Device-to-device (D2D) communication is a promising new feature in LTE-Advanced networks. It is brought up to enable efficient discovery and communication between proximate devices. With D2D capability, devices in physical proximity could be able to discover each other using LTE radio technology and to communicate with each other via a direct data path. This thesis is concerned with the design, coordination and testing of a hybrid D2D and cellular network. Design requirements and choices in physical and MAC layer functions to support D2D discovery and communication underlaying LTE networks are analyzed. In addition, a centralized scheduling strategy in base station is proposed to coordinate D2D data communication operating in LTE spectrum. The scheduling strategy combines multiple techniques, including mode selection, resource and power allocation, to jointly achieve an overall user performance improvement in a cell. Finally the performances of D2D data communication underlaying LTE system are calibrated in a multi-link scenario via system-level simulation.

Ericsson Brasil / Conselho Nacional de Desenvolvimento CientÃfico e TecnolÃgico / Em um mundo onde as pessoas contam com smartphone, smartwatch, tablet e outros dispositivos para mantÃ-las conectadas onde quer que vÃo, t odos esperam que seus aplicativos sejam executados sem problemas, tais como cham adas abandonadas, download lento e vÃdeos com saltos. Neste contexto, comunicaÃÃo dispositivo-a-dispositivo ( do inglÃs, Device-to-Device (D2D)) constitui uma tecnologia promissora, pois à um tipo de comun icaÃÃo direta e utiliza baixa potÃncia entre dispositivos prÃximos, permitindo-se desv iar o trÃfego da rede mÃvel, aumentar a eficiÃncia espectral e de potÃncia. Do ponto de vista do assi nante, D2D significa usar aplicaÃÃo sem problemas e aumentar o tempo de vida da bateria do celular. No entanto, a fim de realizar os ganhos potenciais das comunic aÃÃes D2D, algumas questÃes-chave devem ser abordadas, pois as comunicaÃÃes D 2D podem aumentar a interferÃncia co-canal e comprometer a qualidade do enlace das comunicaÃÃes celulares. Esta dissertaÃÃo foca em tÃcnicas de Gerenciamento de Recur sos de RÃdio (do inglÃs, Radio Resource Management (RRM)) para mitigar a interferÃncia co -canal para comunicaÃÃes D2D que se baseiam na EvoluÃÃo de Longo Prazo (do inglÃs, Long Ter m Evolution (LTE)), visando a reduÃÃo da interferÃncia intra- e inter-celular e na melho ria da eficiÃncia energÃtica. Os principais esquemas de Controle de PotÃncia (do inglÃs, Pow er Control (PC)) (e.g. OLPC,CLPC e SDPC) e um esquema hÃbrido (CLSD) sÃo calibrados e utilizad os no cenÃrio macro ou micro multicelular, usando diferentes cargas e InformaÃÃo do Est ado do Canal (do inglÃs, Channel State Information (CSI)) perfeita ou imperfeita. AlÃm diss o, o impacto da inclinaÃÃo da antena ( downtilt ) à analisado, que à usada para ajustar o raio de cobertura de u ma Evolved Node B (eNB) e reduzir a interferÃncia co-canal, aumentando o iso lamento de cÃlulas. Os resultados numÃricos indicam que os regimes de controle d e potÃncia e inclinaÃÃo da antena, devidamente calibrados, podem fornecer ganhos p ara a comunicaÃÃo celular e D2D. Em outras palavras, a tecnologia D2D pode ser utilizada para aumentar ainda mais a eficiÃncia de espectro e a eficiÃncia energÃtica se algoritm os de RRM forem utilizados adequadamente / In a world where people count on their smartphone, smartwatch, tablet and other devices to keep them connected wherever they go, they expect its application to run without problems, such as dropped calls, slow download and choppy videos. In this context, Device-to-Device (D2D) communication represents a promising technology, because it is a direct and low-power communication between devices close, allowing to offload the data transport network, increase spectral and power efficiency. From the subscriber point of view, D2D means to use applications without problem and increase battery life. However, in order to realize the potential gains of D2D communications, some key issues must be tackled, because D2D communications may increase the co-channel interference and compromise the link quality of cellular communications. This masterâs thesis focuses on Radio Resource Management (RRM) techniques, especially Power Control (PC) schemes, to mitigate the co-channel interference for D2D communications underlaying a Long Term Evolution (LTE) network, aiming at the reduction of the intra- and inter- cell interference and at the improvement of energy efficiency. The main PC schemes (e.g. OLPC, CLPC and SDPC) and a hybrid scheme (CLSD) are calibrated and used in macro- or micro- multicell scenario, using different loads and imperfect Channel State Information (CSI). In addition, the impact of downtilt is analyzed, which is used to adjust the coverage radius of an Evolved Node B (eNB) and reduce co-channel interference by increasing cell isolation. The numerical results indicate that PC schemes and downtilt, duly calibrated, can provide gains to cellular and D2D communications. In other words, D2D technology can be used to further increase the spectral and energy efficiency if RRM algorithms are used suitably.

Submitted by Daniele Amaral (daniee_ni@hotmail.com) on 2016-10-03T19:31:10Z No. of bitstreams: 1 DissFHFM.pdf: 5748298 bytes, checksum: d57e4d617ea74342f31ff21aef4eb98b (MD5) / Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-10T17:27:52Z (GMT) No. of bitstreams: 1 DissFHFM.pdf: 5748298 bytes, checksum: d57e4d617ea74342f31ff21aef4eb98b (MD5) / Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-10T17:27:59Z (GMT) No. of bitstreams: 1 DissFHFM.pdf: 5748298 bytes, checksum: d57e4d617ea74342f31ff21aef4eb98b (MD5) / Made available in DSpace on 2016-10-10T17:28:10Z (GMT). No. of bitstreams: 1 DissFHFM.pdf: 5748298 bytes, checksum: d57e4d617ea74342f31ff21aef4eb98b (MD5) Previous issue date: 2016-03-03 / Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) / Service-based communication is becoming increasingly relevant, as seen in the Internet of Things scenarios. Choosing an adequate service however can be a difficult task, as this form of communication may involve sensible resources and data. A trustworthy, safe, and privacy preserving mechanism is desirable for service selection. Reputation systems can help in this selection. This thesis presents a reputation system for service selection based on the security and privacy mechanisms of crypto-coins. In order to evaluate the performance of the proposed mechanism in the identification of low quality service providers we also investigated the use of different formulations used to determine a reputation based on peer voting. Results from simulation show the proposed system architecture is viable and supports large adoption via a scalable infrastructure. The performance analysis of different formulations for the calculus of reputations also shows that the recent behavior of an entity is the most impacting factor in establishing its reputation. / A comunicação por meio de serviços tem se tornado cada vez mais relevante, como em cenários da Internet das Coisas. A escolha entre serviços, contudo, pode ser uma tarefa difícil, já que essa forma de comunicação pode envolver recursos e dados sensíveis. Assim, é preciso um sistema de seleção de serviços que seja confiável, seguro e privado, garantindo que as expectativas dos utilizadores dos serviços sejam alcançadas. Sistemas de reputação podem ajudar nessa seleção. Assim, este trabalho apresenta um sistema de reputação distribuído para avaliação de interações baseadas em serviços utilizando conceitos da arquitetura de sistemas das cripto moedas. Para avaliar o desempenho na detecção de serviços de baixa qualidade utilizando o mecanismo proposto, apresenta-se também um estudo do comportamento de diferentes formulações para o cálculo de reputações. Resultados obtidos via simulação mostram que a arquitetura do sistema de reputação proposto é viável e permite uma ampla adoção com uma infraestrutura escalável. A análise do comportamento das formulações também permite concluir que o histórico recente do comportamento dos elementos avaliados é o fator que mais influencia na qualificação dos dispositivos.

Les ressources cellulaires sont précieuses et doivent être préservées dès que possible. Dans cette thèse, nous abordons le problème de la dissémination de contenus dans un réseau cellulaire surchargé. La première partie présente SCoD (Scheduled Content Delivery), une stratégie de dissémination purement cellulaire qui exploite la mobilité des utilisateurs ainsi que leur tolérance aux délais afin d’effectuer des transmissions différées. SCoD attend que les utilisateurs se rassemblent autour d’un minimum de points d’accès afin que le nombre total de transmissions soit réduit. Pour déclencher des transmissions, SCoD repose sur différentes fonctions de décision qui déclenchent aux instants opportuns une transmission en multicast. La deuxième partie de cette thèse traite également le problème d’économie de ressources cellulaires, mais en l’attaquant sous un autre angle. Nous exploitons des communications D2D que nous associons au multicast pour réduire la charge sur l’infrastructure. Nous analysons les avantages des communications opportunistes dans le contexte d’un service de diffusion de contenus basé sur les abonnements des utilisateurs. Nous présentons nos résultats pour deux cas de figure. Tout d’abord, nous illustrons le bénéfice des communications D2D dans le cadre d’un processus de diffusion, où le coût d’une transmission opportuniste est négligeable par rapport à celui d’une transmission cellulaire. Nous considérons ensuite le cas où les utilisateurs doivent être indemnisés pour leur participation au processus de diffusion, et où il y a donc un compromis à trouver. Nous fournissons des lignes directrices dans ce sens et nous montrons la variation d’un tel compromis en fonction de plusieurs paramètres du réseau. / Cellular resources are valuable and must be saved whenever possible. In this thesis, we address the problem of content dissemination within an overloaded cellular network. Firstly, we propose SCoD (Scheduled Content Delivery), a purely cellular dissemination strategy that exploits the mobility of users and their delay tolerance in order to postpone transmissions. SCoD waits for users to gather around a minimum number of access points so that the total number of transmissions is reduced. To trigger transmissions, SCoD relies on different decision functions which launch, if necessary, a multicast transmission. The second part of this thesis deals with the same problem of saving cellular resources, but from another angle. We use D2D (Device-to-Device) communications with multicast to mitigate the traffic load on the infrastructure. We study the benefits of opportunistic communications in the context of a content distribution service based on user subscriptions. We present our results in two ways. First, we illustrate the benefits of D2D communications in a content dissemination process where the cost of opportunistic transmission is negligible compared to that of cellular transmission. Then, we consider the case where users must be compensated for their participation in the dissemination process. Therefore, there is a tradeoff to be found, we thus provide guidelines in this direction and show the variation of such a tradeoff as a function of several network parameters.

D. Tech. (Department of Process Control and Computer Systems, Faculty of Engineering and Technology), Vaal University of Technology. / In this research study, a scheme to minimise interference in converged mobile cellular networks (MCNs) and wireless sensor networks (WSNs) was designed and implemented. The focus was the mitigation of interference that arises when proximity service (ProSe)-enabled sensors engage in a device-to device (D2D) communication to alert smartphone users upon the detection of explosives at highly crowded areas like shopping malls. D2D is a technology that academia and industry experts believe will play a prominent role in the implementation of the next generation of mobile networks, specifically, the fifth generation (5G). However, the full roll out of D2D is being impeded by the interference that the technology introduces to the cellular network. D2D devices cause a significant amount of interference to the primary cellular network especially when radio resources are shared. In the downlink phase, primary user equipment is likely to suffer from interference emanating from a D2D transmitter. On the other hand, the immobile base station is affected by interference caused by the D2D transmitter in the uplink phase. This type of interference can be avoided or reduced if radio resources are allocated intelligently under strict coordination of the base station. An NP-hard optimisation problem was formulated and finding a solution to this problem in 1 ms is not possible. 5G has a frame structure duration of 10 ms with 10 subframes of 1 ms each. Heuristic algorithms were then developed to mitigate the interference affecting the primary network that could carry out resource allocation within the fast-scheduling period of 1 ms. Smartphones have progressed into devices capable of generating massive volumes of data. The challenge is that battery technology is not keeping up with the pace of smartphone technology, so any additional feature that designers want to add, is met with a lot of contempt from customers who are concerned about their smartphone batteries depleting rapidly. In this context, the strategy must be energy-efficient for smartphone users to embrace it. A system level simulator was developed using MATLAB to evaluate the efficacy of the proposed design. Extensive simulation results showed that ProSe-enabled sensors can safely be integrated into cellular networks participating in D2D communication with smart phones, without introducing significant harm to the primary cellular network. The results showed that after implementing the proposed strategy, overall user throughput decreased by 3.63 %. In cellular networks, this is a modest figure since a reduction of up to 5% is acceptable to both users and network providers. The figure generally capped in service level agreements signed between network providers and users is 5%. The proposed technique also resulted in a 0 % reduction in SINR of CUEs in a cellular network, according to the findings. In terms of D2D link throughput for different D2D transmit levels, the method proposed in this research work surpassed a similar scheme proposed in literature by an average of 18.3%.

Yes / As 5th Generation research reaches the twilight, the research community must go beyond 5G and look towards the 2030 connectivity landscape, namely 6G. In this context, this work takes a step towards the 6G vision by proposing a next generation communication platform, which aims to extend the rigid coverage area of fixed deployment networks by considering virtual mobile small cells (MSC) that are created on demand. Relying on emerging computing paradigms such as NFV (Network Function Virtualization) and SDN (Software Defined Networking), these cells can harness radio and networking capability locally reducing protocol signalling latency and overhead. These MSCs constitute an intelligent pool of networking resources that can collaborate to form a wireless network of MSCs providing a communication platform for localized, ubiquitous and reliable connectivity. The technology enablers for implementing the MSC concept are also addressed in terms of virtualization, lightweight wireless security, and energy efficient RF. The benefits of the MSC architecture towards reliable and efficient cell-offloading are demonstrated as a use-case. / This project has received funding from the European Union's H2020 research and innovation program under grant agreement H2020-MCSAITN- 2016-SECRET 722424 [2].

Cette thèse étudie les communications directes entre les mobiles, appelées communications D2D, en tant que technique prometteuse pour améliorer les futurs réseaux cellulaires. Cette technologie permet une communication directe entre deux terminaux mobiles sans passer par la station de base. La modélisation, l'évaluation et l'optimisation des différents aspects des communications D2D constituent les objectifs fondamentaux de cette thèse et sont réalisés principalement à l'aide des outils mathématiques suivants: la théorie des files d'attente, l'optimisation de Lyapunov et les processus de décision markovien partiellement observable POMDP. Les résultats de cette étude sont présentés en trois parties. Dans la première partie, nous étudions un schéma de sélection entre mode cellulaire et mode D2D. Nous dérivons les régions de stabilité des scénarios suivants: réseaux cellulaires purs et réseaux cellulaires où les communications D2D sont activées. Une comparaison entre ces deux scénarios conduit à l'élaboration d'un algorithme de sélection entre le mode cellulaire et le mode D2D qui permet d'améliorer la capacité du réseau. Dans la deuxième partie, nous développons un algorithme d'allocation de ressources des communications D2D. Les utilisateurs D2D sont en mesure d'estimer leur propre qualité de canal, cependant la station de base a besoin de recevoir des messages de signalisation pour acquérir cette information. Sur la base de cette connaissance disponibles au niveau des utilisateurs D2D, une approche d'allocation des ressources est proposée afin d'améliorer l'efficacité énergétique des communications D2D. La version distribuée de cet algorithme s'avère plus performante que celle centralisée. Dans le schéma distribué des collisions peuvent se produire durant la transmission de l'état des canaux D2D ; ainsi un algorithme de réduction des collisions est élaboré. En outre, la mise en œuvre des algorithmes centralisé et distribué dans un réseau cellulaire, type LTE, est décrite en détails. Dans la troisième partie, nous étudions une politique de sélection des relais D2D mobiles. La mobilité des relais représente un des principaux défis que rencontre toute stratégie de sélection de relais. Le problème est modélisé par un processus contraint de décision markovien partiellement observable qui prend en compte le dynamisme des relais et vise à trouver la politique de sélection de relais qui optimise la performance du réseau cellulaire sous des contraintes de coût. / This thesis considers Device-to-Device (D2D) communications as a promising technique for enhancing future cellular networks. Modeling, evaluating and optimizing D2D features are the fundamental goals of this thesis and are mainly achieved using the following mathematical tools: queuing theory, Lyapunov optimization and Partially Observed Markov Decision Process (POMDP). The findings of this study are presented in three parts. In the first part, we investigate a D2D mode selection scheme. We derive the queuing stability regions of both scenarios: pure cellular networks and D2D-enabled cellular networks. Comparing both scenarios leads us to elaborate a D2D vs cellular mode selection design that improves the capacity of the network. In the second part, we develop a D2D resource allocation algorithm. We observe that D2D users are able to estimate their local Channel State Information (CSI), however the base station needs some signaling exchange to acquire this information. Based on the D2D users' knowledge of their local CSI, we provide an energy efficient resource allocation framework that shows how distributed scheduling outperforms centralized one. In the distributed approach, collisions may occur between the different CSI reporting; thus, we propose a collision reduction algorithm. Moreover, we give a detailed description on how both centralized and distributed algorithms can be implemented in practice. In the third part, we propose a mobile relay selection policy in a D2D relay-aided network. Relays' mobility appears as a crucial challenge for defining the strategy of selecting the optimal D2D relays. The problem is formulated as a constrained POMDP which captures the dynamism of the relays and aims to find the optimal relay selection policy that maximizes the performance of the network under cost constraints.

The next generation wireless networks i.e. 5G aim to provide multi-Gbps data traffic, in order to satisfy the increasing demand for high-definition video, among other high data rate services, as well as the exponential growth in mobile subscribers. To achieve this dramatic increase in data rates, current research is focused on improving the capacity of current 4G network standards, based on Long Term Evolution (LTE), before radical changes are exploited which could include acquiring additional/new spectrum. The LTE network has a reuse factor of one; hence neighbouring cells/sectors use the same spectrum, therefore making the cell edge users vulnerable to inter-cell interference. In addition, wireless transmission is commonly hindered by fading and pathloss. In this direction, this thesis focuses on improving the performance of cell edge users in LTE and LTE-Advanced (LTE-A) networks by initially implementing a new Coordinated Multi-Point (CoMP) algorithm to mitigate cell edge user interference. Subsequently Device-to-Device (D2D) communication is investigated as the enabling technology for maximising Resource Block (RB) utilisation in current 4G and emerging 5G networks. It is demonstrated that the application, as an extension to the above, of novel power control algorithms, to reduce the required D2D TX power, and multihop transmission for relaying D2D traffic, can further enhance network performance. To be able to develop the aforementioned technologies and evaluate the performance of new algorithms in emerging network scenarios, a beyond-the-state-of-the-art LTE system-level simulator (SLS) was implemented. The new simulator includes Multiple-Input Multiple-Output (MIMO) antenna functionalities, comprehensive channel models (such as Wireless World initiative New Radio II i.e. WINNER II) and adaptive modulation and coding schemes to accurately emulate the LTE and LTE-A network standards. Additionally, a novel interference modelling scheme using the 'wrap around' technique was proposed and implemented that maintained the topology of flat surfaced maps, allowing for use with cell planning tools while obtaining accurate and timely results in the SLS compared to the few existing platforms. For the proposed CoMP algorithm, the adaptive beamforming technique was employed to reduce interference on the cell edge UEs by applying Coordinated Scheduling (CoSH) between cooperating cells. Simulation results show up to 2-fold improvement in terms of throughput, and also shows SINR gain for the cell edge UEs in the cooperating cells. Furthermore, D2D communication underlaying the LTE network (and future generation of wireless networks) was investigated. The technology exploits the proximity of users in a network to achieve higher data rates with maximum RB utilisation (as the technology reuses the cellular RB simultaneously), while taking some load off the Evolved Node B (eNB) i.e. by direct communication between User Equipment (UE). Simulation results show that the proximity and transmission power of D2D transmission yields high performance gains for a D2D receiver, which was demonstrated to be better than that of cellular UEs with better channel conditions or in close proximity to the eNB in the network. The impact of interference from the simultaneous transmission however impedes the achievable data rates of cellular UEs in the network, especially at the cell edge. Thus, a power control algorithm was proposed to mitigate the impact of interference in the hybrid network (network consisting of both cellular and D2D UEs). It was implemented by setting a minimum SINR threshold so that the cellular UEs achieve a minimum performance, and equally a maximum SINR threshold to establish fairness for the D2D transmission as well. Simulation results show an increase in the cell edge throughput and notable improvement in the overall SINR distribution of UEs in the hybrid network. Additionally, multihop transmission for D2D UEs was investigated in the hybrid network: traditionally, the scheme is implemented to relay cellular traffic in a homogenous network. Contrary to most current studies where D2D UEs are employed to relay cellular traffic, the use of idle nodes to relay D2D traffic was implemented uniquely in this thesis. Simulation results show improvement in D2D receiver throughput with multihop transmission, which was significantly better than that of the same UEs performance with equivalent distance between the D2D pair when using single hop transmission.

Tato práce je rozdělena do šesti kapitol. První kapitola vysvětluje rozdíly mezi fyzickou vrstvou uplinků systémů LTE a LTE Advanced, zkoumá charakteristiky kanálu komunikace D2D v rámci sítě LTE Advanced, a navrhuje mechanismy optimalizace interferencí. Rovněž je v práci prezentována struktura softwarově definované rádiové platformy, která může být využita pro vyhodnocení rádiových kanálů. Druhá kapitola hodnotí a porovnává výkony uplinkové části fyzické vrstvy systému LTE a LTE Advanced. V prostředí MATLAB je implementována struktura LTE Advanced vysílače a přijímače se všemi stupni zpracování signálu. Generované signály obou výše uvedených systémů jsou přenášeny přes různé modely kanálu ITU-R. Byly používány různé techniky odhadu kanálů a detekce signálu pro obnovení vysílaného signálu. Výsledky jsou prezentovány formou křivek BER a křivek datové prostupnosti. Třetí kapitola navrhuje způsob opakování frekvencí v celulární síti (frequency-reuse) se třemi úrovněmi výkonu, který se využívá jako typ pokročilé metody snižování interferencí. Jsou ukázány normalizované kapacitní hustoty buněk a jejich podoblastí se třemi různými případy distribuce uživatelů uvnitř buněk. Je zobrazena korelace mezi celkovou kapacitou a poloměrem každého regionu. Dosažené výsledky navrhovaného schématu jsou porovnávány s tradiční technikou opakovaného použití frekvence (Reuse-3). Čtvrtá kapitola se zabývá výzkumem alternativní metody optimalizace interferencí. Bylo provedeno ověření kooperačních metod snímání rádiového spektra ve čtyřech různých reálných prostředích: venkovní-interiérové, vnitřní-venkovní, venkovní-vnitřní a venkovní-venkovní. Navržený systém je testován pomocí zařízení Universal Software Radio Peripheral (USRP) a obsahuje dva typy detektorů; energetický detektor a statistický detektor založený na Kolmogorově-Smirnovově testu, které byly implementovány na přijímací straně. Jedním z hlavních požadavků komunikace D2D je znalost charakteristik impulzních odezev rádiového kanálu. Pátá kapitola proto představuje metodu měření kanálu pomocí Zadoff-Chu sekvencí ve frekvenční oblasti jako alternativní techniku k měření kanálu v časové nebo frekvenční doméně. Pomocí navržené metody se základní charakteristiky kanálu, jako je časové rozšíření kanálu (RMS delay spread, mean excess delay), útlum šířením a koherenční šířka pásma extrahují v (až 20x) kratším čase ve srovnání s klasickou metodou měření kanálu ve frekvenční doméně. Jsou také zkoumány charakteristiky venkovních statických rádiových kanálů na vzdálenost několika kilometrů pro pásma UHF a SHF s ko-polarizovanou horizontální a vertikální konfigurací antény. Šestá kapitola uzavírá tezi a shrnuje závěry.

<p>    </p> <p>In order to advance next-generation communication systems, it is critical to enhance the state-of-the-art communication architectures, such as device-to-device (D2D), multiple- input multiple-output (MIMO), and intelligent reflecting surface (IRS), in terms of achieving high data rate, low latency, and high energy efficiency. In the first part of this dissertation, we address joint learning and optimization methodologies on cutting-edge network archi- tectures. First, we consider D2D networks equipped with MIMO systems. In particular, we address the problem of minimizing the network overhead in D2D networks, defined as the sum of time and energy required for processing tasks at devices, through the design for MIMO beamforming and communication/computation resource allocation. Second, we address IRS-assisted communication systems. Specifically, we study an adaptive IRS control scheme considering realistic IRS reflection behavior and channel environments, and propose a novel adaptive codebook-based limited feedback protocol and learning-based solutions for codebook updates. </p> <p><br></p> <p>Furthermore, in order for revolutionary innovations to emerge for future generations of communications, it is crucial to explore and address fundamental, long-standing open problems for communications, such as the design of practical codes for a variety of important channel models. In the later part of this dissertation, we study the design of practical codes for feedback-enabled communication channels, i.e., feedback codes. The existing feedback codes, which have been developed over the past six decades, have been demonstrated to be vulnerable to high forward/feedback noises, due to the non-triviality of the design of feedback codes. We propose a novel recurrent neural network (RNN) autoencoder-based architecture to mitigate the susceptibility to high channel noises by incorporating domain knowledge into the design of the deep learning architecture. Using this architecture, we suggest a new class of non-linear feedback codes that increase robustness to forward/feedback noise in additive White Gaussian noise (AWGN) channels with feedback. </p>