Citizens Broadband Radio Service Research Articles

A droplet-shape inspired wideband bow-tie dielectric resonator antenna for sub-6 GHz and IoT applications

In this article, an approach to realizing a dielectric resonator based bow-tie shaped antenna for the sub-6 GHz, 5G and IoT applications is discussed that utilizes droplet-shaped radiators for its two arms. The droplet-shaped radiating element is systematically derived to obtain a wider bandwidth response by truncating the sides of an aperture-coupled cylindrical DRA operating at HE11δ mode. The proposed bow-tie dielectric resonator antenna (DRA) is a modified dipole structure that uses a balanced line to differentially feed the two radiating segments to attain an overall wideband characteristics. A wideband matching balun circuit facilitates the antenna feeding which produces equal amplitude signals with 180° phase difference at its two output ports throughout the band of interest. The measurement of the proposed antenna confirms that it can serve several 5G bands like n77 (3300–4200 MHz), n78 (3300–3800 MHz), n48 (3550–3700 MHz) and n79 (4400–5000 MHz) with an overall wide bandwidth of 42.7% in the sub-6 GHz range. This planar configuration has a realized gain value ≥7.5 dBi within 3.37–3.91 GHz and it remains higher than 6 dBi almost throughout the working bandwidth of 3.18–4.91 GHz with considerably wide beamwidth. This broadband DRA has a consistent broadsided radiation pattern with cross-polarization discrimination (XPD)> 20 dB and its radiation efficiency varies between 60%–70% within 3.2–4.8 GHz. The antenna occupies a volume 1.2λ×1.2λ×0.1λ corresponding to its lower frequency of operation and it can support many more significant applications including WiMAX (3.3–3.8 GHz), Citizens Broadband Radio Service (CBRS) (3.55–3.7 GHz) and LTE (3.41–3.5 GHz uplink/3.51–3.6 GHz downlink). All these characteristics make this antenna a suitable candidate for use in transceiver modules for indoor communication, base stations, and vehicular communication.

Optimal Spectral Allocation in Citizens Broadband Radio Service

Optimal Spectral Allocation in Citizens Broadband Radio Service

A comprehensive analysis of the coverage and performance of 4G and 5G deployments

5G New Radio (5G NR), has now been deployed in all available bands: low (<1 GHz), mid (1–6 GHz), and high (>24 GHz), each with a trade-off between coverage and throughput/latency performance. The preceding 4G Long Term Evolution (4G LTE) networks also catching up to 5G mid-band by deploying in the unlicensed 5 GHz (using License Assisted Access/LAA) and the 3.5 GHz Citizens Broadband Radio Service (CBRS). We present a comprehensive analysis of 4G and 5G deployments in Chicago and Miami, focusing on coverage, throughput, and latency performance in low-, mid-, and high-bands, under several scenarios: outdoor, outdoor-to-indoor, and under high temperature. To measure deployed networks, we utilized a scalable methodology with commercial and custom apps to collect detailed signal data (e.g., signal strength, cell ID, throughput) on user device (i.e., smartphones). The analysis based on our measurements yields the following findings: (i) when comparing the throughput and latency performance of optimized mid-band 4G networks to 5G (both standalone (SA) and non-standalone (NSA)), they exhibit comparable performance, and (ii) it is important to note that mmWave 5G has the capability to deliver multi-Gbps throughput, even in NSA mode. However, this high-speed performance is susceptible to limitations imposed by factors such as distance, body interference, obstructions (such as Low-e glass), and overheating, which can render its performance less reliable. Therefore, even though 5G exhibits considerable potential in its early stages, additional efforts are required to guarantee that the stated goals of 5G are met.

A Multi-Blockchain Scheme for Distributed Spectrum Sharing in CBRS System

To overcome the spectrum scarcity issues, the citizens broadband radio service (CBRS) presents a centralized spectrum management solution. The efficiency of spectrum utilization could be further improved by introducing spectrum trading. Blockchain-based spectrum trading has been considered as a decentralized, flexible, and secure approach. However, current studies rarely investigate the interference to incumbent users caused by spectrum trading between CBRS devices (CBSDs), and the scalability issues in blockchain-based spectrum trading are rarely discussed. To address the problems above, this paper develops the blockchain-based spectrum trading mechanisms for CBRS. Particularly, we propose a queuing mechanism for intra-coexistence group (CxG) trading, in which spectrum trading is leveraged to reduce the aggregated interference to incumbents. A new parameter termed “network feature” is proposed to prioritize spectrum transactions in different queues, which helps to achieve the trade-off between the interference to incumbents and resource requirements in spectrum transactions. Furthermore, we propose a multi-blockchain architecture and a corresponding cross-chain mechanism to improve the speed of inter-CxG spectrum trading. Simulation results show that the aggregated interference to incumbents can be reduced by adopting the proposed method. Meanwhile, when adopting the proposed cross-chain spectrum trading mechanism, the network throughput can be improved by up to 24% compared with the traditional CBRS spectrum management framework.

A Survey on Citizens Broadband Radio Service (CBRS)

To leverage the existing spectrum and mitigate the global spectrum dearth, the Federal Communications Commission of the United States has recently opened the Citizens Broadband Radio Service (CBRS) spectrum, spanning 3550–3700 MHz, for commercial cognitive operations. The CBRS has a three-tier hierarchical architecture, wherein the incumbents, including military radars, occupy the topmost tier. The priority access licenses (PAL) and general authorized access (GAA) are second and third tier, respectively, facilitating licensed and unlicensed access to the spectrum. This combination of licensed and unlicensed access to the spectrum in a three-tier model has opened novel research directions in optimal spectrum sharing as well as privacy preservation, and hence, several schemes have been proposed for the same. This article provides a detailed survey of the existing literature on the CBRS. We provide an overview of the CBRS ecosystem and discuss the regulation and standardization process and industrial developments on the CBRS. The existing schemes for optimal spectrum sharing and resource allocation in CBRS are discussed in detail. Further, an in-depth study of the existing literature on the privacy of incumbents, PAL devices, and GAA devices in CBRS is presented. Finally, we discuss the open issues in CBRS, which demand more attention and effort.

Hybrid of Angular and Distance Protection for Coexistence of 5G Base Stations and Satellite Earth Stations

In this study, we investigated the coexistence of the 5G communication network with a fixed-satellite service (FSS) in the 3.5 GHz and 26 GHz frequency bands. We analyzed an angular protection scheme for the FSS Earth station (ES) and 5G base stations (BSs). In addition, we defined the fixed BS-ES relative location, relative distance, and angular changes. The angular protection was integrated into the exclusion and restricted zones proposed by the distance protection scheme for simulation analysis to develop a transmit power control scheme based on the Citizens Broadband Radio Service. Its performances were extensively analyzed through simulations. The proposed scheme was evaluated in practical scenarios: rural macrocells, urban macrocells, and urban microcells, as defined by the 3rd Generation Partnership Project (3GPP). The influence of antenna type was also researched, and BSs with 4 × 4, 8 × 8 and 16 × 16 antenna arrays, as specified by 3GPP, were considered for 5G networks. Finally, the results prove that the angular protection solution can solve the coexistence of the 5G system and the FSS. In addition, when angular protection and distance protection are used simultaneously, the coexistence effect of the two systems can be strengthened. Moreover, this work provides a quantitative perception for selecting system parameters, including an interference margin for the different scenarios and antenna types, the exclusion size, and the reduction area.

Resource Allocation in Spectrum Access System Using Multi-Objective Optimization Methods.

The paradigm of dynamic shared access aims to provide flexible spectrum usage. Recently, Federal Communications Commission (FCC) has proposed a new dynamic spectrum management framework for the sharing of a 3.5 GHz (3550–3700 MHz) federal band, called a citizen broadband radio service (CBRS) band, which is governed by spectrum access system (SAS). It is the responsibility of SAS to manage the set of CBRS-SAS users. The set of users are classified in three tiers: incumbent access (IA) users, primary access license (PAL) users and the general authorized access (GAA) users. In this article, dynamic channel assignment algorithm for PAL and GAA users is designed with the goal of maximizing the transmission rate and minimizing the total cost of GAA users accessing PAL reserved channels. We proposed a new mathematical model based on multi-objective optimization for the selection of PAL operators and idle PAL reserved channels allocation to GAA users considering the diversity of PAL reserved channels’ attributes and the diversification of GAA users’ business needs. The proposed model is estimated and validated on various performance metrics through extensive simulations and compared with existing algorithms such as Hungarian algorithm, auction algorithm and Gale–Shapley algorithm. The proposed model results indicate that overall transmission rate, net cost and data-rate per unit cost remain the same in comparison to the classical Hungarian method and auction algorithm. However, the improved model solves the resource allocation problem approximately up to four times faster with better load management, which validates the efficiency of our model.

Efficient Wideband Spectrum Sensing Using Mems Acoustic Resonators

The ever-increasing demand for wireless applications has resulted in an unprecedented radio frequency (RF) spectrum shortage. Ironically, at the same time, actual utilization of the spectrum is sparse in practice [1]. To exploit previously underutilized frequency bands to accommodate new unlicensed applications and achieve highly efficient usage of the spectrum, the Federal Communications Committee (FCC) has repurposed many frequency bands for dynamic spectrum sharing. This includes the 6 GHz band to be shared between Wi-Fi 6 and the incumbent users [2] as well as the 3.5 GHz Citizens Broadband Radio Service (CBRS) band [3].

Preserving Operation Frequency Privacy of Incumbents in CBRS

Citizens Broadband Radio Service (CBRS) is a novel service band in the United States, spanning 3550 – 3700 MHz, recently opened for commercial cognitive operations. The CBRS has a three tier hierarchical architecture, wherein, the topmost tier users (also called as incumbents) include military radars. The second and third tier facilitate licensed and unlicensed access to the band, respectively. The privacy of incumbents has been a major concern and different schemes have been proposed in the literature to preserve privacy of their location and operation time. However, the privacy of operation frequency of incumbents has not been suitably addressed. The operation frequency of incumbent is vulnerable to inference attacks from the adversary. For instance, an adversary can deduce the operation frequency of incumbent if a compromised device is asked to switch to another channel. Therefore, in this paper, we propose probabilistic usage of dummy incumbents on a channel and analyse the operation frequency privacy of incumbents for snapshot and time based models in the three tier CBRS system. The optimum dummy generation probability is obtained for the snapshot and time based models, varying capabilities of the adversary, and different system parameters. Finally, we verify the proposed results through simulations.

Optimal Resource Allocation for GAA Users in Spectrum Access System Using Q-Learning Algorithm

Spectrum access system (SAS) is a three-tier layered spectrum sharing architecture proposed by the Federal Communications Commission (FCC) for Citizen broadband radio service (CBRS) 3.5 GHz band. The available 150 MHz spectrum is dynamically shared among Incumbent Access (IA), Primary Access Licensees (PAL) and General Authorized Access (GAA) users. IA users are the highest priority federal military users, PAL users are the licensed users and the GAA users are the least priority unlicensed users. In this scenario, PAL operators are willing to give access to their idle spectrum to GAA users to generate extra revenue. SAS will ensure to protect IA users and PAL users from interference caused by lower-tier users. It is the responsibility of SAS to allocate resources to GAA users but the method to do so is left open. In this article, a novel auction algorithm based on Q-learning for dynamic spectrum access (SAS-QLA) is proposed. In SAS-QLA, multiple GAA users dynamically and intelligently bid using Q-learning to access PAL reserved idle channels. SAS will decide to allocate the channels to GAA users with maximum bidding offers. GAA users have their own quality of service (QoS) demands i.e., transmission rate, packet loss, bidding efficiency, and maintain the preference of available PAL reserved idle channels based on Q-learning considering the available QoS. The proposed scenario is also modeled as a knapsack NP-hard problem and solved using dynamic programming and distributed relaxation method. Numerical results demonstrate the effectiveness of the SAS-QLA algorithm in improving the bidding efficiency, maximizing the data rate per unit cost and spectrum utilization.

In-Band Full-Duplex Dynamic Spectrum Sharing in Beyond 5G Networks

Dynamic spectrum sharing (DSS) has recently attracted keen interest from regulatory bodies around the world as a key strategy to overcome spectrum scarcity in beyond 5G networks. In the United States, the Federal Communications Commission has adopted a three-tier DSS model for the Citizens Broadband Radio Service (CBRS) band managed by a spectrum access system (SAS) to share incumbents' spectrum with commercial cellular broadband applications. In this article, we first present a survey of current DSS approaches and their limitations and then discuss the benefits of using in-band full-duplex (IBFD) techniques in DSS networks. To illustrate the improvement in the performance of priority access license (PAL) and general authorized access (GAA) users in an IBFD-assisted CBRS, we consider a CBRS mobile broadband network (MBN) architecture comprising an incumbent in the form of a MIMO radar system and an IBFD MIMO MBN, consisting of PAL and GAA users. In particular, we design joint beamformers at the MBN, with constraints on transmit power at the MBN and detection probability of the radar system, and beamformers at the radar system to mitigate the interference from the radar system toward the cellular system. It is shown that the IBFD CBRS network architecture not only leads to improved performance of PAL and GAA users, but does so while producing less interference toward the radar than state-of-the-art half-duplex solutions. Finally, we present some open research challenges to invigorate research on beyond 5G IBFD DSS networks.

Distance Protection for Coexistence of 5G Base Station and Satellite Earth Station

In this paper, we investigate the coexistence of the 5G communication network with a fixed-satellite service (FSS) in the 3.5 GHz and 26 GHz frequency bands. We analyze a distance protection scheme for the FSS Earth station (ES) and 5G base stations (BS). Furthermore, we define the exclusion and restriction zones to develop a transmit power control scheme based on the Citizens Broadband Radio Service (CBRS). An interactive power control scheme is also devised for the restriction zone and extensively analyzed through simulations. The proposed scheme is examined for practical scenarios such as the rural macrocells (RMa), urban macrocells (UMa), and urban microcells (UMi) as defined by the 3GPP. The impact of the antenna type is also investigated, and BSs with omnidirectional, 4 × 4, 8 × 8, and 16 × 16 antenna arrays are examined, as defined by 3GPP, for the 5G networks. The results confirm that 5G systems can coexist with the FSS and provide quantitative insights into the selection of the system parameters, including interference margins, exclusion sizes, and reduction zones, for different scenarios and antenna types.

Quantum Dot Coherent Comb Laser Source for Converged Optical-Wireless Access Networks

We propose and experimentally demonstrate a converged optical-wireless WDM access network architecture enabled by a highly integrated quantum dot coherent comb laser. The converged optical-wireless WDM network features simultaneous delivery of coherent and millimeter wave (mmWave) / citizens broadband radio service (CBRS) signals over 50-km and 20 km fiber links, respectively.

Optimization of Multi-Band Characteristics in Fan-Stub Shaped Patch Antenna for LTE (CBRS) and WLAN Bands

This study aims to optimize a fan-stub slot patch to get better suitability and performance for Citizens Broadband Radio Service (CBRS). The transition from the tedious configuration of slotted patch antenna in fan-stub shape is evaluated. Also, the impact of stub width W, stub length L, and its orientation are tested. Multiple simulation tests ensure the uniqueness in the type of slots or stubs that affect the multiband nature of patch. The optimization of basic fan-stub structure on return loss S11, Voltage Standing Wave Ratio (VSWR), and the operating band at the desired frequency is performed to accommodate the federal and non-federal use of the band. The simulation results show that the designed antenna is technically suitable to cover 4G LTE in CBRS (LTE-43 and LTE-48 band) as well as 5.5 GHz Wireless Local Area Network (WLAN) band of operation.

Optimization of Citizen Broadband Radio Service Frequency Allocation for Dynamic Spectrum Access System

With the increase in mobile broadband utilization, more spectrum release is recommended by the Federal Communications Commission for spectrum sharing under a three-tire system called Citizens Broadband Radio Service. The standardization, functional and operational necessities of this framework are defined by the Wireless Innovation Forum. If an unavoidable shipborne radar appears on the channel, the channel must be vacated by the lower tier users. The timing constraints on CBRS is also stringent. Wireless stations transmit short beacon frames termed as heartbeat signals. These signals consist of the wireless channel encryption data, Service Set Identifier (SSID) and other credential data. These signals also transmit commands to vacate a channel. The heartbeat interval, timing constraint and domain proxy features are analyzed in this paper. CBSD renunciation and spectrum acquisition is performed with the help of domain proxy based communication. The CBRS-SAS channel allocation algorithm is further investigated. The communication interoperability and network robustness can improved with the introduction of secondary SAS and secondary domain proxy respectively.

Taking Stock of Spectrum Sharing

Shared access to airwaves dates back to the dawn of radio. Yet, recent spectrum policy in the United States has articulated the idea of “spectrum sharing” as a distinct form of radio regulation. In this paper we take stock of spectrum sharing as a public policy, with a focus on four questions. 1. What does it mean to have a spectrum sharing “policy”? We consider different ways of looking at spectrum sharing, including as a form of traditional radio coexistence and as a set of new technologies. We observe: * Sharing technologies can be grouped according to a simple framework, based on whether they use coordinating, sensing, or informing techniques and whether the implementation is centralized or decentralized. * Spectrum sharing as a public policy is not the same as spectrum sharing technology. Spectrum sharing as public policy is necessary when different categories of spectrum users are governed by overlapping, heterogeneous regulatory models. 2. What have we learned from recent spectrum sharing policy approaches? We consider several different spectrum sharing initiatives from recent years, including coordinated sharing in the licensed AWS-3 Band, automated sharing in the UHF, 5 GHz, and 6 GHz Bands (Television White Space, Dynamic Frequency Selection, and Automatedic Frequency Coordination, respectively), and multi-tiered sharing in the 3.5 GHz Band (the Citizens Broadband Radio Service). Key takeaways include the following: * White House leadership is critical when federal spectrum interests are at stake. Convening stakeholders in an organized forum to align expectations and share information is also essential. Sharing scenarios that involve both unlicensed operators and more traditional licensed users generally require an automated sharing technology to operate at scale. This automation can take the different technological forms described above. Enforcement is an important function that can be facilitated through centralized systems. * Multi-tier sharing can be complex but has been shown to work, with over 150,000 network nodes deployed in CBRS and no reported cases of interference. The CBRS rules promote sharing among a wide and heterogeneous range of users and use cases, including public and private networks, mobile and fixed wireless access, and consumer and industrial applications. Rule changes after the original order prevented experiential learning from some of the more innovative aspects of the CBRS regime and limited access to the Priority Access License tier in major markets to large network service providers. 3. What principles should guide future spectrum sharing policies? From these past experiences we distill several principles that are essential to a successful spectrum sharing policy: * Develop interference expectations. Sharing regimes should be informed by reasonable interference expectations, developed using modern analytics, rather than worst-case analysis. * Encourage standards and technologies that facilitate sharing. Sharing can be facilitated through private sector development of cross-industry “meta standards,” designed to be agnostic as to the underlying radio technologies used for transmission. Promote sharing by design, particularly in bands in which there are no incumbents. * Avoid artificial scarcity. Spectrum “scarcity” is often a byproduct of regulation. Wherever possible, the default should be rules that promote the abundance of spectrum through spectrum re-use. * Avoid “Trojan Horses” for market power. No single private entity should hold the key to enabling a centralized shared spectrum policy. * Build in enforcement mechanisms. Enforcement is necessary to ensure various stakeholders trust the sharing mechanism. 4. What spectrum sharing policies might the current Administration pursue? We see two main opportunities for spectrum sharing policy in the near term: * 3 GHz Band. The 3 GHz Band has evolved into a patchwork of different exclusive and shared regimes. We see an opportunity to consolidate “like” types of spectrum access in different parts of the band, reserving the upper 3 GHz for more traditional cellular licensing and extending the multi-tier CBRS framework farther into the lower portion of the band to facilitate sharing with federal systems. * Lower 37 GHz Band. This band is currently allocated for both federal government and commercial use, with little or no incumbent use. It presents a unique opportunity to develop “two-way” sharing from the ground up. There is no magic formula for spectrum sharing policy. A dynamic landscape of heterogeneous spectrum uses, multiple spectrum authorities, technology advances, and evolving national objectives requires case-by-case assessments. However, such assessments should be informed by the experiences and principles described above. This paper was published with support from Schmidt Futures. Note: following initial publication of this working paper, Qualcomm clarified that its proposed approach to licensing the Lower 37 GHz band would accommodate both fixed and mobile operations for federal as well as commercial users.

Anonymous Dynamic Spectrum Access and Sharing Mechanisms for the CBRS Band

The Federal Communications Commission (FCC) has released the 3.5 GHz (3550-3700 MHz) band, termed Citizens Broadband Radio Service (CBRS), for shared broadband use between incumbent federal and secondary users through dynamic and opportunistic spectrum access. FCC requires that this band be operated and managed through the use of spectrum access systems ( $\mathit {SAS}$ s), which are to be deployed specifically for this purpose. The challenge is that $\mathit {SAS}$ requires that secondary users provide some of their private operational data, such as their physical location, identity and spectrum usage, in order for them to acquire spectrum availability information. In this paper, we propose a privacy-preserving $\mathit {SAS}$ framework, $\mathit {TrustSAS}$ , that synergizes state-of-the-art cryptographic mechanisms with blockchain technology to enable anonymous access to $\mathit {SAS}$ by protecting users’ privacy while still complying with FCC’s regulatory design requirements and rules. We evaluate the performance of $\mathit {TrustSAS}$ through theoretic analysis, computer simulation and testbed experimentation, and show that it can offer high security guarantees, making it suitable for $\mathit {SAS}$ environments without needing to compromise private information of its secondary users.

IEEE 802.15.22.3 Spectrum Characterization and Occupancy Sensing Application Testbed

Dynamic Spectrum Access (DSA) is becoming a key enabler for wireless communication technologies. Many DSA concepts—such as the Citizens Broadband Radio Service and TV White Space—rely on spectrum databases to identify available radio channels. However, propagation models and other assumptions used by these databases are usually poor for the given scenario, typically leading to over-conservative calculations in terms of permitted secondary spectrum access, geographical bounds or transmit powers in order to mitigate perceived interference risk. Spectrum sensing allows better understanding of the actual propagation and actual channel impulse response, allowing spectrum databases to tune their propagation models to increase the availability of spectrum for secondary access as assessed by such spectrum databases, or to increase the availability of local access licenses as assessed by the telecommunications regulator. A critical limitation on the uptake of ubiquitous sensing is that measurement systems are either proprietary or do not have commercial use-cases; hence little economy of scale exists to drive deployment. For this reason, the IEEE 802.15.22.3 Task Group was formed to standardize a Spectrum Characterization and Occupancy Sensing (SCOS) system capable of addressing a wide range of sensing tasks and be easily and flexibly deployed across a variety of hardware options. This paper provides a high-level description of this system and a first testbed implementing the standard in a laboratory-controlled environment. Preliminary performance assessments are also reported, where it is shown that the system is able to detect users with a power level down to −80 dBm with a probability of detection equal to 1 and controlled false alarm rates.

Deterministic Move Lists for Federal Incumbent Protection in the CBRS Band.

The 3.5 GHz citizens broadband radio service (CBRS) band in the U.S. is a key portion of mid-band spectrum shared between commercial operators and existing federal and non-federal incumbents. To protect the federal incumbents from harmful interference, a spectrum access system (SAS) is required to use a common, standardized algorithm, called the move list algorithm, to suspend transmissions of some CBRS devices (CBSDs) on channels in which the incumbent becomes active. However, the current reference move list implementation used for SAS testing is non-deterministic in that it uses a Monte Carlo estimate of the 95th percentile of the aggregate interference from CBSDs to the incumbent. This leads to uncertainty in move list results and in the aggregate interference check of the test. This paper uses upper and lower bounds on the aggregate interference distribution to compute deterministic move lists. These include the reference move list used by the testing system and an operational move list used by the SAS itself. We evaluate the performance of the proposed deterministic move lists using reference implementations of the standards and simulated CBSD deployments in the vicinity of federal incumbent dynamic protection areas.

An AI-Based Incumbent Protection System for Collaborative Intelligent Radio Networks

Since the early days of wireless communication, wireless spectrum has been allocated according to a static frequency plan, whereby most of the spectrum is licensed for exclusive use by specific services or radio technologies. While some spectrum bands are overcrowded, many other bands are heavily underutilized. As a result, there is a shortage of available spectrum to deploy emerging technologies that require high demands on data like 5G. Several global efforts address this problem by providing multi-tier spectrum sharing frameworks, for example, the Citizens Broadband Radio Service (CBRS) and Licensed Shared Access (LSA) models, to increase spectrum reuse. In these frameworks, the incumbent (i.e., the technology that used the spectrum exclusively in the past) has to be protected against service disruptions caused by the transmissions of the new technologies that start using the same spectrum. However, these approaches suffer from two main problems. First, spectrum re-allocation to new uses is a slow process that may take years. Second, they do not scale fast since it requires a centralized infrastructure to protect the incumbent and coordinate and grant access to the shared spectrum. As a solution, the Spectrum Collaboration Challenge (SC2) has shown that the collaborative intelligent radio networks (CIRNs) -- artificial intelligence (AI)-based autonomous wireless networks that collaborate -- can share and reuse spectrum efficiently without any coordination and with the guarantee of incumbent protection. In this article, we present the architectural design and the experimental validation of an incumbent protection system for the next generation of spectrum sharing frameworks. The proposed system is a two-step AI-based algorithm that recognizes, learns, and proactively predicts the incumbent's transmission pattern with an accuracy above 95 percent in near real time (less than 300 ms). The proposed algorithm was validated in Colosseum, the RF channel emulator built for the SC2 competition, using up to two incumbents simultaneously with different transmission patterns and sharing spectrum with up to five additional CIRNs.