User Partitioning Research Articles

Profit-Optimized Computation Offloading With Autoencoder-Assisted Evolution in Large-Scale Mobile-Edge Computing

Cloud-edge hybrid systems are known to support delay-sensitive applications of contemporary industrial Internet of Things (IoT). While edge nodes (ENs) provide IoT users with real-time computing/network services in a pay-as-you-go manner, their resources incur cost. Thus, their profit maximization remains a core objective. With the rapid development of 5G network technologies, an enormous number of mobile devices (MDs) have been connected to ENs. As a result, how to maximize the profit of ENs has become increasingly more challenging since it involves massive heterogeneous decision variables about task allocation among MDs, ENs and a cloud data center (CDC), as well as associations of MDs to proper ENs dynamically. To tackle such a challenge, this work adopts a divide-and-conquer strategy which models applications as splittable into multiple subtasks, each of which can be completed in MDs, ENs and a CDC. A joint optimization problem is formulated on task offloading, task partitioning, and associations of users to ENs to maximize the profit of ENs. To solve this high-dimensional mixed integer nonlinear program, a novel deep learning algorithm is developed named Genetic Simulated-annealing-based Particle swarm optimizer with Stacked Autoencoders (GSPSA). Real-life data-based experimental results demonstrate that GSPSA offers higher profit of ENs while strictly meeting latency needs of users’ tasks than state-of-the-art algorithms. Given the same number of iterations, GSPSA is able to solve problems whose size is 50% larger than that of those solved by peers.

Deep Reinforcement Learning-Aided Optimization of Multi-Interface Allocation for Short-Packet Communications

The severe spectrum scarcity and the stringent requirements of Beyond 5G applications call for an integrated use of low frequency Sub-6 GHz and high frequency millimeter Wave bands. Focusing on future Internet of Things (IoT) Short-Packet Communications (SPC), this paper investigates the optimized usage of such diverse wireless interfaces. We propose an unifying framework devoted to SPC that jointly optimizes the user partitioning over each band, and the radio resource scheduling within each band. Leveraging Deep Reinforcement Learning (DRL) tools, the proposed method enables to better tackle the challenges imposed by dynamically varying mobile environments such as the Line-of-Sight situations of each link, and the heterogeneity of individual Quality of Service (QoS) requirements, such as rate, delay and reliability. Regarding the DRL-based user partitioning to each band, we have investigated three different types of partitioning actions to obtain a high network performance as well as a rapid convergence. Regarding the proposed sub-schedulers within each band, we designed two optimization methods, i.e., one that leverages Difference of Convex Programming (DCP) technique, and the second that accelerates convergence to a local optimum. Numerical evaluations show that the proposed methods outperform conventional approaches in terms of sum-rate and QoS outage probabilities.

MP-CLF: An effective Model-Preserving Collaborative deep Learning Framework for mitigating data leakage under the GAN

The development of Internet of Things (IoT) communication technology has accelerated the data transmission between IoT devices, thus facilitating collaborative data processing based on the cloud, such as collaborative deep learning. The collaborative deep learning framework allows local devices to cooperate on training models without sharing private data, which resolves the contradiction of the availability and privacy of data. However, the emergence of the Generative Adversarial Network (GAN) attack has shown that poorly protected local data is vulnerable to being learned by adversaries. In this paper, we aim to address the threat GAN attacks pose to collaborative deep learning. We propose a Model-Preserving Collaborative deep Learning Framework, called MP-CLF, which can effectively resist the GAN attack. Based on fully connected neural network learning, MP-CLF employs a matrix blinding technology to break the local modeling of the GAN attack by blinding specific model parameters and trainers’ data, which is easily implementable and has strong security. Besides, MP-CLF builds a user partition model pre-training to improve training quality and strengthen model protection. Using the MNIST dataset and Fashion-MNIST dataset, we experimentally demonstrate that MP-CLF can completely resist the GAN attack with good computational efficiency.

LDPCD: A Novel Method for Locally Differentially Private Community Detection.

As one of the cores of data analysis in large social networks, community detection has become a hot research topic in recent years. However, user's real social relationship may be at risk of privacy leakage and threatened by inference attacks because of the semitrusted server. As a result, community detection in social graphs under local differential privacy has gradually aroused the interest of industry and academia. On the one hand, the distortion of user's real data caused by existing privacy-preserving mechanisms can have a serious impact on the mining process of densely connected local graph structure, resulting in low utility of the final community division. On the other hand, private community detection requires to use the results of multiple user-server interactions to adjust user's partition, which inevitably leads to excessive allocation of privacy budget and large error of perturbed data. For these reasons, a new community detection method based on the local differential privacy model (named LDPCD) is proposed in this paper. Due to the introduction of truncated Laplace mechanism, the accuracy of user perturbation data is improved. In addition, the community divisive algorithm based on extremal optimization (EO) is also refined to reduce the number of interactions between users and the server. Thus, the total privacy overhead is reduced and strong privacy protection is guaranteed. Finally, LDPCD is applied in two commonly used real-world datasets, and its advantage is experimentally validated compared with two state-of-the-art methods.

Machine Learning for User Partitioning and Phase Shifters Design in RIS-Aided NOMA Networks

A novel reconfigurable intelligent surface (RIS) aided non-orthogonal multiple access (NOMA) downlink transmission framework is proposed. We formulate a long-term stochastic optimization problem that involves a joint optimization of NOMA user partitioning and RIS phase shifting, aiming at maximizing the sum data rate of the mobile users (MUs) in NOMA downlink networks. To solve the challenging joint optimization problem, we invoke a modified object migration automation (MOMA) algorithm to partition the users into equal-size clusters. To optimize the RIS phase shifting matrix, we propose a deep deterministic policy gradient (DDPG) algorithm to collaboratively control multiple reflecting elements (REs) of the RIS. Different from conventional training-then-testing processing, we consider a long-term self-adjusting learning model where the intelligent agent is capable of learning the optimal action for every given state through exploration and exploitation. Extensive numerical results demonstrate that: 1) The proposed RIS-aided NOMA downlink framework achieves enhanced sum data rate compared with the conventional orthogonal multiple access (OMA) framework. 2) The proposed DDPG algorithm is capable of learning a dynamic resource allocation policy in a long-term manner. 3) The performance of the proposed RIS-aided NOMA framework can be improved by increasing the granularity of the RIS phase shifts. The numerical results also show that increasing the number of reflecting elements (REs) is an efficient method to improve the sum data rate of the MUs.

Energy-Efficient Optimization for UAV-Aided Cellular Offloading

This letter studies an energy-efficient unmanned aerial vehicle (UAV)-aided cellular network, where the UAV is dispatched to serve cell edge users in cellular network and helps offload data from the base station by flying with circle path. The goal of this letter is to maximize the energy efficiency of UAV by jointly optimizing resource allocation, user partitioning and UAV trajectory. The formulated problem is shown in a complicated and non-convex form, which is hard to tackle. To this end, the original problem is first decomposed into two sub-problems and then a block coordinate descent method is leveraged, which leads to an efficient iterative algorithm. Simulation results show that the proposed scheme outperforms the benchmarks in terms of the energy efficiency of UAV.

Evolving Bipartite Authentication Graph Partitions

As large scale enterprise computer networks become more ubiquitous, finding the appropriate balance between user convenience and user access control is an increasingly challenging proposition. Suboptimal partitioning of users’ access and available services contributes to the vulnerability of enterprise networks. Previous edge-cut partitioning methods unduly restrict users’ access to network resources. This paper introduces a novel method of network partitioning superior to the current state-of-the-art which minimizes user impact by providing alternate avenues for access that reduce vulnerability. Networks are modeled as bipartite authentication access graphs and a multi-objective evolutionary algorithm is used to simultaneously minimize the size of large connected components while minimizing overall restrictions on network users. Results are presented on a real world data set that demonstrates the effectiveness of the introduced method compared to previous naive methods.

"Game of Platforms: Strategic Expansion into Rival (Online) Territory"

Online platforms, such as Google, Facebook, and Amazon, are constantly expanding their activities while increasing the overlap in their service offerings. This paper asks: Is expansion into rival platforms’ services profit-maximizing when users’ platform choices endogenously change with expansion? We model an expansion game between two online platforms, both incumbents in distinct service markets, that provide their services free of charge to users and earn ad-based revenues. Platforms decide whether or not to expand by adding the service already offered by their rival. Expansion is costly and impacts users’ platform choice—namely, their choice of single- vs. multihoming, which, in turn, affects platform prices and profits derived from the advertisers’ side of the market. We demonstrate that, in equilibrium, platforms may choose not to expand. Strategic “no expansion” decisions are due to the quantity and price effects of changes in the user partition resulting from expansion. We further analyze the effects of expansion-driven changes in interplatform compatibility, expansion costs, probability of users’ ad engagement, switching costs, and intraplatform service complementarity and quality on the optimal expansion strategy. We then incorporate these considerations to derive an optimal expansion rule that can be used to guide managerial decision-making regarding expansion into a rival’s “territory.”

Anomaly Detection Method for Online Discussion

The presented article deals with the analysis of users discussing online, on the two most famous Slovak servers Cas.sk and Sme.sk. They provide a sufficiently representative sample of data to detect and compare the essential common behavioral characteristics of users in online discussions. This also makes it possible to identify user partitioning and to develop new methods to detect anomalies, specifically designed to differentiate discussing users with abnormal behavior. In the presented article, such a method is defined, with multiple tuning parameters, using a classification neural network. The proposed method is applied on real data, obtaining encouraging results.

Device-to-Device Communications Enabled Multicast Scheduling with the Multi-level Codebook in mmWave Small Cells

To keep up with the rapid growth of mobile data, there are increasing interests to deploy small cells in millimeter wave (mmWave) bands to underlay the conventional homogeneous macrocell network as well as in exploiting device-to-device (D2D) communications to improve the efficiency of the multicast service that supports content-based mobile applications. To compensate for high propagation loss in the mmWave band, high-gain directional antennas have to be employed, while it is critical to optimize multicast service in order to improve the network performance. In this paper, we develop an efficient multicast scheduling scheme for small cells in the mmWave band, called MD2D, where both D2D communications in close proximity and multi-level antenna codebook are utilized. Specifically, a user partition and multicast path planning algorithm is proposed to partition the users in the multicast group into subsets and to determine the transmission node for each subset, so as to achieve optimal utilization of D2D communications and multi-level antenna codebook. Then a multicast scheduling algorithm schedules the transmission for each subset. Furthermore, in order to optimize the network performance, the optimal choice of user partition thresholds is analyzed. Extensive simulations demonstrate that the MD2D achieves the best performance, in terms of network throughput and energy efficiency, compared with other existing state-of-the-art schemes. MD2D improves the network throughput compared with the second-best scheme by about 27%.

UAV-Aided Offloading for Cellular Hotspot

In conventional terrestrial cellular networks, mobile terminals (MTs) at the cell edge often pose a performance bottleneck due to their long distances from the serving ground base station (GBS), especially in hotspot period when the GBS is heavily loaded. This paper proposes a new hybrid network architecture by leveraging the use of unmanned aerial vehicle (UAV) as an aerial mobile base station, which flies cyclically along the cell edge to offload data traffic for cell-edge MTs. We aim to maximize the minimum throughput of all MTs by jointly optimizing the UAV's trajectory, bandwidth allocation and user partitioning. We first consider orthogonal spectrum sharing between the UAV and GBS, and then extend to spectrum reuse where the total bandwidth is shared by both the GBS and UAV with their mutual interference effectively avoided. Numerical results show that the proposed hybrid network with optimized spectrum sharing and cyclical multiple access design significantly improves the spatial throughput over the conventional GBS-only network; while the spectrum reuse scheme provides further throughput gains at the cost of slightly higher complexity for interference control. Moreover, compared to the conventional small-cell offloading scheme, the proposed UAV offloading scheme is shown to outperform in terms of throughput, besides saving the infrastructure cost.

Polar-Coded Non-Orthogonal Multiple Access

Non-orthogonal multiple access (NOMA) is one of the key techniques to address the high spectral efficiency and massive connectivity requirements for the fifth generation (5G) wireless system. To efficiently realize NOMA, we propose a joint design framework combining the polar coding and the NOMA transmission, which deeply mines the generalized polarization effect among the users. In this polar coded NOMA (PC-NOMA) framework, the original NOMA channel is decomposed into multiple bit polarized channels by using a three-stage channel transform, that is, user$\to$signal$\to$bit partitions. Specifically, for the first-stage channel transform, we design two schemes, namely sequential user partition (SUP) and parallel user partition (PUP). For the SUP, a joint successive cancellation detecting and decoding scheme is developed, and a search algorithm is proposed to schedule the NOMA detecting order which improves the system performance by enhanced polarization among the user synthesized channels. The "worst-goes-first" idea is employed in the scheduling strategy, and its theoretic performance is analyzed by using the polarization principle. For the PUP, a corresponding parallel detecting scheme is exploited to reduce the latency. The block error ratio performances over the additive white Gaussian noise channel and the Rayleigh fading channel indicate that the proposed PC-NOMA obviously outperforms the state-of-the-art turbo coded NOMA scheme due to the advantages of joint design between the polar coding and NOMA.

Joint Beamforming and Power Optimization With Iterative User Clustering for MISO-NOMA Systems

In this paper, we minimize the transmit power for multiple-input single-output and nonorthogonal multiple access systems. In our analysis, a large number of users are partitioned into multiple user clusters/pairs with small size and uniform power allocation across the clusters and each cluster is associated with a beamforming vector. The considered optimization problem involves how to optimize beamforming vectors, power allocation, and user clustering. Considering the high computational complexity in solving the whole problem, we decompose the problem into two parts, and design a joint algorithm to iteratively optimize them. First, given a user partition, we formulate the beamforming and power allocation problem under a set of practical constraints. The problem is nonconvex. To tackle it, we reformulate, transform, and approximate the nonconvex problem to a quadratically constrained optimization problem, and develop a joint beamforming and power allocation algorithm based on semidefinite relaxation to solve it. Second, to address the issue of high complexity in obtaining the optimal clusters, we propose a low-complexity algorithm to efficiently identify a set of promising clusters, forming as a candidate user partition. Based on these two algorithms, we design an algorithmic framework to iteratively perform them and to improve performance. By the algorithm design, the produced user partition can be further improved in later iterations, in order to further reduce power consumption. Numerical results demonstrate that the performance of the proposed solution with iterative updates for user clustering, and joint beamforming and power allocation optimization outperforms that of previous schemes.

A Movie Recommendation System based on Fuzzy-AHP with User Preference and Partition Algorithm

A Movie Recommendation System based on Fuzzy-AHP with User Preference and Partition Algorithm

Optimal data partitioning in cloud computing system with random server assignment

Cloud computing provides a paradigm where users can utilize various configurable IT resources in an on-demand and cost-effective manner. However, new security risks such as co-resident attacks have arisen. This paper models a situation when a user partitions and distributes sensitive data among several virtual machines to make unauthorized access to the entire data difficult in a cloud environment subject to the co-resident attacks. The attacker creates virtual machines in the same environment aiming to get access to users’ data. The cloud resource management system distributes all virtual machines among servers at random. The unauthorized access to data associated with user’s virtual machine is possible only if this machine co-resides in the same server with the attacker’s virtual machines. It is assumed that creating a side channel and getting access to the data is a common event for all the servers in which user’s and attacker’s virtual machines co-reside. Based on the suggested probabilistic model, an optimal number of user’s virtual machines (i.e., number of different data blocks partitioned) is obtained for a fixed or an uncertain number of attacker’s virtual machines, and for the case where the attacker knows the number of user’s virtual machines and responds optimally on any number of these machines. Examples demonstrate that the proposed optimal data partitioning policy can effectively mitigate effects of the co-resident attacks through minimizing user’s losses.

LATENCY OPTIMIZATION IN COMPUTATION PARTITIONING OF MULTIUSER MOBILE CLOUD APPLICATIONS

In mobile cloud computing, dividing the computations between the mobile devices and the cloud is very significant and Essential. In the existing work , these divisions of computations exists for a single user only . That is, it focuses on to optimize the time of the applications for that particular user only. Such existing works makes an assumption that there are enough resources always available on the cloud for the user to make the computations of the tasks which are offloaded on to the cloud. But this might not be an ideal approach when we consider several users who are trying to offload their tasks on to the cloud. There may arise situations where the resources on the cloud may not be available for the user’s computation to be executed, and hence the user is forced to wait until the resource gets available and only after that the task gets executed. And this results in scheduling latency of the application. The Scheduling latency which when not considered, results in the Performance deprivation. Hence we propose a method in this paper known as Multiple user Partitioning of computations Problem (MPCP). The MPCP approach emphasizes on the divisions of computations of multiple user’s and scheduling the computations that are offloaded on to the resources that are present in the cloud. Unlike the existing works which focuses to minimize the completion time of application for single user, our work aims to minimize the average completion time for all the users that take the services of the cloud.

Personalized Recommender System using Collaborative Filtering Technique and Pyramid Maintenance Algorithm

Location aware recommender system(LAS) make use of spatial ratings for generating personalized recommendations.It uses Collaborative filtering techniques to generate recommendations based on user location,item location or both user and item location . LAS uses spatial ratings for spatial items , Spatial ratings for Non-spatial items, Non spatial ratings for spatial items to generate personalized recommendation. For spatial ratings for non spatial items LAS uses user partitioning technique where spatial ratings are distributed as per user location in the pyramid. Pyramid Maintenance algorithm provided to achieve required scalability or locality.LAS is scalable as number of γ-cells are increased in pyramid and to improve locality α-cells are increased to maintain CF Model. LAS is efficient as compare to traditional recommendation system because algorithm provided is strong enough to cope challenge of locality and scalability.

MUBFP: Multi-User Beamforming and Partitioning for Sum Capacity Maximization in MIMO Systems

The multiuser beamforming (MUBF) scheme has attracted tremendous attention as a suboptimal linear precoding technique to realize the benefits of system capacity in multiple-input–multiple-output (MIMO) systems. Due to mutual interference between cochannel users, the objective of maximizing the system capacity and fair service provisioning to different users should be well balanced in the design of the MUBF scheme. To this end, we propose a framework for the joint multiuser beamforming and partitioning (MUBFP) design problem, which attempts to partition users into a set of disjoint groups, where each group of users is served using the MUBF scheme. By jointly optimizing the grouping number, the user partitioning, and the beamformer design, the average sum capacity can be maximized without sacrificing user fairness. A decomposition approach is presented to decouple this problem into the user partitioning and beamformer design subproblems with the given number of groups, which can be solved using the agglomerative hierarchical clustering (AHC) algorithm and sequential parametric convex approximation (SPCA) approach, respectively. An iterative algorithm is proposed to search the optimal grouping number for the decoupled MUBFP problem by incorporating the algorithms of these two subproblems, and a suboptimal algorithm is developed to reduce the searching times with good approximation performance. Simulation results are provided to show the effectiveness of the proposed schemes in terms of convergence, average sum capacity, and complexity.

Multi-User Computation Partitioning for Latency Sensitive Mobile Cloud Applications

Elastic partitioning of computations between mobile devices and cloud is an important and challenging research topic for mobile cloud computing. Existing works focus on the single-user computation partitioning, which aims to optimize the application completion time for one particular single user. These works assume that the cloud always has enough resources to execute the computations immediately when they are offloaded to the cloud. However, this assumption does not hold for large scale mobile cloud applications. In these applications, due to the competition for cloud resources among a large number of users, the offloaded computations may be executed with certain scheduling delay on the cloud. Single user partitioning that does not take into account the scheduling delay on the cloud may yield significant performance degradation. In this paper, we study, for the first time, multi-user computation partitioning problem (MCPP), which considers the partitioning of multiple users’ computations together with the scheduling of offloaded computations on the cloud resources. Instead of pursuing the minimum application completion time for every single user, we aim to achieve minimum average completion time for all the users, based on the number of provisioned resources on the cloud. We show that MCPP is different from and more difficult than the classical job scheduling problems. We design an offline heuristic algorithm, namely SearchAdjust , to solve MCPP. We demonstrate through benchmarks that SearchAdjust outperforms both the single user partitioning approaches and classical job scheduling approaches by 10 percent on average in terms of application delay. Based on SearchAdjust , we also design an online algorithm for MCPP that can be easily deployed in practical systems. We validate the effectiveness of our online algorithm using real world load traces.

English

The ALQRS proposes a location-query system based on the keyword search that calculates for the nearest location. ALQRS evaluates user partitioning for user locations and travel penalty for item locations. ALQRS uses gap keeping approach for sorting, store the values of locations and it is a good space saving technique.