WO2020165320A1

WO2020165320A1 - Handover of a latency critical application

Info

Publication number: WO2020165320A1
Application number: PCT/EP2020/053718
Authority: WO
Inventors: Dominik Schnieders
Original assignee: Deutsche Telekom AG
Current assignee: Deutsche Telekom AG
Priority date: 2019-02-13
Filing date: 2020-02-13
Publication date: 2020-08-20
Anticipated expiration: 2021-08-13
Also published as: EP3697132B1; US12028767B2; US20220132387A1; EP3697132A1

Abstract

The present invention refers to a method comprising: a) provisioning at a selected edge computing system (212) of a plurality of edge computing systems within a wireless network (110) at least one latency critical application (214) which is to be provided to an end user device (130) in a first cell of the wireless network (110) via a first base station (211) located nearby the selected edge computing system (212), b) determining at the first base station (211) that the end user device (130) is located nearby an edge of the first cell and/or in an overlapping area of the first cell and a second cell of the wireless network (110), c) checking a degree of capacity utilisation of the second cell which is served by a second base station and located nearby the first cell and designated for a potential handover of the end user device (130) from the first cell to the second cell, d) scheduling a handover of the end user device (130) from the first cell to the second cell in case that the second cell has sufficient available capacity, e) transferring, before executing the handover, in real time a first note about the scheduled handover from a first scheduler (218) associated with the first base station (211) to the at least one latency critical application (214) hosted by the selected edge computing system (212), f) executing the handover. Further, a respective system and a respective computer readable medium are provided.

Description

Handover of a latency critical application

The disclosure relates to computer networks, particularly to wireless networks, particularly to mobile networks and, more specifically, to a handover of a latency critical application provided within one of those networks.

A network services exchange provider may employ a communication facility, such as a data center, in which multiple customers of the provider locate net work, server, and storage gear and interconnect to a variety of telecommunica tions and other network service provider(s). Data centers may be shared by the multiple tenants having their networking equipment located within the data cen ters.

With Information Technology (IT) and communications facilities in safe, secure hands, telecommunications, Internet, application service providers, cloud ser vice providers, content providers, and other providers, as well as enterprises, enjoy less latency and the freedom to focus on their core business. Additionally, customers may reduce their traffic back-haul costs and free up their internal networks for other uses.

However, there are some scenarios being realized by server based latency crit ical applications which require data processing near a respective end user.

Autonomous vehicles, for example, will generate a lot of data. Much of this data will be unstructured and will need to be run through powerful analytics programs to produce actionable data with any value to businesses. Edge computing archi tectures will help to prioritize what data needs to remain on the edge to be pro cessed by the vehicle’s onboard computing power or by any computing device nearby the vehicle and what data should be relayed back to data centers for analysis. Edge data centers will serve a critical role in this network, functioning as a relay station and providing extra computing power for mission critical ana lytics that need to remain near end users.

In an autonomous vehicle, even a few milliseconds of delay can result in an ac cident and catastrophic loss of life. The stakes are simply too high to allow the vehicles’ networks to be plagued by lag. Self-driving cars need to react immedi ately to changing road conditions; they cannot simply come to a stop while wait ing for instructions or recommendations from a distant cloud server analyzing data.

Edge computing can offer a solution to this problem. In fact, the heavy invest ment in autonomous vehicle research has been one of the reasons so many tech companies are pushing to improve and expand their edge computing archi tectures. By co-locating servers and computing resources in versatile edge facil ities located in both high traffic areas and more far-flung areas with limited bandwidth access, companies can ensure that their autonomous vehicles are able to access the data they need with minimal latency to make decisions quick ly. As loT devices, self-driving cars also have the ability to make their own deci sions without relying on guidance from servers located in distant data centers.

A further example scenario is given by computer games which experience lag when connecting to a central server and latency could mean the difference be tween victory and defeat.

Edge computing is not a new concept, but several trends have come together to create an opportunity to turn massive amounts of machine-based data into ac tionable intelligence closer to the source of the data. Typical edge computing devices typically reside away from a centralize computing available in a cloud. Edge computing enables analytics and data gathering to occur at or nearby the source of the data. The role of edge computing to date has mostly been used to ingest, store, filter, and send data to cloud systems. Meanwhile, it is also desir able, that edge computing systems are packing more compute, storage, and analytic power to consume and act on the data nearby the end user location.

There are some scenarios where it is useful to bring server based applications closer to terminals, i.e. user equipment (UE) and, thus, to acquire a reduced latency with respect to roundtrip-time (RTT). Specifically, MNOs (Mobile Net work Operators) undertake efforts to integrate edge computing in their net works.

However, it is still quite difficult or even impossible to provide latency critical applications via a wireless interface, i.e. a radio interface as currently used schedulers operate according to a best effort and fair schedule approach when allocating the available resources on the wireless interface, i.e. at a respective base station, which leads to an inacceptable variance in latency and jitter for any latency critical application.

While a parallel patent application entitled "real time adaption of a latency criti cal application" refers to a possibility to determine in real time for each of one or more latency critical applications which are to be provided via a wireless inter face, a respective operating point while simultaneously optimizing the resource use on the wireless interface, it is still an object how to deal with latency critical applications which are to be provided via a wireless interface, in a cell which is used to capacity and/or in an upcoming handover.

As a solution to the above mentioned object, the present disclosure provides a method and a system with the features of the independent claims. Further em bodiments are provided by the dependent claims and the description. Generally, resource use and route optimization suffers from handover delays derived from a signaling message exchange. Handover latency plays an im portant role in the performance of a network scenario, particularly in matters of latency critical applications. Handover latency may result in packet losses and severe end-to-end performance degradation.

Therefore, a method is provided, the method comprising:

a) provisioning at a selected edge computing system of a plurality of edge computing systems within a wireless network at least one latency critical application which is to be provided to an end user device in a first cell via a first base station serving the first cell and being located nearby the se lected edge computing system,

b) determining at the first base station that the end user device is located nearby an edge of the first cell and/or in an overlapping area of the first cell and a second cell and/or between the first cell and the second cell, c) checking a degree of capacity utilisation of the second cell which is served by a second base station and located nearby the first cell and designated for a potential handover of the end user device from the first cell to the second cell,

d) scheduling a handover of the end user device from the first cell to the second cell in case that the second cell has sufficient available capacity, e) transferring, before executing the handover, in real time a first note about the scheduled handover from the first base station to the at least one la tency critical application hosted by the selected edge computing system, f) executing the handover.

Generally, it is to be stated that within a full cell, i.e. a cell which is used to ca pacity, available resources, i.e. resource blocks, resource elements, are distrib uted up to now among all connected end user devices according to a "propor tional fair" algorithm. This may lead to a reduced data throughput and/or an in creased latency for any application which is to be provided to any of the differ- ent connected end user devices. In case of latency critical applications, this may result in a degradation of the performance.

A handover of an end user device between two cells typically leads to signifi cantly higher latencies, several 10ms to several 100ms, which generally leads with latency critical applications to a bad user experience.

In both cases, the latency critical application does not operate correctly or is even interrupted.

In view of these disadvantages, the proposed method of the present disclosure specifically schedule and execute a handover by taking into account the at tendant circumstances, thus allowing the at least one latency critical application to be prepared for the handover and attenuating the above mentioned disad vantages for the at least one latency critical application.

Step a) may comprise that a first scheduler associated with the first base station receives from the at least one latency critical application hosted by the selected edge computing system operation requirements of the at least one latency criti cal application.

It is also possible that the at least one latency critical application is host ed/provisioned directly by the end user device. In this case the first note is sent from the first scheduler to the end user device, i. e. to the at least one latency critical application hosted by the end user device.

According to the proposed method, it is provided to generate and transfer, be fore executing the scheduled handover, in real time an attribute and/or a note about the scheduled handover from the first base station, particularly from the first scheduler associated with the first base station, to the at least one latency critical application hosted by the selected edge computing system. According to one embodiment of the proposed method, the first scheduler as sociated with the first base station communicates with the at least one latency critical application hosted by the selected edge computing system via a service layer radio application (SLRA) which is implemented on both, the first base sta tion, particularly the first scheduler, and the selected edge computing system.

Accordingly, it is provided in step e) of the proposed method that the first scheduler associated with the first base station transfers the first note via the service layer radio application to the at least one latency critical application hosted by the selected edge computing system.

According to one embodiment of the proposed method, the first note comprises at least the following parameters: event of the scheduled handover, lead time (Tv) between scheduling the handover and executing the handover, expected duration of the handover.

The lead time Tv may constitute 0 to some milliseconds (0 - x ms, with x being an integer value).

The expected duration of the handover may constitute some milliseconds (y ms, with y being an integer value).

Optionally, the first note may comprise further parameters.

According to still a further embodiment of the proposed method, step e) further comprises:

e') receiving the first note by the at least one latency critical application hosted by the selected edge computing system, and

e") transferring, in reaction to the scheduled handover, a second note from the at least one latency critical application hosted by the selected edge computing system to the first scheduler associated with the first base station via the service layer radio application, the second note comprising parameters about a strategy of the at least one latency critical application hosted by the se lected edge computing system in order to adapt the at least one latency critical application to the scheduled handover.

In the case that the application is hosted by the end user device, i. e. the appli cation is a client-based application, all notes are transferred directly between the first scheduler and the end user device, preferably also using SLRA which is implemented on both, the first base station and the end user device.

The second note may announce a change of operating point of the at least one latency critical application, i.e. put at least one operating point up for selection (by the scheduler), targeting at least one of the following strategy actions:

• operating point with long enough latency to overcome handover time, i.e. duration of the handover,

• operating point that allows pre-buffering of data at the end user device and/or at the selected edge computing system before the handover takes place in order to overcome handover time,

• operating point with interruption of data transfer ("no data transfer") dur ing the scheduled handover.

The at least one latency critical application can specifically apply one or more strategies in order to be prepared for the scheduled handover, i.e. to adapt itself to the scheduled handover.

Thus, the at least one latency critical application can schedule a change of op erating point, i.e. a change from a current operating point to an operating point which is still acceptable for a good performance of the at least one latency criti cal application and simultaneously adapted to an increased latency and/or a decreased data throughput as possible implications of the scheduled handover.

Further, the at least one latency critical application can provide a pre-buffering of data on the end user device (UE) and/or on the selected edge computing system or on any further remote data storage (as far as this is an option for the at least one application). The second note to the scheduler would comprise the change to the respective operating point that represents the enhanced through put for the pre-buffering of data, as well as a minimum duration time in the op erating point in order to complete the pre-buffering. Such pre-buffering of data can be performed in awareness of quality reduction, leading, however, to a compensation of the undesired effect of the unique high latency during the handover. Further, the at least one latency critical application could envisage an interruption of data transfer during the scheduled handover. The second note to the scheduler would comprise the change to the respective operating point that represents "no data transfer".

Further, the at least one latency critical application can interrupt the data trans fer while the handover is going on. This might be important as data packets can be queued at different positions, namely application, deeper protocol stacks, base station, etc., when the data throughput is reduced or even set to zero. Such undesired queuing leads to additional latency as the queue has to be re moved first when the handover is terminated. Generally, old data packets are rejected for real time/latency critical applications anyway. Insofar the latency is reduced when the data are transferred not at all during the handover but al ready rejected at the data source. This is again comprised in the second note by changing to the respective operating point with no transmission of data.

Transmission is to be understood within the scope of the present disclosure in a broad sense, particularly as data transmission, i.e. as a transfer of data (a digi tal bitstream or a digitized analog signal) over a communication channel, such channels can be copper wires, optical fibers, wireless communication channels, storage media and computer buses. In the present disclosure, particularly wire less communication channels are considered.

Data can be represented as electromagnetic signals, such as radiowaves, mi crowaves, an electrical voltage or infrared signal. Data can be represented as packets, frames, bits, information considering all different communication lay ers.

After completed handover, the latency critical application can pass over to its standard/normal operation/operating modus/point.

Regarding the starting situation that the latency critical application is situated in a full cell, i. e. the first cell is used to capacity. This means a very high capacity utilization of available resource blocks/elements. Further the end user device of the latency critical application is placed at an edge or nearby an edge of the first cell and/or in an overlapping area of the first cell and a second cell and/or be tween the first cell and the second cell.

Referring to such a scenario, it is proposed according to a further embodiment of the proposed method, that step b) is specified as

b') determining at the first base station that the first cell is used to capacity, and step f) is specified as

f) executing an early and immediate handover of the end user device from the first cell to the second cell in case that the second cell has a capacity utilisa tion less than the first cell.

Further step f) comprises:

f") allocating, by the second base station, to the at least one latency critical application available resources from the second cell in consideration of cur rent operation requirements of the at least one latency critical application.

Within the second (new) cell of a respective second base station it is possible to allocate to the latency critical application more resources (resource blocks/elements) due to the lesser capacity utilisation of the second cell. Thus, the situation/performance of the latency critical application is enhanced. Fur thermore, the first cell of the first base station is unburdened due to the early handover. Thus, all other end user devices/applications served/provided via the first base station can be supplied with more resources.

It is to be emphasized that, in the first place, the first scheduler associated with the first base station must have the information that the application for the end user device is a latency critical application. Such information is exchanged be tween the at least one application and the first scheduler via SLRA which is im plemented on both, the first base station and the selected edge computing sys tem hosting the latency critical application.

An advantage of the proposed method is that the operation conditions for the latency critical application as well as for the other applications provided within the first cell are enhanced due to the fact that the handover was brought for ward.

Further, the latency critical application can specifically react to a scheduled handover when being informed, as suggested by the proposed method, before the handover is executed. Thus, the effects of the latency accompanying the handover can be mitigated or even compensated.

Thus, the effect/influence caused by the latency of the handover for the latency critical application when using a wireless network, such as a mobile network can be reduced. Therefore, an introduction and usage of latency critical applica tions within a wireless network, such as a mobile network, become more realis tic.

The present disclosure also refers to a system comprising at least:

- a plurality of edge computing systems each located nearby at least one respective base station of a wireless network and deployed and managed by a network provider, wherein at least one of the plurality of edge computing systems is configured to be selected to provision at least one latency critical application which is to be provided to an end user device within a first cell of the network via a first base station located nearby the selected edge computing system and serving the first cell,

- the first base station located nearby the selected edge computing system,

wherein the selected edge computing system is configured to provision the at least one latency critical application and an application programming interface (API) endpoint for communication with the first base station, wherein the select ed edge computing system is configured to exchange with a first scheduler as sociated with the first base station transmission specific data in real time using a service layer radio application (SLRA), which is implemented on both, the first base station and the selected edge computing system, via the API endpoint and to use those data for scheduling and executing a handover of the end user de vice from the first cell to a second cell taking into account strategy actions for adapting in real time the at least one latency critical application to the handover.

It is also possible that the at least one latency critical application is host ed/provisioned directly by the end user device. In this case the first note is sent from the first scheduler to the end user device, i. e. to the at least one latency critical application hosted by the end user device. In the case that the applica tion is hosted by the end user device all notes are transferred directly between first scheduler and end user device, preferably also using SLRA which is im plemented on both, the first base station and the end user device. In this case the system comprises the end user device, instead or additionally to the plurality of edge computing systems.

The proposed system is particularly configured to execute at least one embodi ment of the above described and proposed method.

Further, a computer readable storage medium is provided which comprises in structions that when executed cause one or more processors of a wireless net work to: A) provision at a selected edge computing system of a plurality of edge computing systems within a wireless network, particularly a mobile net work, at least one latency critical application which is to be provided to an end user device in a first cell of the wireless network via a first base sta tion located nearby the selected edge computing system,

B) determine at the first base station that the end user device is located nearby an edge of the first cell and/or in an overlapping area of the first cell and a second cell of the wireless network and/or between the first cell and the second cell,

C) check a degree of capacity utilisation of the second cell which is served by a second base station and located nearby the first cell and designated for a potential handover of the end user device from the first cell to the second cell,

D) schedule a handover of the end user device from the first cell to the sec ond cell in case that the second cell has sufficient available capacity,

E) transfer, before executing the handover, in real time a note about the scheduled handover from the first base station to the at least one latency critical application hosted by the selected edge computing system,

F) execute the handover.

The computer readable storage medium particularly comprises instructions that when executed cause one or more processors of the wireless network, particu larly the mobile network to execute at least one embodiment of the method dis closed herein.

The details of one or more examples of the techniques are set forth in the ac companying drawings and the description below. Other features, objects, and advantages of the techniques will be apparent from the description and draw ings, and from the claims. Brief description of drawings

Figure 1 is a schematic diagram illustrating schematically a data transfer be tween user equipment, base station and edge computing system in accordance with techniques described herein.

Figure 2 is a more detailed view of a base station and a selected edge compu ting system and a logical connection between the base station and the selected edge computing system in accordance with techniques described herein.

Detailed description of drawings

Figure 1 is a schematic diagram illustrating an example system 100 incorporat ing an embodiment of the claimed system. The system 100 comprises a net work 1 10 of a mobile network operator (MNO), an access layer 120 and an end user device 130 which can access the mobile network 1 10 via the access layer 120. Further, the device 130 can access the Internet (not shown) via the access layer 120 and the mobile network 1 10 and, thus, benefit from all services pro vided by or via the Internet.

The mobile network 1 10 comprises a plurality of access nodes 21 1 , such as a MSAN (Multi-Service Access Node) and/or a cell tower (an antenna support with mobile antennas), a plurality of edge computing systems 212 and a back bone (not shown) interconnecting the mobile network 1 10 with the Internet.

A mobile network operator (MNO), also known as a wireless service provider is a provider of wireless communications services that owns or controls all the el ements necessary to sell and deliver services to an end user device including radio spectrum allocation, wireless network infrastructure, back haul infrastruc ture, provisioning computer systems, etc. In general, edge devices are normally routers that provide authenticated access (most commonly PPPoA and PPPoE) to faster, more efficient backbone and core networks. The edge computing systems 212 provided according to the present disclosure are made smart, so that the edge computing systems 212 are not only routers, but can include Quality of Service (QoS) and multi-service functions to manage different types of traffic and to provision applications, par ticularly latency critical application. Each of the plurality of edge computing sys tems 212 is located nearby at least one base station 21 1 and, thus, nearby a scheduler associated with the at least one respective base station 21 1. Due to the physical proximity of each of the edge computing systems 212 to at least one respective base station 21 1 , information between the edge computing sys tems 212 and the respective schedulers associated with the neighbouring base stations 21 1 can be transferred in real time. This enables the scheduler associ ated with a respective base station 21 1 to allocate in real time available re sources to applications which are provisioned by the respective neighbouring edge computing systems 212.

Considering a latency critical application which is to be provided to an end user device (user equipment - UE) 130, the latency critical application is provisioned by a selected edge computing system 212 which is nearby the base station 21 1 serving the end user device 130. The scheduler associated with the base sta tion 21 1 is provided in real time via the selected edge computing system 212 with input parameters when allocating resources to the latency critical applica tion. Such input parameters are, for example,“channel condition”,“historical throughput”,“packet delay”,“queue length” and further context sensitive param eters of the latency critical application, such as mean latency, maximum latency and data rate which are currently needed by the latency critical application. As those parameters are provided in real time, the scheduler can consider dynami cally requirements of the application which change with time. Thus, the sched uler only blocks resources which are necessary for fulfilling the current require ments of the application in real time. An optimal usage of the spectrum is reached while the latency requirements of the latency critical application are fulfilled at any time.

Figure 1 shows schematically a data transfer between the user equipment 130, the base station 21 1 and the edge computing system 212 which is located nearby the base station 21 1 . The user equipment 130 is currently served by the base station 21 1 because the user equipment 130 is currently positioned within a coverage area of a cell which is served by the base station 21 1 . Thus, data are transferred between the user equipment 130 and the base station 21 1 as indicated by double arrow 231 . Applications which are desired by the user equipment 130 have to be provided via the base station 21 1 . A scheduler asso ciated with the base station 21 1 has to allocate available resources to all appli cations and services which are running via the base station 21 1 . In the case that the user equipment 130 is to be provided, for example on demand, with a latency critical application, it is proposed to select the edge computing system 212 as that edge computing system that is located most nearby the base station 21 1 , as indicated by double arrow 250, for that the selected edge computing system 212 provisions the latency critical application 214. The selected edge computing system 212 comprises further a service layer radio application (SLRA) 215 and a computing unit, i.e. a mobile edge computing unit (MEC) 216.

Multi-access Edge Computing (MEC), formerly Mobile Edge Computing, is a network architecture concept that enables cloud computing capabilities and an IT service environment at the edge of the mobile network 1 10. The basic idea behind MEC is that by running applications and performing related processing tasks closer to the user equipment 130, network congestion is reduced and ap plications perform better. MEC technology is implemented at the selected edge computing system 212, and enables flexible and rapid deployment of the laten cy critical application for the user equipment 130. The selected edge computing system 212 is realized as a cloudlet and is logically connected, as indicated by double arrow 217, with the scheduler associated with the base station 21 1 via the service layer radio application 215 which is implemented on both, the se- lected edge computing system 212 and the base station 21 1 . Via the service layer radio application 215, the scheduler receives in real time context sensitive parameters of the latency critical application 214, such as currently needed mean latency, currently needed maximum latency and currently needed data rate. Thus, the scheduler of the base station 21 1 can consider those context sensitive data when dynamically allocating resources to the latency critical ap plication 214. Therefore, at any time, an optimal usage of the spectrum is reached while latency requirements are simultaneously fulfilled.

Regarding the starting situation that the user equipment 130 is located at the edge of the cell of the network 1 10 which is served by the base station 21 1 , and/or in an overlapping area of this cell and a second neighbouring cell of the network 1 10 and/or between this cell and the second cell, a handover of the user equipment 130 from the (first) cell to the second cell is envisaged. The handover is scheduled in good time so that before executing the scheduled handover, an attribute and/or a first note about the scheduled handover is gen erated and transferred from the base station 21 1 , particularly from the scheduler associated with the base station 21 1 , to the at least one latency critical applica tion 214 hosted by the selected edge computing system 212. The scheduler 218 (see Figure 2) associated with the base station 21 1 communicates with the at least one latency critical application 214 hosted by the selected edge compu ting system 212 via the service layer radio application (SLRA) which is imple mented on both, the base station 21 1 and the selected edge computing system 212 as indicated by reference numbers 215 and 219, respectively (see Figure 2).

Accordingly, it is provided that the scheduler 218 associated with the base sta tion 21 1 transfers the first note via the service layer radio application 219, 215 to the at least one latency critical application 214 hosted by the selected edge computing system 212 as indicated by double arrow 217. The first note may comprise at least the following parameters: event of the scheduled handover, lead time (Tv) between scheduling the handover and exe cuting the handover, expected duration of the handover.

The lead time Tv may constitute 0 to some milliseconds (0 - x ms, with x being a positive integer value).

Optionally, the first note may comprise further parameters.

It is now possible that the at least one latency critical application 214 generates and transfers a second note to the scheduler 218 associated with the base sta tion 21 1 in reaction to the scheduled handover via the service layer radio appli cation 215, 219, the second note comprising parameters about a strategy of the at least one latency critical application 214 hosted by the selected edge compu ting system 212 in order to adapt the at least one latency critical application 214 to the scheduled handover.

The second note may announce a change of operating point of the at least one latency critical application targeting at least one of the following strategy ac tions:

• operating point of the at least one latency critical application 214 with long enough latency to overcome handover time, i.e. the duration of the handover,

• operating point that allows pre-buffering of data at the end user device 130 and/or at the selected edge computing system 212 before the hand over takes place in order to overcome handover time,

• operating point with interruption of data transfer ("no data transfer") dur ing the scheduled handover. The at least one latency critical application 214 can specifically apply one or more strategies in order to be prepared for the scheduled handover, i.e. to adapt itself to the scheduled handover.

Thus, the at least one latency critical application 214 can schedule a change of operating point, i.e. a change from a current operating point to an operating point which is still acceptable for a good performance of the at least one latency critical application and simultaneously adapted to an increased latency and/or a decreased data throughput as possible implications of the scheduled handover.

Further, the at least one latency critical application 214 can provide a pre buffering of data on the end user device (UE) 130 or on the selected edge com puting system 212 or on any further remote data storage (as far as this is an option for the at least one application). Such pre-buffering of data can be per formed in awareness of quality reduction, leading, however, to a compensation of the undesired effect of the unique high latency.

Further, the at least one latency critical application 214 can interrupt the data transfer while the handover is going on. This might be important as data pack ets can be queued at different positions, namely application, deeper protocol stacks, base station, etc., when the data throughput is reduced or even set to zero. Such undesired queuing leads to additional latency as the queue has to be removed first when the handover is terminated. Generally, old data packets are rejected for real time/latency critical applications anyway. Insofar the latency is reduced when the data are transferred not at all during the handover but al ready rejected at the data source.

After completion of the handover, the at least one latency critical application 214 can pass over to its standard/normal operation/operating modus/operating point. In the case that the at least one latency critical application 214, i.e. the user equipment 130 being provided with the at least one latency critical application is situated in a full cell of the wireless network 1 10, i.e. the cell is used to capacity, and the user equipment 130 is located at or nearby the edge of the cell, it is en visaged to schedule and execute an early handover compared to a regular handover in order to disburden the full cell and to provide the possibility to allo cate more resources to the at least one latency critical application 214. Howev er, for this purpose, it is determined at first whether the second cell has more free capacity than the (first) cell.

Figure 2 is a still more detailed view of the base station 21 1 and the selected edge computing system 212 and the logical connection 217 between the base station 21 1 and the selected edge computing system 212 in accordance with techniques described herein. The base station 21 1 comprises a scheduler 218 and a service layer radio application (SLRA) 219. The logical connection 217 between the base station 21 1 and the selected edge computing system 212 is realized via the SLRA 215 of the selected edge computing system 212 and the SLRA 219 of the base station 21 1 .

List of reference signs

100 system

1 10 wireless network

120 access layer

130 end user device

21 1 access node, base station

212 edge computing system

214 latency critical application

215 service layer radio application

216 mobile edge computing unit

217 logical connection

218 first scheduler

219 service layer radio application

231 data transfer

250 double arrow

Claims

1 . A method comprising:

a) provisioning at a selected edge computing system (212) of a plurality of edge computing systems within a wireless network (1 10) at least one la tency critical application (214) which is to be provided to an end user de vice (130) in a first cell of the wireless network (1 10) via a first base sta tion (21 1 ) located nearby the selected edge computing system (212), b) determining at the first base station (21 1 ) that the end user device (130) is located nearby an edge of the first cell and/or in an overlapping area of the first cell and a second cell of the wireless network (1 10),

c) checking a degree of capacity utilisation of the second cell which is served by a second base station and located nearby the first cell and designated for a potential handover of the end user device (130) from the first cell to the second cell,

d) scheduling a handover of the end user device (130) from the first cell to the second cell in case that the second cell has sufficient available ca pacity,

e) transferring, before executing the handover, in real time a first note about the scheduled handover from a first scheduler (218) associated with the first base station (21 1 ) to the at least one latency critical application (214) hosted by the selected edge computing system (212),

f) executing the handover.

2. The method according to any one of the preceding claims, wherein step a) comprises that the first base station (21 1 ), particularly the first scheduler (218) associated with the first base station (21 1 ), receives from the at least one latency critical application (214) hosted by the selected edge computing system (212) operation requirements of the at least one latency critical application (214).

3. The method according to claim 2, wherein the first scheduler (218) asso ciated with the first base station (21 1 ) communicates with the at least one laten cy critical application (214) hosted by the selected edge computing system (212) via a service layer radio application (215, 219) which is implemented on both, the first base station (21 1 ) and the selected edge computing system (212).

4. The method according to claim 3, wherein in step e) the first scheduler (218) associated with the first base station (21 1 ) transfers the first note about the scheduled handover via the service layer radio application (215, 219) to the at least one latency critical application (214) hosted by the selected edge com puting system (212).

5. The method according to claim 4, wherein step e) further comprises: e') receiving the first note by the at least one latency critical application (214) hosted by the selected edge computing system (212), and

e") transferring a second note from the at least one latency critical appli cation (214) hosted by the selected edge computing system (212) to the first scheduler (218) associated with the first base station (21 1 ) in reaction to the scheduled handover via the service layer radio application (215, 219), the sec ond note comprising parameters about a strategy of the at least one latency critical application (214) hosted by the selected edge computing system (212) in order to adapt the at least one latency critical application (214) to the scheduled handover.

6. The method according to claim 5, wherein the second note announces a change of operating point of the at least one latency critical application (214) targeting at least one of the following strategy actions:

• operating point of the at least one latency critical application (214) with long enough latency to overcome handover time, • operating point that allows pre-buffering of data at the end user device (130) and/or at the selected edge computing system (212) before the handover takes place in order to overcome handover time,

• operating point with interruption of data transfer during the scheduled handover.

7. The method according to any one of the preceding claims, wherein the first note comprises at least the following parameters: event of the scheduled handover, lead time (Tv) between scheduling the handover and executing the handover, expected duration of the handover.

8. The method according to any one of the preceding claims, wherein step b) is extended by

b') determining at the first base station (21 1 ) that the first cell is used to ca pacity, and step f) is specified as

f) executing an early handover in case that the second cell has a capacity utilisation less than the first cell.

9. The method according to any one of the preceding claims, wherein step f) comprises:

f") allocating, by the second base station, to the at least one latency critical application (214) available resources from the second cell in consideration of current operation requirements of the at least one latency critical application (214).

10. A system comprising at least:

- a plurality of edge computing systems (212) each located nearby at least one respective base station (21 1 ) of a wireless network (1 10) and deployed and managed by a network provider, wherein at least one of the plurality of edge computing systems (212) is configured to be selected to provision at least one latency critical application (214) which is to be provided to an end user device (130) within a first cell of the wireless network via a first base station (21 1 ) located nearby the selected edge computing system (212) and serving the first cell,

- the first base station (21 1 ) located nearby the selected edge compu ting system (212),

wherein the selected edge computing system (212) is configured to pro vision the at least one latency critical application (214) and an application programming interface (API) endpoint for communication with the first base station (21 1 ), wherein the selected edge computing system (212) is configured to exchange with a first scheduler (218) associated with the first base station (21 1 ) transmission specific data in real time using a service layer radio application (215, 219), which is implemented on both, the first base station (21 1 ) and the selected edge computing system (212), via the API endpoint and to use those data for scheduling and ex ecuting a handover of the end user device (130) from the first cell to a second cell taking into account strategy actions for adapting in real time the at least one latency critical application (214) to the handover.

1 1 . The system according to claim 10, which is configured to execute a method according to any one of claims 1 to 9.

12. A computer readable storage medium comprising instructions that when executed cause one or more processors of a mobile network to:

A) provision at a selected edge computing system (212) of a plurality of edge computing systems within a wireless network (1 10) at least one la tency critical application (214) which is to be provided to an end user de vice (130) in a first cell of the wireless network (1 10) via a first base sta tion (21 1 ) located nearby the selected edge computing system (212),

B) determine at the first base station (21 1 ) that the end user device (130) is located nearby an edge of the first cell and/or in an overlapping area of the first cell and a second cell of the wireless network (1 10),

C) check a degree of capacity utilisation of the second cell which is served by a second base station and located nearby the first cell and designated for a potential handover of the end user device (130) from the first cell to the second cell,

D) schedule a handover of the end user device (130) from the first cell to the second cell in case that the second cell has sufficient available capacity,

E) transfer, before executing the handover, in real time a first note about the scheduled handover from a first scheduler (218) associated with the first base station (21 1 ) to the at least one latency critical application (214) hosted by the selected edge computing system (212),

F) execute the handover.

13. A computer readable storage medium comprising instructions that when executed cause one or more processors of a mobile network to execute a method according to any one of claims 1 to 9.