Search

EP-4541065-B1 - METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR USE IN EVALUATING THE COVERAGE PROVIDED BY BASE STATIONS OF A CELLULAR RADIO ACCESS NETWORK

EP4541065B1EP 4541065 B1EP4541065 B1EP 4541065B1EP-4541065-B1

Inventors

  • MOHAMED, Ayman Gaber Mohamed
  • ZAKI, Mohamed Mahmoud Mohamed

Dates

Publication Date
20260506
Application Date
20230614

Claims (15)

  1. A method for use in evaluating the coverage provided by base stations (104a, 104b) of a cellular radio access network (102), comprising: receiving, for cells provided by base stations (104a, 104b) of a radio access network (102), data representative of a connection metric reported by each base station (104a, 104b) for user equipment (106a-i) having an established connection to one of the base stations (104a, 104b), the connection metric being collected over an operation period of the radio access network (102) for all connections, the collected connection metric data for each base station (104a, 104b) being indicative of a distribution of connections throughout the coverage area for that base station (104a, 104b); generating, for each cell, data representative of a normalised frequency distribution of the connection metric between the base station (104a, 104b) and the user equipment (106a-i) connected to the base station (104a, 104b) over the operation period, the normalised frequency distribution representing a probability density function for the connection metric; determining, for each cell, a set of connection diagnostic features from the probability density function of the connection metric, the connection diagnostic features being selected to indicate characteristics of the distribution of the connection metric in the coverage area provided by the cells; characterized by further comprising: using an unsupervised machine learning algorithm, clustering cells based on the determined connection diagnostic features for the cells into clusters of similar distributions of the connection metric, the data representative of the cell clusters being evaluated to determine diagnostics for the adequacy of the coverage provided by the cells in the cell cluster; and determining, based on the evaluation of the cell clusters, one or more suggested changes to the configuration of base stations (104a, 104b) providing the radio access network (102) to improve the adequacy of the coverage of the radio access network (102).
  2. The method of claim 1, further comprising: receiving data representative of one or more further different connection metrics, each connection metric being indicative of a different quality of the connections as they are distributed throughout the coverage area for a base station (104a, 104b); generating a normalized frequency distribution for each connection metric for each cell, representative of a probability density function for that metric; determining, for each cell, a set of connection diagnostic features from the probability density function for each connection metric; wherein the clustering of the cells using an unsupervised machine learning algorithm is based on the determined connection diagnostic features based on each connection metric.
  3. The method of claim 1 or 2, wherein the or each connection metric is representative of one of: a propagation delay for signals received at the base stations (104a, 104b) from user equipment (106a-1) having an established connection to one of the base stations (104a, 104b); a path loss for signals received at the base stations (104a, 104b) from user equipment (106a-i) having an established connection to one of the base stations (104a, 104b); an available power headroom for connections to user equipment (106a-i) having an established connection to one of the base stations (104a, 104b); a transmission power for connections to user equipment (106a-1) having an established connection to one of the base stations (104a, 104b); a signal to noise ratio for connections to user equipment (106a-1) having an established connection to one of the base stations (104a, 104b); an interference for connections to user equipment (106a-i) having an established connection to one of the base stations (104a, 104b).
  4. The method of claim 3, further comprising: if data representative of a propagation delay is received, converting, for each cell provided by the base stations (104a, 104b), the data representative of a propagation delay to a distance between the base station (104a, 104b) and the connected user equipment (106a-i); generating, for each cell, data representative of a normalised frequency distribution of the connection distance between the base station (104a, 104b) and the user equipment (106a-i) connected to the base station (104a, 104b) over the operation period, the normalised frequency distribution representing a probability density function for the connection distance to user equipment (106a-1) in the cell; optionally wherein the data representative of a propagation delay comprises a timing advance reported by the base stations (104a, 104b) for user equipment (106a-i) connected to the base station (104a, 104b).
  5. The method of any preceding claim, wherein the received data representative of a connection metric is binned, and wherein generating the normalised frequency distribution comprises: randomly allocating each received connection metric data to a non-binned value within the range of its respective bin.
  6. The method of any preceding claim, wherein determining, for each cell, a set of connection diagnostic features from the probability density function of the connection metric comprises determining one or more of: determining, from the probability density function, a modal connection metric value at which a maximum occurs in the probability density function; determining, from the probability density function, one or more connection metric values within which a connection is likely to occur to a given probability from the probability density function; determining, from the probability density function, a median connection metric value at which connection is likely to occur with a 50% probability; determining, from the probability density function, an overspill connection metric value as a difference between the threshold connection metric value within which connection is likely to occur to a given threshold probability and a maximum connection metric value within which connection is likely to occur to a maximum probability; determining an overspill ratio as the ratio of the overspill connection metric value to the threshold connection metric value; optionally wherein the threshold probability is 90% and wherein the maximum probability is 99%.
  7. The method of any preceding claim, wherein one or more of the connection diagnostic features determined from the probability density function of the connection metric is a sufficient statistic summarising all of the information in the data representative of the connection metric for the signals received at the base stations about a population parameter the statistic represents.
  8. The method of any preceding claim, wherein the data representative of the connection metric is received for multiple different bands served in each cell, and wherein a probability density function and set of connection diagnostic features are generated for each band separately, the cells being clustered for each band served by that cell separately, based on the sets of connection diagnostic features generated for each band; optionally further comprising comparing the cell clusters for each band served by a cell to identify cells having different coverage characteristics for different bands in the same cell, indicating that the base station may be configured differently for different bands in the same cell; optionally further comprising determining an overlap between the probability density functions generated for each band in the same cell, and determining one or more suggested changes to the configuration of the base station to optimise load balancing between the different bands in the same cell; optionally wherein the data representative of a connection metric is received for multiple different bands served in each cell across different Radio Access Technologies, RATs, supported by the base stations (104a, 104b), the method optionally further comprising determining an overlap between the probability density functions generated for each band of different Radio Access Technologies in the same cell to identify cells having different coverage characteristics for different Radio Access Technologies in the same cell, indicating that user equipment in the cell may experience connection problems with falling back to different Radio Access Technologies.
  9. The method of any preceding claim, further comprising: receiving topological data including location information for the base stations (104a, 104b) in the radio access network (102); determining, based on the topological data, for each cell, one or more intersite distance features based on the distance between the base station (104a, 104b) providing the cell, and one or more other base stations (104a, 104b) located in the cell; wherein clustering cells is further based on the determined intersite distance features for each cell.
  10. The method of any preceding claim, further comprising labelling a cell or a cell clusters with one or more diagnostic labels based on connection diagnostic features for cells in each cell cluster; optionally, when dependent on claim 3, further comprising labelling a cell as a potential blocked cell based on one or more of: the maximum connection distance being less than a threshold proportion of the minimum intersite distance; the overspill ratio being less than a threshold value; the maximum distance being less than a threshold value; optionally, when dependent on claim 3, further comprising labelling a cell as potentially being poorly located, requiring an additional neighbouring cell site, or requiring antenna realignment based on one or more of: an overspill ratio being greater than a threshold value; a modal distance or a median distance being greater than a threshold value; a maximum distance being greater than a threshold value.
  11. The method of any preceding claim, further comprising evaluating the data representative of the cell clusters to determine diagnostics for the adequacy of the coverage provided by the cells in the cell cluster, the evaluating comprising one or more of: using a trained classifier to apply diagnostic labels to the cells or the cell cluster based on at least the connection diagnostic features for the cells; determining a diagnostic score representative of the adequacy of the coverage provided by the cells.
  12. The method of any preceding claim, further comprising displaying the cells of the cell clusters as an overlay on a map.
  13. The method of any preceding claim, further comprising making one or more of the suggested changes to the configuration of base stations (104a, 104b) providing the radio access network (102) to improve the adequacy of the coverage of the radio access network (102); and comparing a probability density function for the affected cells before and after making the suggested changes to assess an improvement in the adequacy of the coverage of the radio access network (102).
  14. A computing apparatus (108) comprising: a processor; and a memory storing instructions that, when executed by the processor, configure the apparatus (108) to perform the method of any preceding claim.
  15. A computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to perform the method of any of claims 1 to 13.

Description

TECHNICAL FIELD The present application relates to inspecting coverage in a cellular radio access network to assess the adequacy of the coverage provided by the radio access network and to suggest one or more changes to improve the adequacy of the coverage. In particular, the present application provides methods, apparatuses and computer program products for use in evaluating the coverage provided by base stations of a cellular radio access network. BACKGROUND To provide communications to a variety of user equipment, such as smartphones, dispersed throughout a geographic region, mobile network operators assemble Radio Access Networks (RAN) of base stations such as eNodeBs. Each base station provides one or more cells of a radio communications system within which wireless radio connections can be established between the base stations and user equipment. Each base station may support voice and data communication by one or more Radio Access Technologies (RATs), such as UMTS, LTE and 5G NR. The cells provided by each base station are roughly designated as land areas of coverage arranged as sectors emanating from radio antennas arranged at the base station. User equipment located in the cells in which coverage is provided can gain network access by establishing a radio connection with the base station providing the cell. The Radio Access Network can provide access through a Core Network to other networks such as the public Internet, and can allow voice and data communication with other user equipment in the Radio Access Network. The Radio Access Network requires careful planning to seek to provide users of user equipment subscribed to the network with coverage that is adequate to meet the overall demand for voice and data communications in the geographic area. Network planning requires the provision of base stations at selected sites located in the geographic region, and also consideration given to the configuration of the base station antenna in terms of pointing direction, tilt and power, as well as the cellular bands and Radio Access Technologies provided. The planning must take into account anticipated or actual demand, topography of the geographic region in terms of natural and man made features, fading and interference, and other factors. The planning must seek to provide to users a connection that meets certain quality of service levels in terms of data rate, delay and connection stability. Network planning that leads to under-provisioning of a radio access network that provides coverage insufficient to meet demand can lead to poor connection stability and data rates below an expected service level, and even signal voids or black spots, leading to a poor user experience. Similarly, network planning that leads to over-provisioning can lead to a sub-optimal deployment of resources. Network planning using a manual review of the coverage map and signal strength information takes into account only the ability of user equipment within the geographic region to establish a connection to a base station, and does not take into account network traffic or other considerations. Field investigations and error reports may be used to build an ad hoc picture of the actual experience of users of user equipment in the field. However, this is time consuming and does not readily enable the optimisation of the network to meet the needs of the user. Mechanisms to aid the identification of underprovisioning or sub-optimal network planning can greatly facilitate the improvement of the network to meet user demand. Publication R. Cháves-Santiago et al "Enhanced efficiency and frequency assignment by optimizing the base stations location in a mobile radio network", Wireless Networks (4 January 2007) discloses discretizing traffic such that the optimization of vase station locations can be represented through vector quantization. Publication R. Cháves-Santiago et al "Enhanced efficiency and frequency assignment by optimizing the base stations location in a mobile radio network", Wireless Networks (4 January 2007) discloses discretizing traffic such that the optimization of vase station locations can be represented through vector quantization. Publication US10542330B2 discloses a method for automatic adaptive network planning, wherein for each location and for each site a likelihood of the network coverage goals being realized is calculated using a generated wireless network coverage map. It is in the above context that the present disclosure has been devised. BRIEF SUMMARY The invention is defined by the independent claims. Advantageous embodiments of the invention are given in the sub-claims. Viewed from one aspect, the present disclosure provides a method for use in evaluating the coverage provided by base stations of a cellular radio access network, including receiving, for cells provided by base stations of a radio access network, data representative of a connection metric reported by each base station for user equipment having a