Fan Zhou

Fan Zhou

Auto-generated profile, based on publicly available information

Fan Zhou

School Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 200090, P. R. China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 October 2019 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
KSKunal Sankhe
Kunal Sankhe
MBMauro Belgiovine
Mauro Belgiovine
FZFan Zhou
Fan Zhou
LALuca Angioloni
Luca Angioloni
FRFrank Restuccia
Frank Restuccia
KCKaushik Chowdhury
Kaushik Chowdhury
Due to the unprecedented scale of the Internet of Things, designing scalable, accurate, energy-efficient and tamper-proof authentication mechanisms has now become more important than ever. To this end, in this paper we present ORACLE, a novel system based on convolutional neural networks (CNNs) to “fingerprint” (i.e., identify) a unique radio from a large pool of devices by deep-learning the fine-grained hardware impairments imposed by radio circuitry on physical-layer I/Q samples. First, we show how hardware-specific imperfections are learned by the CNN framework. Then, we extensively evaluate the performance of ORACLE on several first-of-its-kind large-scale datasets of WiFi-transmissions collected “in the wild”, as well as a dataset of nominally-identical (i.e., equal baseband signals) WiFi devices, reaching 80-90% accuracy is many cases with the error gap arising due to channel-induced effects. Finally, we show through an experimental testbed, how this accuracy can reach over 99% by intentionally inserting and learning the effect of controlled impairments at the transmitter side, to completely remove the impact of the wireless channel. Furthermore, to scale this approach for classifying potential thousands of radios, we propose an impairment hopping spread spectrum (IHOP) technique that is resilient to spoofing attacks.

11 May 2018 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
WLWei Li
Wei Li
FZFan Zhou
Fan Zhou
KCKaushik Roy Chowdhury
Kaushik Roy Chowdhury
WMWaleed M. Meleis
Waleed M. Meleis
Next generation network access technologies and Internet applications have increased the challenge of providing satisfactory quality of experience for users with traditional congestion control protocols. Efforts on optimizing the performance of TCP by modifying the core congestion control method depending on specific network architectures or apps do not generalize well under a wide range of network scenarios. This limitation arises from the rule-based design principle, where the performance is linked to a pre-decided mapping between the observed state of the network to the corresponding actions. Therefore, these protocols are unable to adapt their behavior in new environments or learn from experience for better performance. We address this problem by integrating a reinforcement-based Q-learning framework with TCP design in our approach called QTCP. QTCP enables senders to gradually learn the optimal congestion control policy in an on-line manner. QTCP does not need hard-coded rules, and can therefore generalize to a variety of different networking scenarios. Moreover, we develop a generalized Kanerva coding function approximation algorithm, which reduces the computation complexity of value functions and the searchable size of the state space. We show that QTCP outperforms the traditional rule-based TCP by providing 59.5% higher throughput while maintaining low transmission latency.

1 May 2016
Verified
Conference Paper
Closed access
WLWei Li
Wei Li
FZFan Zhou
Fan Zhou
WMWaleed Meleis
Waleed Meleis
KCKaushik Chowdhury
Kaushik Chowdhury
Advances in wireless technology have resulted in pervasive deployment of devices of a high variability in form factors, memory and computational ability. The need for maintaining continuous connections that deliver data with high reliability necessitate re-thinking of conventional design of the transport layer protocol. This paper investigates the use of Q-learning in TCP cwnd adaptation during the congestion avoidance state, wherein the classical alternation of the window is replaced, thereby allowing the protocol to immediately respond to previously seen network conditions. Furthermore, it demonstrates how memory plays a critical role in building the exploration space, and proposes ways to reduce this overhead through function approximation. The superior performance of the learning-based approach over TCP New Reno is demonstrated through a comprehensive simulation study, revealing 33.8% and 12.1% improvement in throughput and delay, respectively, for the evaluated topologies. We also show how function approximation can be used to dramatically reduce the memory requirements of a learning-based protocol while maintaining the same throughput and delay.

1 April 2018
Verified
Conference Paper
Closed access
FZFan Zhou
Fan Zhou
MNM. Yousof Naderi
M. Yousof Naderi
KSKunal Sankhe
Kunal Sankhe
KCKaushik Chowdhury
Kaushik Chowdhury
Emerging network architectures in 60GHz millimeter wave bands will likely use dense deployment of access points (APs) given the high attenuation and frequent line-of-sight related outages. We show in this paper that naively connecting to any available AP, or even multiple APs, may not fully realize the promise of efficiently utilizing the extremely large bandwidths available in this band. This paper holistically addresses these problems through the Multi-AP Association Protocol (MAP) that: (i) indicates ideal durations for beam-searching at the physical/link layers of the protocol stack that will result in minimal interruptions to user-traffic, (ii) devises a Multi-AP association framework based on multipath TCP, which increases the network robustness by allowing immediate redirection of traffic to alternative APs whenever an existing connection is interrupted, and (iii) designs an exploration-exploitation aware flow scheduling algorithm that dynamically activates the sub-flows to optimize transport layer performance. MAP is a lightweight, client side system that needs zero modifications to existing protocol stack, though it interacts with the latter to opportunistically trigger standards-defined functions. The paper also presents convergence analysis of throughput, experimental validation on a 60GHz network testbed, and trace-driven simulation studies that shows MAP achieving 5-7x reduction in re-buffering rate in HD video streaming, rapid convergence to the best possible AP, and fair allocation of resources among clients.

13 September 2018 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
FZFan Zhou
Fan Zhou
DCDavid Choffnes
David Choffnes
KCKaushik Chowdhury
Kaushik Chowdhury
As the dominant protocol on the Internet, TCP has attracted significant attention and has been implemented in various ways, each of which optimizes for a single objective such as high throughput or low delay. However, in today's mobile networks that carry traffic from diverse types of flows, this approach may lead to misconfiguration of TCP congestion control algorithms and further degrade performance for many applications. In this paper, we propose Janus, a new transport-layer framework that automatically selects among existing congestion control variants to optimize traffic in accordance with application demands. Janus is easy to deploy because it reuses existing, well-tested congestion control implementations, and does not require any in-network or client-side changes. To explore the potential for this approach, we implement Janus in the Linux kernel and extensively evaluate its performance with both emulated and real Internet traffic. We show Janus outperforms alternative protocols by offering fast convergence times in response to changing network conditions, achieving 5-10X lower delay with comparable or higher throughput. Our approach also significantly improves user-perceived performance according to QoE metrics, with up to 5X fewer interruptions for video streaming applications and 2X faster page loading for web-browsing applications.

1 December 2017
Verified
Conference Paper
Closed access
FZFan Zhou
Fan Zhou
MFMarco Di Felice
Marco Di Felice
BDBenjamin Drozdenko
Benjamin Drozdenko
KCKaushik Chowdhury
Kaushik Chowdhury
Cognitive radio (CR) is an enabling technology that allows opportunistic use of under-utilized licensed spectrum allocated to primary users (PUs). However, the frequent channel sensing and switching interferes with the transport layer functions, leading to slow flow convergence during active transmissions by the CR. In this paper, we propose TCP C2, a method that greatly improves the flow responsiveness to abrupt variation of underlying layer spectrum availability in cellular CR architectures. The key idea of C2 is to allow the sender to estimate the current bottleneck link bandwidth and network load by observing variance in the throughput and round trip time. Following this, fast congestion window scaling allows the flow to converge quickly to the optimal sending rate. Analytic derivations and packet-based simulation results show the increased resiliency of our approach over classical end-to-end TCP protocols in the presence of intermittent spectrum sensing and disruptions caused by PU arrival. Additionally, we show that C2 enforces fairness among flows, and also coexists well with classical TCP flavors.