Method and system for detecting and mitigating tropospheric interference

Abstract

The present invention provides a method and system for predicting tropospheric interference using a digital twin model to detect tropospheric interference and suggest actions to mitigate the effects of tropospheric interference. The system (110) can include a machine learning engine (216) having a digital twin model for predicting / scoring the likelihood of a cell pair having tropospheric interference at a given time by identifying cell pairs with a high probability of interference using cell configuration data, weather data, and Hepburn data at that time. The system (110) is further configured to explore the impact of changing cell configuration parameters such as remote electrical tilt, and identify actions that can mitigate tropospheric interference with minimal impact on coverage. The digital twin model is trained on interference using historical data of interfering pairs combined with tropospheric interference data such as cell configuration parameters, weather parameters, and Hepburn data.

Description

[Technical Field]

[0001] Embodiments of this disclosure generally relate to communication networks. More specifically, this disclosure relates to methods and systems for predictively and automatically detecting and mitigating tropospheric interference in communication networks. [Background technology]

[0002] The following description of related technologies is intended to provide background information on the field of disclosure. This section may include specific aspects of the art that may be relevant to various features of this disclosure. However, it should be understood that this section is used solely to enhance the reader's understanding of this disclosure and not as an endorsement of prior art.

[0003] In general, signal quality between end-user devices and modern wireless communication systems is limited by interference from various sources. Wireless communication systems can experience unexpected network interference from intentional and unintentional radio frequency (RF) generation sources provided by the same or nearby base stations, industrial machinery, and electronic test equipment emitting signals in the target frequency band. Furthermore, interference can also be caused by undesirable mixing of signals generated by wireless communication systems and illegal radio sources operating in the wrong frequency band. The presence of these interference sources degrades intentional system signals, resulting in reduced system service and decreased wireless network capacity coverage.

[0004] Tropospheric ducts can occur when masses of warm and cold air overlap, creating one or more air density interfaces that act as low RF loss surfaces that reflect RF energy. When these conditions occur, RF signals from very far away from the target wireless network can reach sufficiently high energy levels, potentially degrading the performance of the network receiver. Normally, these distant signals are sufficiently attenuated by distance, RF shadowing (buildings, trees, mountains, etc.), and high levels of RF path loss caused by the curvature of the Earth. Thus, the signals do not reach the distant wireless network at a measurable level and therefore do not usually cause interference problems for the target wireless network. However, tropospheric ducts can allow signals from distant sources to impart problematic levels of interference energy to the wireless receiver. Furthermore, tropospheric ducts allow RF signals from distant sources to propagate over long distances, causing interference. Long-range interference often occurs in 4G networks and telecommunications systems. Even when several cell pairs face interference, there is no way to estimate the impact of actions such as changes in remote electrical tilt (RET). Nor is there a way to identify actions that have minimal impact on coverage. Therefore, customer experience and capacity are significantly reduced in victim cells. One current method to mitigate interference is to increase the guard band of victim cells. This approach reduces the available duration on the uplink channel. As a result of increasing the guard band on victim cells, the capacity of the uplink channel in victim cells decreases. This is disadvantageous. Another method to mitigate interference is to update RET changes based on historical data. This approach uses historical information to identify perpetrators or victims on a particular day. This approach may not be able to use available weather data or predictive information such as tropospheric data (Hepburn data). Furthermore, there is no existing approach to determine the amount of antenna tilt required for a pair of cells to mitigate tropospheric interference.

[0005] Yet another way to reduce tropospheric interference is to change the guard band in aggressor cells. In this method, when tropospheric interference is identified in an aggressor cell, the guard band increases. Since increasing the guard band may reduce the upload capacity, it is necessary to reduce the guard band in a timely manner. Also, the reduction of the guard band can only handle tropospheric interference from an aggressor up to a certain distance. Beyond that distance, an increase in the guard band will make it impossible to handle the interference from the aggressor. Once the guard band has increased, there is no mechanism to identify the time required to revert the increase in the guard band, but historical data of interference pairs is used to identify pairs of cells that are likely to interfere.

[0006] These interference pairs are used to identify very aggressive aggressor cells. In these aggressive aggressor cells, the slope value increases. Since the tropospheric phenomenon is very dynamic, relying only on historical data to identify cells and perform actions may not accurately predict pairs of interfering cells and may not be able to identify actions for cells that lead to optimal interference reduction.

[0007] Both methods may not be able to use predictive information such as available weather data and tropospheric data (Hepburn data). Also, there is no method to determine the amount of slope used to reduce interference. Even if weather and tropospheric information is available at a specific future time at the cell location, there is no approach to provide a prediction function for pairs of cells with interference. Also, there is no method to identify pairs of cells that may interfere or are causing high interference. Furthermore, there is no method to propose cell actions that minimize the impact on coverage and maximize the impact of the action, or to propose the amount of slope value for each cell to reduce tropospheric interference.

[0008] Thus, an improved approach for reducing tropospheric interference in remote areas is needed, thereby improving the customer experience and capacity in the victim cell.

[0009] Objects of the present disclosure Some of the objects of the present disclosure that are satisfied by at least one embodiment of the present specification are as listed below in this specification.

[0010] An object of the present disclosure is to provide a system and method for reducing interference by pre-empting cells that cause long-distance interference and performing actions such as increasing remote electrical tilt.

[0011] An object of the present disclosure is to provide a system and method for facilitating the learning of a digital twin model for reducing long-distance tropospheric interference. <00001​​​​​​​​​​​​​​​​​​​​In one embodiment, the Disclosure provides a system for mitigating tropospheric interference in a communication network. The system receives a set of data packets from a first cell and a second cell in the communication network. The set of data packets includes, or a combination thereof, tropospheric interference data for one or more pairs of the first and second cells, the intensity of the tropospheric interference indicating the intensity of the first cell signal received in the second cell, the date of the tropospheric interference, and the time of the tropospheric interference. Furthermore, the system extracts a set of first attributes, a set of second attributes, and a set of third attributes of the first and second cells from the received set of data packets.

[0017] The first set of attributes corresponds to cell configuration data, including total tilt, remote electrical tilt (RET), cell tower height, mechanical tilt, transmission power, and cell tower location. The second set of attributes corresponds to Hepburn data, including the meteorological data index at the cell tower location of a given cell on a given date, and the Hepburn index at a given time on the region joining the first and second cells of a pair. The third set of attributes corresponds to meteorological data. Furthermore, based on the extracted first, second, and third set of attributes, the system identifies one or more pairs of first and second cells affected by tropospheric interference.

[0018] The system calculates a first edge score for one or more identified pairs of first and second cells based on the extracted first attribute set, the extracted second attribute set, and the extracted third attribute set. The first edge score for one or more identified pairs of first and second cells indicates the possibility of tropospheric interference between one or more pairs of first and second cells. The first edge score for one or more identified pairs of first and second cells is calculated using a feature vector obtained by concatenating the first attribute set, the second attribute set, and the third attribute set of one or more pairs of first and second cells.

[0019] The system assigns actions to one or more pairs of first and second cells based on the first edge score. The actions assigned to one or more pairs of first and second cells include changes to the total tilt and remote electrical tilt (RET) of the antennas of one or more pairs of first and second cells. The system calculates the second edge score based on the actions assigned to one or more pairs of first and second cells. The system calculates the impact of the actions assigned to one or more pairs of first and second cells based on the first and second edge scores. The impact of the actions assigned to one or more pairs of first and second cells is the difference between the first edge score and the second edge score.

[0020] Furthermore, the system mitigates tropospheric interference between identified pairs of first and second cells by configuring the total tilt and remote electrical tilt (RET) of the antennas for one or more pairs of first and second cells.

[0021] In one embodiment, the Disclosure provides a method for mitigating tropospheric interference in a communications network. The method includes receiving a set of data packets from a first cell and a second cell in the communications network. The set of data packets includes one or more pairs of tropospheric interference data from the first cell and the second cell, the intensity of the tropospheric interference indicating the intensity of the first cell signal received in the second cell, the date of the tropospheric interference, and the time of the tropospheric interference, or a combination thereof.

[0022] Furthermore, the method includes extracting a first set of attributes, a second set of attributes, and a third set of attributes for a first cell and a second cell from a set of received data packets. The first set of attributes corresponds to cell configuration data, including total tilt, remote electrical tilt (RET), cell tower height, mechanical tilt, transmission power, and cell tower location. The second set of attributes corresponds to Hepburn data, including a meteorological data index at the cell tower location of a given cell on a given date, and a given time and Hepburn index on the region joining the pair of first and second cells. The third set of attributes corresponds to meteorological data. Furthermore, the method includes identifying one or more pairs of first and second cells affected by tropospheric interference based on the extracted first set of attributes, the extracted second set of attributes, and the extracted third set of attributes.

[0023] This method includes calculating a first edge score for one or more pairs of identified first and second cells based on an extracted first attribute set, an extracted second attribute set, and an extracted third attribute set. The first edge score for one or more pairs of identified first and second cells indicates the possibility of tropospheric interference between one or more pairs of first and second cells. The first edge score for one or more pairs of identified first and second cells is calculated using a feature vector obtained by concatenating the first attribute set, the second attribute set, and the third attribute set of one or more pairs of first and second cells.

[0024] This method includes assigning actions to one or more pairs of first and second cells based on a first edge score. The actions assigned to one or more pairs of first and second cells include changing the total tilt and remote electrical tilt (RET) of the antennas of one or more pairs of first and second cells. The system calculates a second edge score based on the actions assigned to one or more pairs of first and second cells. This method includes calculating the impact of the actions assigned to one or more pairs of first and second cells based on the first and second edge scores. The impact of the actions assigned to one or more pairs of first and second cells is the difference between the first edge score and the second edge score.

[0025] Furthermore, this method includes mitigating identified tropospheric interference between one or more pairs of first and second cells by configuring the total tilt and remote electrical tilt (RET) of the antennas for one or more pairs of first and second cells.

[0026] The accompanying drawings incorporated herein and constituting part of the present invention illustrate exemplary embodiments of the disclosed methods and systems, and similar reference numerals throughout different drawings refer to the same parts. Components in the drawings are not necessarily proportional to the actual size, and instead, emphasis is placed on clearly illustrating the principles of this disclosure. Some drawings may use block diagrams to show components, and may not show the internal circuitry of each component. It will be understood by those skilled in the art that the inventions in such drawings include inventions of electrical components, electronic components, or circuits commonly used to mount such components. [Brief explanation of the drawing]

[0027] [Figure 1] This figure shows an exemplary network architecture (100) that can implement the proposed system (110) of the present disclosure according to one embodiment of the present disclosure. [Figure 2] An exemplary representation (200) of the system (110) according to one embodiment of the present disclosure is shown. [Figure 3] A flowchart (300) of an exemplary method illustrating a method for facilitating the detection and mitigation of interference according to one embodiment of the present disclosure is shown. [Figure 4] An exemplary block diagram (400) of a functional block related to the proposed system according to one embodiment of the present disclosure is shown. [Figure 5] An exemplary block diagram (500) of a functional block associated with an ML engine according to one embodiment of the present disclosure is shown. [Figure 6] An exemplary representation (600) of Hepburn data analysis according to one embodiment of the present disclosure is shown. [Figure 7] An exemplary representation (700) of a simulation analysis according to one embodiment of the present disclosure is shown. [Figure 8] An exemplary representation (800) of a long-range interference network according to one embodiment of the present disclosure is shown. [Figure 9] An exemplary representation (900) of the total edge count across different iterations of the simulation, according to one embodiment of the present disclosure, is shown. [Figure 10] This shows an exemplary representation (1000) of a flowchart of interferential digital twin training according to one embodiment of the present disclosure. [Figure 11] An exemplary representation (1100) of a flowchart of the simulation flow of the proposed method according to one embodiment of the present disclosure is shown. [Figure 12] An exemplary computer system (1200) is shown in which embodiments of the present invention can be utilized according to embodiments of the present disclosure. [Figure 13] An exemplary method flowchart (1300) illustrating a method for mitigating tropospheric interference to a pair of cells in a communication network, according to one embodiment of the present disclosure, is shown. [Modes for carrying out the invention]

[0028] The above will become clearer from the following more detailed description of the present invention.

[0029] The following description includes specific details for illustrative purposes to facilitate understanding of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention can be carried out without these specific details. Some of the functions described below can be used independently of each other or in any combination of other functions. Individual functions may not address all of the above problems, or may address only some of them. Some of the above problems may not be fully addressed by any of the functions described herein.

[0030] The following description provides only exemplary embodiments and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the following description of exemplary embodiments provides a useful explanation for carrying out the exemplary embodiments for those skilled in the art. It should be understood that various modifications can be made to the function and arrangement of the elements without departing from the spirit and scope of the invention described herein.

[0031] The following description includes many specific details in order to provide a complete understanding of the invention. However, it will be apparent to those skilled in the art that the various embodiments described can be carried out without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form to avoid obscuring the embodiments with unnecessary details. In other examples, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary details to avoid obscuring the embodiments.

[0032] Furthermore, it should be noted that individual embodiments may be described as processes shown as flowcharts, flow diagrams, data flow diagrams, structure diagrams, or block diagrams. While flowcharts may describe operations as sequential, many operations can be performed in parallel or simultaneously. Moreover, the order of operations can be rearranged. A process terminates when its operations are complete, but there may be additional steps not shown in the diagram. A process may correspond to a method, function, procedure, subroutine, subprogram, etc. If a process corresponds to a function, its termination may correspond to the function's return to the calling function or the main function.

[0033] In this specification, the term “exemplary” is used to mean “serving as an example, illustration, or illustration.” To avoid misunderstanding, the subject matter disclosed herein is not limited by such examples. Furthermore, any aspect or design described herein as “exemplary” and / or “empirical” should not necessarily be construed as being preferable or advantageous to other aspects or designs, nor should it be meant to exclude equivalent exemplary structures and techniques known to those skilled in the art. Furthermore, to the extent that the terms “include,” “have,” “contain,” and other similar terms are used in either the detailed description or the claims, such terms are intended to be as comprehensive as the terms “include” as a free transitional term without excluding additional or other elements.

[0034] Any reference herein to “one embodiment,” “an embodiment,” or similar formulations means that certain features, structures, operations, or characteristics described in relation to an embodiment are included in at least one embodiment of the Art. The phrase “in one embodiment” appearing in various places herein does not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics can be combined in any preferred manner in one or more embodiments.

[0035] The terms used herein are for the sole purpose of describing specific embodiments and are not intended to be limiting. Where used herein, the singular forms “a,” “an,” and “the” are intended to include the plural form unless the context otherwise clearly indicates. It will be further understood that the terms “comprise” and / or “comprising,” when used herein, specify the presence of the described feature, integer, step, action, element, and / or component, but do not exclude the presence of one or more other features, integers, steps, actions, elements, components, and / or groups thereof. Where used herein, the terms “and / or” include any and all combinations of one or more of the relevant list items.

[0036] This disclosure provides an entity or organization with a system and method for mitigating tropospheric interference in a communications network. This system and method can provide predictive capabilities for interfering cell pairs, given that meteorological and tropospheric information is available at the cell location at a given time. Furthermore, the proposed system and method can identify potentially interfering cell pairs and propose actions for these cell pairs to maximize the impact of those actions while minimizing the impact on coverage. In addition, the proposed system and method can also suggest the amount of slope value for cell pairs.

[0037] Increasing the tilt value of a cell pair can significantly reduce the number of customers who can be served in a communication area. Therefore, the tilt value of a cell pair needs to be increased in a way that does not affect the number of customers who can be served in a communication area. Changing the tilt value of a cell pair to eliminate tropospheric interference without affecting the number of customers who can be served can be achieved using a digital twin model. A digital twin model can be a simulation model that simulates the effect of increasing the tilt value of a cell pair and determines the tilt value at which tropospheric interference is eliminated. Note that increasing the tilt value of a cell pair increases the angle of incidence between the cell antenna and the tropospheric duct, thereby reducing tropospheric interference. Simulations using a digital twin model have observed that tropospheric interference can be eliminated by increasing the tilt angle of the cell antenna by only 2-3 degrees. If the tilt angle exceeds 2-3 degrees, the number of customers who can be served in a particular communication area may significantly decrease.

[0038] Figure 1 shows an exemplary network architecture (100) that can implement a system (110) of the Disclosure according to one embodiment of the Disclosure. As shown in the figure, in one embodiment, multiple base stations of multiple cells in a telecommunications network can be associated with multiple user computing devices. By example, but not limited to, a first base station (120-1) of one or more first cells can be communicably associated with multiple user computing devices (102-1, 102-2, 102-3). A second base station (120-2) of one or more second cells can be communicably associated with a second set of user computing devices (102-4, 102-5, 102-6). A third base station (120-3) of one or more third cells can be communicably associated with a third set of user computing devices (102-7, 102-8, 102-9). A fourth base station (120-4) of one or more fourth cells can be communicably associated with a fourth user computing device, and so on. There may be N base stations, one or more of which are communicably associated with N user computing devices within the network architecture (100).

[0039] In exemplary embodiments, one or more first cells are perpetrator cells, and one or more second cells are victim cells. As an example, and not an limitation, one or more first cells and one or more second cells can form a first perpetrator-victim pair. One or more third cells and one or more fourth cells can form a second perpetrator-victim pair, and so on. Those skilled in the art will understand that perpetrator-victim pairs can be formed in any permutation and combination of N cells present in a communication network.

[0040] Multiple base stations (120-1, 120-2…120-N) may be further coupled communicatively to a network (106) and at least a central server (112). More specifically, an exemplary architecture (100) implements a system (110) with a machine learning (ML) engine (216) to facilitate the detection and mitigation of tropospheric interference associated with pairs of aggressor and victim cells. The system (110) may be configured to receive a set of data packets from the first and second cells containing either or a combination of interference data for the first and second cells. The set of data packets may also include interference intensity indicating the strength of the first cell signal received in the second cell, as well as the date and time of the interference. The system (110) may extract a first set of attributes corresponding to cell configuration data from the received set of data packets. The system (110) may then extract a second set of attributes corresponding to meteorological data from the received set of data packets. The Hepburn data may indicate vulnerability of a particular geographic location to tropospheric interference.

[0041] In exemplary embodiments, cell configuration data may include, but are not limited to, total tilt, remote electrical tilt (RET), cell tower height, mechanical tilt, transmit power, cell tower location, and Hepburn data may also include, but are not limited to, a weather data index for location against date and time.

[0042] The system (110) can further generate a trained model corresponding to the digital twin model via the ML engine (216). The trained model may be configured to automatically determine and predict tropospheric interference between one or more pairs of the first and second cells. Based on the extracted first and second attribute sets, the ML engine (216) (see Figure 2) can identify one or more pairs of the first and second cells that may be affected by tropospheric interference. Based on the tropospheric interference, the ML engine (216) can calculate edge scores for one or more pairs of the first and second cells. Based on the calculated edge scores, the ML engine (216) can assign actions based on the first and second attribute sets with updated configuration values ​​to mitigate the tropospheric interference.

[0043] In an exemplary embodiment, the digital twin model can be trained using a third set of attributes that may be related to historical attributes and interference pairs. In another exemplary embodiment, the digital twin model can be used to calculate edge scores based on a first set of attributes, a second set of attributes, and a third set of attributes.

[0044] In an exemplary embodiment, feature vectors may be obtained by searching a first set of attributes, including cell configuration parameters and edge parameters. Multiple feature vectors corresponding to interfering and non-interfering data can be grouped together. Multiple feature vectors may be fed into a digital twin model that provides edge scores. The edge scores indicate the likelihood of tropospheric interference occurring between aggressor and victim pairs.

[0045] In one embodiment, the computing device (104) and / or the user device (120) can communicate with the system (110) via an executable instruction set present on any operating system, including but not limited to Android®, iOS®, Kai OS®, etc. In one embodiment, the computing device (104) and / or the user device (120) may include, but not limited to, any electrical, electronic, electromechanical or any device, or one or more combinations of the above devices. As a mobile phone, smartphone, virtual reality (VR) device, augmented reality (AR) device, laptop, general-purpose computer, desktop, personal digital assistant, tablet computer, mainframe computer, or other computing device, it may include, but not limited to, one or more built-in or externally coupled accessories, including, but not limited to, visual assistance devices such as a computing device camera, voice assistance device, microphone, keyboard, touchpad, touch-enabled screen, and input device for receiving user input such as an electronic pen. It should be understood that the computing device (104) and / or the user device (120) may be used with a variety of other devices, and are not limited to those mentioned. Smart computing devices are one of the appropriate systems for storing data and other personal and confidential information.

[0046] In exemplary embodiments, the network (106) may include, but not limited to, at least part of one or more networks having one or more nodes that transmit, receive, forward, generate, buffer, store, or route; one or more messages, packets, signals, waves, voltage or current levels, or any combination thereof, such as switches, processes, or combinations thereof. The network may include, but not limited to, one or more wireless networks, wired networks, the Internet, intranets, public networks, private networks, packet-switched networks, circuit-switched networks, ad-hoc networks, infrastructure networks, public switched telephone networks (PSTNs), cable networks, cellular networks, satellite networks, fiber optic networks, or any combination thereof.

[0047] In another exemplary embodiment, the centralized server (112) is, but is not limited to, a standalone server, a server blade, a server rack, a bank of servers, a server farm, hardware supporting part of a cloud service or system, a home server, hardware running a virtualized server, one or more processors running code that functions as a server, one or more machines performing server-side functions as described herein, at least some of the above, or a combination thereof.

[0048] In one embodiment, the system (110) may include one or more processors (202) coupled to a memory (204). When the memory (204) is executed by one or more processors (202), it enables the system (110) to detect and mitigate tropospheric interference related to aggressor-victim pairs of cells. Refer to Figure 2 with reference to Figure 1. Figure 1 shows an exemplary representation of the system (110) for facilitating the detection and mitigation of tropospheric interference related to aggressor-victim pairs of cells, based on a machine learning-based architecture according to one embodiment of the present disclosure.

[0049] In one embodiment, the system (110) may comprise one or more processors (202). One or more processors (202) may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuits, and / or any device that processes data based on operational instructions. In particular, one or more processors (202) may be configured to fetch and execute computer-readable instructions stored in the system (110)'s memory (204). The memory (204) may be configured to store one or more computer-readable instructions or routines in a non-temporary computer-readable storage medium that can be fetched and executed to create or share data packets over network services. The memory (204) may comprise any non-temporary storage device, including, for example, volatile memory such as RAM, or non-volatile memory such as EPROM, flash memory, etc.

[0050] In one embodiment, the system (110) may include an interface(s)(206). The interface(s)(206) may include interfaces for various types of data input and output devices, such as I / O devices and storage devices. The interface(s)(206) may facilitate communication of the system (110). The interface(s)(206) may also provide a communication path for one or more components of the system (110). Examples of such components include, but are not limited to, a processing engine(s)(208) and a database(210).

[0051] A processing engine(s)(208) may be implemented as a combination of hardware and programming (e.g., programmable instructions) to implement one or more functions of the processing engine(s)(208). In the examples described herein, such a combination of hardware and programming can be implemented in several different ways. For example, the programming of the processing engine(s)(208) may be processor-executable instructions stored in a non-temporary machine-readable storage medium, and the hardware of the processing engine(s)(208) may include processing resources (e.g., one or more processors) to execute such instructions.

[0052] In this example, the machine-readable storage medium can store instructions that implement a processing engine(s)(208) when executed by a processing resource. In such an example, the system(110) may comprise the machine-readable storage medium for storing the instructions and the processing resource for executing the instructions, or the machine-readable storage medium may be separate but accessible to the system(110) and the processing resource. In other examples, the processing engine(s)(208) may be implemented by electronic circuits.

[0053] The processing engine (208) may include one or more engines selected from among the following: a data acquisition engine (212), an attribute extraction engine (214), a machine learning (ML) engine (216), a digital twin model generation engine (218), and other engines (220). The other engines (220) may include a signal processing engine, a prediction engine, and the like.

[0054] In one embodiment, the data acquisition engine (212) of the system (110) can receive / process / preprocess a set of data packets from a first cell and a second cell. The set of data packets may include interference data from the first cell and the second cell, or a combination thereof. The set of data packets may also include the interference intensity, indicating the strength of the first cell signal received in the second cell, as well as the date and time of the interference.

[0055] In one embodiment, the attribute extraction engine (214) of the system (110) can extract a first set of attributes corresponding to cell configuration data from a set of received data packets. Furthermore, the attribute extraction engine (214) can extract a second set of attributes corresponding to Hepburn data from a set of data packets received from the database (210). The attribute extraction engine (214) of the system (110) can also extract a third set of attributes corresponding to weather data from a set of data packets received from the database (210).

[0056] In one embodiment, the ML engine (216) of system (110) can identify one or more pairs of first and second cells affected by tropospheric interference based on extracted first and second attributes. Furthermore, the ML engine (216) of system (110) can then calculate edge scores for one or more pairs of first and second cells. The trained model can then be generated by a digital twin model generation engine (218) corresponding to a digital twin model. The trained model can be configured to determine and predict tropospheric interference between one or more pairs of first and second cells. Based on a first set of attributes and a second set of attributes with updated values, the ML engine (216) can calculate edge scores and propose actions to mitigate tropospheric interference.

[0057] In exemplary embodiments, a digital twin model may be trained using a first set of attributes, a second set of attributes, and a third set of attributes relating to historical attributes, predicted attributes, and interference pairs. Edge scores can be calculated using the digital twin model based on the first, second, and third set of attributes.

[0058] Figure 3 shows an exemplary method (300) illustrating a method for facilitating the detection and mitigation of tropospheric interference related to a pair of aggravating and vulnerable cells, according to one embodiment of the present disclosure. As shown, in one embodiment, the method can facilitate the detection and mitigation of tropospheric interference related to a pair of aggravating and vulnerable cells.

[0059] The method may include, in 302, receiving a set of data packets from a first cell and a second cell by executing a data acquisition engine (212) by a processor (202). The set of data packets may include either or a combination of interference data from the first cell and the second cell. The set of data packets may also include the interference intensity indicating the strength of the first cell signal received in the second cell, the date of the tropospheric interference, and the time of the tropospheric interference. The first cell is the aggressor cell, and the second cell is the victim cell. The method may include, in 304, extracting a first set of attributes corresponding to cell configuration data from the received set of data packets by executing an attribute extraction engine (214) by a processor (202). The method may include, in 306, extracting a second set of attributes corresponding to Hepburn data from the received set of data packets by executing an attribute extraction engine (214) by a processor (202).

[0060] In step 308, the method may include identifying one or more pairs of first and second cells affected by interference by running the ML engine (216) by the processor (202). Identifying one or more pairs of first and second cells affected by interference may be based on an extracted first attribute set and an extracted second attribute set. The method may include in step 310 calculating the edge scores of one or more pairs of first and second cells by running the ML engine (216).

[0061] The method may include, in 312, a step of generating a trained model corresponding to the digital twin model by a digital twin model generation engine (218). The trained model may be configured to determine and predict tropospheric interference between one or more pairs of first and second cell pairs. The method (300) may further include, in 314, a step of assigning edge scores and proposing actions by an ML engine (216) using a first and second attribute set having updated values ​​to mitigate tropospheric interference.

[0062] Figure 4 shows an exemplary block diagram (400) of a functional block related to a system (110) according to one embodiment of the present disclosure. As illustrated, in one embodiment, given an aggressor-victim pair (a, v), different types of parameters can be extracted for aggressor cells, victim cells, and aggressor-victim pairs from at least three different types of data, such as interference data (402-1), cell configuration data (402-2), and Hepburn data (402-3). One or more aggressor parameters (404) are total slope (x att ), Remote Electrical Tilting (RET) (x aret ), height of the perpetrator's cell tower (x ah ), parameters such as height from mean sea level can be included. (x aamsl ), azimuth (x aazi ), antenna-related parameters (x aant ), transmit power (xatp ) such as the Hepburn data index (x at the perpetrator ahep ), meteorological data parameters at the perpetrator cell such as humidity, etc. can be included. One or more perpetrator parameters (404) are concatenated to form x anode = xatt , xaret , xah , xaamsl , xaazi , xaant , xatp , xahep to form the perpetrator node property represented as

[0063] One or more victim parameters (408) can include parameters such as total tilt, RET, cell tower height, height from mean sea level, azimuth angle, antenna-related parameters, transmission power, etc. One or more victim parameters (408) are concatenated to form x vnode = [x vtt , x vret , x vh , x vamsl , x vazi , x vant , x vtp , x vhep to form the property of the victim node represented as

[0064] One or more perpetrator-victim (edge) parameters (406) can include the following elements. · The maximum total tilt (x emaxtt ) of the total tilt of the perpetrator and the total tilt of the victim · The total tilt on the victim side and the total tilt of the total tilt on the victim side (x emintt ) · The average of the total tilt on the victim side and the total tilt of the total tilt on the victim side (x emeantt ) · The maximum value of RET (x emaxret ) between the perpetrator RET and the victim RET · The minimum value of RET (x eminret ) between the victim-side RET and the victim-side RET · The average of RET (x emeanret ) between the victim-side RET and the victim-side RET • Maximum Hepburn Index between perpetrator and victim (x emaxhep ) • Minimum Hepburn index (x) between the perpetrator's total inclination and the victim's total inclination eminhep ) · The average Hepburn index (x) between the total slope on the victim's side and the total slope on the victim's side. emeantt ) • Weighted sum of Hepburn index values ​​along the path connecting perpetrator and victim (x eweightedhep ) ·Perpetrator wrt victim(x eaggcos ,x eaggsin Take the cosine and sine of the relative direction of ). • Take the cosine and sine of the relative direction of the victim to the perpetrator (x eviccos ,x evicsin ) • Minimum and maximum heights of the perpetrator and victim (x eaggh ,x evich )

[0065] In an exemplary embodiment, one or more perpetrator-victim (edge) parameters (406) are x edge =[x emaxtt , x emintt , x emeantt , x emaxret , x eminret , x emeanret , x emaxhep , x eminhep , x emeantt , x eweightedhep , x eaggcos , x eaggsin , x eviccos , x evicsin x eaggh , x evich It can be represented as ].

[0066] In an exemplary embodiment, the feature vector may be obtained by concatenating the properties of the perpetrator node, the properties of the victim node, and the properties of the perpetrator-victim edge, x edge =[x anode , x vnode , x edgeIt can be represented as ]. Multiple feature vectors can be supplied to a digital twin model (410) to provide edge scores. The edge scores can indicate the probability or likelihood that tropospheric interference (412) occurs between a pair of aggressors and victims. The tropospheric interference detected by the digital twin model (410) can be sent to an interference reduction optimizer (418) for reduction along with a feasible action space (E-slope at any cell) (416). The interference reduction optimizer (418) may be configured to provide possible actions for maximum interference reduction (420). Possible actions for maximum interference reduction (420) may include total tilt and remote electrical tilt (RET) of antennas for one or more pairs of first and second cells to mitigate tropospheric interference for one or more pairs of first and second cells.

[0067] In exemplary embodiments, edge features may include different types of Hepburn features, such as: • Minimum value of the Hepburn Index at the positions of perpetrator and victim • The maximum value of the Hepburn Index in the positions of perpetrator and victim. • Average Hepburn Index at the positions of perpetrator and victim • Parabolichepburn Index: This is the weighted sum of Hepburn index values ​​along the line connecting the perpetrator and the victim. The weights are proportional to the least-squares distance between the locations of the perpetrator and the victim. The weights used are normalized so that their sum equals 1. • Various weighted variations of the Hepburn value, such as mean, minimum, maximum, and median, are calculated and used as features.

[0068] Figure 5 shows an exemplary block diagram (500) of a functional block associated with an ML engine (216) according to one embodiment of the present disclosure. As shown, various types of features may be extracted with respect to the Hepburn data. Interference data (402-1) is utilized via a negative data sampling unit (502) to generate negative data (506) which extracts features of negative data (506-1) and labels (506-2). The negative data sampling unit (502) can supply the negative features (506-1) and labels (506-2) to a train model unit (508) to check feature significance or explainability analysis (510) and generate a model (512). A positive data generation block (504), comprising a positive feature extraction module (504-1) and a label unit (504-2), can directly acquire interference data (402-1) for training a model with a trained model unit (508). The perpetrator cell ID (518) and victim cell ID (520) may provide Hepburn data-related node features (516) that include Hepburn index values ​​at the perpetrator cell location and victim cell location. The Hepburn data associated with the node features (516) is used to predict the edge score (514), which is sent to a reason code generator (522) (contributing factors such as slope and height). The reason code generator (522) can generate a reason (524) or determine the actual edge score (526).

[0069] In one embodiment, during the model training process, feature vectors corresponding to interfering data may be assigned label 1, and feature vectors corresponding to non-interfering data may be assigned label 0. The labeled data may be used to train a digital twin model. Machine learning models and techniques such as random forests, gradient boosted trees, neural networks, or combinations thereof can be used to represent and train the digital twin model. As an example, but not an limitation, a gradient boosting algorithm can be used, as described here. A gradient boosting algorithm may use a training set.

number

number

number

number

number

number

number

[0070] In one exemplary embodiment, the model (512) can be trained using an implementation of a gradient boosting algorithm and can be a representation of a digital twin model.

[0071] In an exemplary embodiment, Table 1 provides a summary of interference and non-interference data in a Time Division Duplex (TDD) system. Furthermore, Table 1 provides details regarding the region, date, and time associated with the interference and non-interference data, as well as other available data points. [Table 1]

[0072] As an example, and not an exhaustive one, the accuracy of gradient boosted trees as a representation and learning technique for digital twin models is provided in Table 2 using one set of parameters where the maximum depth is at least 8 and the number of trees in the gradient boosted tree is at least 50. [Table 2]

[0073] Figure 6 shows an exemplary representation (600) of Hepburn data analysis according to one embodiment of the present disclosure. The parabolic Hepburn feature is an important feature for distinguishing between interfering and non-interfering edges in the digital twin model. As shown in the figure, the parabola is given by the following equation:

number

[0074] Figure 7 shows an exemplary representation (700) of a simulation analysis according to one embodiment of the present disclosure.

[0075] In one embodiment, the simulation may include steps to identify perpetrator-victim pairs that need to be evaluated and to simulate actions against the identified pairs. As an example, but not an limitation, the steps required to estimate the impact of an action on a particular cell tower using a digital twin model are shown. Actions whose impact is evaluated in the simulation process may include changes in the RET values ​​of perpetrator-victim pairs. The simulation analysis consists of the following steps: - Identifying perpetrator-victim pairs that require evaluation. - Extraction of characteristics of identified perpetrator and victim pairs - Calculation of edge scores for identified perpetrator and victim pairs - Change the cell's RET and total slope by 1 degree, keeping all other parameters the same. -Calculate the edge score for identified perpetrator-victim pairs based on the changes made in RET and the total slope of the perpetrator-victim pair cells. -Measure the difference in edge scores as an effect of the action. - Repeat the steps from feature extraction and measure the difference in edge scores for all pairs. -Calculate the edge score improvement for each perpetrator cell by aggregating improvement scores across all perpetrator edges. - The edge score is recalculated using updated parameters such as full slope and RET, and the corresponding action is applied to the perpetrator with the best improvement score. - The process of updating the data, using the updated data, and repeating the steps from feature extraction to recalculation with the updated parameters is repeated until a certain number of actions or the required number of actions are obtained.

[0076] Figure 8 shows an exemplary representation (800) of a long-range interference network according to one embodiment of the present disclosure. As shown in the figure, the circles (C1, C2, C3, C4...C8) are cells, and the cells connected by arrows are interfering cells. Cells with outward-pointing arrows are aggressor cells (C1, C2, C3, C6), and cells with inward-pointing arrows are victim cells (C4, C5, C7, and C8). The weights of the arrows, such as (W16, W14, W15, W12, W23, W35, W34, W36, W37, W38, W67), represent the likelihood of an edge interfering. The sum of all edge weights represents the aggregated edge score based on the configuration of cells in the network.

[0077] Figure 9 shows an exemplary representation (900) of the total edge count across different iterations of a simulation according to one embodiment of the present disclosure. Actions are applied iteratively to cells, and the effect of the action is measured by the number of edges reduced. Figure 9 shows the effect of the simulation run. The Y-axis represents the number of edges, and the X-axis represents the number of iterations.

[0078] Figure 10 shows an exemplary representation (1000) of a flowchart for training a digital twin model according to one embodiment of the present disclosure. As shown in the figure, the flowchart may include raw interference data received by the data acquisition engine (212) in block 1002. In block 1004, the raw interference data can be used to identify aggressor cells having more than five victim cells. In block 1006, edges may be held in attack cells having more than five victim cells. In block 1008, pairs of non-interfering cells may be enumerated. In block 1010, both interfering and non-interfering pairs may be enhanced with cell configuration data (1012-1), Hepburn data (1012-2), and weather data (1012-3). In block 1014, a digital twin model can be constructed. In block 1016, a digital twin model may be used to mitigate tropospheric interference between identified pairs of first and second cells by configuring the total tilt and remote electrical tilt (RET) of the antennas of the pairs of first and second cells.

[0079] Figure 11 shows an exemplary representation (1100) of a simulation flow diagram of the proposed method according to one embodiment of the present disclosure. As shown, the simulation flow diagram may include, in block 1002, that raw interference data is received by a data acquisition engine (212). In block 1102, the ML engine (216) may identify pairs of cells in which the aggressor has a certain number of victims. In block 1104, the pairs of cells may be enhanced with cell configuration data (1012-1), Hepburn data (1012-2), and weather data (1012-3), etc., but not limited to these. In block 1106, the iterations may be initialized to 0. In each iteration, in block 1108, the edge count improvement may be calculated for different actions against each aggressor. In block 1110, the aggressor with the highest edge count improvement may be selected. In block 1112, the N perpetrator configuration can be updated with an action that improves the edge count. In block 1114, if the number of iterations is less than the maximum number of iterations, the loop from block 1108 to block 1114 can be repeated. In block 1114, if the number of iterations is greater than or equal to the maximum number of iterations, the process can be stopped.

[0080] Figure 12 shows an exemplary computer system (1200) in which embodiments of the present invention can be utilized according to embodiments of the present disclosure. As shown in Figure 12, the computer system (1200) may include an external storage device (1210), a bus (1220), main memory (1230), read-only memory (1240), mass storage device (1270), a communication device, a port (1260), and a processor (1270). Those skilled in the art will understand that the computer system (1200) may include two or more processors (1270) and a communication port (1260). Examples of processors (1270) include, but are not limited to, Intel® Itanium® or Itanium 2 processors, or AMD® Opteron® or Athlon MP® processors, Motorola® series processors, FortiSOC® system-on-chip processors, or other future processors. The processor (1270) may include various modules relating to embodiments of the present invention. The communication port (1260) may be an RS-232 port used for modem-based dial-up connections, a 10 / 100 Ethernet port, a Gigabit or 12 Gigabit port using copper or fiber, a serial port, a parallel port, or other existing or future ports. The communication port (1260) may be selected depending on the network to which the computer system (1200) is connected, such as a LAN (Local Area Network), a WAN (Wide Area Network), or any other network to which the computer system (1200) is connected. The memory (1230) may be RAM (Random Access Memory) or any other dynamic storage device commonly known in the art. The read-only memory (1240) may be any static storage device (1240), but is not limited to any static storage device, such as a programmable read-only memory (PROM) chip for storing static information such as processor startup instructions or BIOS instructions (1270).Mass storage (1250) can be a current or future mass storage solution that can be used to store information and / or instructions. Exemplary mass storage solutions include, but are not limited to, PATA (Parallel Advanced Technology Attachment) or SATA (Serial Advanced Technology Attachment) hard disk drives or solid-state drives (e.g., USB (Universal Serial Bus) and / or Firewire interfaces), e.g., those available from Seagate (e.g., Seagate Barracuda 7122 family) or Hitachi (e.g., Hitachi Deskstar 7K1200), one or more optical disks, RAID (Redundant Array of Independent Disks) storage, e.g., array disks available from various vendors (e.g., SATA arrays).

[0081] The bus (1220) connects the processor(s) (1270) to other memory, storage, and communication blocks in a communicative manner. The bus (1220) may be, for example, a PCI (Peripheral Component Interconnect) / PCI-X (PCI Extended) bus, SCSI (Small Computer System Interface), or USB for connecting expansion cards, drives, and other subsystems. Other buses may include a front-side bus (FSB) connecting the processor(s) (1270) to the computer system (1200).

[0082] If necessary, operator and management interfaces such as displays, keyboards, joysticks, and cursor control devices can also be coupled to the bus (1220) to support direct interaction between the operator and the computer system. Other operator and management interfaces can be provided via a network connection connected through a communication port (1260). The external storage device (1212) may be any type of external hard drive, floppy drive, IOMEGA® Zip drive, CD-ROM (Compact Disc - Read-Only Memory), CD-RW (Compact Disc - Re-Writable), or DVD-ROM (Digital Video Disk - Read Only Memory). The components described above are for illustrative purposes only to illustrate various possibilities. The exemplary computer systems described above are not intended to limit the scope of this disclosure.

[0083] Figure 13 shows an exemplary method flowchart (1300) illustrating a method for signature-based verification of an executable set of instructions before execution, according to one embodiment of the present disclosure. Method (900) can be described in the general context of computer executable instructions. Generally, computer executable instructions include routines, programs, objects, components, data structures, etc., that perform a particular function or execute a particular abstract data type.

[0084] The order in which Method (1300) is described is not intended to be construed as limiting, and Method (1300) can be implemented by combining any number of described Method blocks in any order. Furthermore, individual blocks can be removed from any Method without departing from the spirit and scope of the subject matter described herein. In addition, Method (1300) can be implemented with any suitable hardware, software, firmware, or combination thereof.

[0085] In block (1302), the method may include receiving a set of data packets from a first cell and a second cell in a communication network by a data acquisition engine (212) of a processor (202). The set of data packets includes one or more pairs of tropospheric interference data from the first cell and the second cell, the intensity of the tropospheric interference indicating the intensity of the first cell signal received in the second cell, the date of the tropospheric interference, and the time of the tropospheric interference, or a combination thereof.

[0086] In block (1304), the method may include extracting a first set of attributes, a second set of attributes, and a third set of attributes of a first cell by the attribute extraction engine (214) of the processor (202). The second cell is a set of received data packets. The first set of attributes corresponds to cell configuration data, including total tilt, remote electrical tilt (RET), cell tower height, mechanical tilt, power transmission, and cell tower location. The second set of attributes corresponds to meteorological data, including meteorological data indexes at the cell tower location of a given cell on a given date and time, and Hepburn indexes on the region joining the pair of first and second cells. The third set of attributes corresponds to meteorological data.

[0087] In block (1306), the method may include the step of identifying one or more pairs of first and second cells affected by tropospheric interference based on an extracted first set of attributes, an extracted second set of attributes, and an extracted third set of attributes by the ML engine (216) of the processor (202). The processor (202) further calculates a first edge score for one or more identified pairs of first and second cells based on the extracted first set of attributes, the extracted second set of attributes, and the extracted third set of attributes. The first edge score for one or more identified pairs of first and second cells indicates the likelihood of tropospheric interference between one or more pairs of first and second cells. The first edge score for one or more identified pairs of first and second cells is calculated using a feature vector obtained by concatenating the first set of attributes, the second set of attributes, and the third set of attributes of one or more pairs of first and second cells. The processor (202) assigns actions to pairs of first and second cells based on the first edge score. The actions assigned to one or more pairs of first and second cells include changes to the total tilt and remote electrical tilt (RET) of the antennas of one or more pairs of first and second cells. The processor (202) calculates the second edge score based on the actions assigned to one or more pairs of first and second cells. The processor (202) calculates the impact of the actions assigned to one or more pairs of first and second cells based on the first and second edge scores. The impact of the actions assigned to one or more pairs of first and second cells is the difference between the first edge score and the second edge score.

[0088] In block (1308), the method may include mitigating tropospheric interference between identified pairs of first and second cells by having a processor (202) configure the total tilt and remote electrical tilt (RET) of the antenna for one or more pairs of first and second cells.

[0089] While this specification places considerable emphasis on preferred embodiments, it should be understood that many embodiments can be made and many modifications can be made in the preferred embodiments without departing from the principles of the present invention. These and other modifications in the preferred embodiments of the present invention will be obvious to those skilled in the art from the disclosure herein, and it should be clearly understood that the foregoing descriptions are not limiting to the invention but should be implemented merely as examples.

[0090] Benefits of this disclosure This disclosure provides a method and system for modeling a digital twin for long-range tropospheric interference mitigation using gradient boost trees and actions, but is not limited to providing remote electrical tilt changes. Various modeling techniques can be used in the digital twin model, including random forests, neural networks, and deep learning methods. Various actions are possible, such as changes in height, mechanical tilt, and azimuth. Using this unique solution provided in this disclosure, tropospheric interference can be mitigated by proactively targeting cells that cause long-range interference and performing actions such as increasing remote electrical tilt, height, mechanical tilt of azimuth, etc.

[0091] This disclosure provides a method and system for improving network performance by mitigating tropospheric interference to one or more pairs of first and second cells.

[0092] This disclosure provides a method and system for predicting the likelihood of tropospheric interference by calculating edge scores for one or more pairs of first and second cells based on the attributes of one or more pairs of first and second cells. This prevents tropospheric interference and improves network performance.

[0093] This disclosure provides a method and system for identifying actions with minimal impact on coverage and proposing amounts of tilt values ​​for each cell to mitigate tropospheric interference.

[0094] Reservation of rights Some disclosures in this patent document include, but are not limited to, materials subject to intellectual property rights, such as copyrights, designs, trademarks, IC layout designs, and / or trade dress protections, belonging to Jio Platforms Limited (JPL) or its affiliates (hereinafter, the Owners). The Owners of copyrights and trademarks have no objection to any complete copying of the patent document or patent disclosure by any person, as expressed in patent applications and records with the Japan Patent and Trademark Office, but retain all other copyrights and trademark rights. All rights to such intellectual property are fully reserved by the Owners. This disclosure may relate to 3GPP specifications, such as 3GPP® TS36.211 version 12.9.0 release 12.

Claims

1. A system for mitigating tropospheric interference in communication networks, Processor (202), A memory (204) coupled to the processor (202), wherein the memory (204) provides the processor with a function during execution. Receiving a set of data packets relating to the first cell and the second cell in the communication network from the database (210), Extracting the first attribute set, the second attribute set, and the third attribute set of the first cell and the second cell from the set of data packets received from the database (210), Based on the extracted first attribute set, the extracted second attribute set, and the extracted third attribute set, one or more pairs of first and second cells affected by the tropospheric interference are identified. By configuring full tilt and remote electric tilt (RET) for the identified one or more pairs of the first and second cells, the tropospheric interference of the identified one or more pairs of the first and second cells is reduced. The memory includes a processor-executable instruction that causes the operation, The system comprising the above.

2. The system according to claim 1, wherein the set of data packets includes any or a combination of the tropospheric interference data of one or more pairs of the first cell and the second cell, the intensity of the tropospheric interference indicating the intensity of the first cell signal received in the second cell, the date of the tropospheric interference, and the time of the tropospheric interference.

3. The system according to claim 1, wherein the first attribute set corresponds to cell configuration data including total tilt, remote electric tilt (RET), cell tower height, mechanical tilt, power transmission, and cell tower location.

4. The system according to claim 1, wherein the second attribute set corresponds to Hepburn data including a weather data index at the location of a cell tower of a given cell on a given date and time, and a Hepburn index on the region joining the first and second cells of a pair.

5. The system according to claim 1, wherein the third attribute set corresponds to weather data.

6. The system according to claim 1, wherein the processor-executable instruction further causes the processor (202) to calculate a first edge score for one or more pairs of the identified first and second cells based on the extracted first attribute set, the extracted second attribute set, and the extracted third attribute set.

7. The system according to claim 6, wherein the first edge score of one or more pairs of identified first and second cells indicates the possibility of tropospheric interference between the one or more pairs of first and second cells.

8. The system according to claim 6, wherein the first edge score for one or more pairs of identified first and second cells is calculated using a feature vector obtained by concatenating the first attribute set, the second attribute set, and the third attribute set of one or more pairs of first and second cells.

9. The system according to claim 6, wherein the processor-executable instruction further causes the processor (202) to assign actions to one or more pairs of the first and second cells based on the first edge score during execution.

10. The system according to claim 9, wherein the action assigned to one or more pairs of the first and second cells includes changing the total tilt and remote electric tilt (RET) of the one or more pairs of the first and second cells.

11. The system according to claim 9, wherein the processor-executable instruction further causes the processor (202) to calculate a second edge score based on the actions assigned to the one or more pairs of the first and second cells during execution.

12. The system according to claim 11, wherein the processor-executable instruction further causes the processor (202) to calculate the effect of the action assigned to one or more pairs of the first and second cells based on the first and second edge scores during execution.

13. The system according to claim 12, wherein the effect of the action assigned to one or more pairs of the first and second cells is the difference between the first edge score and the second edge score.

14. A method for mitigating tropospheric interference in a communication network, The processor (202) receives a set of data packets relating to the first cell and the second cell in the communication network from the database (210), The processor (202) extracts a first attribute set, a second attribute set, and a third attribute set of the first cell and the second cell from the set of data packets received from the database (210), The processor (202) identifies one or more pairs of the first and second cells affected by tropospheric interference based on the extracted first attribute set, the extracted second attribute set, and the extracted third attribute set. The processor (202) reduces tropospheric interference of the identified one or more pairs of first and second cells by configuring the total tilt and remote electrical tilt (RET) of the identified one or more pairs of first and second cells, The method, including the method described above.

15. The method according to claim 14, wherein the set of data packets includes any or a combination of the tropospheric interference data of one or more pairs of the first cell and the second cell, the intensity of the tropospheric interference indicating the intensity of the first cell signal received in the second cell, the date of the tropospheric interference, and the time of the tropospheric interference.

16. The method according to claim 14, wherein the first attribute set corresponds to cell configuration data including total tilt, remote electrical tilt (RET), cell tower height, mechanical tilt, power transmission, and cell tower location.

17. The method according to claim 14, wherein the second attribute set corresponds to Hepburn data including a weather data index at the location of the cell tower for a given cell at a given date and a given time, and a Hepburn index on the region joining the first and second cells of a pair.

18. The method according to claim 14, wherein the third attribute set corresponds to weather data.

19. The method according to claim 14, wherein the processor (202) further calculates a first edge score for the identified first and second cell pairs based on the extracted first attribute set, the extracted second attribute set, and the extracted third attribute set.

20. The method according to claim 19, wherein the first edge score of the identified first cell-second cell pair indicates the possibility of tropospheric interference of the first cell-second cell pair.

21. The method according to claim 19, wherein the first edge score for one or more pairs of identified first and second cells is calculated using a feature vector concatenating the first attribute set, the second attribute set, and the third attribute set of the one or more pairs of first and second cells.

22. The method according to claim 19, wherein the processor (202) assigns an action to one or more pairs of the first cell and the second cell based on the first edge score.

23. The method according to claim 22, wherein the actions assigned to the one or more pairs of first and second cells include changing the total tilt and remote electric tilt (RET) of the one or more pairs of first and second cells.

24. The method according to claim 22, wherein the processor (202) calculates a second edge score based on the actions assigned to one or more pairs of the first cell and the second cell.

25. The method according to claim 24, wherein the processor (202) calculates the effect of the actions assigned to the one or more pairs of first and second cells based on the first edge score and the second edge score.

26. The method according to claim 25, wherein the effect of the action assigned to the one or more pairs of the first cell and the second cell is the difference between the first edge score and the second edge score.

Images