Collaborative Flow Control in the DARPA Spectrum Collaboration Challenge

Abstract

Wireless network technologies are becoming more and more popular. Because of this, important parts of the wireless spectrum become overloaded. Static spectrum allocation, which has been the norm for decades, is not suitable anymore. To maintain the high demand for spectrum and the continuous development of new wireless technologies, there is a need for an intelligent, dynamic spectrum allocation mechanism, where different network technologies collaboratively optimize the spectrum usage. New wireless network paradigms, such as Neutral Host Networks (NHNs) and private 5G, require a smart, spectrumfootprint-aware flow control algorithm to overcome the spectrum scarcity in collaborative way. This article presents a strategy, vision and flow control mechanism to implement collaboration in a Quality of Service (QoS)-driven way. The solution in this article is based on policies which may activate depending on its current and neighbor's network states. Through a flow ordering and selection strategy, these policies optimize the spectrum footprint, based on the performance and QoS-requirements of the own and surrounding networks. The proposed algorithm is tested extensively and validated on a large scale during the DARPA Spectrum Collaboration Challenge (SC2) competition. The results of the SC2 final event and intermediate scrimmages showed that the proposed approach increased the score, indicating increased inter-network collaboration was achieved. Index Terms-Quality of service, wireless flow control, wireless networks and cellular networks, wireless spectrum collaboration. I. INTRODUCTION C OLLABORATION in the wireless spectrum is key to further exploration of the capacity of today's wireless communication. Driven by the increasing need for wireless capacity [1], spectrum scarcity is a familiar phenomenon,

A General Approach for Traffic Classification in Wireless Networks Using Deep Learning

“…This sub-module combines the output of different radio systems, e.g., the output of the NMS and the QoS requirements of a given application/user, and intelligently and dynamically adapts the radio parameters at different layers to improve performance and increase spectrum efficiency. An example of this module is being presented in [31], [39].…”

“…Examples of such collaborative approaches are the Collaborative Intelligent Radio Networks (CIRN), which were developed during the DARPA Gaussian Processes (SC2) competition [41]. Some of our recent work have demonstrated the capabilities of such networks at the architectural level [34], [39] and validated its performance via experimental results [31]. Moreover, theo-retical and practical developments of collaborative protocols to support such architecture can be found in [42] and [43], respectively.…”

“…The design of the CNN architecture was based on some of our previous experiences solving classification tasks using raw spectrum data such as in [7], [10], [33], [34], [37], [39]. More precisely, we started with a 2D-CNN architecture that worked well in the task of TR with raw IQ samples (see Fig.…”