arXiv subjects

Lailong Luo

Publications and source records attributed to Lailong Luo.

8 recordsLinked to original sources

arXiv2025

Sensing and Storing Less: A MARL-based Solution for Energy Saving in Edge Internet of Things

As the number of Internet of Things (IoT) devices continuously grows and application scenarios constantly enrich, the volume of sensor data experiences an explosive increase. However, substantial data demands considerable energy during computation and transmission. Redundant deployment or mobile assistance is essential to cover the target area reliably with fault-prone sensors. Consequently, the ``butterfly effect" may appear during the IoT operation, since unreasonable data overlap could result in many duplicate data. To this end, we propose Senses, a novel online energy saving solution for edge IoT networks, with the insight of sensing and storing less at the network edge by adopting Muti-Agent Reinforcement Learning (MARL). Senses achieves data de-duplication by dynamically adjusting sensor coverage at the sensor level. For exceptional cases where sensor coverage cannot be altered, Senses conducts data partitioning and eliminates redundant data at the controller level. Furthermore, at the global level, considering the heterogeneity of IoT devices, Senses balances the operational duration among the devices to prolong the overall operational duration of edge IoT networks. We evaluate the performance of Senses through testbed experiments and simulations. The results show that Senses saves 11.37% of energy consumption on control devices and prolongs 20% overall operational duration of the IoT device network.

cs.NI↗

arXiv2025

DHO$_2$: Accelerating Distributed Hybrid Order Optimization via Model Parallelism and ADMM

Scaling deep neural network (DNN) training to more devices can reduce time-to-solution. However, it is impractical for users with limited computing resources. FOSI, as a hybrid order optimizer, converges faster than conventional optimizers by taking advantage of both gradient information and curvature information when updating the DNN model. Therefore, it provides a new chance for accelerating DNN training in the resource-constrained setting. In this paper, we explore its distributed design, namely DHO$_2$, including distributed calculation of curvature information and model update with partial curvature information to accelerate DNN training with a low memory burden. To further reduce the training time, we design a novel strategy to parallelize the calculation of curvature information and the model update on different devices. Experimentally, our distributed design can achieve an approximate linear reduction of memory burden on each device with the increase of the device number. Meanwhile, it achieves $1.4\times\sim2.1\times$ speedup in the total training time compared with other distributed designs based on conventional first- and second-order optimizers.

cs.LG↗

arXiv2025

Analytic Personalized Federated Meta-Learning

Analytic Federated Learning (AFL) is an enhanced gradient-free federated learning (FL) paradigm designed to accelerate training by updating the global model in a single step with closed-form least-square (LS) solutions. However, the obtained global model suffers performance degradation across clients with heterogeneous data distribution. Meta-learning is a common approach to tackle this problem by delivering personalized local models for individual clients. Yet, integrating meta-learning with AFL presents significant challenges: First, conventional AFL frameworks cannot support deep neural network (DNN) training which can influence the fast adaption capability of meta-learning for complex FL tasks. Second, the existing meta-learning method requires gradient information, which is not involved in AFL. To overcome the first challenge, we propose an AFL framework, namely FedACnnL, in which a layer-wise DNN collaborative training method is designed by modeling the training of each layer as a distributed LS problem. For the second challenge, we further propose an analytic personalized federated meta-learning framework, namely pFedACnnL. It generates a personalized model for each client by analytically solving a local objective which bridges the gap between the global model and the individual data distribution. FedACnnL is theoretically proven to require significantly shorter training time than the conventional FL frameworks on DNN training while the reduction ratio is $83\%\sim99\%$ in the experiment. Meanwhile, pFedACnnL excels at test accuracy with the vanilla FedACnnL by $4\%\sim8\%$ and it achieves state-of-the-art (SOTA) model performance in most cases of convex and non-convex settings compared with previous SOTA frameworks.

cs.DC↗

arXiv2024

Air-to-Ground Communications Beyond 5G: CoMP Handoff Management in UAV Network

Air-to-ground (A2G) networks, using unmanned aerial vehicles (UAVs) as base stations to serve terrestrial user equipments (UEs), are promising for extending the spatial coverage capability in future communication systems. Coordinated transmission among multiple UAVs significantly improves network coverage and throughput compared to a single UAV transmission. However, implementing coordinated multi-point (CoMP) transmission for UAV mobility requires complex cooperation procedures, regardless of the handoff mechanism involved. This paper designs a novel CoMP transmission strategy that enables terrestrial UEs to achieve reliable and seamless connections with mobile UAVs. Specifically, a computationally efficient CoMP transmission method based on the theory of Poisson-Delaunay triangulation is developed, where an efficient subdivision search strategy for a CoMP UAV set is designed to minimize search overhead by a divide-and-conquer approach. For concrete performance evaluation, the cooperative handoff probability of the typical UE is analyzed, and the coverage probability with handoffs is derived. Simulation results demonstrate that the proposed scheme outperforms the conventional Voronoi scheme with the nearest serving UAV regarding coverage probabilities with handoffs. Moreover, each UE has a fixed and unique serving UAV set to avoid real-time dynamic UAV searching and achieve effective load balancing, significantly reducing system resource costs and enhancing network coverage performance.

cs.IT↗

arXiv2021

A survey of sketches in traffic measurement: Design, Optimization, Application and Implementation

Network measurement probes the underlying network to support upper-level decisions such as network management, network update, network maintenance, network defense and beyond. Due to the massive, speedy, unpredictable features of network flows, sketches are widely implemented in measurement nodes to approximately record the frequency or estimate the cardinality of flows. At their cores, sketches usually maintain one or multiple counter array(s), and rely on hash functions to select the counter(s) for each flow. Then the space-efficient sketches from the distributed measurement nodes are aggregated to provide statistics of the undergoing flows. Currently, tremendous redesigns and optimizations have been proposed to improve the sketches for better network measurement performance. However, existing reviews or surveys mainly focus on one particular aspect of measurement tasks. Researchers and engineers in the network measurement community desire an all-in-one survey that covers the entire processing pipeline of sketch-based network measurement. To this end, we present the first comprehensive survey of this area. We first introduce the preparation of flows for measurement, then detail the most recent investigations of design, aggregation, decoding, application and implementation of sketches for network measurement. To summarize the existing efforts, we carry out an in-depth study of the existing literature, covering more than 90 sketch designs and optimization strategies. Furthermore, we conduct a comprehensive analysis and qualitative/quantitative comparison of the sketch designs. Finally,we highlight the open issues for future sketch-based network measurement research.

cs.DS↗

arXiv2020

Multiset Synchronization with Counting Cuckoo Filters

Set synchronization is a fundamental task in distributed applications and implementations. Existing methods that synchronize simple sets are mainly based on compact data structures such as Bloom filter and its variants. However, these methods are infeasible to synchronize a pair of multisets which allow an element to appear for multiple times. To this end, in this paper, we propose to leverage the counting cuckoo filter (CCF), a novel variant of cuckoo filter, to represent and thereafter synchronize a pair of multisets. The cuckoo filter (CF) is a minimized hash table that uses cuckoo hashing to resolve collisions. CF has an array of buckets, each of which has multiple slots to store element fingerprints. Based on CF, CCF extends each slot as two fields, the fingerprint field and the counter field. The fingerprint field records the fingerprint of element which is stored by this slot; while the counter field counts the multiplicity of the stored element. With such a design, CCF is competent to represent any multiset. After generating and exchanging the respective CCFs which represent the local multi-sets, we propose the query-based and the decoding-based methods to identify the different elements between the given multisets. The comprehensive evaluation results indicate that CCF outperforms the counting Bloom filter (CBF) when they are used to synchronize multisets, in terms of both synchronization accuracy and the space-efficiency, at the cost of a little higher time-consumption.

cs.DS↗

arXiv2019

HyEdge: Optimal Request Scheduling in Hybrid Edge Computing Environment

With the widespread use of Internet of Things (IoT) devices and the arrival of the 5G era, edge computing has become an attractive paradigm to serve end-users and provide better QoS. Many efforts have been done to provision some merging public network services at the edge. We reveal that it is very common that specific users call for private and isolated edge services to preserve data privacy and enable other security intentions. However, it still remains open to fulfill such kind of mixed requests in edge computing. In this paper, we propose the framework of hybrid edge computing to offer both public and private edge services systematically. To fully exploit the benefits of this novel framework, we define the problem of optimal request scheduling over a given placement solution of hybrid edge servers, so as to minimize the response delay. This problem is further modeled as a mixed integer non-linear problem (MINLP), which is typically NP-hard. Accordingly, we propose the partition-based optimization method, which can efficiently solve this NP-hard problem via the problem decomposition and the branch and bound strategies. We finally conduct extensive evaluations with a real-world dataset to measure the performance of our methods. The results indicate that the proposed method achieves elegant performance with low computation complexity.

cs.DC↗

arXiv2019

Optimizing Bloom Filter: Challenges, Solutions, and Comparisons

Bloom filter (BF) has been widely used to support membership query, i.e., to judge whether a given element x is a member of a given set S or not. Recent years have seen a flourish design explosion of BF due to its characteristic of space-efficiency and the functionality of constant-time membership query. The existing reviews or surveys mainly focus on the applications of BF, but fall short in covering the current trends, thereby lacking intrinsic understanding of their design philosophy. To this end, this survey provides an overview of BF and its variants, with an emphasis on the optimization techniques. Basically, we survey the existing variants from two dimensions, i.e., performance and generalization. To improve the performance, dozens of variants devote themselves to reducing the false positives and implementation costs. Besides, tens of variants generalize the BF framework in more scenarios by diversifying the input sets and enriching the output functionalities. To summarize the existing efforts, we conduct an in-depth study of the existing literature on BF optimization, covering more than 60 variants. We unearth the design philosophy of these variants and elaborate how the employed optimization techniques improve BF. Furthermore, comprehensive analysis and qualitative comparison are conducted from the perspectives of BF components. Lastly, we highlight the future trends of designing BFs. This is, to the best of our knowledge, the first survey that accomplishes such goals.

cs.DS↗