Designing optimal non-terrestrial network (NTN) constellations is essential for maximizing throughput and ensuring fair resource distribution. This paper presents FTA-NTN (Fairness and Throughput Assurance in Non-Terrestrial Networks), a multi-objective optimization framework that jointly maximizes throughput and fairness under realistic system constraints. The framework integrates multi-layer Walker Delta constellations, a parametric mobility model for user distributions across Canadian land regions, adaptive K-Means clustering for beamforming and user association, and Bayesian optimization for parameter tuning. Simulation results with 500 users show that FTA-NTN achieves over 9.88 Gbps of aggregate throughput with an average fairness of 0.42, corresponding to an optimal configuration of 9 planes with 15 satellites per plane in LEO and 7 planes with 3 satellites per plane in MEO. These values align with 3GPP NTN evaluation scenarios and representative system assumptions, confirming their relevance for realistic deployments. Overall, FTA-NTN demonstrates that throughput and fairness can be jointly optimized under practical constraints, advancing beyond throughput-centric designs in the literature and offering a scalable methodology for next-generation NTN deployments that supports efficient and equitable global connectivity.

Machine Learning (ML) techniques have gained extensive attention for network intrusion detection. However, integrating ML approaches faces two primary challenges due to the presence of multi-class attacks and their varying impact levels on the network: the one-size-fits-all dilemma and the consideration of intrusion costs. Since ML models exhibit differing detection performances for each attack class, a single ML model may not suffice for predicting all attacks. Additionally, intrusion cost, a crucial concern for users and network service providers, is often overlooked in intrusion detection scheme development. To address these challenges, we propose a novel ensemble-learning framework called All Predict Cost Efficient Decides (APCED). APCED integrates multiple ML models, selecting an expert ML model for each attack class to minimize intrusion costs. In APCED, both damage cost and response cost determine the cost-efficient base estimators for ensemble learning, with an aggregation strategy employed for final decisions. We evaluate the performance of APCED using the NSL-KDD dataset. Numerical results demonstrate that APCED enhances the overall weighted F1 score by 81.13% compared to Adaboost and achieves an overall cost reduction of 54.7% and 87% compared to XGBoost and Adaboost, respectively.

We propose Deep Dict, a deep learning-based lossy time series compressor designed to achieve a high compression ratio while maintaining decompression error within a predefined range. Deep Dict incorporates two essential components: the Bernoulli transformer autoencoder (BTAE) and a distortion constraint. BTAE extracts Bernoulli representations from time series data, reducing the size of the representations compared to conventional autoencoders. The distortion constraint limits the prediction error of BTAE to the desired range. More-over, in order to address the limitations of common regression losses such as L1/L2, we introduce a novel loss function called quantized entropy loss (QEL). QEL takes into account the specific characteristics of the problem, enhancing robustness to outliers and alleviating optimization challenges. Our evaluation of Deep Dict across diverse time series datasets from various IoT domains reveals that Deep Dict outperforms state-of-the-art lossy compressors in terms of compression ratio by a significant margin by up to 53.66%.

Network Intrusion Detection Systems (NIDS) have been extensively investigated by monitoring real network traffic and analyzing suspicious activities. However, there are limitations in detecting specific types of attacks with NIDS, such as Advanced Persistent Threats (APT). Additionally, NIDS is restricted in observing complete traffic information due to encrypted traffic or a lack of authority. To address these limitations, a Host-based Intrusion Detection system (HIDS) evaluates resources in the host, including logs, files, and folders, to identify APT attacks that routinely inject malicious files into victimized nodes. In this study, a hybrid network intrusion detection system that combines NIDS and HIDS is proposed to improve intrusion detection performance. The host data undergoes a Language Processing (NLP)-based Bidirectional Encoder Representations from Transformers (BERT) model from textual representation to a numerical one in order to process host data in a similar way to the network flow data through machine learning models. The feature flattening technique is applied to flatten two-dimensional host-based features that is provided by BERT into one-dimensional vectors so that host-based and network flow-based features can be processed by advanced Machine Learning (ML) models. In order to enhance HIDS effectiveness, a two-stage collaborative classifier is utilized, which applies two tiers of machine learning algorithms, binary and multi-class classifiers, to detect network intrusions. Once a binary classifier is used to detect benign samples to reduce the complexity of the original problem, the attack data are classified by a multi-class supervised learner to identify attack types. Hence, the overall performance of the two-stage collaborative model outperforms the baseline classifier, XGBoost. The proposed method is shown to generalize across two well-known datasets, CICIDS 2018 and NDSec-1. The performance of XGBoost, which represents conventional ML, is evaluated. Combining host and network features enhances attack detection performance (macro average F1 score) by 8.1% under the CICIDS 2018 dataset and 3.7% under the NDSec-1 dataset. Meanwhile, the two-stage collaborative classifier improves detection performance for most single classes, especially for DoS-LOIC-UDP and DoS-SlowHTTPTest, with improvements of 30.7% and 84.3%, respectively, when compared with the traditional ML models.

Cloud gaming offers excellent potential; however, it presents significant challenges for 5G networks because of its strict requirements for high reliability and low latency. Cloud gaming service deployment can be modeled as a Virtual Network Functions Chain Placement Problem (VNF-CPP), where a service instance is represented by a chain of interconnected Virtual Network Functions (VNFs). Solving the VNF-CPP may result in infeasible solutions when the underlying network infrastructure can not meet the service requirements. In this paper, we propose an automatic feasibility restoration technique and explain how network operators can use it to meet cloud gaming's demands. Our proposed algorithms reveal the origins of the infeasibilities so that network operators can understand the reasons behind them. Moreover, the algorithms suggest the best way to alter the network to regain feasibility by providing realtime elastic resource management. Specifically, two approaches are proposed and evaluated. The first approach is the Irreducible Infeasible Set (IIS) Repair, and the second is the Minimum Cost Redesign. We evaluate the proposed algorithms using two practical use cases: an offline use case, where we need to fix the infeasibility for a bulk of service instances, and an online use case, where we need to fix the infeasibility for a single service instance in realtime. Furthermore, theoretical analysis and results show that the Minimum Cost Redesign method outperforms the IIS Repair method. Results also verify that our algorithms can provide practical solutions for both use cases in realtime.

Incorporating machine learning algorithms with Intrusion Detection System (IDS) can detect network intrusions without human intervention and aims for Zero Touch Networks (ZTN). In this research, an automatic network-based features and host-based features integrated intrusion detection scheme is presented to improve the performance of network attack detection under the SCVIC-CIDS-2021 dataset which is derived from the integration of network packets and host logs of the CSE-CIC-IDS2018 dataset. Auto-encoder (AE) and Gated Recurrent Unit (GRU) are utilized for feature derivation to overcome the dimensionality mismatch between network-based and host-based features. The knowledge-based Prior Knowledge Input (PKI) model is used to combine unsupervised extra knowledge with a pre-trained supervised model for the final classification results. The results of the experiment reveal that the integration of network-based and host-based features is effective and the PKI model improves the performance of the original ML classification algorithm as well. Under the test set, the maximum achievable macro average F1-score reaches up to 97.08% which points out approximately 9% improvement compared to the best baseline performance.

Intrusion Detection Systems (IDS) are critical secu-rity mechanisms that protect against a wide variety of network threats and malicious behaviors on networks or hosts. As both Network-based IDS (NIDS) or Host-based IDS (HIDS) have been widely investigated, this paper aims to present a Combined Intrusion Detection System (CIDS) that integrates network and host data in order to improve IDS performance. Due to the scarcity of datasets that include both network packet and host data, we present a novel CIDS dataset formation framework that can handle log files from a variety of operating systems and align log entities with network flows. A new CIDS dataset named SCVIC-CIDS-2021 is derived from the meta-data from the well-known benchmark dataset, CIC-IDS-2018 by utilizing the proposed framework. Furthermore, a transformer-based deep learning model named CIDS-Net is proposed that can take network flow and host features as inputs and outperform baseline models that rely on network flow features only. Experimental results to evaluate the proposed CIDS-Net under the SCVIC-CIDS-2021 dataset support the hypothesis for the benefits of combining host and flow features as the proposed CIDS- N et can improve the macro F1 score of baseline solutions by 6.36 % (up to 99.89%).

The number of Internet of Things (IoT) devices being deployed into networks is growing at a phenomenal pace, which makes IoT networks more vulnerable in the wireless medium. Advanced Persistent Threat (APT) is malicious to most of the network facilities and the available attack data for training the machine learning-based Intrusion Detection System (IDS) is limited when compared to the normal traffic. Therefore, it is quite challenging to enhance the detection performance in order to mitigate the influence of APT. Therefore, Prior Knowledge Input (PKI) models are proposed and tested using the SCVIC-APT-2021 dataset. To obtain prior knowledge, the proposed PKI model pre-classifies the original dataset with unsupervised clustering method. Then, the obtained prior knowledge is incorporated into the supervised model to decrease training complexity and assist the supervised model in determining the optimal mapping between the raw data and true labels. The experimental findings indicate that the PKI model outperforms the supervised baseline, with the best macro average F1-score of 81.37%, which is 10.47% higher than the baseline.

Internet of things (IoT) networks confront vari-ous network intrusion threats due to massively interconnected nodes that form an extensive attack surface for adversaries. Machine learning (ML)-based approaches are widely investigated to address network intrusions. It becomes further challenging to achieve promising performance for multi-class classification so to identify each attack type rather than detection of the presence of intrusion, which involves binary classification. ML models perform divergent detection performance in each class, so it is challenging to select one ML model applicable to all classes prediction. With this in mind, we propose an innovative ensemble learning framework, namely All Predict Wisest Decides (APWD) that builds on training of multiple ML models and testing them independently so to obtain prediction performance for all classes. For each attack category, an expert (i.e., wisest) model that performs the best F1 score, accuracy, lowest false detection rate is determined according to individual model results. The aggregation module makes decisions relying upon the wisest model determined for each class. APWD is a generic framework, and the types of MLs and the number of MLs can be customized in APWD. Experiments under a popular public dataset, NSL-KDD verify the proposed approach APWD by demonstrating that APWD boosts overall accuracy to 0.797, comparing 0.772 by XGBoost, 0.758 by RF, and 0.584 by Adaboost. Moreover, in certain attack types R2L, APWD increases F1 score by a factor of 18, from 0.022 by RF to 0.421.

Software defined networking (SDN) decouples control plane functionality from the data plane and features the presence of programmable dumb network devices, which have no or little intelligence and take control commands from a central controller at the control plane. The central controller is responsible for controlling data plane hardware and optimizing network operation. Centralized network optimization and control is impractical or infeasible when the network becomes too large in size or loading. Distributed network optimization comes into play under this circumstance. Fully distributed network optimization requires local intelligence at individual network elements, against the basic concept of SDN. In this paper we consider SDN-friendly zone-based distributed network optimization and studies the integral network zoning problem, that is, how to group network elements into zones such as to minimize the overhead of distributed network optimization. We give a mathematical formulation of the problem and show that it is NP complete. We then present three heuristic solutions and evaluate their performance through simulation.

Since video services are expected to constitute a major portion of the mobile downlink traffic, it is important to consider end users' perceptual quality of experience (QoE) for video traffic in the system design and performance evaluation of next generation mobile networks. We present a novel QoE-aware scheduling scheme for buffered video on demand (VoD). Therein, rebuffering is the critical attribute undermining users' QoE. Our scheduling scheme is based on `vacuum pressure scheduling'. We use playback buffer vacancy and apply the `backpressure' scheduling theory to schedule the VoD flows. The proposed scheme is further adjusted to enable joint scheduling of a mixture of VoD and best effort (BE) flows within the same band. A simple control knob is provided to operators to softly adjust the region in which BE flows contend on resources. Results demonstrate substantial user capacity gains compared to prior work without compromising the QoS of BE flows. Sensitivity analysis to feedback periodicity shows remarkable robustness and overhead savings compared to the baseline. Results even hold when requested videos are of heterogeneous qualities, i.e., encoding rates.

We implement a new software-based multihop TDMA MAC protocol (Soft-TDMAC) with microsecond synchronization using a novel system interface for development of 802.11 overlay TDMA MAC protocols (SySI-MAC). SySI-MAC provides a kernel independent message-based interface for scheduling transmissions and sending and receiving 802.11 packets. The key feature of SySI-MAC is that it provides near deterministic timers and transmission times, which allows for implementation of highly synchronized TDMA MAC protocols. Building on SySI-MAC's predictable transmission times, we implement Soft-TDMAC, a software-based 802.11 overlay multihop TDMA MAC protocol. Soft-TDMAC has a synchronization mechanism, which synchronizes all pairs of network clocks to within microseconds of each other. Building on pairwise synchronization, Soft-TDMAC achieves tight network-wide synchronization. With network-wide synchronization independent of data transmissions, Soft-TDMAC can schedule arbitrary TDMA transmission patterns. For example, Soft-TDMAC allows schedules that decrease end-to-end delay and take end-to-end rate demands into account. We summarize hundreds of hours of testing Soft-TDMAC on a multihop testbed, showing the synchronization capabilities of the protocol and the benefits of flexible scheduling.

We devise an optimization framework for generalized proportional fairness (GPF) under different time scales for amplify-and-forward (AF) relay networks. In GPF scheduling, a single input parameter is used to change the fairness from throughput optimal, to proportionally fair and asymptotically to max-min fair. We extend the GPF scheduling to include a new input parameter, which determines the time-scale of fairness from short-term GPF to long-term GPF. We devise a low-complexity near-optimal algorithm to find schedules satisfying the given fairness criteria in a given time-scale. Simulations show that the proposed algorithm indeed allows the flexibility to change the fairness and its time- scale. To the best of our knowledge, this paper is the first to provide a multi-user scheduling framework for AF relays with both flexible fairness and flexible time-scales.

In constellation rearrangement (CoRe), the base-station and the relay use different constellations, with the same number of signal points, to communicate with the user terminal. In contrast to the existing CoRe techniques, which restrict the possible constellations, we propose generalized quadrature amplitude modulation (QAM) constellations. Since generalized CoRe schemes do not restrict constellations, they have the potential of outperforming all other CoRe schemes, with a complexity penalty in decoding. We pose an optimization to find the generalized QAM constellations, which minimize an upper bound on the uncoded symbol error rate (SER). However, since the optimization is not convex, it is not possible to find constellations with globally minimum SER in a reasonable time. Nevertheless, we use a convex solver to find constellations, which are local minima to the optimization. We input the best known restricted CoRe constellations as starting points to the solver to find constellations, which are guaranteed to improve SER. We demonstrate the significant gains achieved by the proposed CoRe scheme with simulations.

Providing ubiquitous very high data rate coverage in next generation wireless networks is a formidable goal, requiring cost-effective radio access network (RAN) devices, such as multi-user enabled amplify- and-forward (AF) relays, and fair radio resource management (RRM). To further this goal, we investigate multi-user enabled AF relays which multiplex user's data in orthogonal frequency division multiple access (OFDMA). These relays are cost-effective, simpler to implement, and introduce less delay in comparison to other relay based routers. We devise a generalized proportionally fair (GPF) RRM framework for multi-user enabled AF relays. In GPF scheduling a single parameter is used to gradually change schedules from throughput optimal to proportionally fair. We formulate the GPF scheduling problem and due to its complexity devise a low complexity heuristic to solve it. We evaluate the performance of the heuristic with extensive simulations and show that the heuristic performs well.

We investigate the problem of multi-user radio resource allocation for orthogonal frequency division multiple access (OFDMA) amplify-and-forward (AF) relays. In the single-user case, the problem reduces to the well know assignment problem, which maximizes the user rate. For the multi-user case we devise a resource allocation algorithm to achieve max-min fairness. We find max-min fairness since it can provide almost flat ubiquitous coverage. We start by formulating a convex optimization, which takes a parameter that asymptotically makes the optimization produce max-min fair rates. Since the optimization is a convex problem, we are able to devise a sub-optimal gradient-based algorithm to solve it quickly. Simulations show that the algorithm achieves results very close to the optimum solutions due to its gradient origins.

We design and implement Soft-TDMAC, a software Time Division Multiple Access (TDMA) based MAC protocol, running over commodity 802.11 hardware. Soft-TDMAC has a synchronization mechanism, which synchronizes all pairs of network clocks to within microseconds of each other. Building on pairwise synchronization, Soft-TDMAC achieves network wide synchronization. With, out-of-band, network wide synchronization Soft-TDMAC can schedule arbitrary TDMA transmission patterns. We summarize hundreds of hours of testing Soft-TDMAC on a multi-hop testbed. Our experimental results show that Soft-TDMAC synchronizes multi-hop networks to within a few microsecond sized TDMA slots. Soft-TDMAC can schedule transmissions to take end-to-end demands into account and in a way that decreases end-to-end delay. With no collisions, under good channel conditions, TCP achieves almost the full wireless channel bandwidth.

In this paper, we propose the Staggered TDMA Underwater MAC Protocol (STUMP), a scheduled, collision free TDMA-based MAC protocol that leverages node position diversity and the low propagation speed of the underwater channel. STUMP uses propagation delay information to overlap node communication and increase channel utilization. Our work yields several important conclusions. First, leveraging node position diversity through scheduling yields large improvements in channel utilization. Second, STUMP does not require tight node synchronization to achieve high channel utilization, allowing nodes to use simple or more energy efficient synchronization protocols. Finally, we briefly present and evaluate algorithms that derive STUMP schedules.

We present a distributed scheduling algorithm for provisioning of guaranteed link bandwidths in ad hoc mesh networks. The guaranteed link bandwidths are necessary to provide deterministic end-to-end bandwidth guarantees. Using Time Division Multiple Access (TDMA), links are assigned slots in each frame and during each slot a number of non-conflicting links can transmit simultaneously. The bandwidth of each link is given by the number of slots assigned to it the frame and the modulation used in the slots. Our scheduling algorithm has two parts. The first part of the algorithm is an iterative procedure that finds locally feasible schedules by exchanging link scheduling information between nodes. The iterative procedure is based on the distributed Bellman-Ford algorithm running on the conflict graph, whose partial view is available at every node. The second part of the algorithm is a wave based termination procedure used to detect when all nodes are locally scheduled and a new schedule should be activated. We use analysis to show the worst case convergence time of the algorithm and simulations to show performance of the algorithm in practice.

Time division multiple access (TDMA) based medium access control (MAC) protocols provide QoS with guaranteed access to wireless channel. However, in multihop wireless networks, these protocols may introduce delay when packets are forwarded from an inbound link to an outbound link on a node. Delay occurs if the outbound link is scheduled to transmit before the inbound link. The total round trip delay can be quite large since it accumulates at every hop in the path. This paper presents a method that finds schedules with minimum round trip scheduling delay. We show that the scheduling delay can be interpreted as a cost collected over a cycle on the conflict graph. We use this observation to formulate a min-max program for the delay across a set of multiple paths. The min-max delay program is NP-complete since the transmission order of links is a vector of binary integer variables. We design heuristics to select appropriate transmission orders. Once the transmission orders are known, a modified Bellman-Ford algorithm is used to find the schedules. The simulation results confirm that the proposed algorithm can find effective min-max delay schedules.

We present diversity coded directed diffusion (DCDD), a reliable and energy efficient transport protocol for sensor networks. In DCDD, the sink uses a number of receivers- called ldquoprongsrdquo-that connect to it with reliable links. Sensors split observations into many fragments and generate parity fragments with an FEC algorithm. The fragments are then distributed over the paths and simultaneously sent to the sink. The sink can reconstruct the observations if it receives a portion of the fragments that is of the same size as their original observation. We use the ns-2 simulator to examine the ability of DCDD to increase end-to-end reliability, as well as the effect of DCDD on energy consumption in the network. Our simulations show that the network where DCDD is used outperforms the network in which the sensors use only MAC retransmissions to increase reliability. DCDD makes the energy use in the network more fair and at the same time it increases the end-to-end reliability in the network. DCDD also decreases the delay in the network.

We study the problem of using path diversification to provide low probability of packet loss (PPL) in wireless networks. Path diversification uses erasure codes and multiple paths in the network to transmit packets. The source uses Forward Error Correction (FEC) to encode each packet into multiple fragments and transmits the fragments to the destination using multiple disjoint paths. The source uses a load balancing algorithm to determine how many fragments should be transmitted on each path. The destination can reconstruct the packet if it receives a number of fragments equal to or higher than the number of fragments in the original packet. We study the load balancing algorithm in two general cases. In the first case, we assume that no knowledge of the performance along the paths is available at the source. In such a case, the source decomposes traffic uniformly among the paths; we call this case blind load balancing. We show that for low PPL, blind load balancing outperforms single-path transmission. In the second case, we assume that a feedback mechanism periodically provides the source with information about the performance along each path. With that information, the source can optimally distribute the fragments. We show how to distribute the fragments for minimized PPL, and maximized efficiency given a bound on PPL. We evaluate the performance of the scheme through numerical simulations.

This paper introduces a novel technique to maximize the lifetime of fault tolerant sensor networks. The proposed architecture uses multipath diversity in the network layer and erasure codes. We use a distributed sink where information arrives at the sink via multiple proxy nodes, called "prongs" in this paper. The sender node uses erasure coding and splits each packet into multiple fragments and transmits the fragments over multiple parallel paths. The erasure coding allows the sink to reconstruct the original packet even if some of the fragments are lost. Occasionally, the sink broadcasts a query to awaken the sensors and to allow them to collect information about probability of packet loss and energy consumption in the network. The awakened sensors then use the collected information to distribute their data among different prongs so as to maximize the network lifetime, while keeping reliability in the network above a certain level