Browsing by Author "Mumtaz, Shahid"

Now showing 1 - 11 of 11
  • Thumbnail Image
    ItemOpen Access
    AI-driven blind signature classification for IoT connectivity: a deep learning approach
    (IEEE, 2022-01-31) Pan, Jianxiong; Ye, Neng; Yu, Hanxiao; Hong, Tao; Al-Rubaye, Saba; Mumtaz, Shahid; Al-Dulaimi, Anwer; Chih-Lin, I.
    Non-orthogonal multiple access (NOMA) promises to fulfill the fast-growing connectivities in future Internet of Things (IoT) using abundant multiple-access signatures. While explicitly notifying the utilized NOMA signatures causes large signaling cost, blind signature classification naturally becomes a low-cost option. To accomplish signature classification for NOMA, we study both likelihood- and feature-based methods. A likelihood-based method is firstly proposed and showed to be optimal in the asymptotic limit of the observations, despite high computational complexity. While feature-based classification methods promise low complexity, efficient features are non-trivial to be manually designed. To this end, we resort to artificial intelligence (AI) for deep learning-based automatic feature extraction. Specifically, our proposed deep neural network for signature classification, namely DeepClassifier, establishes on the insights gained from the likelihood-based method, which contains two stages to respectively deal with a single observation and aggregate the classification results of an observation sequence. The first stage utilizes an iterative structure where each layer employs a memory-extended network to explicitly exploit the knowledge of signature pool. The second stage incorporates the straight-through channels within a deep recurrent structure to avoid information loss of previous observations. Experiments show that DeepClassifier approaches the optimal likelihood-based method with a reduction of 90% complexity.
  • Thumbnail Image
    ItemOpen Access
    Enabling digital grid for industrial revolution: self-healing cyber resilient platform
    (IEEE, 2019-05-15) Al-Rubaye, Saba; Rodriguez, Jonathan; Al-Dulaimi, Anwer; Mumtaz, Shahid; Rodrigues, Joel J. P. C.
    The key market objectives driving digital grid development are to provide sustainable, reliable and secure network systems that can support variety of applications against any potential cyber attacks. Therefore, there is an urgent demand to accelerate the development of intelligent Software-Defined Networking (SDN) platform that can address the tremendous challenges of data protection for digital resiliency. Modern grid technology tends to adopt distributed SDN controllers for further slicing power grid domain and protect the boundaries of electric data at network edges. To accommodate these issues, this article proposes an intelligent secure SDN controller for supporting digital grid resiliency, considering management coordination capability, to enable self-healing features and recovery of network traffic forwarding during service interruptions. A set of advanced features are employed in grid controllers to configure the network elements in response to possible disasters or link failures. In addition, various SDN topology scenarios are introduced for efficient coordination and configurations of network domains. Finally, to justify the potential advantages of intelligent secure SDN system, a case study is presented to evaluate the requirements of secure digital modern grid networks and pave the path towards the next phase of industry revolution.
  • Thumbnail Image
    ItemOpen Access
    Exploiting impacts of antenna selection and energy harvesting for massive network connectivity
    (IEEE, 2021-08-18) Van Nguyen, Minh-Sang; Do, Dinh-Thuan; Al-Rubaye, Saba; Mumtaz, Shahid; Al-Dulaimi, Anwer; Dobre, Octavia
    As a new energy saving approach for green communications, energy harvesting (EH) could be suitable technique to facilitate massive connections for large number of devices in such networks. The spectrum shortage occurs in huge number of devices which access with small-cell and macro-cell networks. To tackle these challenges, we develop a tractable framework relying on prominent techniques such as non-orthogonal multiple access (NOMA), antenna selection and energy harvesting. In this paper, we aim at practical scenarios of small cell networks by jointly evaluating capable of interference management and EH. We benefit from transmission approaches including full duplex (FD) and bi-directional transmission to improve the main performance system metrics such as outage probability and throughput. Three useful schemes are explored by considering EH and inter-cell interference. We derive the closed-form and asymptotic expressions for system metrics. We then perform extensive simulations with different system configurations to confirm the effectiveness of the proposed small-cell NOMA systems.
  • Thumbnail Image
    ItemOpen Access
    A framework of network connectivity management in multi-clouds infrastructure
    (IEEE, 2019-02-21) Al-Dulaimi, Anwer; Mumtaz, Shahid; Al-Rubaye, Saba; Zhang, Siming; Lin, Chih
    The network function virtualization (NFV) transformation is gaining an incredible momentum from mobile operators as one of the significant solutions to improve the resource allocation and system scalability in fifth-generation (5G) networks. However, the ultra-dense deployments in 5G create high volumes of traffic that pushes the physical and virtual resources of cloud-based networks to edge limits. Consider a distributed cloud, replacing the core network with virtual entities in the form of virtual network functions (VNFs) still requires efficient integration with various underlying hardware technologies. Therefore, orchestrating the distribution of load between cloud geo-datacenters starts by instantiating a virtual and physical network typologies that connect involved front haul with relevant VNFs. In this article, we provide a framework to manage calls within 5G network clusters for efficient utilization of computational resources and also to prevent unnecessary signaling. We also propose a new scheme to instantiate virtual tunnels for call forwarding between network clusters leading to new logic networks that combine geo-datacenters and fronthaul. To facilitate service chaining in cloud, we propose a new enhanced management and orchestration (E-MANO) architecture that brings network traffic policies from the application layer tothe fronthaul for instant monitoring of available resources. We provide analysis and testbed results in support of our proposals. the fronthaul for instant monitoring of available resources. We provide analysis and testbed results in support of our proposals.
  • Thumbnail Image
    ItemOpen Access
    Generalized hybrid beamforming for vehicular connectivity using THz massive MIMO
    (IEEE, 2019-06-07) Busari, Sherif Adeshina; Huq, Kazi Mohammed Saidul; Mumtaz, Shahid; Rodriguez, Jonathan; Fang, Yi; Sicker, Douglas C.; Al-Rubaye, Saba; Tsourdos, Antonios
    Hybrid beamforming (HBF) array structure has been extensively demonstrated as the practically-feasible architecture for massive MIMO. From the perspectives of spectral efficiency (SE), energy efficiency (EE), cost and hardware complexity, HBF strikes a balanced performance tradeoff when compared to the fully-analog and the fully-digital implementations. Using the HBF architecture, it is possible to realize three different subarray structures, specifically the fully-connected, the sub-connected and the overlapped subarray structures. This paper presents a novel generalized framework for the design and performance analysis of the HBF architecture. A parameter, known as the subarray spacing, is introduced such that varying its value leads to the different subarray configurations and the consequent changes in system performance. Using a realistic power consumption model, we investigate the performance of the generalized HBF array structure in a cellular infrastructure-to-everything (C-I2X) application scenario (involving pedestrian and vehicular users) using the single-path terahertz (THz) channel model. Simulation results are provided for the comparative performance analysis of the different subarray structures. The results show that the overlapped subarray implementation maintains a balanced tradeoff in terms of SE, EE and hardware cost when compared to the popular fully-connected and the sub-connected structures. The overlapped subarray structure, therefore, offers promising potentials for the beyond-5G networks employing THz massive MIMO to deliver ultra-high data rates whilst maintaining a balance in the EE of the network.
  • Thumbnail Image
    ItemOpen Access
    Machine learning and multi-dimension features based adaptive intrusion detection in ICN
    (IEEE, 2020-07-27) Li, Zhihao; Wu, Jun; Mumtaz, Shahid; Taha, A-E M.; Al-Rubaye, Saba; Tsourdos, Antonios
    As a new network architecture, Information-Centric Networks (ICN) has great advantages in content distribution and can better meet our needs. But it faced with many threats unavoidably. There are four types of attack in ICN: naming related attacks, routing related attacks, caching related attacks and miscellaneous attacks. These attacks will undermine the availability of ICN, the confidentiality and privacy of data. In addition, routers store a large amount of content for the users' request, and it is necessary to protect these intermediate nodes. Since the styles of content stored in nodes are not the same, using a unified set of intrusion detection rules simply will cause a large number of false positives and false negatives. Therefore, every node should perform intrusion detection according to its own characteristics. In this paper, we propose an intrusion detection mechanism to alert for abnormal packets. We introduce a extensive solution using machine learning for attacks in ICN. Moreover, the nodes in this scheme can adapt to the external environment and intelligently detect packets. Simulation on the machine learning algorithm involved prove that the algorithm is effective and suitable for network packets.
  • Thumbnail Image
    ItemOpen Access
    A multi-task learning model for super resolution of wireless channel characteristics
    (IEEE, 2023-01-11) Wang, Xiping; Zhang, Zhao; He, Danping; Guan, Ke; Liu, Dongliang; Dou, Jianwu; Mumtaz, Shahid; Al-Rubaye, Saba
    Channel modeling has always been the core part in communication system design and development, especially in 5G and 6G era. Traditional approaches like stochastic channel modeling and ray-tracing (RT) based channel modeling depend heavily on measurement data or simulation, which are usually expensive and time consuming. In this paper, we propose a novel super resolution (SR) model for generating channel character-istics data. The model is based on multi-task learning (MTL) convolutional neural networks (CNN) with residual connection. Experiments demonstrate that the proposed SR model could achieve excellent performances in mean absolute error and standard deviation of error. Advantages of the proposed model are demonstrated in comparisons with other state-of-the-art deep learning models. Ablation study also proved the necessity of multi-task learning and techniques in model design. The contribution in this paper could be helpful in channel modeling, network optimization, positioning and other wireless channel characteristics related work by largely reducing workload of simulation or measurement.
  • Thumbnail Image
    ItemOpen Access
    A novel mapping technique for ray tracer to system-level simulation
    (Elsevier, 2019-12-02) Awais Khan, Muhammad; Adeshina Busari, Sherif; Mohammed Saidul Huq, Kazi; Mumtaz, Shahid; Al-Rubaye, Saba; Rodriguez, Jonathan; Al-Dulaimi, Anwer
    Simulations have become remarkably useful in evaluating the performance of new techniques and algorithms in communication networks. This is due to its comparative cost, time and complexity advantage over the analytical and field trial approaches. For large-scale networks, system-level simulators (SLS) are used to assess the performance of the systems. The SLS typically employs statistical channel models to characterize the propagation environment. However, the communication channels can be more accurately modeled using the deterministic ray tracing tools, though at the cost of higher complexity. In this work, we present a novel framework for a hybrid system that integrates both the ray tracer and the SLS. In the hybrid system, the channel strength in terms of the signal-to-noise ratio (SNR) is fed from the ray tracer to the SLS which then uses the values for further tasks such as resource allocation and the consequent performance evaluation. Using metrics such as user throughput and spectral efficiency, our results show that the hybrid system predicts the system performance more accurately than the baseline SLS without ray tracing. The hybrid system will thus facilitate the accurate assessment of the performance of next-generation wireless systems.
  • Thumbnail Image
    ItemOpen Access
    Optimization of non-orthogonal multiple access based visible light communication systems
    (IEEE, 2019-01-01) Tahira, Zanib; Asif, Hafiz M.; Khan, Asim Ali; Baig, Sobia; Mumtaz, Shahid; Al-Rubaye, Saba
    In visible light communication (VLC), the data is transmitted by modulating the light emitting diode (LED). The data-rate is throttled by the narrow modulation bandwidth of LEDs, which becomes a barrier for attaining high transmission rates. Non-orthogonal multiple access (NOMA) is a new scheme envisioned to improve the system capacity. In addition to multiple access schemes, optimization techniques are applied to further improve the data rate. In this letter, convex optimization is applied to NOMA-based VLC system for downlink. The proposed optimization system is analyzed in terms of the bit error rate (BER) and the sum-rate.
  • Thumbnail Image
    ItemOpen Access
    Power control optimization for large-scale multi-antenna systems
    (IEEE, 2020-07-28) Zhou, Zhenyu; Yu, Haijun; Mumtaz, Shahid; Al-Rubaye, Saba; Tsourdos, Antonios; Qingyang Hu, Rose
    Large-scale multi-antenna systems can effectively improve data transmission reliability and throughput for smart grid. However, the massive number of antennas and radio frequency (RF) chains also result in high complexity and energy cost. In this paper, we develop a new performance benchmark named energy economic efficiency for measuring the time-average throughput per energy cost. Then, we investigate how to maximize long-term energy economic efficiency via the joint optimization of communication and energy resource allocation. The formulated joint optimization problem is NP-hard because it not only involves long-term nonlinear optimization objective and constraints, but also involves both integer and continuous optimization variables. Next, we propose an online joint antenna selection and power control algorithm by combining nonlinear fractional programming, Lyapunov optimization, and bisection method. The proposed algorithm can achieve bounded performance deviation from the optimum performance without requiring the prior knowledge of future channel state information (CSI), energy arrival, and electricity price. Finally, a comprehensive theoretical analysis is provided, and the proposed algorithm is verified through simulations under various system configurations.
  • Thumbnail Image
    ItemOpen Access
    Two-timescale resource allocation for automated networks in IIoT
    (IEEE, 2022-04-04) He, Yanhua; Ren, Yun; Zhou, Zhenyu; Mumtaz, Shahid; Al-Rubaye, Saba; Tsourdos, Antonios; Dobre, Octavia A.
    The rapid technological advances of cellular technologies will revolutionize network automation in industrial internet of things (IIoT). In this paper, we investigate the two-timescale resource allocation problem in IIoT networks with hybrid energy supply, where temporal variations of energy harvesting (EH), electricity price, channel state, and data arrival exhibit different granularity. The formulated problem consists of energy management at a large timescale, as well as rate control, channel selection, and power allocation at a small timescale. To address this challenge, we develop an online solution to guarantee bounded performance deviation with only causal information. Specifically, Lyapunov optimization is leveraged to transform the long-term stochastic optimization problem into a series of short-term deterministic optimization problems. Then, a low-complexity rate control algorithm is developed based on alternating direction method of multipliers (ADMM), which accelerates the convergence speed via the decomposition-coordination approach. Next, the joint channel selection and power allocation problem is transformed into a one-to-many matching problem, and solved by the proposed price-based matching with quota restriction. Finally, the proposed algorithm is verified through simulations under various system configurations.