skip to main content

Title: FaIR: Federated Incumbent Detection in CBRS Band
The next-generation spectrum access system (SAS) for the Citizens Broadband Radio Service band is equipped with environmental sensors (ESCs) to detect the presence of noninformed incumbent users, which allows the SAS to dynamically reassign spectrum resource for low privilege users to avoid interference. However, the performance of existing single-node detection model is limited by the sensor’s geo-locations; whereas a naive distributed sensing network with improved detection accuracy introduces a high bandwidth overhead due to the frequent communication of spectrum data. In addition, many existing coherent spectrum sensing methods are not feasible for CBRS band due to the unknown operational characteristics of incumbent military wireless applications. To address these issues, we propose a machine learning based non-coherent spectrum sensing system: (F)eder(a)ted (I)ncumbent Detection in CB(R)S (FaIR). FaIR leverages a communication-efficient distributed learning framework, federated learning, for ESCs to collaborate and train a data-driven machine learning model for incumbent detection under minimal communication bandwidth. Our preliminary results show that the federated learning method can exploit the spatial diversity of ESCs and obtain an improved detection model comparing to a naive distributed sensing and centralized model framework. We evaluate the FaIR model with a variety of spectrum waveforms at varying SNRs. Our experiments showed that FaIR improves the average detection accuracy compared to the single-node method, using a fraction of the bandwidth compared to the naive multinode method.  more » « less
Award ID(s):
Author(s) / Creator(s):
Date Published:
Journal Name:
: 2019 IEEE International Symposium on Dy- namic Spectrum Access Networks (DySPAN) - Workshop on Data-Driven Dynamic Spectrum Sharing
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The recent framework for spectrum sharing in the 3.5 GHz band allows for Environment Sensing Capability operators (ESCs) to measure spectrum occupancy so as to enable commercial use of this spectrum when federal incumbent users are not present. Each ESC will contract with one or more Spectrum Access Systems (SASs) to provide spectrum occupancy data. Commercial firms using the band will in turn contract with a SAS to determine when it can access the spectrum. Initially, the decisions of which ESC and SAS to partner with will likely be based on long-term contracts. In this paper, we consider an alternative framework, in which an ESC sells its spectrum management information via a spot market so that from periodto- period a commercial user can select a different ESC from which to acquire spectrum measurements. We develop a game theoretic model to analyze such a market and show that using such a spot market may better enable multiple commercial firms to operate in a given spectrum band. We also show that this increased competition may not benefit consumer surplus unless firms adopt a non-stationary strategy profile. 
    more » « less
  2. null (Ed.)
    The Citizens Broadband Radio Service (CBRS) recently adopted in the U.S. enables commercial users to share spectrum with incumbent federal users. This sharing can be assisted by Environmental Sensing Capability operators (ESCs), that monitor the spectrum occupancy to determine when the use of the spectrum will not harm incumbents. An important aspect of the CBRS is that it enables two tiers of spectrum access by commercial users. The higher tier corresponds to a spectrum access (SA) firm that purchases a priority access license (PAL) in a competitive auction. The PAL holder obtains dedicated licensed access to a portion of the spectrum when the incumbent is not present. The lower tier, referred to as generalized Authorized Access (GAA), does not request a PAL and is similar to unlicensed access, in which multiple firms share a portion of the spectrum. Entry and investment in such a market introduces a number of new dimensions. Should an entrant bid for a PAL? How does the availability of a PAL impact their investment decisions? We develop a game-theoretic model to study these issues in which entrant SAs may bid in a PAL auction and decide on their investment levels and then compete downstream for customers. 
    more » « less
  3. null (Ed.)
    Federated learning (FL) is a highly pursued machine learning technique that can train a model centrally while keeping data distributed. Distributed computation makes FL attractive for bandwidth limited applications especially in wireless communications. There can be a large number of distributed edge devices connected to a central parameter server (PS) and iteratively download/upload data from/to the PS. Due to limited bandwidth, only a subset of connected devices can be scheduled in each round. There are usually millions of parameters in the state-of-art machine learning models such as deep learning, resulting in a high computation complexity as well as a high communication burden on collecting/distributing data for training. To improve communication efficiency and make the training model converge faster, we propose a new scheduling policy and power allocation scheme using non-orthogonal multiple access (NOMA) settings to maximize the weighted sum data rate under practical constraints during the entire learning process. NOMA allows multiple users to transmit on the same channel simultaneously. The user scheduling problem is transformed into a maximum-weight independent set problem that can be solved using graph theory. Simulation results show that the proposed scheduling and power allocation scheme can help achieve a higher FL testing accuracy in NOMA based wireless networks than other existing schemes within the same learning time. 
    more » « less
  4. The recent framework for tiered spectrum sharing in the 3.5 GHz band establishes rules in which multiple firms called Environment Sensing Capability operators (ESCs) may measure spectrum occupancy and sell these measurements to other firms to help facilitate spectrum access. Motived by this we consider a scenario in which two spectrum access firms (SAs) seeks to access a shared band of spectrum and must in turn purchase spectrum measurements from one of two ESCs. Given the measurements they purchase, the SA firms then compete on price to serve customers in a shared band of spectrum. We study how differences in the quality and price of the spectrum measurements impact the resulting market equilibrium between the SAs and find that having different qualities of measurements available to different SAs can lead to better economic welfare. 
    more » « less
  5. In dynamic spectrum access (DSA), Environmental Sensing Capability (ESC) systems are implemented to detect the incumbent users' (IU) activities for protecting them from secondary users' (SU) interference as well as maximizing secondary spectrum usage. However, IU location information is often highly sensitive and hence it is preferable to hide its true location under the detection of ESCs. In this paper, we design novel schemes to preserve both static and moving IU's location information by adjusting IU's radiation pattern and transmit power. We first formulate IU privacy protection problem for static IU. Due to the intractable nature of this problem, we propose a heuristic approach based on sampling. We also formulate the privacy protection problem for moving IUs, in which two cases are analyzed: (1) protect IU's moving traces; (2) protect its real-time current location information. Our analysis provides insightful advice for IU to preserve its location privacy against ESCs. Simulation results show that our approach provides great protection for IU's location privacy. 
    more » « less