11 March 2019 in IEEE Journal on Selected Areas in Communications
In this paper, we aim to study networking problems from a whole new perspective by leveraging emerging deep learning, to develop an experience-driven approach, which enables a network or a protocol to learn the best way to control itself from its own experience (e.g, runtime statistics data), just as a human learns a skill. We present design, implementation and evaluation of a Deep Reinforcement Learning (DRL) based control framework, DRL-CC (DRL for Congestion Control), which realizes our experience-driven design philosophy on Multi- Path TCP (MPTCP) congestion control. DRL-CC utilizes a single (instead of multiple independent) agent to dynamically and jointly perform congestion control for all active MPTCP flows on an end host with the objective of maximizing the overall utility. The novelty of our design is to utilize a flexible Recurrent Neural Network (RNN), LSTM, under a DRL framework for learning a representation for all active flows and dealing with their dynamics. Moreover, we, for the first time, integrate the above LSTM-based representation network into an actor-critic framework for continuous (congestion) control, which leverages the emerging deterministic policy gradient to train critic, actor and LSTM networks in an end-to-end manner. We implemented DRL-CC based on the MPTCP implementation in the Linux kernel. The experimental results show that 1) DRLCC consistently and significantly outperforms a few well-known MPTCP congestion control algorithms in terms of goodput without sacrificing fairness; 2) it is flexible and robust to highlydynamic network environments with time-varying flows; and 3) it is friendly to regular TCP.
7 December 2017 in IEEE Transactions on Mobile Computing
With the rapid growth of smartphones, mobile crowdsensing emerges as a new paradigm which takes advantage of the pervasive sensor-embedded smartphones to collect data efficiently. Many auction-based incentive mechanisms have been proposed to stimulate smartphone users to participate in the mobile crowdsensing applications and systems. However, none of them has taken into consideration both the bid privacy of smartphone users and the social cost. In this paper, we design two frameworks for privacypreserving auction-based incentive mechanisms that also achieve approximate social cost minimization. In the former, each user submits a bid for a set of tasks it is willing to perform; in the latter, each user submits a bid for each task in its task set. Both frameworks select users based on platform-defined score functions. As examples, we propose two score functions, linear and log functions, to realize the two frameworks. We rigorously prove that both proposed frameworks achieve computational efficiency, individual rationality, truthfulness, differential privacy, and approximate social cost minimization. In addition, with log score function, the two frameworks are asymptotically optimal in terms of the social cost. Extensive simulations evaluate the performance of the two frameworks and demonstrate that our frameworks achieve bid-privacy preservation although sacrificing social cost.
14 January 2019 in IEEE Transactions on Network Science and Engineering
Spatial crowdsourcing (SC) enables task owners (TOs) to outsource spatial-related tasks to a SC-server who engages mobile users in collecting sensing data at some specified locations with their mobile devices. Data aggregation, as a specific SC task, has drawn much attention in mining the potential value of the massive spatial crowdsensing data. However, the release of SC tasks and the execution of data aggregation may pose considerable threats to the privacy of TOs and mobile users, respectively. Besides, it is nontrivial for the SC-server to allocate numerous tasks efficiently and accurately to qualified mobile users, as the SC-server has no knowledge about the entire geographical user distribution. To tackle these issues, in this paper, we introduce a fog-assisted SC architecture, in which many fog nodes deployed in different regions can assist the SC-server to distribute tasks and aggregate data in a privacy-aware manner. Specifically, a privacy-aware task allocation and data aggregation scheme (PTAA) is proposed leveraging bilinear pairing and homomorphic encryption. PTAA supports representative aggregate statistics (e.g.,sum, mean, variance, and minimum) with efficient data update while providing strong privacy protection. Security analysis shows that PTAA can achieve the desirable security goals. Extensive experiments also demonstrate its feasibility and efficiency.
28 October 2019 in IEEE/ACM Transactions on Networking
5 October 2017 in IEEE Journal on Selected Areas in Communications
The ever-increasing mobile traffic has inspired deployment of capacity and performance enhancing network services within mobile networks. Owing to recent advances in network function virtualization, such network services can be flexibly and cost-efficiently deployed in the mobile network as software components, avoiding the need for costly hardware deployment. Nevertheless, this complicates network planning by bringing the need for service function chaining. In this paper, we study mobile network planning through a software-defined approach, considering both quality-of-service and reliability of different classes of traffic. We define and formulate the traffic steering problem for service function chaining in mobile networks, which turns out to be $\mathcal {NP}$ -hard. We then develop a fast approximation scheme for the problem, and evaluate its performance via extensive simulation experiments. The results show that our algorithm is near-optimal, and achieves much better performance compared with baseline algorithms.
22 August 2017 in IEEE Transactions on Mobile Computing
How to allocate the limited wireless resource in dense radio access networks (RANs) remains challenging. By leveraging a software-defined control plane, the independent base stations (BSs) are virtualized as a centralized network controller (CNC). Such virtualization decouples the CNC from the wireless service providers (WSPs). We investigate a virtualized RAN, where the CNC auctions channels at the beginning of scheduling slots to the mobile terminals (MTs) based on bids from their subscribing WSPs. Each WSP aims at maximizing the expected long-term payoff from bidding channels to satisfy the MTs for transmitting packets. We formulate the problem as a stochastic game, where the channel auction and packet scheduling decisions of a WSP depend on the state of network and the control policies of its competitors. To approach the equilibrium solution, an abstract stochastic game is proposed with bounded regret. The decision making process of each WSP is modeled as a Markov decision process (MDP). To address the signalling overhead and computational complexity issues, we decompose the MDP into a series of single-agent MDPs with reduced state spaces, and derive an online localized algorithm to learn the state value functions. Our results show significant performance improvements in terms of per-MT average utility.