Pub Date : 2019-06-01DOI: 10.1109/CCAAW.2019.8904896
Jingyang Lu, Lun Li, John Nguyen, Dan Shen, X. Tian, Genshe Chen, K. Pham
In this paper, we have developed a machine learning based adaptive predistorter for high power amplifier linearization approach under dynamically changing environment. In the “bent-pipe” transponder in satellite communication (SATCOM) system, the High Power Amplifiers (HPAs), which are similar to other amplifiers in the communication system, can cause nonlinear distortions to transmitted signals, deteriorating the system transmission performance. The traditional model based processing techniques such as the Extended Saleh's Model (ESM) based predistortion design can be applied to maximize transponder throughput along with HPA power efficiency but sensitive to dynamically changing environment. In this paper, the compensated HPA linearity characterized through Amplitude Modulation-to-Amplitude Modulation (AM-AM) and Amplitude Modulation-to-Phase Modulation (AM-PM) effects is used as the system reward, we leveraged reinforcement learning approach to dynamically optimize the parameter set for the ESM based PD to improve system performance in various environmental conditions. Finally, simulation results are provided to evaluate and verify Bit Error Rate (BER) improvement for the considered SATCOM system by applying our proposed PD technique.
{"title":"Machine Learning based Adaptive Predistorter for High Power Amplifier Linearization","authors":"Jingyang Lu, Lun Li, John Nguyen, Dan Shen, X. Tian, Genshe Chen, K. Pham","doi":"10.1109/CCAAW.2019.8904896","DOIUrl":"https://doi.org/10.1109/CCAAW.2019.8904896","url":null,"abstract":"In this paper, we have developed a machine learning based adaptive predistorter for high power amplifier linearization approach under dynamically changing environment. In the “bent-pipe” transponder in satellite communication (SATCOM) system, the High Power Amplifiers (HPAs), which are similar to other amplifiers in the communication system, can cause nonlinear distortions to transmitted signals, deteriorating the system transmission performance. The traditional model based processing techniques such as the Extended Saleh's Model (ESM) based predistortion design can be applied to maximize transponder throughput along with HPA power efficiency but sensitive to dynamically changing environment. In this paper, the compensated HPA linearity characterized through Amplitude Modulation-to-Amplitude Modulation (AM-AM) and Amplitude Modulation-to-Phase Modulation (AM-PM) effects is used as the system reward, we leveraged reinforcement learning approach to dynamically optimize the parameter set for the ESM based PD to improve system performance in various environmental conditions. Finally, simulation results are provided to evaluate and verify Bit Error Rate (BER) improvement for the considered SATCOM system by applying our proposed PD technique.","PeriodicalId":196580,"journal":{"name":"2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW)","volume":"25 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114114235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-01DOI: 10.1109/CCAAW.2019.8904912
Carson D. Schubert, Rigoberto Roche', J. Briones
The future of space exploration depends on robust, reliable communication systems. As the number of such communication systems increase, automation is fast becoming a requirement to achieve this goal. A reinforcement learning solution can be employed as a possible automation method for such systems. The goal of this study is to build a reinforcement learning algorithm which optimizes data throughput of a single actor. A training environment was created to simulate a link within the NASA Space Communication and Navigation (SCaN) infrastructure, using state of the art simulation tools developed by the SCaN Center for Engineering, Networks, Integration, and Communications (SCENIC) laboratory at NASA Glenn Research Center to obtain the closest possible representation of the real operating environment. Reinforcement learning was then used to train an agent inside this environment to maximize data throughput. The simulation environment contained a single actor in low earth orbit capable of communicating with twenty-five ground stations that compose the Near-Earth Network (NEN). Initial experiments showed promising training results, so additional complexity was added by augmenting simulation data with link fading profiles obtained from real communication events with the International Space Station. A grid search was performed to find the optimal hyperparameters and model architecture for the agent. Using the results of the grid search, an agent was trained on the augmented training data. Testing shows that the agent performs well inside the training environment and can be used as a foundation for future studies with added complexity and eventually tested in the real space environment.
{"title":"Reinforcement Learning Applied to Cognitive Space Communications","authors":"Carson D. Schubert, Rigoberto Roche', J. Briones","doi":"10.1109/CCAAW.2019.8904912","DOIUrl":"https://doi.org/10.1109/CCAAW.2019.8904912","url":null,"abstract":"The future of space exploration depends on robust, reliable communication systems. As the number of such communication systems increase, automation is fast becoming a requirement to achieve this goal. A reinforcement learning solution can be employed as a possible automation method for such systems. The goal of this study is to build a reinforcement learning algorithm which optimizes data throughput of a single actor. A training environment was created to simulate a link within the NASA Space Communication and Navigation (SCaN) infrastructure, using state of the art simulation tools developed by the SCaN Center for Engineering, Networks, Integration, and Communications (SCENIC) laboratory at NASA Glenn Research Center to obtain the closest possible representation of the real operating environment. Reinforcement learning was then used to train an agent inside this environment to maximize data throughput. The simulation environment contained a single actor in low earth orbit capable of communicating with twenty-five ground stations that compose the Near-Earth Network (NEN). Initial experiments showed promising training results, so additional complexity was added by augmenting simulation data with link fading profiles obtained from real communication events with the International Space Station. A grid search was performed to find the optimal hyperparameters and model architecture for the agent. Using the results of the grid search, an agent was trained on the augmented training data. Testing shows that the agent performs well inside the training environment and can be used as a foundation for future studies with added complexity and eventually tested in the real space environment.","PeriodicalId":196580,"journal":{"name":"2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127722936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-01DOI: 10.1109/CCAAW.2019.8904886
G. Clark, G. Landis, Ethan Barnes, Blake LaFuente, Kristina Collins
The cognitive communications project has been working to refine artificial intelligence and machine learning approaches to support their deployment and sustained use in space environments. It has historically been difficult to implement such techniques on space platforms, however, due to the computational requirements they levy onto general-purpose avionics hardware. While technologies exist to accelerate the computation of aspects of neural networks, such platforms have not historically been deployed in space environments. Given that testing payloads in such environments can be both cost-and time-prohibitive, high-altitude balloons can be used as a way to approximate a space environment at a much lower cost, thus providing a cost-effective way in which to test newer approaches to hardware acceleration for artificial intelligence which may be deployed onto spacecraft more directly. This paper describes a successful test of a commercial off-the-shelf neural network accelerator on a high-altitude balloon. It begins by explaining our selection criteria when evaluating different commercial neural network acceleration techniques: primary considerations include size, weight, and power (SWaP) as well as ease of integration. Next, the paper describes the development and implementation of an experimental flight test platform: flight and ground components are discussed. Afterward, the paper discusses the experimental payload itself: this includes the experimental procedure as well as the specific image and method used for testing. Finally, the paper concludes with an evaluation of both the experimental device tested at altitude as well as the flight test framework itself, identifying how the existing platform can be used to continue testing commercial off-the-shelf (COTS) solutions for acceleration.
{"title":"Testing a Neural Network Accelerator on a High-Altitude Balloon","authors":"G. Clark, G. Landis, Ethan Barnes, Blake LaFuente, Kristina Collins","doi":"10.1109/CCAAW.2019.8904886","DOIUrl":"https://doi.org/10.1109/CCAAW.2019.8904886","url":null,"abstract":"The cognitive communications project has been working to refine artificial intelligence and machine learning approaches to support their deployment and sustained use in space environments. It has historically been difficult to implement such techniques on space platforms, however, due to the computational requirements they levy onto general-purpose avionics hardware. While technologies exist to accelerate the computation of aspects of neural networks, such platforms have not historically been deployed in space environments. Given that testing payloads in such environments can be both cost-and time-prohibitive, high-altitude balloons can be used as a way to approximate a space environment at a much lower cost, thus providing a cost-effective way in which to test newer approaches to hardware acceleration for artificial intelligence which may be deployed onto spacecraft more directly. This paper describes a successful test of a commercial off-the-shelf neural network accelerator on a high-altitude balloon. It begins by explaining our selection criteria when evaluating different commercial neural network acceleration techniques: primary considerations include size, weight, and power (SWaP) as well as ease of integration. Next, the paper describes the development and implementation of an experimental flight test platform: flight and ground components are discussed. Afterward, the paper discusses the experimental payload itself: this includes the experimental procedure as well as the specific image and method used for testing. Finally, the paper concludes with an evaluation of both the experimental device tested at altitude as well as the flight test framework itself, identifying how the existing platform can be used to continue testing commercial off-the-shelf (COTS) solutions for acceleration.","PeriodicalId":196580,"journal":{"name":"2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128133471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-01DOI: 10.1109/CCAAW.2019.8904898
R. Dudukovich, G. Clark, C. Papachristou
The growing popularity of small cost-effective satellites (SmallSats, CubeSats, etc.) creates the potential for a variety of new science applications involving multiple nodes functioning together to achieve a task, such as swarms and constellations. As this technology develops and is deployed for missions in Low Earth Orbit and beyond, the use of delay tolerant networking (DTN) techniques may improve communication capabilities within the network. In this paper, a network hierarchy is developed from heterogeneous networks of SmallSats, surface vehicles, relay satellites and ground stations which form an integrated network. There is a trade-off between complexity, flexibility, and scalability of user defined schedules versus autonomous routing as the number of nodes in the network increases. To address these issues, this work proposes a machine learning classifier based on DTN routing metrics. A framework is developed which will allow for the use of several categories of machine learning algorithms (decision tree, random forest, and deep learning) to be applied to a dataset of historical network statistics, which allows for the evaluation of algorithm complexity versus performance to be explored. We develop the emulation of a hierarchical network, consisting of tens of nodes which form a cognitive network architecture. CORE (Common Open Research Emulator) is used to emulate the network using bundle protocol and DTN IP neighbor discovery.
小型卫星(SmallSats, CubeSats等)的日益普及为各种新的科学应用创造了潜力，这些应用涉及多个节点一起工作以完成任务，例如群和星座。随着这项技术的发展和部署在低地球轨道及更远的任务中，使用容忍延迟网络(DTN)技术可以提高网络内的通信能力。本文从小卫星、地面飞行器、中继卫星和地面站组成的异构网络出发，建立了一个网络层次结构。随着网络中节点数量的增加，用户定义调度的复杂性、灵活性和可伸缩性与自主路由之间存在权衡。为了解决这些问题，本工作提出了一种基于DTN路由度量的机器学习分类器。开发了一个框架，允许将几种机器学习算法(决策树，随机森林和深度学习)应用于历史网络统计数据集，从而允许对算法复杂性与性能的评估进行探索。我们开发了一个由数十个节点组成的认知网络结构的分层网络仿真。CORE (Common Open Research Emulator)是利用捆绑协议和DTN IP邻居发现对网络进行仿真的工具。
{"title":"Evaluation of Classifier Complexity for Delay Tolerant Network Routing","authors":"R. Dudukovich, G. Clark, C. Papachristou","doi":"10.1109/CCAAW.2019.8904898","DOIUrl":"https://doi.org/10.1109/CCAAW.2019.8904898","url":null,"abstract":"The growing popularity of small cost-effective satellites (SmallSats, CubeSats, etc.) creates the potential for a variety of new science applications involving multiple nodes functioning together to achieve a task, such as swarms and constellations. As this technology develops and is deployed for missions in Low Earth Orbit and beyond, the use of delay tolerant networking (DTN) techniques may improve communication capabilities within the network. In this paper, a network hierarchy is developed from heterogeneous networks of SmallSats, surface vehicles, relay satellites and ground stations which form an integrated network. There is a trade-off between complexity, flexibility, and scalability of user defined schedules versus autonomous routing as the number of nodes in the network increases. To address these issues, this work proposes a machine learning classifier based on DTN routing metrics. A framework is developed which will allow for the use of several categories of machine learning algorithms (decision tree, random forest, and deep learning) to be applied to a dataset of historical network statistics, which allows for the evaluation of algorithm complexity versus performance to be explored. We develop the emulation of a hierarchical network, consisting of tens of nodes which form a cognitive network architecture. CORE (Common Open Research Emulator) is used to emulate the network using bundle protocol and DTN IP neighbor discovery.","PeriodicalId":196580,"journal":{"name":"2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122786459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-01DOI: 10.1109/CCAAW.2019.8904914
M. Koets, Justin Blount, Jarred Blount
This paper presents a mathematical model for a cognitive communication network applicable to satellite communications with ground stations. The model employs abstract elements to describe a communications network, allowing the approach to be applied to a wide range of real-world communications systems and problems. The model includes representation of communications paths, spacecraft capabilities, time-varying demand for data transfer, changes in visibility due to satellite motion, time-varying availability of channels, and regulatory constraints on the use of radio communication bands. These model elements permit the detailed description of the structure and constraints of a communications problem. The model establishes a formal definition for a communication schedule which assigns communications resources to specific communicators at specific times. The model also formalizes constraints on the interactions between communicators, establishing the definition of a valid schedule in which communications conflicts do not occur and the definition of a good schedule in which communications resources are used efficiently. The paper also presents a dynamic reasoning methodology which uses the model to allocate communications resources in response to changing network conditions and communications loads. Implementation of the reasoning process using Answer Set Programming is demonstrated, providing illustration of the practicality of the approach. The application of the model and methodology to an example satellite communication network is presented. Using this approach significantly improved performance with respect to static resource allocation is demonstrated.
{"title":"Cognitive Scheduling and Resource Allocation for Space to Ground Communication","authors":"M. Koets, Justin Blount, Jarred Blount","doi":"10.1109/CCAAW.2019.8904914","DOIUrl":"https://doi.org/10.1109/CCAAW.2019.8904914","url":null,"abstract":"This paper presents a mathematical model for a cognitive communication network applicable to satellite communications with ground stations. The model employs abstract elements to describe a communications network, allowing the approach to be applied to a wide range of real-world communications systems and problems. The model includes representation of communications paths, spacecraft capabilities, time-varying demand for data transfer, changes in visibility due to satellite motion, time-varying availability of channels, and regulatory constraints on the use of radio communication bands. These model elements permit the detailed description of the structure and constraints of a communications problem. The model establishes a formal definition for a communication schedule which assigns communications resources to specific communicators at specific times. The model also formalizes constraints on the interactions between communicators, establishing the definition of a valid schedule in which communications conflicts do not occur and the definition of a good schedule in which communications resources are used efficiently. The paper also presents a dynamic reasoning methodology which uses the model to allocate communications resources in response to changing network conditions and communications loads. Implementation of the reasoning process using Answer Set Programming is demonstrated, providing illustration of the practicality of the approach. The application of the model and methodology to an example satellite communication network is presented. Using this approach significantly improved performance with respect to static resource allocation is demonstrated.","PeriodicalId":196580,"journal":{"name":"2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW)","volume":"401 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130179151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-01DOI: 10.1109/CCAAW.2019.8904907
Aaron Smith, J. Downey
Autoencoder-based communication systems use neural network channel models to backwardly propagate message reconstruction error gradients across an approximation of the physical communication channel. In this work, we develop and test a new generative adversarial network (GAN) architecture for the purpose of training a stochastic channel approximating neural network. In previous research, investigators have focused on additive white Gaussian noise (AWGN) channels and/or simplified Rayleigh fading channels, both of which are linear and have well defined analytic solutions. Given that training a neural network is computationally expensive, channel approximation networks-and more generally the autoencoder systems-should be evaluated in communication environments that are traditionally difficult. To that end, our investigation focuses on channels that contain a combination of non-linear amplifier distortion, pulse shape filtering, intersymbol interference, frequency-dependent group delay, multipath, and non-Gaussian statistics. Each of our models are trained without any prior knowledge of the channel. We show that the trained models have learned to generalize over an arbitrary amplifier drive level and constellation alphabet. We demonstrate the versatility of our GAN architecture by comparing the marginal probability density function of several channel simulations with that of their corresponding neural network approximations.
{"title":"A Communication Channel Density Estimating Generative Adversarial Network","authors":"Aaron Smith, J. Downey","doi":"10.1109/CCAAW.2019.8904907","DOIUrl":"https://doi.org/10.1109/CCAAW.2019.8904907","url":null,"abstract":"Autoencoder-based communication systems use neural network channel models to backwardly propagate message reconstruction error gradients across an approximation of the physical communication channel. In this work, we develop and test a new generative adversarial network (GAN) architecture for the purpose of training a stochastic channel approximating neural network. In previous research, investigators have focused on additive white Gaussian noise (AWGN) channels and/or simplified Rayleigh fading channels, both of which are linear and have well defined analytic solutions. Given that training a neural network is computationally expensive, channel approximation networks-and more generally the autoencoder systems-should be evaluated in communication environments that are traditionally difficult. To that end, our investigation focuses on channels that contain a combination of non-linear amplifier distortion, pulse shape filtering, intersymbol interference, frequency-dependent group delay, multipath, and non-Gaussian statistics. Each of our models are trained without any prior knowledge of the channel. We show that the trained models have learned to generalize over an arbitrary amplifier drive level and constellation alphabet. We demonstrate the versatility of our GAN architecture by comparing the marginal probability density function of several channel simulations with that of their corresponding neural network approximations.","PeriodicalId":196580,"journal":{"name":"2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115893086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-01DOI: 10.1109/CCAAW.2019.8904887
Mohamed A. Aref, S. Jayaweera
This paper presents a design of a cognitive engine for interference and jamming resilience based on deep reinforcement learning (DRL). The proposed scheme is aimed at finding the spectrum opportunities in a heterogeneous wideband spectrum. In this paper we discuss a specific DRL mechanism based on double deep Q-learning (DDQN) with a convolutional neural network (CNN) to successfully learn such interference avoidance operation over a wideband partially observable environment. It is shown, through simulations, that the proposed technique has a low computational complexity and significantly outperforms other techniques in the literature, including other DRL-based approaches.
{"title":"Robust Deep Reinforcement Learning for Interference Avoidance in Wideband Spectrum","authors":"Mohamed A. Aref, S. Jayaweera","doi":"10.1109/CCAAW.2019.8904887","DOIUrl":"https://doi.org/10.1109/CCAAW.2019.8904887","url":null,"abstract":"This paper presents a design of a cognitive engine for interference and jamming resilience based on deep reinforcement learning (DRL). The proposed scheme is aimed at finding the spectrum opportunities in a heterogeneous wideband spectrum. In this paper we discuss a specific DRL mechanism based on double deep Q-learning (DDQN) with a convolutional neural network (CNN) to successfully learn such interference avoidance operation over a wideband partially observable environment. It is shown, through simulations, that the proposed technique has a low computational complexity and significantly outperforms other techniques in the literature, including other DRL-based approaches.","PeriodicalId":196580,"journal":{"name":"2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116426310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-01DOI: 10.1109/CCAAW.2019.8904902
Lixing Yu, Jinlong Ji, Y. Guo, Qianlong Wang, Tianxi Ji, P. Li
In the forthcoming space communications, there would be a large number of spacecrafts that belong to different organizations or countries. How to efficiently allocate spectrum resources for such heterogeneous spacecraft networks becomes a very important and challenging issue. While spectrum auction provides a potential solution to spectrum allocation, how to preserve the privacy during the auction process in the spacecraft networks has not been well studied yet. In this paper, we propose a secure spectrum auction scheme by utilizing blockchain and cryptography technologies, which can preserve bidders' identity and bid privacy, and protect the auctions against collusion attacks. We evaluate our method with well-designed experiments and demonstrate its effectiveness and practicability.
{"title":"Smart Communications in Heterogeneous Spacecraft Networks: A Blockchain Based Secure Auction Approach","authors":"Lixing Yu, Jinlong Ji, Y. Guo, Qianlong Wang, Tianxi Ji, P. Li","doi":"10.1109/CCAAW.2019.8904902","DOIUrl":"https://doi.org/10.1109/CCAAW.2019.8904902","url":null,"abstract":"In the forthcoming space communications, there would be a large number of spacecrafts that belong to different organizations or countries. How to efficiently allocate spectrum resources for such heterogeneous spacecraft networks becomes a very important and challenging issue. While spectrum auction provides a potential solution to spectrum allocation, how to preserve the privacy during the auction process in the spacecraft networks has not been well studied yet. In this paper, we propose a secure spectrum auction scheme by utilizing blockchain and cryptography technologies, which can preserve bidders' identity and bid privacy, and protect the auctions against collusion attacks. We evaluate our method with well-designed experiments and demonstrate its effectiveness and practicability.","PeriodicalId":196580,"journal":{"name":"2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131716464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-01DOI: 10.1109/CCAAW.2019.8904895
Anu Jagannath, Jithin Jagannath, A. Drozd
In this position paper, the authors argue the need for a novel framework that provides flexibility, autonomy and optimizes the use of scarce resources to ensure reliable communication during next-generation space missions. To this end, the authors present the shortcomings of existing space architectures and the challenges in realizing adaptive autonomous space-networking. In this regard, the authors aim to jointly exploit the immense capabilities of deep reinforcement learning (DRL) and cross-layer optimization by proposing an artificial intelligence-based cognitive cross-layer decision engine to bolster next-generation space missions. The presented software-defined cognitive cross-layer decision engine is designed for the resource-constrained Internet-of-Space-Things. The framework is designed to be flexible to accommodate varying (with time and location) requirements of multiple space missions such as reliability, throughput, delay, energy-efficiency among others. In this work, the authors present the formulation of the cross-layer optimization for multiple mission objectives that forms the basis of the presented framework. The cross-layer optimization problem is then modeled as a Markov Decision Process to be solved using deep reinforcement learning (DRL). Subsequently, the authors elucidate the DRL model and concisely explain the deep neural network architecture to perform the DRL. This position paper concludes by providing the different phases of the evaluation plan for the proposed cognitive framework.
{"title":"Artificial Intelligence-based Cognitive Cross-layer Decision Engine for Next-Generation Space Mission","authors":"Anu Jagannath, Jithin Jagannath, A. Drozd","doi":"10.1109/CCAAW.2019.8904895","DOIUrl":"https://doi.org/10.1109/CCAAW.2019.8904895","url":null,"abstract":"In this position paper, the authors argue the need for a novel framework that provides flexibility, autonomy and optimizes the use of scarce resources to ensure reliable communication during next-generation space missions. To this end, the authors present the shortcomings of existing space architectures and the challenges in realizing adaptive autonomous space-networking. In this regard, the authors aim to jointly exploit the immense capabilities of deep reinforcement learning (DRL) and cross-layer optimization by proposing an artificial intelligence-based cognitive cross-layer decision engine to bolster next-generation space missions. The presented software-defined cognitive cross-layer decision engine is designed for the resource-constrained Internet-of-Space-Things. The framework is designed to be flexible to accommodate varying (with time and location) requirements of multiple space missions such as reliability, throughput, delay, energy-efficiency among others. In this work, the authors present the formulation of the cross-layer optimization for multiple mission objectives that forms the basis of the presented framework. The cross-layer optimization problem is then modeled as a Markov Decision Process to be solved using deep reinforcement learning (DRL). Subsequently, the authors elucidate the DRL model and concisely explain the deep neural network architecture to perform the DRL. This position paper concludes by providing the different phases of the evaluation plan for the proposed cognitive framework.","PeriodicalId":196580,"journal":{"name":"2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW)","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126049882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-01DOI: 10.1109/CCAAW.2019.8904901
J. Luis, Markus Guerster, Iñigo Del Portillo, E. Crawley, B. Cameron
Many of the next generation of satellites will be equipped with numerous degrees of freedom in power and bandwidth allocation capabilities, making manual resource allocation impractical. Therefore, it is desirable to automate the operation of these highly flexible satellites. This paper presents a novel approach based on Deep Reinforcement Learning to allocate power in multibeam satellite systems. The proposed architecture represents the problem as continuous state and action spaces. We make use of the Proximal Policy Optimization algorithm to optimize the allocation policy for minimum unmet system demand and power consumption. Finally, the performance of the algorithm is analyzed through simulations of a multibeam satellite system. The analysis shows promising results for Deep Reinforcement Learning to be used as a dynamic resource allocation algorithm.
{"title":"Deep Reinforcement Learning for Continuous Power Allocation in Flexible High Throughput Satellites","authors":"J. Luis, Markus Guerster, Iñigo Del Portillo, E. Crawley, B. Cameron","doi":"10.1109/CCAAW.2019.8904901","DOIUrl":"https://doi.org/10.1109/CCAAW.2019.8904901","url":null,"abstract":"Many of the next generation of satellites will be equipped with numerous degrees of freedom in power and bandwidth allocation capabilities, making manual resource allocation impractical. Therefore, it is desirable to automate the operation of these highly flexible satellites. This paper presents a novel approach based on Deep Reinforcement Learning to allocate power in multibeam satellite systems. The proposed architecture represents the problem as continuous state and action spaces. We make use of the Proximal Policy Optimization algorithm to optimize the allocation policy for minimum unmet system demand and power consumption. Finally, the performance of the algorithm is analyzed through simulations of a multibeam satellite system. The analysis shows promising results for Deep Reinforcement Learning to be used as a dynamic resource allocation algorithm.","PeriodicalId":196580,"journal":{"name":"2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123989404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：