This paper introduces an innovative multi-queue fog architecture coupled with an intelligent controller, aimed at enhancing the efficiency and adaptability of fog computing environments. Unlike conventional single-queue fog architectures that typically rely on basic first-in-first-out (FIFO) task execution models in fog servers, our approach offers heightened granularity and flexibility in task scheduling. This feature enables effective task management, catering specifically to Internet of Things (IoT) applications characterized by varying degrees of time-sensitivity and resource requirements. Our proposed deep weighted-fair fog servers (DeepWFFS) scheme comprises two key elements: the weighted-fair fog server (WFFS) framework and an intelligent deep controller (DC) leveraging deep reinforcement learning (DRL) for task prioritization. The WFFS framework adopts multiple queues within fog servers, each assigned a predefined weight representing task priority. This prevents task starvation and promotes equitable task execution. Meanwhile, the DC continuously monitors task workloads and priorities, ensuring optimal task allocation to the most suitable queues within fog and cloud servers. Through simulation, our results exhibit the superior performance of DeepWFFS compared to benchmark schemes. This advancement showcases the potential of our architecture to efficiently manage diverse tasks in fog computing environments.

In this paper, we introduce the DRJLRA algorithm, a load and resource allocation scheme based on deep reinforcement learning (DRL) for a generic multi-master, multi-worker coded distributed computing (CDC) system. Our aim is to minimize the combined delay of communication and computation for a set of matrix-vector multiplication tasks. The proposed DRL-based approach has several unique features that set it apart from existing literature. Firstly, it is applicable to general CDC systems with multiple masters and workers. Additionally, it considers multi-task CDC systems with stochastic task arrivals, takes into account the heterogeneity of workers with random computation and communication delays, and utilizes the state-of-the-art soft actor-critic (SAC) DRL algorithm, making it versatile and efficient in handling complex and dynamic CDC environments. Our results demonstrate that DRJLRA outperforms benchmark schemes significantly. It is thus well-suited for real-world CDC systems with diverse and dynamic workloads.

This article studies the network lifetime optimization problem in a multiuser mobile-edge computing (MEC)-enabled Internet of Things (IoT) system comprising an access point (AP), a MEC server, and a set of$K$mobile devices (MDs) with limited battery capacity. Considering the residual battery energy at the MDs, stochastic task arrivals, and time-varying wireless fading channels, a soft actor–critic (SAC)-based deep reinforcement learning (DRL) lifetime maximization, called DeepLM, is proposed to jointly optimize the task splitting ratio, the local CPU-cycle frequencies at the MDs, the bandwidth allocation, and the CPU-cycle frequency allocation at the MEC server subject to the task queuing backlogs constraint, the bandwidth constraint, and maximum CPU-cycle frequency constraints at the MDs and the MEC server. Our results reveal that DeepLM enjoys a fast convergence rate and a small oscillation amplitude. We also compare the performance of DeepLM with three benchmark offloading schemes, namely, fully edge computing (FEC), fully local computing (FLC), and random computation offloading (RCO). DeepLM increases the network lifetime by 496% and 229% compared to the FLC and RCO schemes. Interestingly, it achieves such a colossal lifetime improvement when its nonbacklog probability is 0.99, while that of FEC, FLC, and RCO is 0.69, 0.53, and 0.25, respectively, showing a significant performance gain of 30%, 46%, and 74%.

We study the performance of a network-coded cooperative (NCC) system in an underlay cognitive radio network (CRN). The primary network (PN) consists of a single transmitter-receiver pair, and the secondary network (SN) is an NCC system with$N$users,$M$relays, and a single destination. The relays employ decode-and-forward (DF) protocol and use network coding (NC). We study the performance of the SN under two types of power constraints: i) the combined peak interference power constraint on the PN and maximum transmit power constraint at the SN; and ii) the single peak interference power constraint on the PN. For the SN, an exact closed-form expression and an asymptotically tight end-to-end outage probability are derived, and the diversity order and coding gain are quantified. Compared to the existing literature, the proposed CRN NCC has four main distinguishable features: i) it applies to general CRN NCC network settings with an arbitrary number of users and relays; ii) it considers general relay selection mechanism and independent and non-identically distributed (i.n.i.d.)$Nakagami-m$fading channels; iii) it assumes secondary-to-primary and primary-to-secondary interference links; and iv) it provides a generalization of previous work and includes existing results in the literature as special cases.

This paper investigates the performance of a network-coded cooperative (NCC) system in an underlay cognitive radio network (CRN). The primary network (PN) consists of a single transmitter-receiver pair, while the secondary network (SN) is composed of N sources, a single destination, and M decode-and-forward (DF) relays, employing network coding (NC) over non-binary Galois field. For the SN, a closed-form expression and an asymptotically tight end-to-end (E2E) outage probability (OP) are derived and the diversity order is quantified. Compared to the existing literature, the proposed CRN NCC has four main distinguishable features: i) it is applicable to general CRN NCC network settings with arbitrary number of sources and relays; ii) it considers general relay selection and independent and non-identically distributed (i.n.i.d.) Nakagami-m fading channels; iii) it accounts for maximum transmit power at the SN and assumes secondary-to-primary (S2P) and primary-to-secondary (P2S) interference links; and iv) it provides a generalization of previous works and includes existing results in the literature as special cases. Simulation results are further provided to confirm the correctness of our analysis.

We study the effect of outdated channel state information (CSI) and co-channel interference (CCI) on the performance of relay selection (RS) network-coded cooperative (NCC) multiple-input multiple-output (MIMO) systems. Specifically, we consider a RS MIMO-NCC system where N single-antenna sources communicate with one multiple-antenna destination using M decode-and-forward (DF) multiple-antenna relays. The destination selects K best relays according to the quality of relay-destination channels. The selected relays apply network coding (NC) on the received sources' symbols using network code coefficients based on maximum distance separable (MDS) codes. The exact closed-form outage probability (OP) of the system is derived. The asymptotic high signal-to-noise ratio (SNR) OP is also obtained, through which the diversity order and the coding gain are found. Numerical results are further presented to illustrate the adverse effect of outdated CSI and CCI on the system performance and to validate the accuracy of our analysis.

Although the hybrid of cell-free (CF) massive multiple-input multiple-output (MIMO) and non-orthogonal multiple access (NOMA) promises massive spectral efficiency gains, the type of precoders employed at the access points (APs) impacts the gains. In this paper, we thus comprehensively evaluate the system performance with maximum ratio transmission (MRT), full-pilot zero-forcing (fpZF) and modified regularized ZF (mRZF) precoders. We derive their closed-form sum rate expressions by considering Rayleigh fading channels, the effects of intra-cluster pilot contamination, inter-cluster interference, and imperfect successive interference cancellation (SIC). Our results reveal that this system supports significantly more users simultaneously at the same coherence interval compared to its OMA equivalent. However, intra-cluster pilot contamination and imperfect SIC degrade the system performance when the number of users is low. Moreover, with perfect SIC, mRZF and fpZF significantly outperform MRT. Also, we show that this system with either mRZF or fpZF precoding outperforms OMA systems with MRT. The analytical findings are verified by numerical results.

We consider a network-coded cooperative (NCC) system that consists of N ≥ 2 sources, M ≥ 1 decode- and-forward (DF) relays, and a single destination. The relays perform network coding (NC) on the received sources' symbols using maximum distance separable (MDS) codes. For this system, we propose the most generalized user-relay selection (GURS) scheme in the literature that selects any arbitrary subsets of K users and any arbitrary subsets of L relays subject to practical constraints such as load balancing conditions and scheduling policy. Our analytical results and design guidelines generalize and subsume all existing results as special cases. To this end, we derive a new closed-form outage probability (OP) expression, assuming non-identically and independently distributed (n.i.i.d.) Rayleigh fading channels. The asymptotic outage expression at high signal-to-noise ratio (SNR) regime is further derived, based on which, the achievable diversity order and coding gain are quantified. The theoretical derivations are also validated through Monte-Carlo simulation.

We study the performance of generalized user-relay selection (GURS) scheme in network-coded cooperation systems. In particular, we propose the most general case of user-relay selection mechanism that selects any arbitrary subsets of users and relays subject to any practical constraints such as load balancing conditions, scheduling policy, and other factors. Our results thus can be applied to a large set of situations and include all existing results in the literature as special cases. We develop performance characterizations of the system under consideration in terms of outage probability over non-identically and independently distributed (n.i.i.d.) Rayleigh fading channels. The asymptotic outage expressions at high signal-to-noise ratio (SNR) regime are further derived and then, based on the derived expressions, we quantify the diversity order. The theoretical derivations are validated through Monte-Carlo simulations.

In this paper, we study the performance of opportunistic source selection (OSS) in multisource multirelay network-coded cooperative (NCC) systems. For this system, we derive the exact outage probability and asymptotic measures such as the diversity and coding gains. The derived analytical results provide an efficient means to evaluate the impact of different system parameters on the system performance. Our results reveal that the proposed NCC system greatly exploits the diversity gains in multisource multirelay NCC systems and thus provides a considerable performance improvement. From the derived closed-form diversity gains, we also evaluate the optimal number of selected relays that maximizes the achievable diversity gain. Numerical results are also presented to validate the theoretical analysis.

Network-coded cooperation (NCC) has recently gained interest as it improves the network throughput in multi-source cooperative systems. NCC has been studied for single-antenna terminals only. Employing multiple-input multiple-output (MIMO) techniques can significantly improve the performance of NCC systems. Furthermore, the existing relay selection (RS) strategies for NCC utilize the “max-min” end-to-end (E2E) criterion. This selection strategy (called Strategy A) is complicated even for a network with single-antenna terminals as it requires global channel state information (CSI). This requirement makes it hard to implement RS-based NCC. To counter this issue, we introduce a new RS strategy (Strategy B), which utilizes only the local CSI (not global CSI), significantly reducing the signaling overhead without sacrificing the performance. The performance of MIMO-NCC under Strategies A and B is studied over independent and non-identically distributed (i.n.i.d.) Rayleigh fading channels. Relays and the destination are equipped with multiple antennas, whereas sources have a single antenna. The exact outage probability expressions of the system under consideration are derived. The asymptotic outage expressions are further provided to obtain valuable insights into the practical system-design parameters such as the diversity order and coding gain. Furthermore, numerical results are provided in support of the analytical results.

Network coded cooperative (NCC) systems have recently gained increasing attention due to their high power and spectral efficiency. For high speed data transmission over frequency-selective channels, NCC is further combined with orthogonal frequency division multiple access (OFDMA). In this paper, we derive outage probability and diversity gain of NCC-OFDMA systems in the presence of carrier frequency offset (CFO). Our results demonstrate that NCC-OFDMA system is capable to achieve full spatial and frequency diversity in noise limited system where the CFO variance σ2ε→ 0. However, in interference limited case where the CFO variance σ2ε> 0, error floor occurs leading zero diversity gain. Numerical results are further presented to validate our analytical findings.

Network coded cooperation (NCC) has recently gained interest due to its ability to increase the network throughput in multisource cooperative systems. NCC with single relay selection (SRS) or multiple relay selection (MRS) has been studied for single-antenna terminals only. Employing multiple-input multiple-output (MIMO) can significantly improve the performance of NCC systems. In this paper, we consider a NCC system with decode-and-forward (DF) relaying where relays use maximum distance separable (MDS) codes as their encoding vectors. More specifically, we consider N sources, M relays and a single destination. Relays and the destination are equipped with multiple antennas whereas sources have single antenna. The performance of the system under consideration is investigated by deriving exact outage probability expressions for both SRS and MRS protocols. The asymptotical diversity orders are further provided to obtain valuable insights into practical system design. Furthermore, numerical results are provided to validate the accuracy of our derivations and quantify the effect of system parameters on the outage probability and diversity order.

In this paper, we investigate the performance of network coded cooperation (NCC) systems based on relay selection in the presence of imperfect channel state information (CSI). Specifically, we consider an uplink cellular scenario with N sources, M relays and a single destination. The relays adopt decode and forward (DF) relaying and use maximum distance separable (MDS) codes as their encoding vectors. We investigate the impact of imperfect CSI on outage probability and asymptotic and finite-SNR diversity-multiplexing tradeoff (DMT) of the system under consideration. Simulation results are further presented to corroborate the analytical findings and provide insight into the system design where imperfect CSI and finite SNR regime are taken into account.

Network-coded cooperation (NCC) is an effective method to improve the throughput efficiency in cooperative wireless networks. The combined use of orthogonal frequency division multiplexing (OFDM) with NCC has been further studied in the literature to exploit the multipath diversity gains. In this paper, we consider orthogonal frequency division multiple access (OFDMA), an extension of OFDM to a multiuser system where subsets of carriers are assigned to different users. We first derive a closed-form expression for the outage probability of NCC-OFDMA over Rician fading channels and then present the asymptotical and finite-SNR DMT expressions. Our results provide insight into the performance mechanisms under practical SNR regime of NCC-OFDMA systems and demonstrate that NCC-OFDMA is able to fully exploit both frequency and spatial diversity. We also show that the derived finite-SNR DMT converges to an asymptotical one as expected. Furthermore, special cases for our derived analytical expressions are presented, to show that the derived expression is a generalized case of the related the state of the art results. Simulation results are further presented to verify our theoretical analyses.

Network coded cooperative (NCC) systems have recently attracted attention with their high spectral and power efficiency. In this paper, we investigate the information theoretical limits of NCC systems in the presence of imperfect channel state information (CSI). Specifically, we derive exact outage probability and finite-SNR diversity- multiplexing tradeoff (DMT) for general multisource multirelay NCC wireless networks over Rayleigh fading channels. Numerical results are presented to verify our analytical derivations and provide insight into the impact of imperfect CSI on the NCC system performance.

Strong molecular and aerosol scattering in ultraviolet (UV) wavelengths enable the non-line-of-sight (NLOS) outdoor wireless connectivity which is attractive in many applications due to covertness and security. In the current literature, atmospheric turbulence effects are typically ignored under the assumption of short link distances and clear weather conditions. In this paper, we investigate the performance of multiple-input multiple-output (MIMO) UV systems over turbulence channels. Specifically, we derive bit error rate (BER) expressions over an NLOS UV channel which is modeled as an overlap of two log-normal LOS links. Our results demonstrate that fading variance is scaled by the number of transmitters and receivers and MIMO deployment with proper configurations results in significant BER improvements. Simulation results are further provided to confirm the analytical findings.

Network coded cooperation (NCC) is an effective method to improve the throughput efficiency in cooperative wireless networks. In an effort to have further gains over the initial works, which build upon the assumption of time division multiple access, the combined use of orthogonal frequency division multiplexing (OFDM) with NCC has been proposed in the literature. In this paper, we consider orthogonal frequency division multiple access (OFDMA), an extension of the OFDM to a multiuser system where subsets of carriers are assigned to different users. We derive a closed-form expression for the outage probability of the system under consideration and present the diversity-multiplexing tradeoff (DMT) analysis. Our results demonstrate that NCC-OFDMA system is able to fully exploit both frequency and spatial diversity. Simulation results are presented to verify our theoretical analysis.