Unified Coverage System

Abstract

A method and system for identifying Radio Access Network (RAN) coverage at a geographic location includes generating a grid layer of real-time RAN coverage based on key performance indicators (KPIs); generating a predicted RAN coverage grid layer; generating a viewport representation corresponding to the geographic locations supported by the RAN; overlaying the real-time RAN coverage grid layer, the predicted RAN coverage grid layer, and the viewport representation onto a unified coverage representation; and determining RAN availability at the selected geographic location based on the unified coverage representation.

Description

[Technical field]

[0001] Priority claims and cross references This application claims priority to U.S. Non-provisional Application No. 17 / 647,161, filed January 5, 2022, which is incorporated by reference in its entirety herein. [Background technology]

[0002] A cellular network is a mobile telecommunications system in which mobile devices (e.g., mobile phone devices) communicate by radio waves through local antennas at cellular base stations (e.g., cell towers). The coverage area served is divided into small geographic areas called "cells." Each cell is equipped with a separate low-power multi-channel transceiver and antenna at the cell tower. All mobile devices within a cell communicate through that cell's antenna on multiple and separate frequency channels assigned by the base station from a common pool of frequencies used by the cellular network.

[0003] The Radio Access Network (RAN) is part of a mobile telecommunications system. The RAN provides radio access technology. Conceptually, the RAN resides between devices such as mobile phones, computers, or any remote control machine and provides their connectivity to the Core Network (CN). Depending on the standard, mobile phones and other wirelessly connected devices are variously known as User Equipment (UE), terminal equipment, Mobile Station (MS), etc. [Brief description of the drawings]

[0004] Aspects of the present disclosure are best understood from the following detailed description when read in conjunction with the accompanying drawings, in which: In accordance with standard industry practice, various features have not been drawn to scale, and in fact, dimensions of various features have been arbitrarily increased or decreased for clarity of illustration.

[0005] [Figure 1] 1 is a diagrammatic representation of a radio access network (RAN) in accordance with some embodiments. [Diagram 2] FIG. 2 illustrates a data flow diagram of a Unified Coverage Module (UCM) in accordance with some embodiments. [Diagram 3] 1 is a flow diagram representation of a Unified Coverage Algorithm (UCA), according to some embodiments. [Figure 4] 1 is a visual representation of a viewport according to some embodiments. [Diagram 5] 1 is a visual representation of a viewport according to some embodiments. [Figure 6A] 1 is a flow diagram representation of a Unified Coverage Algorithm (UCA), according to some embodiments. [Figure 6B] 1 is a flow diagram representation of a Unified Coverage Algorithm (UCA), according to some embodiments. [Figure 7] 1 is a visual representation of a Graphical User Interface (GUI) according to some embodiments. [Figure 8] FIG. 1 is a high-level functional block diagram of a processor-based system according to some embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0006] The following disclosure provides many different embodiments or examples for implementing various features of the provided subject matter. To simplify the disclosure, specific examples of components, values, operations, materials, arrangements, etc. are described below. Of course, these are merely examples and are not intended to be limiting. Other components, values, operations, materials, arrangements, etc. are contemplated. For example, forming a first feature on or above a second feature in the following description includes embodiments in which the first feature and the second feature are formed in direct contact, and also includes embodiments in which an additional feature is formed between the first feature and the second feature such that the first feature and the second feature are not in direct contact. In addition, the present disclosure repeats reference numbers and / or reference characters in various examples. This repetition is for the purposes of brevity and clarity and does not in itself dictate a relationship between the various embodiments and / or configurations described.

[0007] Additionally, spatially relative terms such as "below," "below," "at the bottom," "above," and "on top" are used herein to describe the relationship of one element or feature to another element or feature as shown in the figures for ease of description. The spatially relative terms are intended to encompass different orientations of the device during use or operation in addition to the orientation shown in the figures. The device may be otherwise oriented (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.

[0008] In some embodiments, one or more computer systems are configured to perform a particular operation or behavior by installing software, firmware, hardware, or combinations thereof on the system that cause the system to perform the operation during operation. In some embodiments, one or more computer programs are configured to perform a particular operation or behavior when executed by a data processing device by including instructions that cause the device to perform the operation. In some embodiments, a method for identifying Radio Access Network (RAN) coverage at a geographic location includes generating a grid layer of RAN coverage in real time based on Key Performance Indicators (KPIs). In some embodiments, a grid layer of predicted RAN coverage is generated. In some embodiments, a viewpoint representation corresponding to the geographic location supported by the RAN is generated. In some embodiments, the real-time RAN coverage grid layer, the predicted RAN coverage grid layer, and the viewport representation into a unified coverage management representation are overlaid. In some embodiments, the availability of RAN at the selected geographic location is determined based on the unified coverage representation.

[0009] In some embodiments, the method includes displaying a unified coverage representation. In some embodiments, the method includes identifying a RAN quality corresponding to a particular geographic location. In some embodiments, the method includes notifying a RAN service provider of each geographic location with a RAN quality below a predefined threshold. In some embodiments, displaying the unified coverage representation further includes displaying a RAN signal quality corresponding to the selected geographic location. In some embodiments, the method includes displaying the RAN quality and displaying a user equipment (UE) verification layer included in the real-time RAN coverage grid layer. In some embodiments, the KPI is a multi-KPI and includes a first KPI of Reference Signal Received Power (RSRP), which is a measurement of a received power level at the RAN. In some embodiments, a second KPI is a Signal to Interference and Noise Ratio (SINR), which is a ratio of a signal of interest to interference and noise. In some embodiments, the method includes receiving Radio Frequency (RF) drive test data corresponding to geographic locations supported by the RAN. In some embodiments, the method includes receiving geographic site data including topographical parameters, electrical parameters, and logical parameters. In some embodiments, the method includes receiving projection detail data that converts geographic coordinates to latitude and longitude. Implementations of the described techniques may include hardware, methods or processes, or computer software on a computer-accessible medium.

[0010] In some embodiments, the unified coverage algorithm generates an actual RAN visualization from a superimposed layer of actual and planned RAN coverage. In some embodiments, the generated superimposed layer generates an actual network visualization based on coverage KPIs. The network area optimization generates improved RAN communication services by identifying geographical areas of reduced RAN coverage and informing the service provider of the geographical areas of reduced RAN coverage. In this way, the service provider can optimize the RAN coverage and expand the RAN coverage area.

[0011] In other approaches, RAN service providers are unaware of geographic areas of reduced RAN coverage due to inaccurate or insufficient data. These other approaches result in suboptimal RAN coverage below a predefined threshold, customer dissatisfaction, and loss of business. In some embodiments, the geographic areas identified with sub-threshold RAN coverage are identified by identifying gaps in RAN coverage. In some embodiments, RAN availability is determined by a centralized coverage algorithm. In some embodiments, RAN quality is identified for an entire geographic area or for a specific geographic area.

[0012] FIG. 1 is a diagrammatic representation of a Unified Coverage System (UCS) 100, according to some embodiments.

[0013] The UCS 100 includes a core network 102 communicatively connected to a RAN 104 via a backhaul 106 communicatively connected to base stations 108A and 108B (hereinafter base stations 108), and antennas 110 wirelessly connected to UEs 112 located in a geographic coverage area 114. The core network 102 includes one or more service providers 116, a forecasting and KPI server 118, and a centralized coverage module (UCM) 120.

[0014] The core network 102 (also known as a backbone) is the portion of a computer network that interconnects networks and provides a pathway for exchanging information between different Local Area Networks (LANs) or sub-networks. In some embodiments, the core network 102 ties together diverse networks, whether in the same building, in different buildings in a campus environment, or across a large geographic area.

[0015] In some embodiments, the RAN 104 is a Global System for Mobile Communications (GSM) RAN, a GSM / EDGE RAN, a Universal Mobile Telecommunications System (UMTS) RAN (UTRAN), an Evolved Universal Terrestrial Radio Access Network (E-UTRAN), an Open RAN (O-RAN), or a Cloud-RAN (C-RAN). The RAN 104 resides between user equipment 112 (e.g., a mobile phone, a computer, or any remote control machine) and the core network 102. The RAN 104 is denoted as a C-RAN for purposes of simplified representation and discussion. In some embodiments, a Base Band Unit (BBU) replaces the C-RAN.

[0016] In traditional distributed cellular networks, the equipment at the bottom and top of the base station at the cell site is the BBU. The BBU is a radio device that links the UE to the core network and processes billions of bits of information per hour. BBUs are traditionally placed in an enclosure or shelter located at the bottom of the base station. In contrast, C-RAN uses the large signal carrying capacity of optical fiber to concentrate many BBUs in dedicated pool locations or base stations. This reduces the amount of equipment required at the base station and provides many other benefits, including less latency.

[0017] In a hierarchical telecommunications network, the backhaul section 106 of the UCS 100 comprises an intermediate link between the core network 102 and the RAN 104. The two main methods in mobile backhaul implementations are fiber-based backhaul and point-to-point wireless backhaul. Other methods such as copper-based wired, satellite communication, and point-to-multipoint wireless technologies are being phased out as capacity and latency requirements become more stringent in 4G and 5G networks. Backhaul generally refers to the side of the network that communicates with the global Internet. The UEs 112 that communicate with the base stations 108 constitute a local sub-network. The connection between the base stations 108 and the UEs 112 starts from the backhaul 106 that is connected to the core network 102. In some embodiments, the backhaul 106 includes wired, optical fiber, and wireless components. The wireless section includes mesh network topologies and edge network topologies that use microwave bands and use high-capacity wireless channels to get packets to microwave or fiber links.

[0018] In some embodiments, the base station 108 is a lattice or freestanding tower, a mesh tower, a monopole tower, and a hidden tower (e.g., a tower designed to resemble a tree, a cactus, a water tower, a sign, a light pole, and other types of structures). In some embodiments, the base station 108 is a cellular-enabled mobile device site where antennas and electronic communication equipment are typically located on a radio mast, tower, or other structure that is elevated to create a cell (or adjacent cells) in the network. The elevated structure typically accommodates an antenna 110, as well as one or more of a transmitter / receiver transceiver, a digital signal processor, control electronics, a Remote Radio Head (RRH), a primary and backup power source, and a shelter. Base stations are known by other names, such as base transceiver station, cellular phone mast, or cell tower. In some embodiments, the base station is replaced by other edge devices configured to wirelessly communicate with UEs. The edge devices provide an entry point into a service provider core network, such as the core network 102. Examples include routers, routing switches, Integrated Access Devices (IADs), multiplexers, and various Metropolitan Area Network (MAN) and Wide Area Network (WAN) access devices.

[0019] In at least one embodiment, antenna 110 is a sector-shaped antenna. In some embodiments, antenna 110 is a type of directional microwave antenna with a sector-shaped radiation pattern. In some embodiments, the angle of the sector of the arc is a 60°, 90°, or 120° design with a few extra degrees to ensure overlap. Additionally, sector-shaped antennas are mounted in multiples when wider or all-around coverage is desired. In some embodiments, antenna 110 is a rectangular antenna, sometimes called a panel antenna or radio antenna, used to transmit and receive radio waves or data between mobile devices or other devices and base stations. In some embodiments, antenna 110 is a circular antenna. In some embodiments, antenna 110 operates at microwave or ultra-high frequency (UHF) frequencies (300 MHz to 3 GHz). In other implementations, antenna 110 is selected for its size and directional characteristics.

[0020] In some embodiments, the UE 112 is a computer or computing system. Additionally or alternatively, the UE 112 has a Liquid Crystal Display (LCD), Light-Emitting Diode (LED) or Organic Light-Emitting Diode (OLED) screen interface, such as a User Interface (UI) 822 (FIG. 8), and provides a touch screen interface with digital buttons along with a physical keyboard and digital keyboard or physical buttons. In some embodiments, the UE 112 connects to the Internet and interconnects with other devices. Additionally or alternatively, the UE 112 incorporates a built-in camera, the ability to make and receive voice and video calls, video games, and Global Positioning System (GPS) capabilities. Additionally or alternatively, the UE runs an Operating System (OS) that allows for the installation and execution of feature-specific third-party applications.In some embodiments, the UE 112 is a computer (such as a tablet computer, a notebook, a digital media player, a digital assistant, a graphing calculator, a portable game, a handheld personal computer (PC), a laptop, a Mobile Internet Device (MID), a Personal Digital Assistant (PDA), a pocket calculator, a portable media player, or an ultra-mobile PC), a mobile phone (such as a camera phone, a feature phone, a smartphone, a phablet, or the like), a digital camera (such as a digital camcorder, a digital still camera (DSC), a digital video camera (DVC), a front camera, or the like), a pager, a personal navigation device (PND), a wearable computer (such as a calculator watch, a smart watch, a head mounted display, an earpiece, or a biometric device), or a smart card.

[0021] In at least one embodiment, the geographic coverage area 114 can be of almost any shape and size. In some embodiments, the geographic coverage area 114 is a macrocell (covering 1 Km to 30 Km), a microcell (covering 200 m to 2 Km), or a picocell (covering 4 m to 200 m). In some embodiments, the geographic coverage area is circular, elliptical, or sector-shaped, although the geographic coverage area 114 can be of almost any shape or size. The geographic coverage area 114 represents the geographic area over which the antenna 110 and the UE 112 are configured to communicate. Coverage depends on several factors, such as terrain (i.e., mountains) and buildings, technology, radio frequency, and perhaps most importantly for two-way telecommunications, the sensitivity and transmission efficiency of the UE 112. Some frequencies provide better coverage of an area, while other frequencies penetrate obstacles such as city buildings better. The ability of the UE to connect to the base station depends on the strength of the signal. Coverage gaps can be caused by most things, such as faulty equipment, bad weather, animals, accidents, etc. Coverage gaps can result from the loss of one or more of the following: transmitters, receivers, transceivers, digital signal processors, control electronics, GPS receivers, primary and backup power sources, and antenna sets. Additionally or alternatively, coverage gaps exist due to areas that were not previously covered by cellular service, or areas created by the removal of cell towers, etc. In some embodiments, coverage gaps occur after service covering an area is lost for some reason. In other examples, a coverage gap is any area where there is no cell coverage service to the UE for some reason.

[0022] A service provider 116 is a company or organization that sells bandwidth or network access by providing direct Internet backbone access to Internet service providers and usually access to their Network Access Points (NAPs). Service providers are sometimes called backbone providers or Internet providers. Service providers consist of telecommunications companies, data carriers, wireless communication providers, Internet service providers, and cable television operators that offer high speed Internet access.

[0023] The Prediction and KPI Server 118 generates both predictions and live network data. The live network data (KPIs, UE / cell / Minimization оf Drive Test (MDT) traces, and crowd-sourced data) enables modeling of network traffic, hotspot identification, and wireless signal propagation. RF Drive Test is a method of measuring and evaluating the coverage, capacity, and Quality of Service (QoS) of a mobile wireless network, such as the RAN 104. The technique consists of using automated vehicles that contain mobile wireless network air interface measurement equipment that can detect and record a wide variety of physical and virtual parameters of mobile cellular services in a given geographic area. By measuring what wireless network subscribers will experience in any particular area, wireless carriers can make changes to their networks that provide better coverage and service to their customers. Drive Test requires a moving vehicle equipped with drive test measurement equipment. This equipment is typically a highly specialized electronic device that connects to a mobile transceiver by an Original Equipment Manufacturer (OEM). This ensures that the measurements are realistic and comparable to real user experiences.

[0024] The UE / cell / MDT traces collected in the Operations Support System (OSS) or via dedicated tools provide user level information to the Service Provider 116. Once geographically located, the UE / cell / MDT traces are used to enhance path loss calculations and prediction plots, and to identify and locate problem areas and traffic hotspots. The Prediction and KPI Server 118 allows the Service Provider 116 to use the UE / cell / MDT traces together with the actual network visualization from the UCM 120 for planning and optimization processes. The Prediction and KPI Server 118 generates predictions and prediction plots that combine propagation calculations and measurements.

[0025] In some embodiments, the UCM 120 identifies coverage gaps, geographic areas with no coverage, or geographic areas with substandard coverage below a predefined threshold. In some embodiments, the service provider 116 can perform coverage optimization methods such as beam tilt optimization, beam selection, etc. to optimize coverage for customer UEs, such as the UE 112. In some embodiments, the UCM 120 creates a superposition layer of actual and predicted coverage from the Prediction and KPI Server 118. In some embodiments, this superposition layer generates a visualization of the actual network for the service provider 116 based on key performance indicators (KPIs). A KPI or performance indicator is a type of performance measurement. In other approaches, information about poor quality RAN coverage areas in their networks cannot currently be provided to service providers, such as the service provider 116, due to the accuracy of their data and the method of optimization of the data.

[0026] In some embodiments, a service provider, such as service provider 116, can check the signal quality, network quality, and user verification layers (e.g., KPIs). In some embodiments, UCM 120 generates a network visualization of the coverage KPIs. In some embodiments, the overlay layer creates a centralized coverage layer that allows service provider 116 to monitor or check the signal quality, network quality, and user verification layers. In some embodiments, the centralized coverage layer includes various KPIs, such as RSRP and SINR.

[0027] RSRP is an acronym for Reference Signal Received Power, which is a measurement of the received power level in a Long Term Evolution (LTE) cell network. Average power is a measurement of the power received from a single reference signal. RSRP is the power of the LTE reference signal propagated over the full bandwidth and narrow bands. In some embodiments, the file data is in a specific file format (e.g., a grid type pattern).

[0028] SINR is a quantity used to provide a theoretical upper limit on channel capacity (or rate of information transfer) in a wireless communication system such as the RAN 104. Similar to the signal-to-noise ratio (SNR) often used in wired communication systems, SINR is defined as the power of a particular signal of interest divided by the sum of the interference power (from all other interfering signals) and the power of any background noise.

[0029] FIG. 2 is a data flow diagram of the Unified Coverage Module (UCM) 102 according to some embodiments.

[0030] The UCM 102 includes a NIFI component 202, a Spark component 204, an Hbase component 206, an HDFS component 208, a MySQL component 210, a microservices component 212, and an application component 214.

[0031] In some embodiments, a computer readable medium, such as a memory 804 of the centralized coverage processing circuit 800 (FIG. 8), includes instructions, such as instructions 806 of the centralized coverage processing circuit 800, executable by a controller, such as the processor 802 of the centralized coverage processing circuit 800, to cause the controller to perform operations. The computer readable medium 804 further includes receiving predicted coverage data from a radio access network (RAN) in operation 218. The predicted coverage data corresponds to planned radio access network coverage for a plurality of reference points in the geographical area. In operation 218, the site coverage data is received from a site coverage database. The site coverage data corresponds to geographic data for the geographical area. In operation 218, network visualization data is received. The network visualization data is based on one or more key performance indicators (KPIs). The one or more KPIs correspond to a plurality of reference points in the geographical area. Generating an overlay layer of the network visualization data and the predicted coverage data on a viewport representing the geographical area. The viewport is displayed at operation 220. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs stored on one or more computer storage devices, each configured to perform the operations of the method.

[0032] Implementations may include one or more of the following features: A computer-readable medium 804, the instructions 806 executable by the controller 802 further cause the controller 802 to perform operations including, for one or more grids in the viewport, identifying a RAN quality of the one or more grids. The instructions 806 executable by the controller 802 further cause the controller 802 to perform operations including locating corresponding grids that lack RAN ​​coverage. Implementations of the described techniques may include hardware, a method or process, or computer software on a computer-accessible medium.

[0033] The NIFI component 202 automates the flow of data between the UCM 120 and the Forecasting & KPI Server 118. The NIFI component 202 ingests data including forecast files containing raster data, database files containing color, legend mapping and real-time KPI values ​​for each grid in the map, projection files converting coordinates to latitude and longitude, database files containing geographically located real-time data such as site details and MDT. In some embodiments, the NIFI component 202 is an open source platform based on the concept of extract, transform, and load. The software design is based on a flow-based programming model and provides a set of features including the ability to run in a cluster, security using Transport Layer Security (TLS) encryption, extensibility (e.g., users can write their own software to extend its capabilities), and improved usability features such as a portal that can be used to visually view and modify behavior. The NIFI component 202 is used to schedule jobs, trigger flows, and ingest data from third-party applications such as forecast coverage raw files from the Forecasting & KPI Server 118.

[0034] In some embodiments, the prediction file contains raster data in a txt file format. The raster data contains primary input values ​​and index numbers in a grid format. Most computer images are stored in raster graphics formats or compressed varieties, including GIF, JPEG, and PNG. Raster data structures are based on tessellation of a 2D plane (usually rectangular, square-based) into cells that each contain a single value. To store the data in a file, the two-dimensional array is aligned in a row. The most common way to do this is in a row-major format, where the cells along the first (usually top) row are enumerated from left to right, immediately followed by the cells of the second row, and so on.

[0035] The Spark component 204 is an open source, unified analytics engine for large-scale data processing. It provides an interface for programming across server clusters with implicit data parallelism and fault tolerance. It is a parallel processing framework for running large-scale data analytics applications across clustered computers. It handles both batch and real-time analytics and data processing workloads.

[0036] The NIFI component 202 and Spark component 204 are deployed in the map partition 206 and perform the generation of map partition layers including actual coverage layer (e.g., site details for base stations and edge devices), predicted / planned coverage layer, user verification layer (based on UE KPI data), and actual coverage overlay (unified coverage) layer. The Spark component 204 outputs a dbf file (dBase database file) containing color and legend mapping information as well as actual KPI values ​​for each grid based on the data from the NIFI component 202.

[0037] The HBase component 208 provides a fault-tolerant way to store large amounts of sparse data (e.g., small amounts of information captured within a large collection of empty or unimportant data). The HBase component 208 is a column-oriented, non-relational database management system that runs on top of the Hadoop Distributed File System (HDFS component 210). HBase provides a fault-tolerant way to store sparse data sets that are common in many big data use cases.

[0038] The HDFS component 210 is a distributed file system that stores data on commodity machines and provides very high aggregate bandwidth across a server cluster. HDFS is utilized to store the raw prediction data in operation 222. All batched data sources are first stored in the HDFS component 210 and then processed using the Spark component 204. The Hbase component 208 also utilizes HDFS as its data storage infrastructure.

[0039] The MySQL component 212 is an open source Relational Database Management System (RDBMS). A relational database organizes data into one or more data tables where data types are related to each other, and these relationships help structure the data. SQL creates, modifies, and extracts data from the Spark component 204 in operations 224 and controls user access. The MySQL component 212 is utilized for retrieval by the Application Programming Interface (API) and to satisfy any real-time UI requirements. Aggregated and correlated data is also stored in MySQL.

[0040] A microservices component 214 deploys an application 216 as a collection of loosely coupled services. In a microservices architecture, services are fine-grained and protocols are lightweight.

[0041] The application component 216 allows a user to visualize the unified coverage layer (a combination of the predicted and actual coverage layers, FIG. 7) in operation 220 via a UI, such as UI 822 in FIG. 8. The user can visualize this unified coverage layer in real time. In some embodiments, the application component 216 interacts with the microservices 214 via an API.

[0042] The microservices component 214 fetches the centralized coverage layer data from the Hbase component 208 in operation 226, and the centralized coverage layer data is stored after being processed by the Spark component 204. The Hbase component 208 responds to the request for providing the centralized coverage layer data in operation 228. The MySQL component 212 reads the site details from the Spark component 204 in operation 224. The site details from the Spark component 204 include physical parameters, electrical parameters, logical parameters, site coverage status, and network coverage status of the base station or edge device provided by the Prediction & KPI Server 118. The HDFS component 210 stores the raw predicted coverage file from the Spark component 204 in operation 222. The Hbase 208 reads the Network Visualization (NV) samples (captured KPI data) from the Spark component 204 in operation 230. In some embodiments, the NV data is from a Prediction and KPI Server 118 that provides captured KPIs such as RSRP and SINR values.

[0043] FIG. 3 is a flow diagram representation of a Unified Coverage Algorithm (UCA) 300, according to some embodiments.

[0044] The UCA 300 includes an input detail operation 302 , a unified coverage layer generation operation 304 , and a representation operation 306 .

[0045] Input details operation 302 includes receiving input details configured for use in creating a unified coverage layer. In operation 308 of operation 302, forecast coverage raw data (e.g., raster data in txt file format) is read from the Forecasting & KPI Server 118. Flow proceeds from operation 308 to operation 310.

[0046] In operation 310 of operation 302, site details are read for base stations and edge devices, including color and legend mapping (such as viewports in FIG. 5), site coverage status, physical parameters, electrical parameters, and logical parameters. Flow proceeds from operation 310 to operation 312.

[0047] In operation 312 of operation 302, the Network Visualization (NV) data including projection details (in a prj file) is read from the Prediction & KPI Server 118. The prj file is a plain text file that describes the projection information using a coordinate system and text format. The Network Visualization data further includes KPI data such as RSRP and SINR.

[0048] In operation 302, in response to reading the input file in operation 308, operation 310, and operation 312, the prediction file including the txt file raster data is converted to a grid. Also, from the site details, a viewport 400 (FIG. 4) is identified from the site data. Furthermore, identified geo-located UE samples within the identified viewport are identified from the data extracted from the Prediction & KPI Server 116. Furthermore, the prediction file provides raster data in the form of grids 402a-402aj (FIG. 4). The viewport 400 is divided into grids 402a-402aj, each grid including a reference point 404. In some embodiments, the grids 402a-402aj are 15 square meters.

[0049] In operation 314 of operation 304, a unified coverage layer algorithm is executed for each reference point 404. The unified coverage layer algorithm begins with identifying the reference points 404 from operation 302. For each grid 402a-grid 402aj, the unified coverage layer algorithm identifies the KPI value for the grid. In some embodiments, the viewport 500 provides a representation of the KPI for each grid 502a-grid 502ax represented in a color profile (FIG. 5) and the corresponding reference point 504. In some embodiments, each color represents a grid, such as grid 502a-grid 502ax, that has a KPI above a predefined threshold.

[0050] In a non-limiting example, grids above the upper threshold 508 include a color or shading similar to the legend box 506a, such as grids 502v-502x, grids 502ad-502af, grids 502al-502an, and grids 502at-502av. In some embodiments, grids above the upper threshold 508 represent geographic locations with the highest KPI values ​​and most desirable coverage available to a RAN, such as the RAN 104. Continuing with this example, grids above the threshold 510 include a color or shading similar to the legend box 506b, such as grids 502d-502g, grids 502l-502o, grids 502s-502u, grids 502ab-502ac, and grids 502aj-502ak. In some embodiments, grids above the threshold 510 represent geographic locations with the next highest KPI values ​​and areas with room for improvement. Continuing with this example, grids above threshold 512 include a color or shading similar to legend box 506c, such as grids 502a-502c, grids 502i-502k, and grids 502q-502r. In some embodiments, grids above threshold 512 represent geographic locations with mid-range KPI values ​​and areas with room for improvement. Continuing with this example, grids above threshold 514 include a color or shading similar to legend box 506d, such as grids 502h, 502p, 502y, 502ag, 502ao, and 502ax. In some embodiments, grids above threshold 514 represent geographic locations with low-level KPI values ​​and areas with room for improvement. Continuing with this example, grids above threshold 516 include a color or shading similar to legend box 506e, such as grids 502z-502aa, grids 502ah-502ai, and grids 502ap-502as. In some embodiments, grids above threshold 516 represent geographic locations with the lowest levels of KPI values ​​and areas where there is room for improvement or where no coverage is provided at all. Operation 314 proceeds to operation 316 where the centralized layer is stored in an HBase, such as Hbase 208.From operation 316 , the flow proceeds to operation 320 .

[0051] In operation 320, a graphical user interface representation of the unified coverage layer (FIG. 7) is presented in a UI, such as UI 822 (FIG. 8).

[0052] 6A and 6B are flow diagram representations of a Unified Coverage Algorithm (UCA) 600, according to some embodiments. In some embodiments, UCA 600 is similar to UCA 300. In some embodiments, UCA 600 is an extension or expansion of UCA 300. For purposes of illustration, the operations are arranged in the order described, but unless otherwise indicated, the operations are not limited to being performed in the order described. Each operation is configured to be performed at any time in UCA 600.

[0053] In operation 602 of method 600, a forecast coverage raw file is read. The forecast file contains raster data in a text file format and provides corresponding index numbers in a grid format. The forecast coverage raw file is obtained from the forecast and KPI server 116. The forecast file provides data in the form of a grid corresponding to the viewport divided into grids, each grid having a reference point. From operation 602, the flow proceeds to operation 604.

[0054] At operation 604 of method 600, a viewport is identified based on the predicted coverage raw file and the UE samples. A viewport, such as viewport 400, is identified from the input to the NIFI component 202 by the Spark component 204, which reads site information and information of geographically located UE samples associated with the identified viewport. Like viewport 400, the viewport is divided into grids 402a-402aj, each having a reference point 404. From operation 604, flow proceeds to operation 606.

[0055] At operation 606 of method 600, a number of UE samples are identified. In some embodiments, the UE sample data is in the NV data. In some embodiments, the minimum number of geographically located nearby UE samples is 11. In some embodiments, the UE samples include KPI data for each UE. In some embodiments, the minimum number of UEs is greater than 1. In some embodiments, the maximum number of UEs is 101 (to reduce latency from processing each UE sample). From operation 606, flow proceeds to operation 608.

[0056] In response to identifying less than a minimum number of UE samples, such as 11, within each grid area in operation 608 of method 600 (the “>Min. No. of UE Samples” branch of operation 608), flow proceeds to operation 610 where the centralized coverage algorithm selects predicted coverage values ​​for the geographic coverage of each grid without the minimum number of UE samples for the centralized coverage layer ( FIG. 7 ).

[0057] In response to finding a number equal to or greater than the minimum number of UE samples (the "Locate Closest UE Sample" branch of operation 608), flow proceeds to operation 612 to determine the distance between the closest UE and a grid reference point, such as grid reference point 404, where the closest UE sample is located. Flow proceeds from operation 612 to operation 614.

[0058] In operation 614 of method 600, in response to the distance between a reference point, such as reference point 404, and the first neighboring UE exceeding a predetermined threshold (the "NO" branch of operation 614), the centralized coverage algorithm is configured in operation 610 to use this predicted coverage value for the same grid in the centralized coverage layer. In some embodiments, the maximum distance is 600 meters. In some embodiments, the maximum distance is 100 meters. In some embodiments, the maximum distance is 1,000 meters. In response to the distance being less than the threshold (the "YES" branch of operation 614), the flow proceeds to operation 616.

[0059] At operation 616 of method 600, window samples are determined. In some embodiments, the window samples are samples identified over incremental radiuses of 25 meters from the reference point. In some embodiments, the incremental radius is configurable. From operation 616, operation proceeds to operation 618.

[0060] In response to the neighboring geographically located UE samples being within the single increment radius at operation 618 of method 600 (the "YES" branch of operation 618), the operational flow proceeds to operation 620 to determine whether there are more neighboring geographically located UE samples. In some embodiments, the number of detectable or usable UE samples is 101. In some embodiments, the maximum number is 1000 UE neighbor samples. In some embodiments, there is no maximum number of neighboring UE samples. However, there may be latency due to the number of results to be processed. In response to the neighboring geographically located UE samples not being within the single increment radius (the "NO" branch of operation 618), the operational flow proceeds to operation 622 where the unified coverage algorithm again increments the radius outward and continues to determine whether there are neighboring geographically located UE samples within the single increment radius.

[0061] In operation 622 of method 600, the window sample is incremented by a predetermined radius to determine whether any nearby geographically located UE samples are within the single incremented radius. In response to there being no geographically located UE samples within the single incremented radius (the "NO" branch of operation 622), the centralized coverage algorithm is configured to use the predicted coverage values ​​of the grids in the centralized coverage layer in operation 610. In response to it being determined that the window sample has nearby geographically located US samples within the single incremented radius (the "YES" branch of operation 622), the operation proceeds to operation 624.

[0062] At operation 624 of method 600, in response to all window samples being identified up to a threshold or maximum amount of UE samples, the unified algorithm filters the UE samples according to priority at operation 624. In a non-limiting example, the UE samples are prioritized based on category type, highest priority drive data, stationary data, lowest combined outdoor data, Drive Test (DRI), Stealth (STH), etc. In some embodiments, the UE category and class definitions define the performance specifications of the device. Flow proceeds from operation 624 to operation 626.

[0063] At operation 626 of the method 600, the distance between each nearest neighbor site (eg, a base station or edge device) and each grid reference point is determined. Flow proceeds from operation 626 to operation 628.

[0064] In operation 628 of method 600, the centralized coverage algorithm determines whether the site has been located. In response to the site not being located (the "NO" branch of operation 628), operation proceeds to operation 630.

[0065] In operation 630, the RSRP value is determined based on an offset of the outer ring. The outer ring is a predetermined distance from the reference point. In some embodiments, the outer ring is 300 meters. In some embodiments, the outer ring is greater than 300 meters. In some embodiments, the outer ring is less than 300 meters.

[0066] In operation 632 of method 600, the first UE distance of operation 612 is compared to the outer ring offset distance. In response to the first UE distance exceeding the outer ring distance from the reference point (the "YES" branch of operation 632), the geographically located UE samples are averaged with the predicted value in operation 636. This average of the geographically located UE samples and the predicted value is used for the unified coverage layer.

[0067] In response to the first UE distance being less than the outer ring distance from the reference point (the "NO" branch of operation 632), the geographically located samples of the UE are averaged in operation 634. This average value of the geographically located UE samples is used for the centralized coverage layer.

[0068] In operation 628, responsive to the nearest neighbor site being located ("YES" branch of 628), the distance of the site is compared to the first neighbor distance of operation 612 and the safety distance in operation 638. In some embodiments, the safety distance is 100 meters. In some embodiments, the safety distance is less than 100 meters. Additionally or alternatively, the safety distance is greater than 100 meters.

[0069] Depending on whether the nearest neighbor site is greater than or equal to the first UE proximity sample distance or whether the site distance is less than a safe distance (e.g., 100 meters) (the “YES” branch of operation 638), the process flow proceeds to operation 630 to determine a value to be used within the centralized coverage layer.

[0070] In response to the nearest neighbor site being less than the first UE nearby sample distance or the site distance being greater than a safe distance (e.g., 100 meters) (the "NO" branch of operation 638), the sample centroid is determined in operation 640. In some embodiments, the centroid is the arithmetic central mean location of all points.

[0071] In operation 640 of operation 600, in response to the first UE proximity distance exceeding the nearest neighbor site distance and the site distance exceeding the safe distance, a centroid of filtered UE data samples that lie within a single incremental radius is calculated. Processing proceeds from operation 640 to operation 642.

[0072] The distance of the reference point relative to the centroid is determined in operation 642. In response to the centroid distance being less than the site distance in operation 644, the unified coverage algorithm selects the predicted coverage for the same area used in the unified coverage layer in operation 610.

[0073] In response to the centroid distance exceeding the site distance to the reference point, the operational flow proceeds to operation 630 to determine a value to be used in the unified coverage layer.

[0074] FIG. 7 is a visual representation of a graphical user interface (GUI) 700, according to some embodiments.

[0075] The GUI 700 displays a visualization of the centralized coverage layer 701 as described in operation 320. In the example of FIG. 7, the centralized coverage layer is based on the RSRP in the coverage representation. However, in some embodiments, the centralized coverage layer is based on the SINR. In some embodiments, the centralized coverage layer is based on both KPI selections.

[0076] A user, such as a service provider, can select from many different layer representations from a pull-down window 702. From the pull-down 702, a user can select a number of layers including a predicted coverage layer, a unified layer including 5G and 4G (both 5G and 4G configured to select RSRP, SINR, or both), an in-building layer for internal RAN, a contention layer, a service layer, and a centralized IO coverage management layer.

[0077] The GUI 700 is also configured to present a legend and filter that shows a dbm legend 704 that indicates the color or shade that the selected KPI is from maximum to minimum, thus allowing the service provider to determine the gaps in the service. Additionally, the legend is configured in a pull down 706 window to allow the user to select the legend they wish to view.

[0078] A user can select the + sign 708 to expand and drill down on the GUI 700, allowing the service provider to visualize specific locations of gaps in coverage or lack of coverage in the RAN.

[0079] 8 is a block diagram of a centralized coverage processing circuit 800, according to some embodiments. In some embodiments, the centralized coverage processing circuit 800 is a general-purpose computing device that includes a hardware processor 802 and a non-transitory computer-readable storage medium 804. The storage medium 804 stores, among other things, computer program code 806, i.e., a set of executable instructions, such as a centralized coverage algorithm, such as UCA 300 and 600. Execution of the instructions 806 by the hardware processor 802 represents (at least in part) a RAN coverage gap discovery tool that performs some or all of the methods described herein (hereinafter, the described processes and / or methods) according to one or more embodiments.

[0080] The processor 802 is electrically coupled to the computer readable storage medium 804 via a bus 808. The processor 802 is also electrically coupled to an I / O 1 interface 810 by the bus 808. A network interface 812 is also electrically connected to the processor 802 via the bus 808. The network interface 812 is connected to a network 814 such that the processor 802 and the computer readable storage medium 804 can connect to external elements via the network 814. The processor 802 is configured to execute computer program code 806 encoded on the computer readable storage medium 804 such that the centralized coverage processing circuit 800 can be used to perform some or all of the processes and / or methods described. In one or more embodiments, the processor 802 is a Central Processing Unit (CPU), a multiprocessor, a distributed processing system, an Application Specific Integrated Circuit (ASIC), and / or other suitable processing unit.

[0081] In one or more embodiments, the computer readable storage medium 804 is an electronic, magnetic, optical, electromagnetic, infrared, and / or semiconductor system (or apparatus or device). For example, the computer readable storage medium 804 includes a semiconductor or solid state memory, a magnetic tape, a removable computer diskette, a Random Access Memory (RAM), a Read-Only Memory (ROM), a rigid magnetic disk, and / or an optical disk. In one or more embodiments using an optical disk, the computer readable storage medium 804 includes a Compact Disk-Read Only Memory (CD-ROM), a Compact Disk-Read / Write (CD-R / W), and / or a Digital Video Disc (DVD).

[0082] In one or more embodiments, the storage medium 804 stores computer program code 806 configured to enable the centralized coverage processing circuit 500 to perform some or all of the processes and / or methods described. In one or more embodiments, the storage medium 804 also stores information such as centralized coverage algorithms that facilitate performing some or all of the processes and / or methods described.

[0083] The unified coverage processing circuit 800 includes an I / O interface 810. The I / O interface 810 couples to external circuitry. In one or more embodiments, the I / O interface 810 includes a keyboard, a keypad, a mouse, a trackball, a trackpad, a touch screen, and / or cursor direction keys for communicating information and commands to the processor 802.

[0084] The centralized coverage processing circuit 800 also includes a network interface 812 coupled to the processor 802. The network interface 812 allows the centralized coverage processing circuit 800 to communicate with a network 814 to which one or more other computer systems are connected. The network interface 812 includes a wireless network interface such as BLUETOOTH, WIFI, WIMAX, GPRS, WCDMA, or a wired network interface such as ETHERNET, USB, IEEE-864, etc. In one or more embodiments, some or all of the processes and / or methods described are performed in two or more centralized coverage processing circuits 800.

[0085] The unified coverage compensation processing circuit 800 is configured to receive information via an I / O interface 810. The information received via the I / O interface 810 includes one or more of instructions, data, design rules, standard cell libraries, and / or other parameters for processing by the processor 802. The information is transferred to the processor 802 via a bus 808. The unified coverage compensation processing circuit 800 is configured to receive information related to a UI via the I / O interface 810. The information is stored in the computer-readable medium 804 as a user interface (UI) 822.

[0086] In some embodiments, some or all of the described processes and / or methods are implemented as a stand-alone software application for execution by a processor. In some embodiments, some or all of the described processes and / or methods are implemented as a software application that is part of an additional software application. In some embodiments, some or all of the described processes and / or methods are implemented as a plug-in to a software application.

[0087] In some embodiments, the processing is implemented as a function of a program stored on a non-transitory computer-readable recording medium, examples of which include, but are not limited to, one or more of external / removable and / or internal / built-in storage or memory units, such as optical disks, such as DVDs, magnetic disks, such as hard disks, semiconductor memories, such as ROM, RAM, memory cards, etc.

[0088] The one or more computer systems are configured to perform certain operations or actions by installing on the system software, firmware, hardware, or combinations thereof that cause the system to perform the operations during operation. The one or more computer programs are configured to perform certain operations or actions by including instructions that, when executed by a data processing device, cause the device to perform the operations. In some embodiments, a method for identifying Radio Access Network (RAN) coverage at a geographic location includes: generating a grid layer of RAN coverage in real time based on Key Performance Indicators (KPIs); generating a predicted RAN coverage grid layer; generating a viewport representation corresponding to the geographic locations supported by the RAN; overlaying the real-time RAN coverage grid layer, the predicted RAN coverage grid layer, and the viewport representation onto a centralized coverage representation; and determining RAN availability at the selected geographic location based on the centralized coverage representation. Other embodiments of this aspect include corresponding computer systems, devices, and computer programs recorded on one or more computer storage devices, each configured to perform the operations of the method.

[0089] In an implementation, the method may include one or more of the following features. The method includes displaying a unified coverage representation. The method includes identifying RAN qualities corresponding to specific geographic locations. The method includes notifying a RAN service provider of each geographic location with RAN qualities below a predefined threshold. Displaying the unified coverage representation further includes displaying RAN signal qualities corresponding to the selected geographic locations. Displaying the RAN quality and displaying a user equipment (UE) verification layer included in the real-time RAN coverage grid layer. The KPIs are a plurality of KPIs and include a first KPI of Reference Signal Received Power (RSRP), which is a measurement of a received power level at the RAN. A second KPI is a Signal to Interference and Noise Ratio (SINR), which is a ratio of a signal of interest to interference and noise. The method includes receiving RF drive test data corresponding to geographic locations supported by the RAN. The method includes receiving geographic site data including topographical parameters, electrical parameters, and logical parameters. The method includes receiving projection detail data converting geographic coordinates to latitude and longitude. Implementations of the described techniques may include hardware, a method or process, or computer software on a computer-accessible medium.

[0090] A system for identifying radio access network (RAN) coverage at one or more computer geographic locations is configured to perform a particular operation or behavior by installing software, firmware, hardware, or a combination thereof on the system that causes the system to perform the operation during operation. The one or more computer programs are configured to perform a particular operation or behavior by including instructions that, when executed by a data processing device, cause the device to perform the operation. In some embodiments, the system includes a memory having stored non-transitory instructions and a processor coupled to the memory. The processor executes the instructions, whereby the device is configured to receive raw predicted coverage data from the radio access network (RAN). Convert the raw predicted coverage data into a grid format. Receive user equipment (UE) key performance indicator (KPI) values ​​from neighboring cells in the RAN. Identify a viewport based on the raw predicted coverage data and the UE KPI values. The viewport is divided into grids, each grid including a reference point. A layer of predicted coverage data and a layer of UE KPI values ​​are overlaid on the viewport to obtain RAN availability by location. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs stored on one or more computer storage devices, each configured to perform the operations of the method.

[0091] Implementations may include one or more of the following features: A system, wherein a processor configured to execute instructions causes the apparatus to further identify KPI values ​​for the UE at each grid of the viewport; A processor configured to execute instructions causes the apparatus to further identify KPI values ​​for the UE closest to each grid reference point; A processor configured to execute instructions causes the apparatus to further calculate a distance between each grid reference point and the nearest UE KPI value; A processor configured to execute instructions causes the apparatus to further calculate a window sample of a predetermined radius in response to the distance being less than a maximum threshold; A processor configured to execute instructions causes the apparatus to further determine whether a KPI value for the UE at each grid is included in the window sample; A processor configured to execute instructions causes the apparatus to further determine whether additional UE KPI values ​​are present in other window samples in response to the distance being greater than a maximum threshold; A processor configured to execute instructions causes the apparatus to further use raw predicted coverage data for the grid reference point in response to no KPI value for the UE close to the grid reference point; A processor configured to execute instructions causes the apparatus to further use raw predicted coverage data for the grid reference point in response to no KPI value for the UE close to the grid reference point. Implementations of the described techniques may include hardware, a method or process, or computer software on a computer-accessible medium.

[0092] In some embodiments, the computer readable medium includes controller executable instructions to cause the controller to perform the operations. The computer readable medium further includes receiving predicted coverage data from a radio access network (RAN). The predicted coverage data corresponds to planned radio access network coverage for a plurality of reference points in the geographical area. Receiving site coverage data from a site coverage database. The site coverage data corresponds to geographic data for the geographical area. Receiving network visualization data. The network visualization data is based on one or more key performance indicators (KPIs). The one or more KPIs correspond to a plurality of reference points in the geographical area. Generating an overlay layer of the network visualization data and the predicted coverage data on a viewport representing the geographical area. Displaying the viewport. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs stored on one or more computer storage devices, each configured to perform the operations of the method.

[0093] Implementations may include one or more of the following features: A computer-readable medium with instructions executable by the controller further causing the controller to perform operations including, for one or more grids in the viewport, identifying a RAN quality of the one or more grids. The controller executable instructions further cause the controller to perform operations including identifying locations of grids corresponding to a lack of RAN coverage. Implementations of the described techniques may include hardware, a method or process, or computer software on a computer-accessible medium.

[0094] The above outlines features of some embodiments so that those skilled in the art may better understand the aspects of the present disclosure. It should be understood that those skilled in the art may readily use this disclosure as a basis for designing or modifying other processes and structures for carrying out the same purposes and / or achieving the same advantages of the embodiments introduced herein. Those skilled in the art should also understand that such equivalent constructions do not depart from the spirit and scope of the present disclosure, and that various changes, substitutions, and alterations may be made herein without departing from the spirit and scope of the present disclosure.

Claims

1. 1. A method for identifying radio access network (RAN) coverage at a geographic location, comprising: generating a grid layer of real-time RAN coverage based on key performance indicators (KPIs); generating a grid layer of predicted RAN coverage; generating viewport representations corresponding to geographic locations supported by the RAN; overlaying a real-time RAN coverage grid layer, a predicted RAN coverage grid layer, and the viewport representation onto a unified coverage representation; determining RAN availability at a selected geographic location based on the unified coverage representation.

2. The method of claim 1 , further comprising displaying the unified coverage representation.

3. The method of claim 1 , further comprising identifying a RAN quality corresponding to a particular geographic location.

4. 4. The method of claim 3, further comprising notifying a RAN service provider of each geographic location with the RAN quality below a predetermined threshold.

5. Displaying the unified coverage representation Displaying a RAN signal quality corresponding to a selected geographic location; and Indicating RAN quality; and 2. The method of claim 1, further comprising displaying a user equipment (UE) validation layer included in the real-time RAN coverage grid layer.

6. The KPI is a plurality of KPIs, and the plurality of KPIs are a first KPI, the first KPI being a Reference Signal Received Power (RSRP) which is a measurement of the received power level in the RAN; 2. The method of claim 1, further comprising: a second KPI, the second KPI comprising: a second KPI of a signal-to-interference-and-noise ratio (SINR), which is a ratio of a signal of interest to interference and noise.

7. The method of claim 1 , further comprising receiving RF drive test data corresponding to the geographic locations supported by the RAN.

8. 1. A method for receiving geographic site data, the geographic site data comprising: Topographic parameters; Electrical parameters; The method of claim 1 , further comprising: a logical parameter.

9. The method of claim 1 , further comprising receiving projection detail data that converts geographic coordinates into latitude and longitude.

10. 1. A system for identifying radio access network (RAN) coverage at a geographic location, comprising: a memory having stored thereon non-transitory instructions; a processor coupled to the memory and configured to execute the instructions, the processor causing the apparatus to: receiving raw predicted coverage data from a radio access network (RAN); converting the raw predicted coverage data into a grid format; receiving user equipment (UE) key performance indicator (KPI) values ​​from neighboring cells in the RAN; identifying a viewport based on the raw predicted coverage data and a KPI value for the UE, the viewport being divided into grids, each grid including a reference point; The system overlays a layer of predicted coverage data and a layer of UE KPI values ​​onto the viewport to obtain RAN availability by location.

11. The processor configured to execute the instructions causes the apparatus to: The system of claim 10 , further comprising: identifying a KPI value for the UE in each grid of the viewport.

12. The processor configured to execute the instructions causes the apparatus to: The system of claim 10, further comprising: identifying a KPI value for a UE closest to each grid reference point.

13. The processor configured to execute the instructions causes the apparatus to: The system of claim 12, further comprising: calculating a distance between each grid reference point and the KPI value of a nearest UE.

14. The processor configured to execute the instructions causes the apparatus to: The system of claim 12 , further comprising: responsive to an absence of a KPI value for a UE proximate to a grid reference point, further using the raw predicted coverage data for the grid reference point.

15. The processor configured to execute the instructions causes the apparatus to: The system of claim 13, further comprising: responsive to the distance being less than a maximum threshold, calculating a window sample of a predetermined radius.

16. The processor configured to execute the instructions causes the apparatus to: The system of claim 13 , further comprising: responsive to the distance exceeding a maximum threshold, further using the raw predicted coverage data for the grid reference point.

17. The processor configured to execute the instructions causes the apparatus to: Determine whether the KPI value of the UE in each grid is included in the window sample; 16. The system of claim 15, responsive to the KPI values ​​for the UEs of each grid being included in the window sample, further determining whether KPI values ​​for additional UEs are present in other window samples.

18. A computer-readable storage medium containing instructions executable by a controller to cause the controller to perform an operation, the instructions comprising: receiving predicted coverage data from a radio access network (RAN), the predicted coverage data corresponding to planned radio access network coverage for a plurality of reference points in a geographic region; receiving site coverage data from a site coverage database, the site coverage data corresponding to geographic data for the geographic area; receiving network visualization data based on one or more key performance indicators (KPIs), the one or more KPIs corresponding to the plurality of reference points in the geographic region; generating an overlay layer of the network visualization data and the predicted coverage data over a viewport representing the geographic region; and displaying the viewport.

19. The instructions executable by the controller cause the controller to:

20. The computer-readable storage medium of claim 18, further performing operations comprising: for one or more grids in the viewport, identifying a RAN quality for the one or more grids.

20. The instructions executable by the controller cause the controller to:

20. The computer-readable storage medium of claim 19, further performing operations comprising identifying grid locations corresponding to lack of RAN coverage.

Images