Bradley Department of Electrical and Computer Engineering

Permanent URI for this community

https://hdl.handle.net/10919/18738

From pervasive computing, to smart power systems, Virginia Tech ECE faculty and students delve into all major areas of electrical and computer engineering. The main campus is in Blacksburg, and the department has additional research and teaching facilities in Arlington, Falls Church, and Hampton, Virginia.

Browse

Now showing 1 - 13 of 13

Abnormal Behavior Detection Based on Traffic Pattern Categorization in Mobile Cellular Networks
De Almeida, J. M.; Pontes, C. F. T.; DaSilva, Luiz A.; Both, C. B.; Gondim, J. J. C.; Ralha, Celia G.; Marotta, M. A. (IEEE, 2021-01-01)
Abnormal behavior in mobile cellular networks can cause network faults and consequent cell outages, a major reason for operational cost increase and revenue loss for operators. Nonetheless, network faults and cell outages can be avoided by monitoring abnormal situations in the network and acting accordingly. Thus, anomaly detection is an important component of self-healing control and network management. Network operators may use the detected abnormal behavior to quantify numerically their intensity. The quantification of abnormal behavior assists the characterization of potential regions for infrastructure updates and to support the creation of public policies for local connectivity enhancements. We propose an unsupervised learning solution for anomaly detection in mobile networks using Call Detail Records (CDR) data. We evaluate our solution using a real CDR data set provided by an Italian operator and compare it against other state-of-the-art solutions, showing a performance improvement of around 35%. We also demonstrate the relevance of considering the distinct traffic patterns of diverging geographic areas for anomaly detection in mobile networks, an aspect often ignored in the literature.
AIRTIME: End-to-end Virtualization Layer for RAN-as-a-Service in Future Multi-Service Mobile Networks
Kist, Maicon; Santos, Joao F.; Collins, Diarmuid; Rochol, Juergen; DaSilva, Luiz A.; Both, Cristiano (IEEE, 2020)
Future mobile networks are envisioned to become multi-service systems, enabling the dynamic deployment of services with vastly different performance requirements, accommodating the needs of diverse service providers. Virtualizing the mobile network infrastructure is of fundamental importance for realizing this vision in a cost-effective manner. While there have been extensive research efforts in virtualization for the mobile core network, virtualization in the radio access network (RAN) is still at an early stage. In this paper, we present AIRTIME, a new RAN slicing system that enables the dynamic on-the-fly virtualization of RANs, with the programmability required by service providers to customize any aspect of their virtual RAN to meet their service needs. We present a prototype implementation of AIRTIME and evaluate the: (i) capacity to create virtual RANs on-the-fly, (ii) performance experienced by slice owners, (iii) isolation among multiple virtual RANs sharing the same physical infrastructure, and (iv) scalability to accommodate a large number of virtual RANs.
Breaking Down Network Slicing: Hierarchical Orchestration of End-to-End Networks
Santos, Joao F.; Liu, Wei; Jiao, Xianjun; Neto, Natal V.; Pollin, Sofie; Marquez-Barja, Johann M.; Moerman, Ingrid; DaSilva, Luiz A. (IEEE, 2020-10-01)
Network slicing is one of the key enabling techniques for 5G, allowing Network Providers (NPs) to support services with diverging requirements on top of their physical infrastructure. In this paper, we address the limited support and oversimplified resource allocation on different network segments of existing End-to-End (E2E) orchestration solutions. We propose a hierarchical orchestration scheme for E2E networks, breaking down the E2E resource management and network slicing problems per network segment. We introduce a higherlevel orchestrator, the hyperstrator, to coordinate the distributed orchestrators and deploy Network Slices (NSs) across multiple network segments. We developed a prototype implementation of the hyperstrator and validated our hierarchical orchestration concept with two proof-of-concept experiments, showing the NS deployment and the impact of the resource allocation per network segment on the performance of NSs. The results show that the distributed nature of our orchestration architecture introduces negligible overhead for provisioning NSs in our particular setting, and confirm the need of a hyperstrator for coordinating network segments and ensuring consistent QoS for NSs.
Cumulative Message Authentication Codes for Resource-Constrained IoT Networks
Li, He; Kumar, Vireshwar; Park, Jung-Min (Jerry); Yang, Yaling (IEEE, 2021-08-01)
In resource-constrained Internet-of-Things networks, the use of conventional message authentication codes (MACs) to provide message authentication and integrity is not possible due to the large size of the MAC output. A straightforward yet naive solution to this problem is to employ a truncated MAC which undesirably sacrifices cryptographic strength in exchange for reduced communication overhead. In this article, we address this problem by proposing a novel approach for message authentication called cumulative MAC (CuMAC), which consists of two distinctive procedures: 1) aggregation and 2) accumulation. In aggregation, a sender generates compact authentication tags from segments of multiple MACs by using a systematic encoding procedure. In accumulation, a receiver accumulates the cryptographic strength of the underlying MAC by collecting and verifying the authentication tags. Embodied with these two procedures, CuMAC enables the receiver to achieve an advantageous tradeoff between the cryptographic strength and the latency in the processing of the authentication tags. Furthermore, for some latency-sensitive messages where this tradeoff may be unacceptable, we propose a variant of CuMAC that we refer to as CuMAC with speculation (CuMAC/S). In addition to the aggregation and accumulation procedures, CuMAC/S enables the sender and receiver to employ a speculation procedure for predicting future message values and precomputing the corresponding MAC segments. For the messages which can be reliably speculated, CuMAC/S significantly reduces the MAC verification latency without compromising the cryptographic strength. We have carried out a comprehensive evaluation of CuMAC and CuMAC/S through simulation and a prototype implementation on a real car.
Customization and Trade-offs in 5G RAN Slicing
Sexton, Conor; Marchetti, Nicola; DaSilva, Luiz A. (IEEE, 2019-04-01)
The heterogeneity of the requirements for 5G necessitate a versatile 5G radio access network (RAN); slicing offers a way of realising a flexible RAN through customised virtual subnetworks. In this paper, we focus on how enabling lower layer flexibility in the RAN affects the development of RAN slicing, particularly in relation to ensuring isolation between RAN slices. We first examine how RAN slices may be individually tailored for different services. We follow this up with an examination of the potential time-frequency resource structure of the RAN, focusing on the trade-off between flexibility and the overhead related to ensuring coexistence between contrasting RAN slices. Based on this analysis, we suggest an approach that permits the allocation of resources to a service-type to be performed separately to resource allocation for individual services belonging to that type.
Differential Privacy Meets Federated Learning under Communication Constraints
Mohammadi, Nima; Bai, Jianan; Fan, Qiang; Song, Yifei; Yi, Yang; Liu, Lingjia (IEEE, 2021)
The performance of federated learning systems is bottlenecked by communication costs and training variance. The communication overhead problem is usually addressed by three communication-reduction techniques, namely, model compression, partial device participation, and periodic aggregation, at the cost of increased training variance. Different from traditional distributed learning systems, federated learning suffers from data heterogeneity (since the devices sample their data from possibly different distributions), which induces additional variance among devices during training. Various variance-reduced training algorithms have been introduced to combat the effects of data heterogeneity, while they usually cost additional communication resources to deliver necessary control information. Additionally, data privacy remains a critical issue in FL, and thus there have been attempts at bringing Differential Privacy to this framework as a mediator between utility and privacy requirements. This paper investigates the trade-offs between communication costs and training variance under a resource-constrained federated system theoretically and experimentally, and studies how communication reduction techniques interplay in a differentially private setting. The results provide important insights into designing practical privacy-aware federated learning systems.
Energy Aware Deep Reinforcement Learning Scheduling for Sensors Correlated in Time and Space
Hribar, Jernej; Marinescu, Andrei; Chiumento, Alessandro; DaSilva, Luiz A. (IEEE, 2021-01-01)
Millions of battery-powered sensors deployed for monitoring purposes in a multitude of scenarios, e.g., agriculture, smart cities, industry, etc., require energy-efficient solutions to prolong their lifetime. When these sensors observe a phenomenon distributed in space and evolving in time, it is expected that collected observations will be correlated in time and space. This paper proposes a () based scheduling mechanism capable of taking advantage of correlated information. The designed solution employs () algorithm. The proposed mechanism can determine the frequency with which sensors should transmit their updates, to ensure accurate collection of observations, while simultaneously considering the energy available. The solution is evaluated with multiple datasets containing environmental observations obtained in multiple real deployments. The real observations are leveraged to model the environment with which the mechanism interacts as realistically as possible. The proposed solution can significantly extend the sensors’ lifetime and is compared to an idealized, all-knowing scheduler to demonstrate that its performance is near-optimal. Additionally, the results highlight the unique feature of proposed design, energy-awareness, by displaying the impact of sensors’ energy levels on the frequency of updates.
FUTEBOL Control Framework: Enabling Experimentation in Convergent Optical, Wireless, and Cloud Infrastructures
Both, Cristiano; Guimaraes, Rafael S.; Slyne, Frank; Wickboldt, Juliano Araujo; Martinello, Magnos; Dominicini, Cristina; Martins, Rafael; Zhang, Yi; Cardoso, Diego; Villaca, Rodolfo; Ceravolo, Isabella; Nejabati, Reza; Marquez-Barja, Johann M.; Ruffini, Marco; DaSilva, Luiz A. (IEEE, 2019-10-01)
Large-scale testing and evaluation of network solutions are complex and typically involve multiple domains (e.g., optical, wireless, and cloud). The FUTEBOL project has deployed geographically distributed testbeds in Brazil and Europe that enable the experimentation and validation of new cross-domain network solutions. In this article, we introduce a Control Framework that allows experimenters to slice, reserve, and orchestrate optical, wireless, and cloud resources in a coordinated manner. We illustrate the features of our Control Framework and evaluate it through an experiment involving resource orchestration and automatic service scaling across multiple domains.
Multi-Operator Connectivity Sharing for Reliable Networks: A Data-Driven Risk Analysis
Gomes, Andre; Kibilda, Jacek; Farhang, Arman; Farrell, Ronan; DaSilva, Luiz A. (IEEE, 2021-09-01)
A key distinction between today's and future networks is the appetite for reliable communication to support emerging critical-communication services. In this paper, we study multi-operator connectivity as a form of redundancy to support the design of reliable networks and investigate its trade-offs. This approach is motivated by 3GPP standardisation initiatives of dual-connectivity and similar techniques in industrial wired networks. We deploy a risk awareness performance metric to assess reliability: this superquantile metric accounts for periods of connectivity shortfalls. Our analysis shows that multi-operator connectivity brings significant reliability gains, in particular when network deployments by different operators exhibit high complementarity in coverage. We also explore the effects of multi-connectivity on spectral efficiency in times of high demand for bandwidth. Our study is based on a real-world dataset comprising signal strength indicators of three mobile operators in Dublin, Ireland.
Radio Access Technology characterisation through object detection
Fonseca, Erika; Santos, Joao F.; Paisana, Francisco; DaSilva, Luiz A. (Elsevier, 2021-02-15)
Radio Access Technology (RAT) classification and monitoring are essential for efficient coexistence of different communication systems in shared spectrum. Shared spectrum, including operation in license-exempt bands, is envisioned in the fifth generation of wireless technology (5G) standards (e.g., 3GPP Rel. 16). In this paper, we propose a Machine Learning (ML) approach to characterise the spectrum utilisation and facilitate the dynamic access to it. Recent advances in Convolutional Neural Networks (CNNs) enable us to perform waveform classification by processing spectrograms as images. In contrast to other ML methods that can only provide the class of the monitored RATs, the solution we propose can recognise not only different RATs in shared spectrum, but also identify critical parameters such as inter-frame duration, frame duration, centre frequency, and signal bandwidth by using object detection and a feature extraction module to extract features from spectrograms. We have implemented and evaluated our solution using a dataset of commercial transmissions, as well as in a Software-Defined Radio (SDR) testbed environment. The scenario evaluated was the coexistence of WiFi and LTE transmissions in shared spectrum. Our results show that our approach has an accuracy of 96% in the classification of RATs from a dataset that captures transmissions of regular user communications. It also shows that the extracted features can be precise within a margin of 2%, and can detect above 94% of objects under a broad range of transmission power levels and interference conditions.
Taming the Contention in Consensus-Based Distributed Systems
Arun, Balaji; Peluso, Sebastiano; Palmieri, Roberto; Losa, Giuliano; Ravindran, Binoy (IEEE, 2021-11-01)
Contention plays a crucial role in the design of consensus protocols. State-of-the-art solutions optimize their performance for either very low or high contention situations. We propose Caesar, a novel multi-leader Generalized Consensus protocol, most suitable for geographical replication, that is optimized for low-to-moderate contention. With an evaluation study, we show that Caesar outperforms other multi-leader (e.g., EPaxos) and single-leader (e.g., Multi-Paxos) competitors by up to 1.7x and 3.5x, respectively, in the presence of 30 percent conflicting requests, in a geo-replicated setting. Furthermore, we acknowledge that there is no one-size-fits- all consensus solution, especially for all levels of contentious workloads. Thus, we also propose Spectrum, a consensus framework that is able to switch consensus protocols at runtime to enable a dynamic reaction to changes in the workload and deployment characteristics. We show empirically that Spectrum can guarantee high availability even during periods of transition between consensus protocols.
UAVs as Mobile Infrastructure: Addressing Battery Lifetime
Galkin, Boris; Kibilda, Jacek; DaSilva, Luiz A. (IEEE, 2019-06-01)
Unmanned Aerial Vehicles (UAVs) can play an important role in next generation cellular networks, acting as flying infrastructure which can serve ground users when regular infrastructure is overloaded or unavailable. As these devices operate wirelessly they rely on an internal battery for their power supply, which limits the amount of time they can operate over an area of interest before having to recharge. To accommodate this limitation UAV networks will have to rely on dedicated infrastructure to recharge the UAVs in-between deployments. In this article, we outline three battery charging options that may be considered by a network operator and use simulations to demonstrate the performance impact of incorporating those options into a cellular network where UAV infrastructure provides wireless service.
Using correlated information to extend device lifetime
Hribar, Jernej; Costa, Maice; Kaminski, Nicholas; DaSilva, Luiz A. (IEEE, 2019-04-01)
The massive device deployments in the Internet of Things (IoT) generate immense amounts of data that can be leveraged to improve overall network performance. This paper outlines how data gathered from correlated sensor nodes can be used to improve the timeliness of updates of another sensor node in the network. We consider a system of two correlated information sources, i.e., sensor nodes, which periodically send updates to a gateway, regarding the observed physical phenomenon distributed in space and evolving in time. The optimal use of updates in such a system greatly depends on the correlation between the two sources, and to explore this effect we investigate three different models of the covariance between independently obtained observations of the phenomenon of the interest. We extract values for the parameters in the covariance models from data coming from a real sensor network, to provide the reader with a realistic feel for scaling parameters values and the applicability of our analysis in a real scenario. We demonstrate that using correlated information results in a significant increase in device lifetime and compare our approach to others proposed in the literature.

Browse

Browsing Bradley Department of Electrical and Computer Engineering by Subject "0805 Distributed Computing"

Results Per Page

Sort Options