Machine Learning-Based Interference Detection for Hierarchical Licensing Deployment

Abstract

Examples for machine learning-based interference detection for hierarchical licensing deployment are described. Network entities in a General Authorized Access (GAA) deployment check a local spectrum access database of GAA users to determine that a portion of the shared spectrum is freed from known local users in a geographic area. The network entity receives samples of wireless signals containing at least a desired signal on a portion of the shared spectrum. The network entity determines whether the wireless signal contains a plurality of unrelated signals. The network entity identifies an interference signal in response to determining that the wireless signal contains a plurality of unrelated signals.

Description

Background Art

[0001] A radio access network (RAN) can provide wireless access to a network to a plurality of user devices. The user devices can communicate wirelessly with a base station, and the base station forwards the communication towards the core network. Conventionally, the base station in a RAN is implemented by dedicated processing hardware (e.g., an embedded system) located near a radio unit including an antenna. The base station can perform lower layer processing including physical (PHY) layer processing and media access control (MAC) layer processing for one or more cells. There can be costs associated with deploying dedicated processing hardware for each base station in a RAN, particularly for a RAN including small cells having a relatively small coverage area. Further, the dedicated processing hardware can be a single point of failure for a cell. A virtualized radio access network may utilize one or more data centers having general - purpose computing resources to perform RAN processing for one or more cells. That is, instead of performing PHY - layer processing and MAC - layer processing locally on dedicated hardware, a virtualized radio access network may forward radio signals from a radio unit to an edge data center for processing and, similarly, forward signals from the edge data center to the radio unit for wireless transmission. In a specific example, a cloud - computing environment may be used to provide mobile edge computing (MEC), where some functions of a mobile network may be provided as workloads on nodes in the cloud - computing environment. In MEC, a centralized unit (CU) may be implemented at a backend node, one or more distributed units (DU) may be implemented at intermediate nodes, and various radio units (RU) may be deployed at edge servers having connections to antennas. The RU can communicate with the CU via one or more DUs. In one example, the DU can provide upper - layer network - layer functions for the RAN, such as radio link control (RLC) layer functions or packet data convergence protocol (PDCP) layer functions. The RU can facilitate access to the CU for various downstream devices, such as user equipment (UE), Internet of Things (IoT) devices, etc. Since the data center utilizes general - purpose computing resources, the virtualized RAN can provide scalability and fault tolerance for base - station processing. For example, the data center can allocate a variable number of computing resources (e.g., servers) to perform processing for radio units based on the workload. Further, the virtualized RAN can implement multiple layers of RAN processing in the data center and enable the collection of multiple data feeds. Hierarchical licensing deployment refers to a system deployed in a shared access band with two or more tiers of licensees. For example, the Citizens Broadband Radio Service (CBRS) band has a three-tier access and authorization framework for the 3550 - 3700 MHz (3.5 GHz) band. The three tiers include incumbent access, priority access, and General Authorized Access (GAA). GAA users must not cause harmful interference to incumbent access users or priority access licensees and must tolerate interference from these users. GAA users also do not expect protection from interference from other GAA users.

Summary of the Invention

[0002] The following presents a simplified overview of such aspects in order to provide a basic understanding of one or more aspects. The summary of the invention is not an extensive overview of all contemplated aspects, nor does it identify the main or important elements of all aspects, nor does it delimit the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description presented later.

[0003] In some aspects, the techniques described herein are for an apparatus for wireless communication, the apparatus including a memory storing computer-executable instructions, and a processor coupled to the memory, the processor configured to execute instructions to check a local spectrum access database of known General Authorized Access (GAA) users to determine that a portion of the shared spectrum is free from known local users in a geographic area, receive a sample of a wireless signal including at least a desired signal on the portion of the shared spectrum, determine whether the wireless signal includes a plurality of uncorrelated signals, and identify an interference signal in response to determining that the wireless signal includes a plurality of uncorrelated signals.

[0004] In some aspects, the techniques described herein relate to an apparatus, wherein the processor is further configured to mitigate interference signals. In some aspects, the techniques described herein relate to an apparatus, wherein the processor is further configured to shift a carrier frequency into a shared spectrum to mitigate interference signals.

[0005] In some aspects, the techniques described herein relate to an apparatus, wherein the processor is further configured to add an interference signal to a local spectrum access database to mitigate the interference signal.

[0006] In some aspects, the techniques described herein relate to an apparatus, wherein the processor is further configured to determine a difference between an expected decoding rate and an actual decoding rate based on a measured signal quality, and determining whether a wireless signal includes a plurality of uncorrelated signals is in response to the difference exceeding a threshold.

[0007] In some aspects, the techniques described herein relate to an apparatus, wherein the processor is configured to apply samples of a wireless signal to a machine learning-based source separation algorithm to determine whether the wireless signal includes a plurality of uncorrelated signals.

[0008] In some aspects, the techniques described herein relate to an apparatus, wherein a machine learning-based source separation algorithm is configured to indicate multiple copies of a desired signal with different delays to determine whether a wireless signal includes a plurality of uncorrelated signals.

[0009] In some aspects, the techniques described herein relate to an apparatus configured such that a machine learning-based source separation algorithm determines whether a wireless signal includes a plurality of unrelated signals and indicates at least one signal unrelated to a desired signal.

[0010] In some aspects, the techniques described herein relate to an apparatus configured such that a processor checks a spectrum access system (SAS) database of license users at an access stratum higher than that of GAA users and selects a portion of the shared spectrum to avoid interference with license users.

[0011] In some aspects, the techniques described herein relate to a method including checking a local spectrum access database of known general authorized access (GAA) users to determine that a portion of the shared spectrum is free from known local users in a geographic area, receiving a sample of a wireless signal including at least a desired signal on the portion of the shared spectrum, determining whether the wireless signal includes a plurality of unrelated signals, and identifying an interference signal in response to determining that the wireless signal includes a plurality of unrelated signals.

[0012] In some aspects, the techniques described herein relate to a method further including mitigating an interference signal. In some aspects, the techniques described herein relate to a method, wherein mitigating the interference signal includes shifting a carrier frequency within the shared spectrum.

[0013] In some aspects, the techniques described herein relate to a method, wherein mitigating the interference signal includes adding the interference signal to a local spectrum access database.

[0014] In some aspects, the techniques described herein are methods that further include determining a difference between an expected decoding rate and an actual decoding rate based on a measured signal quality, wherein the step of determining whether a wireless signal includes a plurality of uncorrelated signals is in response to the difference exceeding a threshold, and relate to a method.

[0015] In some aspects, the techniques described herein are methods, wherein the step of determining whether a wireless signal includes a plurality of uncorrelated signals includes applying a sample of the wireless signal to a machine learning-based source separation algorithm, and relate to a method.

[0016] In some aspects, the techniques described herein are methods, wherein the step of determining whether a wireless signal includes a plurality of uncorrelated signals includes the output of a machine learning-based source separation algorithm indicating a plurality of copies of a desired signal with different delays, and relate to a method.

[0017] In some aspects, the techniques described herein are methods, wherein the step of determining whether a wireless signal includes a plurality of uncorrelated signals includes the output of a machine learning-based source separation algorithm indicating at least one signal unrelated to the desired signal, and relate to a method.

[0018] In some aspects, the techniques described herein are methods that further include checking a spectrum access system (SAS) database of license users at an access stratum higher than that of GAA users, and selecting a portion of the shared spectrum to avoid interference to license users, and relate to a method.

[0019] In some aspects, the techniques described herein, when executed by a processor, cause the processor to check a local spectrum access database of known general authorized access (GAA) users to determine that a portion of the shared spectrum is freed from known local users in a geographic area, receive samples of a wireless signal including at least a desired signal on the portion of the shared spectrum, determine whether the wireless signal includes a plurality of uncorrelated signals, and identify an interference signal in response to determining that the wireless signal includes a plurality of uncorrelated signals, and relate to a non-transitory computer-readable medium storing computer-executable instructions for doing so.

[0020] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium further including instructions for mitigating an interference signal.

[0021] To achieve the above and related objects, one or more aspects are described in sufficient detail below and particularly pointed out in the claims. The following description and the accompanying drawings detail some exemplary features of one or more aspects. However, these features represent only some of the various ways in which the principles of the various aspects may be employed and this description is to be considered as including all such aspects and their equivalents.

Brief Description of the Drawings

[0022]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

[0023] The detailed description set forth below in connection with the appended drawings is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of various concepts. It will be apparent to those skilled in the art, however, that these concepts may be practiced without these specific details. In some instances, well-known components are shown in block diagram form in order to avoid obscuring such concepts.

[0024] This disclosure describes various examples related to the operation of a General Authorized Access (GAA) system within a hierarchical licensing system. For example, in the United States, the Citizens Broadband Radio Service (CBRS) spectrum is available on the 3.5 GHz band from 3550 to 3700 MHz. The upper tier is the incumbent access, which includes federal users, fixed satellite service earth stations, and some legacy wireless broadband licensees. Incumbent access users are protected from harmful interference from priority access licensees and general authorized access users. The second tier is the Priority Access License (PAL) that has a license for a 10 MHz channel within the CBRS spectrum. The PAL protects and tolerates interference from incumbent access users but must be protected from general authorized access users. The third tier is GAA. GAA users must not cause harmful interference to incumbent access users or priority access licensees and must tolerate interference from these users. GAA users also do not expect protection from interference from other GAA users.

[0025] To provide protection to incumbent access users and PAL users, a spectrum access system (SAS) provides information regarding use by incumbent access users and PAL users. Thus, a GAA user may access the SAS to avoid causing interference to higher tier users and to avoid interference signals from higher tier users. However, the SAS does not provide information regarding other GAA users. Since a GAA user does not expect interference protection from other GAA users, a GAA system may experience interference from other GAA users. Thus, it may be desirable for an enterprise implementing a GAA system to attempt to identify and mitigate interference signals from other GAA users. In a conventional licensing system, a licensee may be protected from external interferers, and thus, interference detection techniques may not be necessary or may be limited to the detection of interference between devices within the licensing system. In a conventional non-licensing system, the spectrum may be shared using techniques such as clear channel assessment (CCA) and listen before talk (LBT). However, in the case of GAA users, there may be no guarantee that interferers will share the spectrum based on such techniques.

[0026] In a software radio access network (also called virtual RAN or vRAN), various base station components can be implemented in software that runs on general-purpose computing resources. For example, in a cloud network implementation, vRAN components can be run as workloads on servers or in data centers. A major transformation in the radio access network (RAN) for 5G is the shift to an open RAN architecture, which refers to a virtualized and disaggregated 5G RAN across multiple open interfaces. This approach fosters innovation by enabling multiple vendors to find their own solutions for different components at a faster pace. Additionally, a new component introduced in the open RAN architecture, called the Radio Intelligent Controller (RIC), enables third parties to build new, vendor-agnostic monitoring and optimization use cases on interfaces standardized by O-RAN.

[0027] In one aspect, the present disclosure provides a system for identifying and mitigating interference signals from other GAA users. The system can maintain and / or access a local spectrum access database of known GAA users to determine whether portions of the shared spectrum are available from known local users in a geographic area. Unlike the SAS for higher-tier users, the local spectrum access database can be autonomous and can be incomplete or legacy. The system can also detect other GAA users not in the local spectrum access database. A disaggregated O-RAN architecture can provide access to in-phase and quadrature (IQ) samples received at network entities such as base stations. Such IQ samples may not have been previously available to network operators or network operators have had little control over the processing of such IQ samples. In one aspect, the system can identify signals that actually interfere with the desired signal using machine learning signal separation techniques applied to the received IQ samples. For example, the desired signal can experience multipath propagation and arrive at the receiver as a superposition of multiple copies of the transmitted signal. Such multipath propagation can appear to be interference but may not be considered an actual interfering signal from outside the system. Interference signals from outside the system can be independent of the desired signal. The machine learning signal separation techniques can output the independent signals and / or output the possibility that the received signal contains multiple independent signals. Thus, the system can detect signals that are received simultaneously with the desired signal and interfere with the desired signal. In some implementations, the system can be configured to mitigate interference from such external interference signals. For example, the system can select different portions of the shared spectrum to avoid the interference signal. In some implementations, the system can add the interference signal to the local spectrum access database to facilitate avoiding the interference signal.

[0028] Next, referring to FIGS. 1 to 5, examples are shown with respect to one or more components and one or more methods that can perform the actions or operations described herein, where the dashed components and / or actions / operations may be optional. Although the operations described below in FIG. 4 are presented as being performed in a particular order and / or by exemplary components, the ordering of the actions and the components performing the actions can be varied in some examples depending on the implementation. Moreover, in some examples, one or more of the actions, functions, and / or components described can be performed by a specially programmed processor, a processor executing specially programmed software or a computer-readable medium, or by any other combination of hardware components and software components capable of performing the described actions or functions.

[0029] FIG. 1 is a diagram of an exemplary mobile network 100 that includes a radio access network (RAN) connecting user equipment (UE) 110 to a core network 160. The RAN can be implemented at least in part as a virtualized radio access network (vRAN) 102. The vRAN 102 can include a radio unit (RU) 120 that transmits and receives wireless signals with the UE 110 over a wireless link 112. Each RU 120 can provide a cell 122 having a coverage area that may overlap with other cells. Each RU 120 can include one or more antennas for transmitting and receiving radio frequency (RF) signals with the UE 110 within the cell 122.

[0030] vRAN 102 may include virtual network components that can be implemented on general-purpose computing resources, such as in cloud network 104. Cloud network 104 may include a underlying wide area network (WAN) having computing resources, such as servers or data centers, that can be used to instantiate software network functions. For example, vRAN 102 may include one or more virtual distributed units (vDUs) 130 that perform processing for cell 122, for example, in the physical (PHY) layer, media access control (MAC) layer, and radio link control (RLC) layer. vRAN 102 may include one or more virtual central units (vCUs) 140 that perform processing in the upper layers of the wireless protocol stack. In an exemplary architecture, vCU 140 may be split into a central unit control plane (CU-CP) and a central unit user plane (CU-UP). CU-UP may include the packet data convergence protocol (PDCP) layer, service data adaptation (SDAP) layer, and radio resource control (RRC) layer.

[0031] The split of functions or protocol layers between vDU 130 and vCU 140 may depend on the functional split architecture. For example, as shown, the functional split may be between the RLC layer and the PDCP layer and may sometimes be referred to as Option 2. Other options may include a functional split between the RRC layer and the PDCP layer (Option 1), or a functional split between or within the layers shown in vDU 130. Thus, vRAN 102 may enable network operators to have greater flexibility in where network equipment vendors should locate computing resources for various protocol layers.

[0032] vRAN 102 may include a Radio Access Network Intelligent Controller (RIC) 150 that performs autonomous configuration and optimization of vRAN 102. In some implementations, the RIC 150 may allocate resources of the cloud network 104 to instantiate vRAN components such as vDUs 130 and vCUs 140. For example, the RIC 150 may provide a configuration file for each vDU 130 or vCU 140. The RIC 150 may allocate network resources such as frequency sub-bands to cells. Further, the RIC may monitor the performance of vRAN 102 and adapt the configuration. For example, the RIC 150 may receive monitoring information such as performance metrics from vRAN components such as vDUs 130 and vCUs 140.

[0033] In one aspect, the RIC 150 may include a GAA control component 152 configured to control the deployment of vRAN 102 as a GAA user on a shared access band subject to hierarchical licensing. The GAA control component 152 may communicate with an interference detection component 170 that may be located in the vDU 130. For example, the interference detection component 170 may operate within or in parallel with the PHY layer processing. For example, the interference detection component 170 may receive IQ samples from the RU 120 and detect interference signals based on the IQ samples, as described in more detail below. The GAA control component 152 may also communicate with a local spectrum access database 180 and a SAS database 182. The SAS database 182 may provide information regarding incumbent access users and / or PALs. The GAA control component 152 may avoid interfering with such higher-tier users in accordance with the GAA license.

[0034] The local spectrum access database 180 may store information about GAA users. In some implementations, the GAA control component 152 may host or control the local spectrum access database 180. Alternatively, the local spectrum access database 180 may be a publicly accessible database or, for example, a proprietary database provided by a third party based on a subscription. In some implementations, the GAA control component 152 includes a mitigation component 154 configured to mitigate interference caused by interference signals from other GAA users. Information about other GAA users may be stored in the local spectrum access database 180. Participation in the local spectrum access database 180 may be voluntary. For example, an enterprise acting as a GAA user may provide information about its system (e.g., vRAN 102) so that other GAA users can avoid interference. Similarly, the enterprise may wish to obtain information about neighboring GAA users to avoid causing and receiving interference from neighboring GAA users. However, some GAA users may not wish to provide information about network deployment to other GAA users. In some implementations, when interference from such GAA users is detected and made public, information about such GAA users may be added to the local spectrum access database 180.

[0035] FIG. 2 is a diagram 200 of an exemplary deployment scenario in which a first GAA user experiences interference from a second GAA user. The first GAA user may deploy an RU 220 that provides a cell 222 for wireless communication with the UE 110. The RU 220 may communicate with a vDU 130 that performs PHY processing for the cell. The vDU 130 may be controlled by the RIC 150 of the first GAA user.

[0036] A second GAA user may deploy RU240 that provides cell 242 for communication with UE250. In some implementations, there may be no cooperation between the first GAA user and the second GAA user. The downlink signal from RU240 and / or the uplink signal from UE250 may interfere with reception at RU220. In a licensed spectrum, such interference can be avoided because only one party controls the spectrum and that party can coordinate the RUs to avoid cross-link interference. In an unlicensed spectrum, users may follow a CCA procedure or an LBT procedure to avoid interference. However, in a hierarchical access system, GAA users may cause interference to each other.

[0037] The interference detection component 170 in the vDU may detect signals that interfere with the desired signal. For example, UE110 may transmit the desired signal 210 towards RU220. The desired signal 210 may propagate along multiple paths such as the line-of-sight path 212 and a second path 214 that reflects from one or more objects 216. From the perspective of RU220, the desired signal 210 arriving via multiple paths may appear to be an interference signal but may actually be a time-delayed version of the same signal. An actual interference signal 252 may be transmitted by RU240 or UE250. The interference signal 252 may be independent of the desired signal 210.

[0038] In one aspect, the interference detection component 170 may determine whether the wireless signal received at RU220 includes a plurality of unrelated signals. For example, the interference detection component 170 may apply the received IQ samples to a machine learning (ML) source separation algorithm. The ML source separation algorithm may utilize a deep neural network (DNN) model. For example, a DNN for single channel source separation that may be used by the interference detection component 170 is described in Grais et al., "Deep Neural Networks for Single Channel Source Separation", arXiv:1311.2746v1, where samples of an audio signal were applied to the model to separate a vocal source and an instrument source. To separate the sources of the wireless signal in the IQ samples, training data for the desired signal may be obtained by collecting samples from interference-free transmissions. The training data also includes transmissions with interference from controlled transmissions. The training data may also be supplemented with simulated transmissions. Training may be performed in an offline manner. However, the training data set may be updated when the bit error rate is statistically much higher than expected from the signal quality.

[0039] The ML source separation algorithm may output one or more unrelated signals. If the ML source separation algorithm outputs a single unrelated signal, the interference detection component 170 may determine that the received signal includes multiple copies of the desired signal 210 with different delays. If the ML source separation algorithm outputs a plurality of unrelated signals, the interference detection component 170 may determine that the received signal includes an interference signal 252.

[0040] In some implementations, the interference detection component 170 can be triggered to detect the interference signal 252 based on performance characteristics. For example, the interference detection component 170 can monitor the decoding rate or the error rate (e.g., the block error rate (BLER)), and determine the difference between the expected decoding rate based on the measured signal quality and the actual decoding rate. If the difference exceeds a threshold, the interference detection component 170 can determine whether the wireless signal contains multiple unrelated signals.

[0041] The interference detection component 170 can provide information about the interference signal 252 to the GAA control component 152. For example, the interference detection component 170 can identify the time of the interference signal 252, or the receive beam when the interference signal 252 is detected.

[0042] In some implementations, the GAA control component 152 and / or the mitigation component 154 can attempt to mitigate the interference signal 252. For example, the GAA control component 152 and / or the mitigation component 154 can shift the carrier frequency for the RU 220 within the shared spectrum, or otherwise allocate different frequency resources to avoid the interference signal 252. As another example, the GAA control component 152 and / or the mitigation component 154 can add the interference signal to the local spectrum access database 180. Thus, the GAA control component 152 and other GAA systems can avoid the interference signal 252.

[0043] FIG. 3 is a schematic diagram of an example of an apparatus 300 (e.g., a computing device) for implementing the vDU 130 that includes the interference detection component 170. The apparatus 300 can be an example of a network entity. The apparatus 300 can be present within a data center that can be an edge data center. The apparatus 300 can be connected to other servers within the data center or to other servers in other data centers via a switch 340. For example, the apparatus 300 can be connected to the RU 120, the vCU 140, and the RIC 150. In some implementations, one or more of the RU 120, the vCU 140, or the RIC 150 can implement the interference detection component 170 or a component thereof.

[0044] In one example, the apparatus 300 can include a processor 302 and / or a memory 304 configured to execute or store instructions or other parameters related to providing an operating system 306, and the operating system 306 can execute one or more applications or processes, including but not limited to the interference detection component 170. For example, the processor 302 and the memory 304 can be separate components communicatively coupled by a bus (e.g., on an integrated circuit such as a system-on-chip (SoC) on a motherboard or other part of a computing device), components incorporated within each other (e.g., the processor 302 can include the memory 304 as an on-board component), and the like. The memory 304 can store instructions, parameters, data structures, etc. for use / execution by the processor 302 to implement the functions described herein.

[0045] In one example, the interference detection component 170 can include one or more of a configuration component 172, a receiving component 174, a separating component 176, or an identifying component 178. The constituent component 172 can be configured to check the local spectrum access database 180 of known GAA users in order to determine that a portion of the shared spectrum has been released from known local users in a geographical area. For example, the interference detection component 170 can provide the geographical coordinates of the RU 120 to the GAA control component 152 for comparison with the local spectrum access database 180. For example, the GAA control component 152 can query the local spectrum access database 180 with the geographical coordinates of known GAA users within an interfering distance (e.g., 1 km in the case of a macro cell) and compare the portion of the shared spectrum with the portion of the spectrum used by known GAA users. In some implementations, the constituent component 172 and / or the GAA control component 152 can also check the SAS database 182 of licensed users who are in a higher access stratum than GAA users. In some implementations, the constituent component 172 and / or the GAA control component 152 can select a portion of the shared spectrum to avoid interference to licensed users and / or other GAA users.

[0046] The receiving component 174 can be configured to receive samples of a wireless signal including at least a desired signal on a portion of the shared spectrum. For example, the receiving component 174 can receive IQ samples from the RU 120. In some implementations, the receiving component 174 can include a network interface controller (NIC) configured to receive IP packets via the switch 340. The receiving component 174 can be configured to implement an O-RAN interface for receiving IQ samples within the IP packets. The above samples can include at least the desired signal 210. For example, the above samples can be collected when an uplink transmission from the UE 110 is scheduled. The above samples can also include an interference signal 252.

[0047] The separation component 176 can be configured to determine whether a wireless signal includes a plurality of uncorrelated signals. For example, the separation component 176 can be configured to apply the above sample to an ML source separation algorithm. The separation component 176 can output the number of uncorrelated signals or actual uncorrelated signals.

[0048] The identification component 178 can be configured to identify an interference signal in response to determining that a wireless signal includes a plurality of uncorrelated signals. For example, the identification component 178 can identify an interference signal 252 to the GAA control component 152 and / or the local spectrum access database 180. The identification component 178 can identify the interference signal 252 based on the frequency range in which the interference signal 252 is detected, or other signal properties.

[0049] In some implementations, the apparatus 300 can include a GAA control component 152. For example, the GAA control component 152 can be implemented in the vDU 130, or can be implemented on the same data center as the vDU 130 and the RIC. The GAA component 152 can be configured to communicate with the local spectrum access database 180 and / or the SAS database 182. The GAA component 152 can include a mitigation component 154 configured to mitigate the interference signal 252. For example, the GAA component 152 can shift the carrier frequency into the shared spectrum, or add the interference signal 252 to the local spectrum access database 180.

[0050] FIG. 4 is a flowchart of an example of a method 400 for interference detection by a GAA user. For example, the method 400 can be implemented by the apparatus 300 and / or one or more of its components to detect an interference signal 252. Some blocks of the method 400 can optionally be implemented by other network components communicating with the apparatus 300.

[0051] In block 410, method 400 optionally includes checking the SAS database of license users at an access level higher than that of GAA users. In one example, constituent component 172 can check the SAS database 182 of license users at an access level higher than that of GAA users, for example, together with processor 302, memory 304, and operating system 306. For example, constituent component 172 can access the SAS database 182 directly or via the GAA control component 152.

[0052] In block 420, method 400 optionally includes selecting a portion of the shared spectrum to avoid interfering with license users. In one example, constituent component 172 can select a portion of the shared spectrum to avoid interfering with license users, for example, together with processor 302, memory 304, and operating system 306. For example, constituent component 172 can receive an indication of the portion of the shared spectrum from the GAA control component 152 or autonomously select a portion of the shared spectrum not being used by the license users.

[0053] In block 430, method 400 includes checking the local spectrum access database of known GAA users to determine that the portion of the shared spectrum is free from known local users in the geographical area. In one example, constituent component 172 can check the local spectrum access database 180 of known GAA users to determine that the portion of the shared spectrum is free from known local users in the geographical area, for example, together with processor 302, memory 304, and operating system 306. For example, constituent component 172 can access the local spectrum access database 180 directly or via the GAA control component 152.

[0054] In block 440, method 400 includes receiving samples of a wireless signal that includes at least a desired signal on a portion of the shared spectrum. In one example, receiving component 174 can receive samples of a wireless signal that includes at least a desired signal on a portion of the shared spectrum, for example, together with processor 302, memory 304, and operating system 306. For example, receiving component 174 can receive the samples from RU120.

[0055] In block 450, method 400 can optionally include determining a difference between an expected decoding rate and an actual decoding rate based on the measured signal quality. In one example, receiving component 174 can determine a difference between an expected decoding rate and an actual decoding rate based on the measured signal quality, for example, together with processor 302, memory 304, and operating system 306.

[0056] In block 460, method 400 includes determining whether the wireless signal includes a plurality of uncorrelated signals. In one example, separation component 176 can determine whether the wireless signal includes a plurality of uncorrelated signals, for example, together with processor 302, memory 304, and operating system 306. In some implementations, in sub-block 462, block 460 can include applying samples of the wireless signal to a machine learning-based source separation algorithm. The output of the machine learning-based source separation algorithm can indicate multiple copies of the desired signal with different delays that are not considered to be a plurality of uncorrelated signals. Alternatively, the output of the machine learning-based source separation algorithm can indicate at least one signal that is uncorrelated with the desired signal.

[0057] In block 470, method 400 includes identifying an interference signal in response to determining that the wireless signal includes a plurality of uncorrelated signals. In one example, identification component 178 can identify interference signal 252 in response to determining that the wireless signal includes a plurality of uncorrelated signals, for example, together with processor 302, memory 304, and operating system 306.

[0058] In block 480, method 400 may optionally include mitigating the interference signal. In one example, mitigation component 154 can mitigate the interference signal, for example, together with processor 302, memory 304, and operating system 306. For example, in some implementations, in sub-block 482, block 480 may include shifting the carrier frequency within the shared spectrum. As another example, in some implementations, in sub-block 484, block 480 may include adding interference signal 252 to local spectrum access database 180.

[0059] FIG. 5 shows an example of a device 500 that includes additional optional component details such as those shown in FIG. 3. In one aspect, device 500 may include a processor 502 similar to processor 302 for performing processing functions related to one or more of the components and functions described herein. Processor 502 can include a single or multiple sets of processors, or a multi-core processor. Additionally, processor 502 can be implemented as an integrated processing system and / or a distributed processing system.

[0060] Device 500 may further include a memory 504, similar to memory 304, for storing local versions of an operating system (or components thereof) and / or applications executed by processor 502, such as interference detection component 170, GAA control component 154, etc. Memory 504 can include types of memory usable by a computer, such as random access memory (RAM), read only memory (ROM), tapes, magnetic disks, optical disks, volatile memory, non-volatile memory, and any combination thereof.

[0061] Furthermore, device 500 may include a communication component 506 that enables it to establish and maintain communication with one or more other devices, parties, entities, etc., using the hardware, software, and services described herein. Communication component 506 can carry communication between components on device 500, as well as between device 500 and external devices, such as devices located across a communication network and / or devices serially or locally connected to device 500. For example, communication component 506 can include one or more buses and may further include a transmit chain component and a receive chain component associated with a wireless or wired transmitter and receiver, respectively, operable to interface with external devices.

[0062] Furthermore, device 500 may include a data store 508, which can be any suitable combination of hardware and / or software that provides large-capacity storage of information, databases, and programs employed in the aspects described herein. For example, data store 508 can be, or can include, a data repository for an operating system (or components thereof), applications, relevant parameters, etc., that are not currently being executed by processor 502. Additionally, data store 508 can be a data repository for interference detection component 170, GAA control component 152, and / or one or more other components of device 500.

[0063] Optionally, device 500 may include a user interface component 510 that is operable to receive input from a user of device 500 and is further operable to generate an output for presentation to the user. User interface component 510 can include one or more input devices including, but not limited to, a keyboard, number pad, mouse, touch-sensitive display, navigation keys, function keys, microphone, speech recognition component, gesture recognition component, depth sensor, eye-tracking sensor, switch / button, any other mechanism capable of receiving input from a user, or any combination thereof. Additionally, user interface component 510 can include one or more output devices including, but not limited to, a display, speaker, haptic feedback mechanism, printer, any other mechanism capable of presenting an output to the user, or any combination thereof.

[0064] As described herein, device 500 may further include an interference detection component 170 for detecting interference signal 252 and / or a GAA control component 152 for avoiding interference.

[0065] As an example, an element, or any part of an element, or any combination of elements, may be implemented in a "processing system" that includes one or more processors. Examples of processors include microprocessors, microcontrollers, digital signal processors (DSPs), field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gate logic, individual hardware circuits, and other suitable hardware configured to perform the various functions described throughout this disclosure. One or more processors in the processing system may execute software. Software shall be broadly construed to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc., regardless of the name given to it, such as software, firmware, middleware, microcode, hardware description language, etc.

[0066] Accordingly, in one or more aspects, one or more of the described functions may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or encoded as one or more instructions or code on a computer-readable medium. The computer-readable medium includes computer storage media. The storage media can be any available media that can be accessed by a computer. By way of example and not limitation, such computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. As used herein, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), and floppy disk, where disk typically magnetically reproduces data, and disc optically reproduces data with a laser. Combinations of the above should also be included within the scope of computer-readable media.

[0067] The previous description has been provided to enable a person of ordinary skill in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Accordingly, the claims are not intended to be limited to the aspects shown herein but are to be accorded the full scope consistent with the claim language. References to elements in the singular are not intended to mean "only" unless expressly so stated, but rather "one or more." Unless otherwise specified, the term "some" refers to one or more. Additionally, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from the context, the phrase "X adopts A or B" is intended to mean any of the natural inclusive permutations. That is, the phrase "X adopts A or B" is satisfied by any of the following instances: X adopts A, X adopts B, or X adopts both A and B. Further, the articles "a" and "an" as used in this application and the appended claims are generally to be construed to mean "one or more" unless otherwise specified or it is clear from the context that the reference is to the singular form. Additionally, nothing disclosed herein is to be made publicly available regardless of whether such disclosure is expressly recited in the claims. No claim element is to be construed as a means-plus-function unless the element is expressly recited using the phrase "means for."

Claims

1. A memory storing computer-executable instructions, coupled to the memory, to execute the instructions to check a local spectrum access database of known general authorization access (GAA) users to determine that a portion of the shared spectrum is freed from known local users in a geographic area, receive samples of a wireless signal including at least a desired signal on the portion of the shared spectrum, determine whether the wireless signal includes a plurality of uncorrelated signals, and identify an interference signal in response to determining that the wireless signal includes a plurality of uncorrelated signals and a processor configured to perform An apparatus for wireless communication, comprising.

2. The apparatus according to claim 1, wherein the processor is further configured to mitigate the interference signal.

3. The apparatus according to claim 2, wherein the processor is further configured to shift a carrier frequency within the shared spectrum to mitigate the interference signal.

4. The apparatus according to claim 2, wherein the processor is further configured to add the interference signal to the local spectrum access database to mitigate the interference signal.

5. The apparatus according to claim 1, wherein the processor is further configured to determine a difference between an expected decoding rate and an actual decoding rate based on a measured signal quality, and the determination of whether the wireless signal includes a plurality of uncorrelated signals is in response to the difference exceeding a threshold.

6. The apparatus according to claim 1, wherein the processor is configured to apply the sample of the wireless signal to a machine learning-based source separation algorithm to determine whether the wireless signal includes a plurality of uncorrelated signals.

7. The apparatus according to claim 6, wherein the machine learning-based source separation algorithm is configured to indicate a plurality of copies of the desired signal with different delays to determine whether the wireless signal includes a plurality of uncorrelated signals.

8. The apparatus according to claim 6, wherein the machine learning-based source separation algorithm is configured to indicate at least one signal unrelated to the desired signal in order to determine whether the wireless signal includes a plurality of unrelated signals.

9. The apparatus according to claim 1, wherein the processor checks a spectrum access system (SAS) database of license users at an access layer higher than the GAA user, selects the portion of the shared spectrum to avoid interference with the license user and is configured to perform.

10. Checking a local spectrum access database of known general authorized access (GAA) users to determine that a portion of the shared spectrum is free from known local users in a geographic area; Receiving samples of a wireless signal including at least a desired signal on the portion of the shared spectrum; Determining whether the wireless signal includes a plurality of unrelated signals; Identifying an interference signal in response to determining that the wireless signal includes a plurality of unrelated signals and a method comprising.

11. The method according to claim 10, further comprising the step of mitigating the interference signal.

12. The method according to claim 11, wherein the step of mitigating the interference signal includes shifting a carrier frequency within the shared spectrum or adding the interference signal to the local spectrum access database.

13. The method according to claim 10, further comprising determining a difference between an expected decoding rate and an actual decoding rate based on a measured signal quality, and determining whether the wireless signal includes a plurality of unrelated signals is in response to the difference exceeding a threshold.

14. The method according to claim 10, wherein the step of determining whether the wireless signal includes a plurality of unrelated signals includes applying the sample of the wireless signal to a machine learning-based source separation algorithm.

15. A computer-readable medium storing computer-executable instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 10 to 14.

Images