances executing in an application plane of the SDN (not shown) in order to support processing of mobile cellular network connections with different user equipment (UE) 290 through distributed units (DUs) 280.

[0033] An NEF 300A is provided in the host computing platform 240. The NEF 300A instantiates a set of VNF instances 260 for VNFs 200 defined in the host computing platform 240 and groups different ones of the VNF instances 260 into different collections within different CUs 250 of different network slices 270 so as to provide different performance characteristics in terms of latency, bandwidth and reliability. The NEF 300A, then provides access to the mobile applications instances tothe exposed network services provided by the VNF instances 260 by way of assigned ones of the slices 270 at respectively different network endpoint addresses, each of the network slices 270 being assigned a different network endpoint address.

[0034] Importantly, a slice orchestrator 300 is included in the host computing platform 240 and executes by at least one of the processors 220B of the host computing platform 240. The slice orchestrator 300 includes computer program instructions that when executing by one or more of the processors 220B, is enabled to access performance data collected by a performance monitor 300B extending the network data analytics function (NWDAF) of the core network in respect to the observed performance of each of the slices 270 in supporting the execution of different ones of the mobile application instances. The computer program instructions further are enabled to compare the performance data for the mobile application instances to the performance requirements of each of the mobile application instances set forth in a requirements table 285.

[0035] To the extent that a mismatch is detected between the performance requirements of an identified one of the application instances and the performance data retrieved for a network slice 270 to which the identified one of the application instances is assigned, the computer program instructions re-assign the identified one of the application instances to another of the network slices 270 more likely to support the performance requirements of the identified one of the application instances. More specifically, the identified one of the application instances is assigned to the network endpoint address of the another one of the network slices 270 determined more likely tosupport the performance requirements of the identified one of the application instances. Optionally, each of the application instances can be assigned to one of several tiers of a service level range in an application priority list 275 so that access to a particular one of the network slices of specific VNF instance 260 configuration can be preferential to application instances of a higher tier of the service level range.

[0036] In one aspect of the embodiment, the computer program instructions of the slice orchestrator 300 encapsulates the performance metrics collected for a selected one or the application instances by the performance monitor 300B into a data structure 265. Thereafter, as UE 290 accessing the selected one of the application instances is determined to physically approach an adjacent C-RAN 230B, the computer program instructions of the slice orchestrator 300 transmits the data structure 265 of the performance metrics for the selected one of the application instances to a counter-part slice orchestrator 300 in the core network of the adjacent C-RAN 230B. In this way, in the event that the UE 290 roams onto the adjacent C-RAN 230B, a counter-part form of the selected one of the application instances can be assigned to network slice 270 of sufficient configuration to support the performance requirements of the selected one of the application instances.

[0037] In yet further illustration of the operation of the slice orchestrator 300, Figure 3 is a flow chart illustrating a process of slice orchestration in a mobile communications network. Beginning in block 310, a set of network slices are separately configured to include different network resources in order to provide different performancecharacteristics in the form of latency, bandwidth and reliability. In block 320, the core network of the cellular telecommunications network bootstraps according to the network slice configuration. Then, in block 330, an application instance accessible at the edge of the cellular telecommunications network is selected and in block 340, the performance requirements for the selected application instance are determined. Based upon the determination, in block 350 the selected application instance is assigned to a specific one of the network slices expected to include sufficient network resources to support the performance requirements for the selected application instance.

[0038] In block 360, a performance monitor monitors the performance of the selected one of the application instances in the assigned network slice. To that end, in block 370, performance data is retrieved from the performance monitor for the selected one of the application instances. In decision bock 380, it is determined whether or not the performance data shows that the monitored performance of the selected one of the application instances is within a threshold range of the performance requirements of the selected one of the application instances. If not, in block 390 the slice pool can be inspected to identify different network slices in the slice pool and corresponding performance capabilities. As such, in block 400, one of the inspected network slices determined to have a sufficient resource configuration to support the performance requirements of the selected one of the application instances is selected and in block 410, the selected one of the application instances is assigned to the matching slice.

[0039] Of import, the foregoing flowchart and block diagram referred to herein illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computing devices according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which includes one or more executable instructions for implementing the specified logical function or functions. In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

[0040] More specifically, the present invention may be embodied as a programmatically executable process. As well, the present invention may be embodied within a computing device upon which programmatic instructions are stored and from which the programmatic instructions are enabled to be loaded into memory of a data processing system and executed therefrom in order to perform the foregoing programmatically executable process. Even further, the present invention may be embodied within a data processing system adapted to load the programmatic instructionsfrom a computing device and to then execute the programmatic instructions in order to perform the foregoing programmatically executable process.

[0041] To that end, the computing device is a non-transitory computer readable storage medium or media retaining therein or storing thereon computer readable program instructions. These instructions, when executed from memory by one or more processing units of a data processing system, cause the processing units to perform different programmatic processes exemplary of different aspects of the programmatically executable process. In this regard, the processing units each include an instruction execution device such as a central processing unit or "CPU" of a computer. One or more computers may be included within the data processing system. Of note, while the CPU can be a single core CPU, it will be understood that multiple CPU cores can operate within the CPU and in either instance, the instructions are directly loaded from memory into one or more of the cores of one or more of the CPUs for execution.

[0042] Aside from the direct loading of the instructions from memory for execution by one or more cores of a CPU or multiple CPUs, the computer readable program instructions described herein alternatively can be retrieved from over a computer communications network into the memory of a computer of the data processing system for execution therein. As well, only a portion of the program instructions may be retrieved into the memory from over the computer communications network, while other portions may be loaded from persistent storage of the computer. Even further, only a portion of the program instructions may execute by one or more processing cores of oneor more CPUs of one of the computers of the data processing system, while other portions may cooperatively execute within a different computer of the data processing system that is either co-located with the computer or positioned remotely from the computer over the computer communications network with results of the computing by both computers shared therebetween.

[0043] The corresponding structures, materials, acts, and equivalents of all means or step plus function elements in the claims below are intended to include any structure, material, or act for performing the function in combination with other claimed elements as specifically claimed. The description of the present invention has been presented for purposes of illustration and description but is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the invention. The embodiment was chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.

[0044] Having thus described the invention of the present application in detail and by reference to embodiments thereof, it will be apparent that modifications and variations are possible without departing from the scope of the invention defined in the appended claims as follows:

Claims

CLAIMS1. A network slice orchestration method comprising: deploying both a performance monitor and a slice orchestrator in a core network of a host cellular telecommunications network; defining a multiplicity of network slices in the host cellular telecommunications network, each with a different set of network resources accessible by different application instances of different applications, the application instances executing at an edge portion of the host cellular telecommunications network; receiving from the performance monitor performance data in respect to a particular mobile device accessing a corresponding one of the different application instances through an assigned one of the network slices; determining in the slice orchestrator a mismatch in the performance data with respect to an expected performance for the one of the different application instances; and, responsive to the determined mismatch, selecting in the slice orchestrator a different one of the network slices and re-assigning by the slice orchestrator the one of the different application instances to the selected different one of the network slices.

2. The method of claim 1 , further comprising storing application performance requirements for different ones of the applications and determining the mismatch responsive to the performance data failing the stored application performance requirements for the one of the application instances.

3. The method of claim 1, further comprising retrieving, into the slice orchestrator, a rule mapping application performance requirements to specific ones of the network slices, the selection comprising applying the rule to performance requirements of the one of the application instances in order to identify the alternative one of the network slices mapped to performance requirements of an application corresponding to the one of the application instances.

4. The method of claim 1 , wherein the performance requirements are performance criteria selected from the group consisting of:• latency;• bandwidth; and,• reliability.

5. The method of claim 1, wherein each of the different application instances are assigned to different subscription tiers corresponding to different re-assignment priorities, the method further comprising: identifying multiple different ones of the different applications instances requiring re-assignment to the selected different one of the network slices; and, prioritizing the re-assignment by the slice orchestrator to the different one of the network slices based upon a highest one of the priorities associated with respective ones of the different subscription tiers of the multiple different ones of the different applications.

6. The method of claim 1 , the edge portion of the host cellular telecommunications network is adjacent to a different edge portion of a different cellular telecommunications network, the method further comprising: populating, in memory accessible by the core network, a data structure encapsulating the performance data in respect to the particular mobile device accessing the corresponding one of the different application instances through the assigned one of the network slices; and, transmitting the data structure to the different edge portion for use by the different edge portion in assigning a counterpart instance of the of the corresponding one of the application instances to a suitable network slice executing at the different edge portion providing an expected performance matching the performance data encapsulated in the data structure.

7. A computing device comprising a non- transitory computer readable storage medium having program instructions stored therein, the instructions being executable by at least one processing core of a processing unit to cause the processing unit to perform network slice orchestration by: defining a set of network slices of a host cellular telecommunications network, each with a different slice configuration to produce different performance metrics in operation;bootstrapping a core network extending to an edge portion of the host cellular telecommunications network with the set of network slices in a pool of available slices, and assigning each of the slices to a specific endpoint address; loading into memory a list of the slices and the different performance metrics; determining for each corresponding one of different application instances of respectively different applications executing at edge locations of the cellular data communications networks, slice performance requirements, and assigning each corresponding one of the different application instances to the specific endpoint address of a matching one of the slices in the pool based upon the determined slice performance requirements of the corresponding one of the respectively different applications and the different performance metrics of the matched one of the slices; performance monitoring each of the different applications; and, responsive to determining that the determined slice performance requirements of a monitored one of the corresponding ones of the different application instances for the matched one of the slices differs by a threshold value from performance metrics produced by the performance monitoring, matching the monitored one of the corresponding ones of the different application instances to a different one of the slices with values of the different performance metrics that are within the threshold value of the observed performance metrics and re-assigning the monitored one of the corresponding ones of the different application instances to the endpoint address of the different one of the slices.

8. The device of claim 7, wherein both the assignment and re-assignment are performed by a core service of the host cellular telecommunications network.

9. The device of claim 7, wherein the determined slice performance requirements are performance criteria selected from the group consisting of:• latency;• bandwidth; and,• reliability.

10. The device of claim 7, wherein each of the different applications are assigned to different subscription tiers corresponding to different re-assignment priorities, the instructions being executable by at least one processing core of a processing unit to further cause the processing unit to perform network slice orchestration by: identifying multiple different ones of the different application instances requiring re-assignment to the selected different one of the network slices; and, prioritizing the re-assignment to the different one of the network slices based upon a highest one of the priorities associated with respective ones of the different subscription tiers of the different applications of the different application instances.

11. The device of claim 7, wherein the edge portion of the host cellular telecommunications network is adjacent to a different edge portion of a different cellular telecommunications network, the instructions being executable by at least one processingcore of a processing unit to further cause the processing unit to perform network slice orchestration by: populating a data structure encapsulating the performance data in respect to the corresponding one of the different application instances through the assigned one of the network slices; and, transmitting the data structure to the different edge portion for use by the different edge portion in assigning a counterpart instance of the of the corresponding one of the application instances to a suitable network slice executing at the different edge portion providing an expected performance matching the performance data encapsulated in the data structure.

12. A data processing system adapted for network slice orchestration in a mobile communications network, the system comprising: a host computing platform disposed within a central unit (CU) of a cellular communications network, the CU comprising a communicative coupling to a multiplicity of different distributed units (DUs), the platform comprising one or more computers, each comprising memory and at least one processor; a software defined network (SDN) established in the host computing platform; a core network defined within the SDN and controlling both data and also control plane operations within the CU; a multiplicity of different network slices defined across the core network, each network slice including a different set of network resources accessible by differentapplication instances of different applications delivering application services to different user equipment (UE) coupled to the DUs; a performance monitor executing in the core network and collecting performance data for the instances of the application executing within respective ones of the different network slices; and a slice orchestrator comprising computer program instructions enabled while executing in the host computing platform to perform network slice orchestration by: receiving from the performance monitor performance data in respect to the UE accessing a corresponding one of the different application instances through an assigned one of the network slices; determining in the slice orchestrator a mismatch in the performance data with respect to an expected performance for the one of the different application instances; and, responsive to the determined mismatch, selecting in the slice orchestrator a different one of the network slices and re-assigning by the slice orchestrator the one of the different application instances to the selected different one of the network slices.

13. The system of claim 12, wherein the computer program instructions are further enabled while executing in the host computing platform to perform network slice orchestration by storing application performance requirements for different ones of theapplications and determining the mismatch responsive to the performance data failing the stored application performance requirements for the one of the application instances.

14. The system of claim 12, wherein the computer program instructions are further enabled while executing in the host computing platform to perform network slice orchestration by retrieving a rule mapping application performance requirements to specific ones of the network slices, the selection comprising applying the rule to performance requirements of the one of the application instances in order to identify the alternative one of the network slices mapped to performance requirements of an application corresponding to the one of the application instances.

15. The system of claim 12, wherein the performance requirements are performance criteria selected from the group consisting of:• latency;• bandwidth; and,• reliability.

16. The system of claim 12, wherein each of the different application instances are assigned to different subscription tiers corresponding to different re-assignment priorities, wherein the computer program instructions are further enabled while executing in the host computing platform to perform network slice orchestration by:identifying multiple different ones of the different applications instances requiring re-assignment to the selected different one of the network slices; and, prioritizing the re-assignment by the slice orchestrator to the different one of the network slices based upon a highest one of the priorities associated with respective ones of the different subscription tiers of the multiple different ones of the different applications.

17. The system of claim 2, an edge portion of the host cellular telecommunications network is adjacent to a different edge portion of a different cellular telecommunications network, wherein the computer program instructions are further enabled while executing in the host computing platform to perform network slice orchestration by: populating, in memory accessible by the core network, a data structure encapsulating the performance data in respect to the particular mobile device accessing the corresponding one of the different application instances through the assigned one of the network slices; and, transmitting the data structure to the different edge portion for use by the different edge portion in assigning a counterpart instance of the of the corresponding one of the application instances to a suitable network slice executing at the different edge portion providing an expected performance matching the performance data encapsulated in the data structure.

Images