arXiv subjects

Saeedeh Parsaeefard

Publications and source records attributed to Saeedeh Parsaeefard.

At least 19 recordsLinked to original sources

arXiv2024

Leader Selection and Follower Association for UE-centric Distributed Learning in Future Wireless Networks

User equipment (UE) devices with high compute performance acting on data with dynamic and stochastic nature to train Artificial Intelligence/Machine Learning (AI/ML) models call for real-time, agile distributed machine learning (DL) algorithms. Consequently, we focus on UE-centric DL algorithms where UEs initiate requests to adapt AI/ML models for better performance, e.g., locally refined AI/ML models among a set of headsets or smartphones. This new setup requires selecting a set of UEs as aggregators (here called leaders) and another set as followers, where all UEs update their models based on their local data, and followers share theirs with leaders for aggregation. From a networking perspective, the first question is how to select leaders and associate followers efficiently. This results in a high dimensional mixed integer programming problem and involves internal UE state information and state information among UEs, called external state information in this paper. To address this challenge, we introduce two new indices: a Leader Internal Index (LII), which is a function of the internal states of each device, demonstrating the willingness to be a leader such as battery life and AI/hardware accelerators, and a Leader eXternal Index (LXI), which is a function of external state information among UEs, such as trust, channel condition, and any aspect relevant for associating a follower with a leader. These two indices transform the highly complex leader selection and follower association problem into a better tractable formulation. More importantly, LIIs and LXIs allow to keep the internal and external state information of this problem inside of each device without compromising users' privacy.

cs.NI↗

arXiv2022

A Deep Learning-Based Approach for Cell Outage Compensation in NOMA Networks

Cell outage compensation enables a network to react to a catastrophic cell failure quickly and serve users in the outage zone uninterruptedly. Utilizing the promising benefits of non-orthogonal multiple access (NOMA) for improving the throughput of cell edge users, we propose a newly NOMA-based cell outage compensation scheme. In this scheme, the compensation is formulated as a mixed integer non-linear program (MINLP) where outage zone users are associated to neighboring cells and their power are allocated with the objective of maximizing spectral efficiency, subject to maintaining the quality of service for the rest of the users. Owing to the importance of immediate management of cell outage and handling the computational complexity, we develop a low-complexity suboptimal solution for this problem in which the user association scheme is determined by a newly heuristic algorithm, and power allocation is set by applying an innovative deep neural network (DNN). The complexity of our proposed method is in the order of polynomial basis, which is much less than the exponential complexity of finding an optimal solution. Simulation results demonstrate that the proposed method approaches the optimal solution. Moreover, the developed scheme greatly improves fairness and increases the number of served users.

eess.SP↗

arXiv2022

Missing Data Estimation in Temporal Multilayer Position-aware Graph Neural Network (TMP-GNN)

GNNs have been proven to perform highly effective in various node-level, edge-level, and graph-level prediction tasks in several domains. Existing approaches mainly focus on static graphs. However, many graphs change over time with their edge may disappear, or node/edge attribute may alter from one time to the other. It is essential to consider such evolution in representation learning of nodes in time varying graphs. In this paper, we propose a Temporal Multi-layered Position-aware Graph Neural Network (TMP-GNN), a node embedding approach for dynamic graph that incorporates the interdependence of temporal relations into embedding computation. We evaluate the performance of TMP-GNN on two different representations of temporal multilayered graphs. The performance is assessed against the most popular GNNs on node-level prediction tasks. Then, we incorporate TMP-GNN into a deep learning framework to estimate missing data and compare the performance with their corresponding competent GNNs from our former experiment, and a baseline method. Experimental results on four real-world datasets yield up to 58% of lower ROC AUC for pairwise node classification task, and 96% of lower MAE in missing feature estimation, particularly for graphs with a relatively high number of nodes and lower mean degree of connectivity.

cs.LG↗

arXiv2021

Interaction and Conflict Management in AI-assisted Operational Control Loops in 6G

This paper studies autonomous and AI-assisted control loops (ACLs) in the next generation of wireless networks in the lens of multi-agent environments. We will study the diverse interactions and conflict management among these loops. We propose "interaction and conflict management" (ICM) modules to achieve coherent, consistent and interactions among these ACLs. We introduce three categories of ACLs based on their sizes, their cooperative and competitive behaviors, and their sharing of datasets and models. These categories help to introduce conflict resolution and interaction management mechanisms for ICM. Using Kubernetes, we present an implementation of ICM to remove the conflicts in the scheduling and rescheduling of Pods for different ACLs in networks.

cs.NI↗

arXiv2021

Toward Efficient Transfer Learning in 6G

6G networks will greatly expand the support for data-oriented, autonomous applications for over the top (OTT) and networking use cases. The success of these use cases will depend on the availability of big data sets which is not practical in many real scenarios due to the highly dynamic behavior of systems and the cost of data collection procedures. Transfer learning (TL) is a promising approach to deal with these challenges through the sharing of knowledge among diverse learning algorithms. with TL, the learning rate and learning accuracy can be considerably improved. However, there are implementation challenges to efficiently deploy and utilize TL in 6G. In this paper, we initiate this discussion by providing some performance metrics to measure the TL success. Then, we show how infrastructure, application, management, and training planes of 6G can be adapted to handle TL. We provide examples of TL in 6G and highlight the spatio-temporal features of data in 6G that can lead to efficient TL. By simulation results, we demonstrate how transferring the quantized neural network weights between two use cases can make a trade-off between overheads and performance and attain more efficient TL in 6G. We also provide a list of future research directions in TL for 6G.

cs.NI↗

arXiv2021

Generalized ADMM in Distributed Learning via Variational Inequality

Due to the explosion in size and complexity of modern data sets and privacy concerns of data holders, it is increasingly important to be able to solve machine learning problems in distributed manners. The Alternating Direction Method of Multipliers (ADMM) through the concept of consensus variables is a practical algorithm in this context where its diverse variations and its performance have been studied in different application areas. In this paper, we study the effect of the local data sets of users in the distributed learning of ADMM. Our aim is to deploy variational inequality (VI) to attain an unified view of ADMM variations. Through the simulation results, we demonstrate how more general definitions of consensus parameters and introducing the uncertain parameters in distribute approach can help to get the better results in learning processes.

cs.NI↗

arXiv2021

Robust Federated Learning by Mixture of Experts

We present a novel weighted average model based on the mixture of experts (MoE) concept to provide robustness in Federated learning (FL) against the poisoned/corrupted/outdated local models. These threats along with the non-IID nature of data sets can considerably diminish the accuracy of the FL model. Our proposed MoE-FL setup relies on the trust between users and the server where the users share a portion of their public data sets with the server. The server applies a robust aggregation method by solving the optimization problem or the Softmax method to highlight the outlier cases and to reduce their adverse effect on the FL process. Our experiments illustrate that MoE-FL outperforms the performance of the traditional aggregation approach for high rate of poisoned data from attackers.

cs.LG↗

arXiv2021

Estimation of Missing Data in Intelligent Transportation System

Missing data is a challenge in many applications, including intelligent transportation systems (ITS). In this paper, we study traffic speed and travel time estimations in ITS, where portions of the collected data are missing due to sensor instability and communication errors at collection points. These practical issues can be remediated by missing data analysis, which are mainly categorized as either statistical or machine learning(ML)-based approaches. Statistical methods require the prior probability distribution of the data which is unknown in our application. Therefore, we focus on an ML-based approach, Multi-Directional Recurrent Neural Network (M-RNN). M-RNN utilizes both temporal and spatial characteristics of the data. We evaluate the effectiveness of this approach on a TomTom dataset containing spatio-temporal measurements of average vehicle speed and travel time in the Greater Toronto Area (GTA). We evaluate the method under various conditions, where the results demonstrate that M-RNN outperforms existing solutions,e.g., spline interpolation and matrix completion, by up to 58% decreases in Root Mean Square Error (RMSE).

cs.LG↗

arXiv2020

Energy Efficiency Through Joint Routing and Function Placement in Different Modes of SDN/NFV Networks

Network function virtualization (NFV) and software defined networking (SDN) are two promising technologies to enable 5G and 6G services and achieve cost reduction, network scalability, and deployment flexibility. However, migration to full SDN/NFV networks in order to serve these services is a time consuming process and costly for mobile operators. This paper focuses on energy efficiency during the transition of mobile core networks (MCN) to full SDN/NFV networks, and explores how energy efficiency can be addressed during such migration. We propose a general system model containing a combination of legacy nodes and links, in addition to newly introduced NFV and SDN nodes. We refer to this system model as partial SDN and hybrid NFV MCN which can cover different modes of SDN and NFV implementations. Based on this framework, we formulate energy efficiency by considering joint routing and function placement in the network. Since this problem belongs to the class of non-linear integer programming problems, to solve it efficiently, we present a modified Viterbi algorithm (MVA) based on multi-stage graph modeling and a modified Dijkstra's algorithm. We simulate this algorithm for a number of network scenarios with different fractions of NFV and SDN nodes, and evaluate how much energy can be saved through such transition. Simulation results confirm the expected performance of the algorithm which saves up to 70% energy compared to network where all nodes are always on. Interestingly, the amount of energy saved by the proposed algorithm in the case of hybrid NFV and partial SDN networks can reach up to 60-90% of the saved energy in full NFV/SDN networks.

cs.NI↗

arXiv2019

Representation of Federated Learning via Worst-Case Robust Optimization Theory

Federated learning (FL) is a distributed learning approach where a set of end-user devices participate in the learning process by acting on their isolated local data sets. Here, we process local data sets of users where worst-case optimization theory is used to reformulate the FL problem where the impact of local data sets in training phase is considered as an uncertain function bounded in a closed uncertainty region. This representation allows us to compare the performance of FL with its centralized counterpart, and to replace the uncertain function with a concept of protection functions leading to more tractable formulation. The latter supports applying a regularization factor in each user cost function in FL to reach a better performance. We evaluated our model using the MNIST data set versus the protection function parameters, e.g., regularization factors.

cs.LG↗

arXiv2019

Cloud-based Queuing Model for Tactile Internet in Next Generation of RAN

Ultra-low latency is the most important requirement of the Tactile Internet (TI), which is one of the proposed services for the next-generation wireless network (NGWN), e.g., fifth generation (5G) network. In this paper, a new queuing model for the TI is proposed for the cloud radio access network (CRAN) architecture of the NGWN by applying power domain non-orthogonal multiple access (PD-NOMA) technology. In this model, we consider both the radio remote head (RRH) and baseband processing unit (BBU) queuing delays for each end-to-end (E2E) connection between a pair of tactile users. In our setup, to minimize the transmit power of users subject to guaranteeing an acceptable delay of users, and fronthaul and access constraints, we formulate a resource allocation (RA) problem. Furthermore, we dynamically set the fronthaul and access links to minimize the total transmit power. Given that the proposed RA problem is highly non-convex, in order to solve it, we utilize diverse transformation techniques such as successive convex approximation (SCA) and difference of two convex functions (DC). Numerical results show that by dynamic adjustment of the access and fronthaul delays, transmit power reduces in comparison with the fixed approach per each connection. Also, energy efficiency of orthogonal frequency division multiple access (OFDMA) and PD-NOMA are compared for our setup.

cs.NI↗

arXiv2019

Resource Management and Admission Control for Tactile Internet in Next Generation of RAN

In this paper, a new queuing model for the Tactile Internet (TI) is proposed for the cloud radio access network (C-RAN) architecture of the next generation wireless networks, e.g., 5G, assisted via orthogonal frequency division multiple access (OFDMA) technology. This model includes both the radio remote head (RRH) and baseband processing unit (BBU) queuing delays and reliability for each end to end (E2E) connection between each pair of tactile users. For this setup, with the aim to minimize the transmit power of users subject to guaranteeing tolerable delay of users, and fronthaul and access limitations, we formulate a resource allocation problem. Since the proposed optimization problem is highly non-convex, to solve it in an efficient manner, we utilize diverse transformation techniques such as successive convex approximation (SCA) and difference of two convex functions (DC). In addition, we propose an admission control (AC) algorithm to make problem feasible. In our proposed system model, we dynamically adjust the fronthaul and access links to minimize the transmit power. Simulation results reveal that by dynamic adjustment of the access and fronthaul delays, transmit power can be saved compared to the case of fixed approach per each transmission session. Moreover, the number of rejected users in the network is significantly reduced and more users are accepted.

cs.NI↗

arXiv2019

Power-Efficient Resource Allocation in Massive MIMO Aided Cloud RANs

This paper considers the power-efficient resource allocation problem in a cloud radio access network (C-RAN). The C-RAN architecture consists of a set of base-band units (BBUs) which are connected to a set of radio remote heads (RRHs) equipped with massive multiple input multiple output (MIMO), via fronthaul links with limited capacity. We formulate the power-efficient optimization problem in C-RANs as a joint resource allocation problem in order to jointly allocate the RRH and transmit power to each user, and fronthaul links and BBUs assign to active RRHs while satisfying the minimum required rate of each user. To solve this non-convex optimization problem we suggest iterative algorithm with two-step based on the complementary geometric programming (CGP) and the successive convex approximation (SCA). The simulation results indicate that our proposed scheme can significantly reduce the total transmission power by switching off the under-utilized RRHs.

eess.SP↗

arXiv2019

Spectrum Sensing and Resource Allocation for 5G Heterogeneous Cloud Radio Access Networks

In this paper, the problem of opportunistic spectrum sharing for the next generation of wireless systems empowered by the cloud radio access network (C-RAN) is studied. More precisely, low-priority users employ cooperative spectrum sensing to detect a vacant portion of the spectrum that is not currently used by high-priority users. The design of the scheme is to maximize the overall throughput of the low-priority users while guaranteeing the quality of service of the high-priority users. This objective is attained by optimally adjusting spectrum sensing time with respect to imposed target probabilities of detection and false alarm as well as dynamically allocating and assigning C-RAN resources, i.e., transmit powers, sub-carriers, remote radio heads (RRHs), and base-band units. The presented optimization problem is non-convex and NP-hard that is extremely hard to tackle directly. To solve the problem, a low-complex iterative approach is proposed in which sensing time, user association parameters and transmit powers of RRHs are alternatively assigned and optimized at every step. Numerical results are then provided to demonstrate the necessity of performing sensing time adjustment in such systems as well as balancing the sensing-throughput tradeoff.

eess.SP↗

arXiv2019

Artificial Intelligence as a Services (AI-aaS) on Software-Defined Infrastructure

This paper investigates a paradigm for offering artificial intelligence as a service (AI-aaS) on software-defined infrastructures (SDIs). The increasing complexity of networking and computing infrastructures is already driving the introduction of automation in networking and cloud computing management systems. Here we consider how these automation mechanisms can be leveraged to offer AI-aaS. Use cases for AI-aaS are easily found in addressing smart applications in sectors such as transportation, manufacturing, energy, water, air quality, and emissions. We propose an architectural scheme based on SDIs where each AI-aaS application is comprised of a monitoring, analysis, policy, execution plus knowledge (MAPE-K) loop (MKL). Each application is composed as one or more specific service chains embedded in SDI, some of which will include a Machine Learning (ML) pipeline. Our model includes a new training plane and an AI-aaS plane to deal with the model-development and operational phases of AI applications. We also consider the role of an ML/MKL sandbox in ensuring coherency and consistency in the operation of multiple parallel MKL loops. We present experimental measurement results for three AI-aaS applications deployed on the SAVI testbed: 1. Compressing monitored data in SDI using autoencoders; 2. Traffic monitoring to allocate CPUs resources to VNFs; and 3. Highway segment classification in smart transportation.

cs.LG↗

arXiv2019

Analytical Channel Models for Millimeter Wave UAV Networks under Hovering Fluctuations

The integration of unmanned aerial vehicles (UAVs) and millimeter wave (mmWave) wireless systems has been recently proposed to provide high data rate aerial links for next generation wireless networks. However, establishing UAV-based mmWave links is quite challenging due to the random fluctuations of hovering UAVs which can induce antenna gain mismatch between transmitter and receiver. To assess the benefit of UAV-based mmWave links, in this paper, tractable, closed-form statistical channel models are derived for three UAV communication scenarios: (i) a direct UAV-to-UAV link, (ii) an aerial relay link in which source, relay, and destination are hovering UAVs, and (iii) a relay link in which a hovering UAV connects a ground source to a ground destination. The accuracy of the derived analytical expressions is corroborated by performing Monte-Carlo simulations. Numerical results are then used to study the effect of antenna directivity gain under different channel conditions for establishing reliable UAV-based mmWave links in terms of achieving minimum outage probability. It is shown that the performance of such links is largely dependent on the random fluctuations of hovering UAVs. Moreover, higher antenna directivity gains achieve better performance at low SNR regime. Nevertheless, at the high SNR regime, lower antenna directivity gains result in a more reliable communication link. The developed results can therefore be applied as a benchmark for finding the optimal antenna directivity gain of UAVs under the different levels of instability without resorting to time-consuming simulations.

eess.SP↗

arXiv2019

Cooperative Multi-Bitrate Video Caching and Transcoding in Multicarrier NOMA-Assisted Heterogeneous Virtualized MEC Networks

Cooperative video caching and transcoding in mobile edge computing (MEC) networks is a new paradigm for future wireless networks, e.g., 5G and 5G beyond, to reduce scarce and expensive backhaul resource usage by prefetching video files within radio access networks (RANs). Integration of this technique with other advent technologies, such as wireless network virtualization and multicarrier non-orthogonal multiple access (MC-NOMA), provides more flexible video delivery opportunities, which leads to enhancements both for the network's revenue and for the end-users' service experience. In this regard, we propose a two-phase RAF for a parallel cooperative joint multi-bitrate video caching and transcoding in heterogeneous virtualized MEC networks. In the cache placement phase, we propose novel proactive delivery-aware cache placement strategies (DACPSs) by jointly allocating physical and radio resources based on network stochastic information to exploit flexible delivery opportunities. Then, for the delivery phase, we propose a delivery policy based on the user requests and network channel conditions. The optimization problems corresponding to both phases aim to maximize the total revenue of network slices, i.e., virtual networks. Both problems are non-convex and suffer from high-computational complexities. For each phase, we show how the problem can be solved efficiently. We also propose a low-complexity RAF in which the complexity of the delivery algorithm is significantly reduced. A Delivery-aware cache refreshment strategy (DACRS) in the delivery phase is also proposed to tackle the dynamically changes of network stochastic information. Extensive numerical assessments demonstrate a performance improvement of up to 30% for our proposed DACPSs and DACRS over traditional approaches.

cs.IT↗

arXiv2018

Dynamic Non-Orthogonal Multiple Access (NOMA) and Orthogonal Multiple Access (OMA) in 5G Wireless Networks

In this paper, facilitated via the flexible software defined structure of the radio access units in 5G, we propose a novel dynamic multiple access technology selection among orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA) techniques for each subcarrier. For this setup, we formulate a joint resource allocation problem where a new set of access technology selection parameters along with power and subcarrier are allocated for each user based on each user's channel state information. Here, we define a novel utility function taking into account the rate and costs of access technologies. This cost reflects both the complexity of performing successive interference cancellation and the complexity incurred to guarantee a desired bit error rate. This utility function can inherently demonstrate the trade-off between OMA and NOMA. Due to non-convexity of our proposed resource allocation problem, we resort to successive convex approximation where a two-step iterative algorithm is applied in which a problem of the first step, called access technology selection, is transformed into a linear integer programming problem, and the nonconvex problem of the second step, referred to power allocation problem, is solved via the difference-of-convex-functions (DC) programming. Moreover, the closed-form solution for power allocation in the second step is derived. For diverse network performance criteria such as rate, simulation results show that the proposed new dynamic access technology selection outperforms single-technology OMA or NOMA multiple access solutions.

eess.SP↗