Automatic performance optimization in communication networks

专利摘要:
A computer implemented method of performance optimization in a communication network. A first parameter of a first cell of the communication network; is optimized by gathering (303) a first set of performance indicator data over a first time period; making (304) a chance in value of the first parameter after the first time period; gathering (305) a second set of performance indicator data over a second time period after making the change; determining (306) difference between the first set of performance indicator data and the second set of performance indicator data; and based on the difference, performing one of: keeping the change (310), reverting the change (311), and making a further change (312) in the same direction.
公开号:FI20195665A1
申请号:FI20195665
申请日:2019-08-06
公开日:2021-02-07
发明作者:Petteri Lundén；Jukka-Pekka Salmenkaita
申请人:Elisa Oyj；
IPC主号:

专利说明:

[0001] [0001] The present application generally relates to automatic performance optimization in communication networks.BACKGROUND
[0002] [0002] This section illustrates useful background information without admission of any technique described herein representative of the state of the art.
[0003] [0003] For a communication network operator there is a need to monitor and optimize performance of the communication network to ensure quality of service for the users of the communication network. As operational load and usage of the communication network changes and often increases and technology advances, there is a need to continuously optimize performance of the network.
[0004] [0004] Optimization may be performed for example by making configuration or parameter changes in devices of the communication network. The amount of possible changes is huge and therefore there is a need for automatic performance optimization.SUMMARY
[0005] [0005] Various aspects of examples of the invention are set out in the claims. Any devices and/or methods in the description and/or drawings which are not covered by the claims are examples useful for understanding the invention.
[0008] [0008] In an embodiment, the second time period is dynamically variable. The first time period is typically fixed.
[0009] [0009] In an embodiment, the second time period is varied by gathering the second set of performance indicator data until statistically reliable data is obtained for the determining of difference between the first set of performance indicator data and the second set of performance indicator data.
[0010] [0010] In an embodiment, the method further comprises blocking certain parameter changes over the first and second time periods.
[0011] [0011] In an embodiment, parameter changes are blocked in a geographically limited area.
[0012] [0012] In an embodiment, blocking parameter changes comprises blocking changes of at least one second parameter in the first cell.
[0013] [0013] In an embodiment, blocking parameter changes comprises blocking parameter changes in at least one second cell.
[0014] [0014] In an embodiment, blocking parameter changes comprises blocking changes of the first parameter in at least one second cell.
[0015] [0015] In an embodiment, blocking parameter changes comprises blocking parameter changes in at least one neighbor cell of the first cell. In an embodiment, the at least one neighbor cell is selected based on distance between the first cell and the neighbor cells, and antenna directions of the first cell and the neighbor cells.
[0016] [0016] In an embodiment, blocking parameter changes comprises blocking O parameter changes in 3-7 neighbor cells of the first cell. N [0017] In an embodiment, the first time period and/or the second time period 3 is selected from group of: 1-2 days, 3-5 days, a week, two weeks, a month. S [0018] In an embodiment, the first parameter is antenna tilt parameter, E parameter related to beamforming pattern or parameter related to handover. O [0019] According to a second example aspect of the present invention, there LO is provided an apparatus comprising a processor and a memory including computer > program code; the memory and the computer program code configured to, with the processor, cause the apparatus to perform the method of the first aspect or any related embodiment. 2
[0020] [0020] According to a third example aspect of the present invention, there is provided a computer program comprising computer executable program code which when executed by a processor causes an apparatus to perform the method of the first aspect or any related embodiment.
[0021] [0021] The computer program of the third aspect may be a computer program product stored on a non-transitory memory medium.
[0022] [0022] Different non-binding example aspects and embodiments of the present invention have been illustrated in the foregoing. The embodiments in the foregoing are used merely to explain selected aspects or steps that may be utilized in implementations of the present invention. Some embodiments may be presented only with reference to certain example aspects of the invention. It should be appreciated that corresponding embodiments may apply to other example aspects as well.BRIEF DESCRIPTION OF THE DRAWINGS
[0023] [0023] For a more complete understanding of example embodiments of the present invention, reference is now made to the following descriptions taken in connection with the accompanying drawings in which:
[0024] [0024] Fig. 1 shows an example scenario according to an embodiment;
[0025] [0025] Fig. 2 shows an apparatus according to an embodiment;
[0026] [0026] Fig. 3 shows a flow diagram illustrating example methods according to certain embodiments;
[0027] [0027] Fig. 4 illustrates parameter grouping for the purpose of blocking certain parameter changes; and O [0028] Fig. 5 illustrates grouping of cells for the purpose of blocking certain N parameter changes.S
[0031] [0031] As operational load and network complexity increase due to increasing number of cells and base stations and increasing usage of communication networks automated performance optimization is clearly beneficial. A challenge is to decide which optimization actions to take and how to evaluate the impact of each optimization action. The impact of an optimization action is typically observed not only in one cell, but also in its neighboring cells. Due to variation in network usage (type of traffic, amount of traffic, user locations, number of active users etc.) impact of an optimization action may not be immediately observed. Still further, other parameters may be changed in parallel and isolating the effect of a particular change may not be straightforward. Due to large amount of possible changes and their impact on each other, complete simulation of network operation may not be practical.
[0032] [0032] In an embodiment of the invention performance optimization is performed in real time in real network environment. In an embodiment an automation system is set to gather performance indicator data before and after making a parameter change, and based on difference between the performance indicator data before and after the change, the system keeps the change, reverts the change, or makes a further change in the same direction. As human interaction is not needed, it is possible to continuously make the changes. In this way it is possible to make changes in small steps and to check suitability of the changes before proceeding to larger scale changes. As a result, the network may automatically learn how to O improve performance.
[0035] [0035] In an embodiment of the invention the scenario of Fig. 1 operates as follows: In phase 11, the automation system 111 starts optimization of a first parameter. Start of the optimization process may be triggered by some other system that identifies a need to optimize, or maintenance personnel of the network may identify a need to optimize and responsively trigger the optimization process. The need to optimize may be based on identified performance problems or there may be a desire to experiment with certain parameters and to learn how the network behaves.
[0036] [0036] The automation system 111 may first block certain other changes in the communication network 101. The blocking may be implemented, for example, by storing the identities of the blocked cells and/or parameters in a list or a database or some other storage means. In an embodiment, before performing further changes, the list or database of the blocked cells and/or parameters is checked, and any changes targeted at cells and/or parameters in the list or database are cancelled. The cells and/or parameters are maintained in the list or database for a predetermined time period. The predetermined time period may cover for example the first and second time period discussed in the following phases. In this way changes in the blocked cells and/or parameters are avoided until the operation causing the blocking has been completed.
[0037] [0037] In phase 12, the automation system 111 gathers a first set of performance indicator data from the communication network 101. The performance indicators may comprise for example KPI, key performance indicators, of different network devices. Examples of the performance indicators include signal strength, O user distribution (e.g. in terms of timing advance or propagation distance from the N base station antenna), transmission power, number of dropped calls, throughput, 3 and transmission error rate. The performance indicators are in general readily S available from the communication network 101. The performance indicator values E may be collected from the network or fetched from a storage where they are O continuously stored. The first set of performance indicator data is gathered over a LO first time period. The first time period may be for example 1-2 days, 3-5 days, a > week, two weeks, or a month.
[0038] [0038] In phase 13, the automation system 111 makes a chance in value of the first parameter.
[0039] [0039] In phase 14, the automation system 111 gathers a second set of performance indicator data from the communication network 101 over a second time period. The second time period may be for example 1-2 days, 3-5 days, a week, two weeks, or a month and the second time period may be the same as or different from the first time period.
[0040] [0040] In an embodiment, the list or database of blocked cells and/or parameters may be cleaned from respective entries in the end of the second time period. In this way, the time period of blocking changes may be variable, and it may be possible to minimize the time period of blocking changes.
[0041] [0041] In phase 15, the automation system 111 determines difference between the first set of performance indicator data and the second set of performance indicator data to determine impact of the change that was made. Based on the difference the automation system 111 keeps the change, reverts the change, and makes a further change in the same direction. If the difference indicates that desired performance improvement was obtained, the change may be kept as it is and the process stops. If the difference indicates that performance degraded, the change may be reverted, and the process stops. If the difference indicates that desired performance improvement was obtained, a further change in the same direction may be made, i.e. the parameter may be further increased or decreased, and the process is continuously repeated as long as further change is needed or as long as performance improvement is observed.
[0042] [0042] The automation system 111 may use historical data and/or models of network performance to determine which performance indicators are substantially impacted by changes of the first parameter and these performance indicators are O then gathered in phases 12 and 14. In one example, the models may be trained N using data obtained from past actions of the same automation system (i.e. observing 3 which performance indicators were impacted by changes of the first parameter). This S information may be used also for deciding which parameters should be blocked and E where. Still further this information may be used for deciding the action in phase 15. O [0043] Parameter changes may be blocked in a geographically limited area. LO Changes may be blocked in one or more second cells, e.g. neighbor cells of the cell > where the change is being made. Blocking may involve blocking changes of the first parameter in one or more other cells, e.g. in in 3-7 other cells. Additionally or alternatively, blocking may involve blocking changes of the one or more other 6 parameters in the cell where the change is being made and/or in one or more other cells.
[0044] [0044] The neighbor cells where changes are blocked may be selected based on distance between the first cell and the neighbor cells, and/or antenna directions of the first cell and the neighbor cells.
[0045] [0045] Additionally or alternatively, the neighbor cells where changes are blocked may be selected based on historical data and/or network performance models predicting which of the neighbor cells would be impacted by the parameter change. The models may be trained using the data obtained earlier from the automation system, observing which of the neighbor cells were (substantially) impacted by the previous parameter changes.
[0046] [0046] The shown phases may be continuously repeated so that continuous performance optimization is provided.
[0047] [0047] Fig. 2 shows an apparatus 20 according to an embodiment. The apparatus 20 is for example a general-purpose computer or server or some other electronic data processing apparatus. The apparatus 20 can be used for implementing embodiments of the invention. That is, with suitable configuration the apparatus 20 is suited for operating for example as the automation system 111 of foregoing disclosure.
[0048] [0048] The general structure of the apparatus 20 comprises a processor 21, and a memory 22 coupled to the processor 21. The apparatus 20 further comprises software 23 stored in the memory 22 and operable to be loaded into and executed in the processor 21. The software 23 may comprise one or more software modules and can be in the form of a computer program product. Further, the apparatus 20 O comprises a communication interface 25 coupled to the processor 21. N [0049] The processor 21 may comprise, e.g., a central processing unit 3 (CPU), a microprocessor, a digital signal processor (DSP), a graphics processing S unit, or the like. Fig. 2 shows one processor 21, but the apparatus 20 may comprise E a plurality of processors. O [0050] The memory 22 may be for example a non-volatile or a volatile LO memory, such as a read-only memory (ROM), a programmable read-only memory > (PROM), erasable programmable read-only memory (EPROM), a random-access memory (RAM), a flash memory, a data disk, an optical storage, a magnetic storage, a smart card, or the like. The apparatus 20 may comprise a plurality of memories. 7
[0051] [0051] The communication interface 25 may comprise communication modules that implement data transmission to and from the apparatus 20. The communication modules may comprise, e.g., a wireless or a wired interface module. The wireless interface may comprise such as a WLAN, Bluetooth, infrared (IR), radio frequency identification (RF ID), GSM/GPRS, CDMA, WCDMA, LTE (Long Term Evolution) or 5G radio module. The wired interface may comprise such as Ethernet or universal serial bus (USB), for example. Further the apparatus 20 may comprise a user interface (not shown) for providing interaction with a user of the apparatus. The user interface may comprise a display and a keyboard, for example. The user interaction may be implemented through the communication interface 25, too.
[0052] [0052] A skilled person appreciates that in addition to the elements shown in Fig. 2, the apparatus 20 may comprise other elements, such as displays, as well as additional circuitry such as memory chips, application-specific integrated circuits (ASIC), other processing circuitry for specific purposes and the like. Further, it is noted that only one apparatus is shown in Fig. 2, but the embodiments of the invention may equally be implemented in a cluster of shown apparatuses.
[0053] [0053] Fig. 3 shows a flow diagram illustrating example methods according to certain embodiments. The methods may be implemented in the automation system 111 of Fig. 1 and/or in the apparatus 20 of Fig. 2. The methods are implemented in a computer and do not require human interaction unless otherwise expressly stated. It is to be noted that the methods may however provide output that may be further processed by humans and/or the methods may require user input to start. Different phases shown in Fig. 3 may be combined with each other and the order of phases may be changed expect where otherwise explicitly defined.
[0056] [0056] Phase 302: Certain parameter changes are blocked. The parameter that are blocked may depend on the first parameter and the effects the first 8 parameter may have and/or the first cell and surrounding cells.
[0057] [0057] The parameter changes may be blocked in a geographically limited area. In various embodiments, blocking the parameter changes comprises one or more of the following: blocking changes of at least one second parameter in the first cell, blocking parameter changes in at least one second cell, blocking changes of the first parameter in at least one second cell, blocking parameter changes in at least one neighbor cell of the first cell. In case changes are blocked in neighbor cells, the neighbor cells may be selected based on distance between the first cell and the neighbor cells, and antenna directions of the first cell and the neighbor cells. Parameter changes may be blocked for example in 2, 3, 4, 5, 7, 10 or 15 neighbor cells of the first cell or in some other number of neighbor cells.
[0058] [0058] Phase 303: A first set of performance indicator data is gathered over a first time period. The first time period may be for example one of: 1-2 days, 3-5 days, a week, two weeks, a month.
[0059] [0059] Phase 304: After completing gathering the first set of performance indicator data, a chance in value of the first parameter is made.
[0060] [0060] Phase 305: A second set of performance indicator data is gathered over a second time period after making the change. The second time period may be for example one of: 1-2 days, 3-5 days, a week, two weeks, a month. In an embodiment the second time period is dynamically variable while the first time period may be fixed. The second time period may be varied for example by gathering the second set of performance indicator data until statistically reliable data is obtained for the determining of difference between the first set of performance indicator data and the second set of performance indicator data. In this way the second time period O adapts to different network conditions and to different types of changes.
[0062] [0062] Fig. 4 illustrates parameter grouping for the purpose of blocking certain parameter changes. Fig. 4 shows three parameters 401: parameter 1, 9 parameter 2 and parameter 3, and three performance indicators 402: KPI 1, KPI 2, and KPI 3. Parameter 1 has substantial impact on KPI 1, parameter 2 has substantial impact on KPI 1 and KPI 2, and parameter 3 has substantial impact on KPI 2 and KPI 3.
[0063] [0063] Based on the substantial impacts of KPIs, the parameters 401 are divided into (possibly overlapping) groups. In the example of Fig. 4, parameter 1 and parameter 2 belong to group 405, parameter 2 and parameter 3 belong to group 406, and parameter 1, parameter 2 and parameter 3 belong to group 407. In an embodiment, when certain parameter is being changed, changes in other parameters in the same group are blocked to avoid interfering effects caused by other changes. That is, if parameter 1 is being changed, parameter 2 is blocked, but parameter 3 can be freely changed as parameters 1 and 3 do not have substantial impact on same KPIs.
[0064] [0064] It is to be noted that parameters may have minor effects on different KPIs, but they are not of relevance here. E.g. adjusting handover parameters to reduce the handover failure rates (RLF/HOF being the KPI to monitor) can somewhat impact also the UE throughputs as there are fewer interruptions. But the UE throughput is not a substantially impacted KPI, so other parameter changes impacting UE throughput, but not RLF/HOF rates, could be evaluated on parallel. That is, parameters affecting UE throughput do not need to be blocked while adjusting handover parameters.
[0065] [0065] The information about which KPIs are affected by certain parameter may be based on historical data concerning correlation between parameter and KPI values.
[0068] [0068] In an embodiment, even though neighborhoods 510 and 511 overlap,
[0069] [0069] In an embodiment, gathering the first and/or the second set of performance indicator data comprises gathering the data until statistically reliable performance sample has been obtained or at least a predefined time period has elapsed. That is, the first and second time periods may dynamically vary, for example depending on how stable the measured performance indicators during the gathering period are. In particular, the second set of performance indicator data may be gathered only as long as necessary to obtain statistically reliable difference compared to the first set of performance indicator data. This may mean, for example, that the length of the data collection for the second set depends on the performance difference observed so far while gathering the data for the second set. If the observed performance difference is large, a shorter time period may be sufficient to observe it reliably, whereas for a more subtle difference a longer gathering period is likely needed. Furthermore, the flexibility in gathering the second set may be asymmetric in the sense that if the performance appears to have decreased, less evidence (and thus shorter time period and lower reliability) is needed for deciding to revert the change than if the performance appears to have improved. In one example, if the observed performance after a short period of gathering the second set is substantially worse than the performance observed in the first set, the gathering is stopped early, and the parameter change reverted to limit the adverse effect on the network performance and user experience. In one example O embodiment, there could be one or more thresholds for performance impact N associated with specific gathering periods, so that e.g. if the performance in terms of 3 the performance indicator(s) is decreased by more than 20% after 3 days, or by S more than 10% after 7 days, the gathering is stopped early, otherwise it runs until 14 E days (this is one concrete example, other thresholds and time periods may be used 3 as well). O [0070] Additionally or alternatively, the sample may be gathered in smaller > non-contiguous pieces so that data is not gathered e.g. during periods of interruptions in service, if any. That is, several data gathering periods may be combined to avoid starting over the gathering period in case of interruptions. In this 11 way the time period needed for gathering the data may adapt to different operating environments and conditions.
[0071] [0071] In an embodiment, the second set of performance indicator data of previous change is used as the first set of performance indicator data in case the previous change was kept. In an embodiment, the first set of performance indicator data may be reused for evaluating more than one change. For example, if previous change is reverted the first set of performance indicator data of the previous change may be used also for the following change.
[0072] [0072] In an embodiment, the performance indicator data may be normalized by certain variables such as cell load, weekday, time of year etc. In this way one may achieve shorter data gathering periods, as the performance variations explainable by the known seasonal or trend changes can be accounted for and the evaluation is done considering the residual performance changes after these known factors.
[0073] [0073] In an embodiment, the first parameter is changed in two or more interacting cells at the same time. For example, a parameter related to handover may be suitable for this.
[0074] [0074] Without in any way limiting the scope, interpretation, or application of the claims appearing below, a technical effect of one or more of the example embodiments disclosed herein is an improved or at least alternative method for performance optimization in communication networks.
[0075] [0075] Another technical effect of one or more of the example embodiments disclosed herein is that by automatically making changes and evaluating their impact one achieves ability make changes in stepwise manner as human interaction is not required. That is, it is possible to make small changes in network devices and to O check suitability of the changes before proceeding to larger scale changes.
[0078] [0078] If desired, the different functions discussed herein may be performed in a different order and/or concurrently with each other. Furthermore, if desired, one 12 or more of the before-described functions may be optional or may be combined.
[0079] [0079] Although various aspects of the invention are set out in the independent claims, other aspects of the invention comprise other combinations of features from the described embodiments and/or the dependent claims with the features of the independent claims, and not solely the combinations explicitly set out in the claims.
[0080] [0080] It is also noted herein that while the foregoing describes example embodiments of the invention, these descriptions should not be viewed in a limiting sense. Rather, there are several variations and modifications, which may be made without departing from the scope of the present invention as defined in the appended claims.
oOO
N © <QOO
I a aLOOO
LO oO
N 13

权利要求:
Claims (15)
[1] 1. A computer implemented method of performance optimization in a communication network, the method comprising optimizing of a first parameter of a first cell of the communication network; the optimization comprising gathering (303) a first set of performance indicator data over a first time period; making (304) a chance in value of the first parameter after the first time period; gathering (305) a second set of performance indicator data over a second time period after making the change; determining (306) difference between the first set of performance indicator data and the second set of performance indicator data; and based on the difference, performing one of: keeping the change (310), reverting the change (311), and making a further change (312) in the same direction.
[2] 2. The method of claim 1, wherein the second time period is dynamically variable.
[3] 3. The method of claim 2, wherein the second time period is varied by gathering the second set of performance indicator data until statistically reliable data is obtained for the determining of difference between the first set of performance indicator data and the second set of performance indicator data.
2 N
[4] 4. The method of any preceding claim, further comprising blocking certain 3 parameter changes over the first and second time periods. 3 z
[5] 5. The method of claim 4, wherein parameter changes are blocked in a geographically limited area.
O 3 I
[6] 6. The method of any one of claims 4-5, wherein blocking parameter changes comprises blocking changes of at least one second parameter in the first cell. 14
[7] 7. The method of any one of claims 4-6, wherein blocking parameter changes comprises blocking parameter changes in at least one second cell.
[8] 8. The method of any one of claims 4-7, wherein blocking parameter changes comprises blocking changes of the first parameter in at least one second cell.
[9] 9. The method of any one of claims 4-8, wherein blocking parameter changes comprises blocking parameter changes in at least one neighbor cell of the first cell.
[10] 10. The method of claim 9, wherein the at least one neighbor cell is selected based on distance between the first cell and the neighbor cells, and antenna directions of the first cell and the neighbor cells.
[11] 11. The method of claim 9 or 10, wherein blocking parameter changes comprises blocking parameter changes in 3-7 neighbor cells of the first cell.
[12] 12. The method of any preceding claim, wherein the first time period and/or the second time period is selected from group of: 1-2 days, 3-5 days, a week, two weeks, a month.
[13] 13. The method of any preceding claim, wherein the first parameter is antenna tilt parameter, parameter related to beamforming pattern or parameter related to handover. O
[14] 14. An apparatus (20, 111) comprising N a processor (21), and 3 a memory (22) including computer program code; the memory and the S computer program code configured to, with the processor, cause the apparatus to E perform the method of any one of claims 1-13.
LO
O O
[15] 15. A computer program comprising computer executable program code (23) > which when executed by a processor causes an apparatus to perform the method of any one of claims 1-13.

类似技术:

---

公开号 | 公开日 | 专利标题

---

US9439081B1|2016-09-06|Systems and methods for network performance forecasting

---

EP3539316B1|2021-04-14|Prediction of performance indicators in cellular networks

---

US9503919B2|2016-11-22|Wireless communication network using multiple key performance indicators and deviations therefrom

---

EP2750432A1|2014-07-02|Method and system for predicting the channel usage

---

EP2429228A1|2012-03-14|Network management system, wireless coverage control method, and wireless coverage control program

---

CN105744553B|2021-05-04|Network association analysis method and device

---

CN107171831B|2020-09-11|Network deployment method and device

---

CN107204894B|2020-07-07|Method and device for monitoring network service quality

---

EP2934037B1|2016-04-13|Technique for Evaluation of a Parameter Adjustment in a Mobile Communications Network

---

US20160014617A1|2016-01-14|Wireless Communication Network Performance and Robustness Tuning and Optimization Using Deviations in Multiple Key Performance Indicators

---

CN102487523B|2014-12-10|User compliant analysis method and device

---

CN103841602B|2017-02-22|Neighborhood configuration method and system

---

CN105471663A|2016-04-06|Abnormal network detection method, abnormal network detection device, communication network detection device and communication network detection system

---

EP3136650A1|2017-03-01|Method and system for optimizing network parameters to improve customer satisfaction of network content

---

EP2695328B1|2019-10-09|Optimization of network configuration

---

EP2681967B1|2015-07-15|Resource managing method, resource management device and apparatus for supporting operation of a radio communication network

---

EP2510650B1|2019-04-03|A method of and an operating support system for providing performance management in a mobile telecommunications system

---

CN105472660B|2019-10-15|A kind of load-balancing method, the network equipment and system

---

CN102883332A|2013-01-16|Method and device for determining base station site

---

FI129200B|2021-09-15|Automatic performance optimization in communication networks

---

CN102158886B|2015-09-09|The method and apparatus of network operation maintenance is carried out by user awareness information

---

Godinho et al.2019|Cloud-based cellular network planning system: Proof-of-concept implementation for GSM in AWS

---

EP3163932A1|2017-05-03|Interference coordination method and device

---

CN104918270A|2015-09-16|Wireless network parameter obtaining method, apparatus and terminal

---

CN105630503A|2016-06-01|Selecting method for mobile device application and development based on operating records of user

同族专利:

---

公开号 | 公开日

---

FI129200B|2021-09-15|

引用文献:

---

公开号 | 申请日 | 公开日 | 申请人 | 专利标题

---

---

法律状态:
2021-09-15| FG| Patent granted|Ref document number: 129200 Country of ref document: FI Kind code of ref document: B |

优先权:

---

申请号 | 申请日 | 专利标题

---

FI20195665A|FI129200B|2019-08-06|2019-08-06|Automatic performance optimization in communication networks|FI20195665A| FI129200B|2019-08-06|2019-08-06|Automatic performance optimization in communication networks|