Abstract: An edge network computing system includes: a plurality of terminal devices; a plurality of edge servers connected to the terminal device through an access network; and a plurality of cloud servers connected to the plurality of edge servers through a core network. Each edge server is configured to: receive a plurality of computing tasks originated from one of the plurality of terminal devices; use a deep Q-learning neural network (DQN) with experience replay to select one of the plurality of could servers to offload a portion of the plurality of computing tasks; and send the portion of the plurality of computing tasks to the selected cloud server and forward results of the portion of the plurality of computing tasks received from the selected cloud server to the originating terminal device.

Abstract: Embodiments of the present disclosure provide a method of a burst-based route discovery process. The method includes sending a probing interest packet to an NDN network; when one NDN forwarder receives the probing interest packet from a corresponding face, sending the probing interest packet to neighboring NDN forwarders; after anyone NDN forwarder receives the probing interest packet, sending back a burst of K probing data packets; as the burst of K probing data packets being received by an NDN forwarder, evaluating gaps between arrival times of the burst of K probing data packets; determining an available network throughput level of a face of the NDN forwarder; and if determined available network throughput level indicates a predefined increase in network throughput, setting the face of the NDN forwarder as a face for forwarding interest packets; and sending the burst of K probing data packets to neighboring NDN forwarders.

Abstract: Embodiments of the present disclosure provide a method, a device, and a storage medium for targeted adversarial discriminative domain adaptation (T-ADDA). The method includes pre-training a source model including a source feature encoder and a source classifier, adapting a target feature encoder, and generating a target model by concatenating the adapted target feature encoder with the pre-trained source classifier.

Abstract: Embodiments of the present disclosure provide a method, a device, and a storage medium for hybrid automatic gain control in a communication system. The method includes amplifying an input signal to generate an amplified signal which is converted into a plurality of output signals; obtaining a moving average amplitude of a plurality of output signals of a current input signal; and calculating a signal amplitude difference according to the moving average amplitude and a desired output signal amplitude level; calculating a signal amplitude ratio according to a plurality of output signals of two previous output signal blocks and AGC gains corresponding to the plurality of output signals of the two previous output signal blocks; obtaining a step size according to the signal amplitude difference and the signal amplitude ratio; and calculating an AGC gain of the current input signal according to the step size and a corresponding previous AGC gain.

Abstract: A system includes: a named data networking (NDN) based Spark distributed computing network including a Spark distributed computing network including a master computer node and a plurality of slave computer nodes, and a named data networking (NDN) protocol installed on the Spark distributed computing network, and a coded distributed computing (CDC) target recognition model deployed on the NDN-based Spark distributed computing network. The NDN-based Spark distributed computing network is configured to: receive one or more batches of input images; generate a parity image from each batch of the input images; predict a label for each image of the batch of the input images; process the generated parity image; upon a label prediction of one image of the batch of the input images being unavailable, reconstruct the unavailable label prediction; and classify labels for the input images.

Abstract: A system and method are provided for enhanced multi-way time transfer for time synchronization between at least one slave node and one master node. A slave node sends a first message to the master node to launch a time synchronization between the slave node and the master node. Upon receiving the first message, the master node adds a receiving time on a master clock to the first message to form a second message. The master node sends the second message back to the slave node and the slave node adds a receiving time on the slave clock to the second message to form an updated message. The slave node performs a time adjustment to the slave clock based on the updated message, thereby synchronizing time between the slave node and the master node.

Abstract: A hidden chamber detector includes a linear frequency modulated continuous wave (LFMCW) radar, a synthetic aperture radar (SAR) imaging processor, and a time division multiple access (TDMA) multiple input multiple output (MIMO) antenna array, including a plurality of transmitting and receiving (Tx-Rx) antenna pairs. A Tx-Rx antenna pair is selected, in a time division manner, as a Tx antenna and an Rx antenna for the LFMCW radar. The LFMCW radar is configured to transmit an illumination signal, receive an echo signal, convert the echo signal to a baseband signal, collect baseband samples, and send the collected samples to the SAR imaging processor. The SAR imaging processor is configured to receive the collected samples, collect structure/configuration of the antenna array and scanning information, and form an SAR image based on the collected samples, the structure/configuration of the antenna array, and the scanning information.

Abstract: An apparatus includes a camera for capturing an image at a first moment; a range finder for measuring a distance to an object at a center of the image; a rotatable mounting platform, fixedly hosting the camera and the range finder; and a controller. The controller is configured to receive the captured image and the measured distance; determine whether a target of interest (TOI) appears in the image; in response to determining a TOI appearing in the image, determine whether the TOI appears at the center of the image; calculate position parameters of the rotatable mounting platform for centering the TOI in an image to be captured at a second moment, separated from the first moment by a pre-determined time interval; control the rotatable mounting platform to rotate according to the calculated position parameters; and calculate and store the position parameters of the TOI with respect to the apparatus.

Abstract: Various embodiments provide a method for transmission control protocol (TCP) packet transmission. The method includes receiving, by a receiver performance enhancing node (PEN), one or more TCP packets each with a timestamp and a sequence number from a sender PEN; evaluating a packet delivery time from the sender PEN to the receiver PEN; detecting whether any TCP packet is lost based on a packet sequence and determining a delay shaping time for each TCP packet based on a maximum number of retransmissions and an evaluated delivery time distribution; in response to a lost TCP packet being detected, determining whether the lost TCP packet needs to be retransmitted based on the maximum number of retransmissions; and in response to the determined delay shaping time, determining when a received TCP packet needs to be forwarded based on the determined delay shaping time and a timestamp associated with the received TCP packet.

Abstract: A method for rapid discovery of satellite behavior, applied to a pursuit-evasion system including at least one satellite and a plurality of space sensing assets. The method includes performing transfer learning and zero-shot learning to obtain a semantic layer using space data information. The space data information includes simulated space data based on a physical model. The method further includes obtaining measured space-activity data of the satellite from the space sensing assets; performing manifold learning on the measured space-activity data to obtain measured state-related parameters of the satellite; modeling the state uncertainty and the uncertainty propagation of the satellite based on the measured state-related parameters; and performing game reasoning based on a Markov game model to predict satellite behavior and management of the plurality of space sensing assets according to the semantic layer and the modeled state uncertainty and uncertainty propagation.

Abstract: Various embodiments of the present disclosure provide a method, a device, and a storage medium for performance prediction of a communication waveform in a communication system. The method includes measuring, by a receiver, an actual SNR distribution of a communication link between a transmitter and the receiver; further includes evaluating, by a waveform performance prediction device, a normalized minimum SNR shift required for the communication waveform to operate, where the normalized minimum SNR shift is obtained based on a normalized SNR distribution using a neural network (NN), the normalized SNR distribution corresponding to the actual SNR distribution; and further includes, according to the normalized minimum SNR shift, obtaining, by a waveform performance prediction device, an actual minimum SNR shift for the actual SNR distribution, where according to the actual minimum SNR shift, the communication system is adjusted for operation.

Abstract: A system for hybrid modulation and demodulation includes a transmitter and a receiver. The transmitter is configured to receive a hybrid signal of a space-ground link system (SGLS), including a first component and a second component; perform a double sideband (DSB) modulation on the first component using a carrier frequency to obtain a first waveform; perform a single sideband (SSB) modulation on the second component using the carrier frequency to obtain a second waveform; mix the first waveform and the second waveform to generate a hybrid waveform; and transmit the hybrid waveform. The receiver is configured to receive the hybrid waveform; determine the carrier frequency; separate the first waveform and the second waveform; perform a DSB demodulation on the first waveform to obtain a first demodulated signal; and perform an SSB demodulation on the second waveform to obtain a second demodulated signal.

Abstract: A method for emulating a communication system with fast changing link condition, applied to a testbed system including an interference emulator, a transmitter, and a receiver, includes: by the transmitter, generating code-word symbols, in an initial symbol sequence, according to information bits; evaluating an interference condition and a time duration for each code-word symbol; reordering the code-word symbols to a reordered symbol sequence based on interference conditions; evaluating a total time duration of code-word symbols under each interference condition; and transmitting the code-word symbols in the reordered symbol sequence. The method also includes: by the interference emulator, obtaining the total time duration of code-word symbols under each interference condition from the transmitter; and providing an emulated interference environment by ordering the time durations of different interference conditions.

Abstract: Various embodiments provide a method for free space optical communication performance prediction method. The method includes: in a training stage, collecting a large number of data representing FSOC performance from external data sources and through simulation in five feature categories; dividing the collected data into training datasets and testing datasets to train a prediction model based on a deep neural network (DNN); evaluating a prediction error by a loss function and adjusting weights and biases of hidden layers of the DNN to minimize the prediction error; repeating training the prediction model until the prediction error is smaller than or equal to a pre-set threshold; in an application stage, receiving parameters entered by a user for an application scenario; retrieving and preparing real-time data from the external data sources for the application scenario; and generating near real-time FSOC performance prediction results based on the trained prediction model.

Abstract: The present disclosure provides a high power amplifier (HPA) linearization method, applied to a ground hub which includes a predistorter and a PD controller. The ground hub is arranged in a satellite communication system together with a transmitter and a satellite transponder, and the satellite transponder includes an HPA. The HPA linearization method includes determining an initial correction signal based on a physical model with a plurality of PD parameters to compensate AM-AM and AM-PM characteristics of the HPA; receiving a signal from the satellite transponder; determining a reward function for an action taken by the PD controller; examining an action-value function for actions taken in a preset past period; taking an action to adjust the plurality of PD parameters for the PD to generate an updated correction signal; sending the update correction signal to the transmitter to compensate the AM-AM and AM-PM characteristics of the HPA.

Abstract: A decision support method for machinery control includes extracting entities and relations from information sources, and creating subject-predicate-object (SPO) triples. Each SPO triple includes a subject entity and an object entity, and a relation between the subject entity and the object entity. The method further includes constructing a knowledge graph (KG) based on the SPO triples. The KG includes a plurality of nodes corresponding to the entities, and a plurality of links corresponding to the relations between the entities.

Abstract: The present disclosure provides a method for wave propagation prediction based on a 3D ray tracing engine and machine-learning based dominant ray selection. The method includes receiving, integrating, and processing input data. Integrating and processing the input data includes dividing a cone of the original millimeter wave (mmWave) into a plurality of sub cones; determining a contribution weight of rays coming from each sub cone to the received signal strength (RSS) at a receiving end of interest; and determining rays coming from one or more sub cones that have a total contribution weight to the RSS larger than a preset threshold value as dominant rays using a neural network obtained through a machine learning approach. The method further includes performing ray tracing based on the input data and the dominant rays to predict wave propagation.

Abstract: The present disclosure provides a method for joint manifold learning based heterogenous sensor data fusion, comprising: obtaining learning heterogeneous sensor data from a plurality sensors to form a joint manifold, wherein the plurality sensors include different types of sensors that detect different characteristics of targeting objects; performing, using a hardware processor, a plurality of manifold learning algorithms to process the joint manifold to obtain raw manifold learning results, wherein a dimension of the manifold learning results is less than a dimension of the joint manifold; processing the raw manifold learning results to obtain intrinsic parameters of the targeting objects; evaluating the multiple manifold learning algorithms based on the raw manifold learning results and the intrinsic parameters to determine one or more optimum manifold learning algorithms; and applying the one or more optimum manifold learning algorithms to fuse heterogeneous sensor data generated by the plurality sensors.

Abstract: A satellite communication framework includes a satellite system controller; at least one satellite transponder; and a plurality of remote terminals, each including a modem, a router, and a terminal agent. The terminal agent is configured to, based on a current allowable data rate and measurements of a current router queue size and a current router packet arrival rate, use a delayed uplink resource assignment for each modem and an MCV-based flow-control policy to forecast a future router queue size and a future router packet arrival rate and further update the delayed uplink resource request for a time after an uplink allocation delay. The modem is configured to communicate with the router and also with the satellite system controller through the satellite transponder, perform modulation and demodulation, and manage packet loss and delay according to the future router queue size and the future router packet arrival rate.

Abstract: A multiple-input and multiple-output (MIMO) bolt-on device for a single-input and single-output (SISO) radio, a MIMO channel emulator for testing the MIMO bolt-on device, and a MIMO channel emulation method are provided. The MIMO bolt-on device includes: a plurality of antennas, a multi-channel receiver, a plurality of couplers, a micro-controller, and a switch device. The multi-channel receiver includes a plurality of channels for signal transmission. Each coupler is configured to couple the multi-channel receiver with one of the plurality of antennas. The micro-controller is coupled to the multi-channel receiver to compare signals from the plurality of channels, thereby identifying a channel with a highest signal-to-noise (SNR) among the plurality of channels. The switch device is coupled to the micro-controller and configured to select an antenna corresponding to the channel with the highest SNR among the plurality of antennas for a connection between a selected antenna and the SISO radio.