Zongpeng Li

Zongpeng Li

Auto-generated profile, based on publicly available information

Zongpeng Li

Tsinghua University

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
16 February 2018 in IEEE/ACM Transactions on Networking
Verified
Journal Article
Closed access
YJYongzheng Jia
Yongzheng Jia
CWChuan Wu
Chuan Wu
ZLZongpeng Li
Zongpeng Li
FLFranck Le
Franck Le
ALAlex X. Liu
Alex X. Liu
Network Function Virtualization (NFV) is an emerging paradigm that turns hardware-dependent implementation of network functions (i.e., middleboxes) into software modules running on virtualized platforms, for significant cost reduction and ease of management. Such virtual network functions (VNFs) commonly constitute service chains, to provide network services that traffic flows need to go through. Efficient deployment of VNFs for network service provisioning is a key to realize the NFV goals. Existing efforts on VNF placement mostly deal with offline or one-time placement, ignoring the fundamental, dynamic deployment and scaling need of VNFs to handle practical time-varying traffic volumes. This work investigates dynamic placement of VNF service chains across geo-distributed datacenters to serve flows between dispersed source and destination pairs, for operational cost minimization of the service chain provider over the entire system span. An efficient online algorithm is proposed, which consists of two main components: 1) A regularization-based approach from online learning literature to convert the offline optimal deployment problem into a sequence of one-shot regularized problems, each to be efficiently solved in one time slot and 2) An online dependent rounding scheme to derive feasible integer solutions from the optimal fractional solutions of the one-shot problems, and to guarantee a good competitive ratio of the online algorithm over the entire time span. We verify our online algorithm with solid theoretical analysis and trace-driven simulations under realistic settings.

10 July 2025 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
SLSichun Luo
Sichun Luo
BHBowei He
Bowei He
HZHaohan Zhao
Haohan Zhao
WSWei Shao
Wei Shao
YQYanlin Qi
Yanlin Qi
LSLinqi Song
Linqi Song
Large language models (LLMs) have demonstrated remarkable capabilities and have been extensively deployed across various domains, including recommender systems. Prior research has employed specialized prompts to leverage the in-context learning capabilities of LLMs for recommendation purposes. More recent studies have utilized instruction tuning techniques to align LLMs with human preferences, promising more effective recommendations. However, existing methods suffer from several limitations. The full potential of LLMs is not fully elicited due to low-quality tuning data and the overlooked integration of conventional recommender signals. Furthermore, LLMs may generate inconsistent responses for different ranking tasks in the recommendation, potentially leading to unreliable results. In this article, we introduce Ranker for top- k Recommendations (RecRanker), tailored for instruction tuning LLMs to serve as the Ranker for top- k Recommendations. Specifically, we introduce importance-aware sampling, clustering-based sampling, and penalty for repetitive sampling for sampling high-quality, representative, and diverse training data. To enhance the prompt, we introduce a position shifting strategy to mitigate position bias and augment the prompt with auxiliary information from conventional recommendation models, thereby enriching the contextual understanding of the LLM. Subsequently, we utilize the sampled data to assemble an instruction-tuning dataset with the augmented prompts comprising three distinct ranking tasks: pointwise, pairwise, and listwise rankings. We further propose a hybrid ranking method to enhance the model performance by ensembling these ranking tasks. Our empirical evaluations demonstrate the effectiveness of our proposed RecRanker in both direct and sequential recommendation scenarios. 1

24 November 2017 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
Ruiting ZhouRuiting Zhou
Ruiting Zhou
ZLZongpeng Li
Zongpeng Li
CWChuan Wu
Chuan Wu
Effective incentive mechanisms are invaluable in mobile crowd sensing, for stimulating participation of smartphone users. Online auction mechanisms represent a natural solution for such sensing task allocation. Departing from existing studies that focus on an isolated system round, we optimize social cost across the system lifespan, while considering location constraints and capacity constraints when assigning sensing tasks to users. The winner determination problem (WDP) at each round is NP-hard even without inter-round coupling imposed by user capacity constraints. We first propose a truthful one-round auction, comprising of an approximation algorithm for solving the one-round WDP and a payment scheme for computing remuneration to winners. We then propose an online algorithm framework that employs the one-round auction as a building block towards a flexible mechanism that makes on-spot decisions upon dynamically arriving bids. Through both theoretical analysis and trace-driven simulations, we demonstrate that our online auction is truthful, individually rational, computationally efficient, and achieves a good competitive ratio.

19 November 2018 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
ZZZhi Zhou
Zhi Zhou
FLFangming Liu
Fangming Liu
SCShutong Chen
Shutong Chen
ZLZongpeng Li
Zongpeng Li
Datacenter demand response is envisioned as a promising tool for mitigating operational stability issues faced by smart grids. It enables significant potentials in peak load reduction and facilitates the incorporation of distributed generation. Monetary refund from the smart grid can also alleviate the cloud's burden in escalating electricity cost. However, the current demand response paradigm is inefficient towards incentivizing a cloud service provider (CSP) that operates geo-distributed datacenters. To incentivize CSP participation, this work presents an auction mechanism that enables smart grids to voluntarily submit bids to the CSP to procure diverse amounts of demand response with different payments. To maximize the social welfare of the auction, the CSP that acts as the auctioneer needs to solve the winner determination problem at large-scale. By applying the proximal Jacobian alternating direction method of multipliers, we propose a distributed algorithm for each datacenter to solve a small-scale problem in a parallel fashion. Desirable properties of the proposed auction, such as social welfare maximization and truthfulness are achieved through Vickrey-Clarke-Groves (VCG) payment. Through evaluations based on real datacenter workload traces and IEEE 14-bus test systems, we demonstrate our incentive mechanism constitutes a win-win mechanism for both the geo-distributed cloud and the smart grid.

2 February 2017 in IEEE Journal on Selected Areas in Communications
Verified
Journal Article
Closed access
MHMohammad H. Hajiesmaili
Mohammad H. Hajiesmaili
LDLei Deng
Lei Deng
MCMinghua Chen
Minghua Chen
ZLZongpeng Li
Zongpeng Li
The device-to-device load balancing (D2D-LB) paradigm has been advocated in recent small-cell architecture design for cellular networks. The idea is to exploit inter-cell D2D communication and dynamically relay traffic of a busy cell to adjacent under-utilized cells to improve spectrum temporal efficiency, addressing a fundamental drawback of small-cell architecture. Technical challenges of D2D-LB have been studied in previous works. The potential of D2D-LB, however, cannot be fully realized without providing proper incentive mechanism for device participation. In this paper, we address this economical challenge using an online procurement auction framework. In our design, multiple sellers (devices) submit bids to participate in D2D-LB and the auctioneer (cellular service provider) evaluates all the bids and decides to purchase a subset of them to fulfill load balancing requirement with the minimum social cost. Different from similar auction design studies for cellular offloading, battery limit of relaying devices imposes a time-coupled capacity constraint that turns the underlying problem into a challenging multi-slot one. Furthermore, the dynamics in the input to the multi-slot auction problem emphasize the need for online algorithm design. We first tackle the single-slot version of the problem, show that it is NP-hard, and design a polynomial-time offline algorithm with a small approximation ratio. Building upon the single-slot results, we design an online algorithm for the multi-slot problem with sound competitive ratio. Our auction algorithm design ensures that truthful bidding is a dominant strategy for devices. Extensive experiments using real-world traces demonstrate that our proposed solution achieves near offline-optimum and reduces the cost by 45% compared with an alternative heuristic.

1 July 2020 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
PZPing Zhao
Ping Zhao
WLWuwu Liu
Wuwu Liu
Guanglin  ZhangGuanglin Zhang
Guanglin Zhang
ZLZongpeng Li
Zongpeng Li
LWLin Wang
Lin Wang
Benefiting from the development of wireless communication, WiFi localization plays a vital role in various mobile applications. However, users’ locations are breached by untrusted localization servers, thus disclosing users’ location privacy and other sensitive personal information. Existing work onWiFi localization preservation employed homomorphic encryption, which incurs extremely high overheads. On the other hand, lightweight methods like k-anonymity and dummy-based approaches are hardly used for privacy preservation in WiFi localization scenarios due to their inherent drawbacks, i.e., k-anonymity approaches rely on trusted third parties while dummy-based approaches are susceptible to spatio-temporal correlation attacks. To design an effective yet lightweight WiFi localization privacy algorithm, this paper proposes to reinforce dummy techniques with plausible dummy location to resist the attacks. This study presents a novel algorithm, referred to as Location Preservation Algorithm with Plausible Dummies (LPPD), which is the first attempt towards WiFi localization privacy preservation using dummy techniques. The benefits of the algorithm are three-fold: First, it is lightweight. Second, it does not rely on trusted third parties. Third, it can resist spatio-temporal correlation attacks. Moreover, this study implements a WiFi localization system that integrates the proposed privacy-preserving algorithm with a WiFi fingerprint based indoor localization algorithm. Experiments results are presented to demonstrate the effectiveness and efficiency of our approach when compared with existing algorithms.