Search

To address the issue of reliable communication under complicated scenarios, an online learning-assisted intelligent OFDM receiver was proposed.The variations of the channel environment could be precepted by the receiver, and the optimal parameters of the receiver under the current scenario were obtained by collecting data and training online.In the channel estimation module of the OFDM system, a performance comparator based on the mean square error of noisy channel samples was designed as the indicator of channel environment variations.To accelerate the online training progress, a lightweight neural network structure was applied.The proposed method was further implemented and verified based on universal software radio peripherals.The numerical simulation and over-the-air experimental results demonstrate that the proposed receiver can perceive and adapt to new environments effectively, and outperforms existing machine learning methods in terms of receiving performance and convergence rate with a limited number of pilots.

The intelligent communication and networking technologies for manned/unmanned cooperation was comprehensively surveyed.Firstly, the requirements on communication and networking were analyzed from the application scenarios of manned/unmanned cooperation.Then, in context of physical layer, link layer and network layer respectively, the key issues regarding channel modeling, waveform design, networking protocol and intelligent collaboration were analyzed.And the states-of-the-art in this research area and the characteristics of representative technologies were deeply studied.In the end, the possible development trends and promising technologies were prospected on the way to make the manned/unmanned cooperative communication and networking more intelligent, more efficient and more flexible.

The intelligent communication and networking technologies for manned/unmanned cooperation was comprehensively surveyed.Firstly, the requirements on communication and networking were analyzed from the application scenarios of manned/unmanned cooperation.Then, in context of physical layer, link layer and network layer respectively, the key issues regarding channel modeling, waveform design, networking protocol and intelligent collaboration were analyzed.And the states-of-the-art in this research area and the characteristics of representative technologies were deeply studied.In the end, the possible development trends and promising technologies were prospected on the way to make the manned/unmanned cooperative communication and networking more intelligent, more efficient and more flexible.

To address the issue of reliable communication under complicated scenarios, an online learning-assisted intelligent OFDM receiver was proposed.The variations of the channel environment could be precepted by the receiver, and the optimal parameters of the receiver under the current scenario were obtained by collecting data and training online.In the channel estimation module of the OFDM system, a performance comparator based on the mean square error of noisy channel samples was designed as the indicator of channel environment variations.To accelerate the online training progress, a lightweight neural network structure was applied.The proposed method was further implemented and verified based on universal software radio peripherals.The numerical simulation and over-the-air experimental results demonstrate that the proposed receiver can perceive and adapt to new environments effectively, and outperforms existing machine learning methods in terms of receiving performance and convergence rate with a limited number of pilots.

In response to the problem of limited performance and low spectral efficiency in complex multipath environments of traditional direct sequence spread spectrum communication, a cyclic prefix (CP) block transmission structure spread spectrum system with a time-frequency hybrid direct sequence spread spectrum receiver structure was proposed.The system adopted maximum ratio combination (MRC) in the frequency domain to achieve equalization and de-spreading processes simultaneously, while achieving optimal reception performance and omitting the IFFT process to reduce computational complexity significantly.On this basis, it was proposed to replace the m-sequence with the constant amplitude zero auto correlation (CAZAC) sequence as the spread spectrum sequence, which significantly improved the system performance without increasing computational complexity.Finally, a high-speed spread spectrum communication method based on cyclic code shift keying (CCSK) was proposed to solve the problems of low spectrum utilization efficiency and limited transmission rate in traditional direct sequence spread spectrum.By utilizing the property of Fourier transform time-domain cyclic shift, a low implementation complexity CCSK decoding method was designed, which reduced the multiplication number required for CCSK de-spreading by O(N2) reduced to O (Nlog N), greatly reducing resource consume.The simulation results show that compared to existing direct sequence spread spectrum methods, the proposed method achieves approximately 3 dB gain in both Gaussian and complex multipath channel environments.

In response to the problem of limited performance and low spectral efficiency in complex multipath environments of traditional direct sequence spread spectrum communication, a cyclic prefix (CP) block transmission structure spread spectrum system with a time-frequency hybrid direct sequence spread spectrum receiver structure was proposed.The system adopted maximum ratio combination (MRC) in the frequency domain to achieve equalization and de-spreading processes simultaneously, while achieving optimal reception performance and omitting the IFFT process to reduce computational complexity significantly.On this basis, it was proposed to replace the m-sequence with the constant amplitude zero auto correlation (CAZAC) sequence as the spread spectrum sequence, which significantly improved the system performance without increasing computational complexity.Finally, a high-speed spread spectrum communication method based on cyclic code shift keying (CCSK) was proposed to solve the problems of low spectrum utilization efficiency and limited transmission rate in traditional direct sequence spread spectrum.By utilizing the property of Fourier transform time-domain cyclic shift, a low implementation complexity CCSK decoding method was designed, which reduced the multiplication number required for CCSK de-spreading by O(N2) reduced to O (Nlog N), greatly reducing resource consume.The simulation results show that compared to existing direct sequence spread spectrum methods, the proposed method achieves approximately 3 dB gain in both Gaussian and complex multipath channel environments.

Aiming at the problem that most current researches on text semantic communication mainly rely on simulation system for theoretical verification, an extensible hierarchical semantic communication system was proposed by taking advantage of the separation of hierarchical encoding and decoding architecture in semantic level and grammatical level.The system was compatible with the reliable communication technology under the framework of Shannon information through the mode of semantic and syntactic separation, and realized the nested combination of semantic communication and traditional communication.Furthermore, a universal and extensible verification system was built based on the software radio platform to verify the proposed semantic communication system architecture.The verification system took semantic communication software platform as the driving core of hardware drive and algorithm call, integrated the whole process of signal generation, information transmission, data acquisition, decoding and evaluation at the receiving end, and could be further extended for semantic and syntactic level.Finally, the text semantic communication was tested based on this verification system, which verified that it had higher validity and reliability than the traditional communication mode.

Aiming at the problem that most current researches on text semantic communication mainly rely on simulation system for theoretical verification, an extensible hierarchical semantic communication system was proposed by taking advantage of the separation of hierarchical encoding and decoding architecture in semantic level and grammatical level.The system was compatible with the reliable communication technology under the framework of Shannon information through the mode of semantic and syntactic separation, and realized the nested combination of semantic communication and traditional communication.Furthermore, a universal and extensible verification system was built based on the software radio platform to verify the proposed semantic communication system architecture.The verification system took semantic communication software platform as the driving core of hardware drive and algorithm call, integrated the whole process of signal generation, information transmission, data acquisition, decoding and evaluation at the receiving end, and could be further extended for semantic and syntactic level.Finally, the text semantic communication was tested based on this verification system, which verified that it had higher validity and reliability than the traditional communication mode.

A communication system based on extended contextual semantic features was proposed by using an end-to-end integrated design method based on deep learning.Unlike existing research that focused only on local context while neglecting global context, the proposed system integrated both local and global contextual knowledge, semantic encoding and decoding was utilized by extended contextual knowledge, thereby enhancing the reliability of the semantic communication system.At the transmitter, efficient semantic representation was achieved through extended contextual semantic encoding.At the receiver, the accuracy of semantic inference was improved by combining mechanisms such as historical communication text mining, contextual semantic feature learning, and heuristic graph-based decoding strategy.When comparing with the traditional communication system and the existing semantic communication systems, simulation results demonstrate that the proposed system significantly improves the reliability of the communication system under low signal-to-noise ratio.

A communication system based on extended contextual semantic features was proposed by using an end-to-end integrated design method based on deep learning.Unlike existing research that focused only on local context while neglecting global context, the proposed system integrated both local and global contextual knowledge, semantic encoding and decoding was utilized by extended contextual knowledge, thereby enhancing the reliability of the semantic communication system.At the transmitter, efficient semantic representation was achieved through extended contextual semantic encoding.At the receiver, the accuracy of semantic inference was improved by combining mechanisms such as historical communication text mining, contextual semantic feature learning, and heuristic graph-based decoding strategy.When comparing with the traditional communication system and the existing semantic communication systems, simulation results demonstrate that the proposed system significantly improves the reliability of the communication system under low signal-to-noise ratio.

To solve the performance limitation of direct sequence spread spectrum system in complex multipath environment, an adaptive anti-jamming spread spectrum framework that organically combines single carrier frequency domain equalization (SCFDE) and direct sequence spread spectrum (DSSS) technologies was proposed.The frequency multipath fading was overcame by frequency domain equalization, and the transmission rates and high reliability was reconfigured by deploying variable spread factors.Moreover, the inherent fast Fourier transform process was made full use at the receiver to realize the adjoint detection and analysis of interference intensity, interference type and other information, etc.Then, the frequency domain bearing point online was optimized and selected to improve the adaptability to the interference, especially blocking interference.The simulation results show that the proposed direct spread spectrum waveform based on SCFDE has good communication performance in both Gaussian and multipath environments, and the notch of some frequency bands has little impact on the communication performance, which verifies the effectiveness of anti-jamming by adaptive optimizing information frequency domain bearers.

To solve the performance limitation of direct sequence spread spectrum system in complex multipath environment, an adaptive anti-jamming spread spectrum framework that organically combines single carrier frequency domain equalization (SCFDE) and direct sequence spread spectrum (DSSS) technologies was proposed.The frequency multipath fading was overcame by frequency domain equalization, and the transmission rates and high reliability was reconfigured by deploying variable spread factors.Moreover, the inherent fast Fourier transform process was made full use at the receiver to realize the adjoint detection and analysis of interference intensity, interference type and other information, etc.Then, the frequency domain bearing point online was optimized and selected to improve the adaptability to the interference, especially blocking interference.The simulation results show that the proposed direct spread spectrum waveform based on SCFDE has good communication performance in both Gaussian and multipath environments, and the notch of some frequency bands has little impact on the communication performance, which verifies the effectiveness of anti-jamming by adaptive optimizing information frequency domain bearers.

For orthogonal frequency division multiplexing (OFDM) systems, a hybrid model and data driven channel estimation algorithm was proposed.Combined with two existing channel estimation methods, including a low complex learning-based channel estimation method and the linear minimum mean square error (LMMSE) channel estimation, the estimator with the ability was facilitated to employ online training to improve estimation performance.Meanwhile, the pilot overhead consumed by generating online training data was saved due to the use of the model-based method in the proposed algorithm, which improved the spectrum efficiency.The simulation results demonstrate that the proposed algorithm has better performance under low signal-to-noise ratio (SNR) and better adaptation to practical imperfections compared with conventional channel estimation methods.

For orthogonal frequency division multiplexing (OFDM) systems, a hybrid model and data driven channel estimation algorithm was proposed.Combined with two existing channel estimation methods, including a low complex learning-based channel estimation method and the linear minimum mean square error (LMMSE) channel estimation, the estimator with the ability was facilitated to employ online training to improve estimation performance.Meanwhile, the pilot overhead consumed by generating online training data was saved due to the use of the model-based method in the proposed algorithm, which improved the spectrum efficiency.The simulation results demonstrate that the proposed algorithm has better performance under low signal-to-noise ratio (SNR) and better adaptation to practical imperfections compared with conventional channel estimation methods.

In order to solve the problem that the data packets were out of order at the receiving end in the multipath transmission,which greatly reduced the transmission performance,an optimization algorithm was proposed for multipath transmission path scheduling based on forward delay in the vehicle heterogeneous network.The main idea of the proposed algorithm was to schedule data packets through a concurrent path according to the forward delay and throughput difference estimated by the sender.A simulation experiment was carried out on NS-3.The simulation results show that compared with the previous algorithm,the proposed algorithm has better performance than other algorithms in reorder-buffer-occupancy density (RBD) and throughput.The problem of out-of-order data packets at the receiving end is significantly reduced,and the total system throughput and network utilization have been improved.

In order to solve the problem that the data packets were out of order at the receiving end in the multipath transmission,which greatly reduced the transmission performance,an optimization algorithm was proposed for multipath transmission path scheduling based on forward delay in the vehicle heterogeneous network.The main idea of the proposed algorithm was to schedule data packets through a concurrent path according to the forward delay and throughput difference estimated by the sender.A simulation experiment was carried out on NS-3.The simulation results show that compared with the previous algorithm,the proposed algorithm has better performance than other algorithms in reorder-buffer-occupancy density (RBD) and throughput.The problem of out-of-order data packets at the receiving end is significantly reduced,and the total system throughput and network utilization have been improved.

In order to achieve the best balance between latency,computational rate and energy consumption,for a edge access network of IoV,a distribution offloading algorithm based on deep Q network (DQN) was considered.Firstly,these tasks of different vehicles were prioritized according to the analytic hierarchy process (AHP),so as to give different weights to the task processing rate to establish a relationship model.Secondly,by introducing edge computing based on DQN,the task offloading model was established by making weighted sum of task processing rate as optimization goal,which realized the long-term utility of strategies for offloading decisions.The performance evaluation results show that,compared with the Q-learning algorithm,the average task processing delay of the proposed method can effectively improve the task offload efficiency.

In order to achieve the best balance between latency,computational rate and energy consumption,for a edge access network of IoV,a distribution offloading algorithm based on deep Q network (DQN) was considered.Firstly,these tasks of different vehicles were prioritized according to the analytic hierarchy process (AHP),so as to give different weights to the task processing rate to establish a relationship model.Secondly,by introducing edge computing based on DQN,the task offloading model was established by making weighted sum of task processing rate as optimization goal,which realized the long-term utility of strategies for offloading decisions.The performance evaluation results show that,compared with the Q-learning algorithm,the average task processing delay of the proposed method can effectively improve the task offload efficiency.

In order to accurately evaluate the autonomous communication and networking capability of these unmanned system which was instructive to the intelligent collaboration of UAV (unmanned aerial vehicle) system,the research of the UAV system which was adapted to the complex environment with countermeasure possibilities was focused on.The autonomous communication and networking capability of UAV system and their relationship from multiple perspectives was analyzed and modeled,including self-adaptation,self-decision,man-UAV interaction,cyber-physical integration and evolution,and an example was provided to illustrate the detailed evaluation process.The example results show that the proposed method comprehensively consider all the key aspects of the performance evaluation,which can be used to quantitatively evaluate the autonomous communication and networking capability of different UAVs or other unmanned systems.

In order to accurately evaluate the autonomous communication and networking capability of these unmanned system which was instructive to the intelligent collaboration of UAV (unmanned aerial vehicle) system,the research of the UAV system which was adapted to the complex environment with countermeasure possibilities was focused on.The autonomous communication and networking capability of UAV system and their relationship from multiple perspectives was analyzed and modeled,including self-adaptation,self-decision,man-UAV interaction,cyber-physical integration and evolution,and an example was provided to illustrate the detailed evaluation process.The example results show that the proposed method comprehensively consider all the key aspects of the performance evaluation,which can be used to quantitatively evaluate the autonomous communication and networking capability of different UAVs or other unmanned systems.

The trend of energy transformation is to integrate smart grid into comprehensive energy.The research method is to establish the framework of energy information,physics and social system research.The active support of power transformation is the guarantee of the success of energy transformation.The proposed scheme emphasized the importance of social factors in practical engineering and research.As a new research methodology,it was compatible with mixed simulation of data,model and behavior.The widely used method in engineering was extended to economics and sociology,and the decision-making method based on subjective experience was made more scientific.In addition,in the definition of the Internet of things,the idea of removing the limitations of the Internet was proposed,and a unified framework was used to reflect the impact of the combination of the Internet/private network and other technologies.

The trend of energy transformation is to integrate smart grid into comprehensive energy.The research method is to establish the framework of energy information,physics and social system research.The active support of power transformation is the guarantee of the success of energy transformation.The proposed scheme emphasized the importance of social factors in practical engineering and research.As a new research methodology,it was compatible with mixed simulation of data,model and behavior.The widely used method in engineering was extended to economics and sociology,and the decision-making method based on subjective experience was made more scientific.In addition,in the definition of the Internet of things,the idea of removing the limitations of the Internet was proposed,and a unified framework was used to reflect the impact of the combination of the Internet/private network and other technologies.

The inter-vehicle transmission interference is one of the key factors to impact the communication performance of vehicular Ad Hoc networks. When vehicles send signals at the same time, it will inevitably have an impact on the surrounding vehicles, which has a negative effect on network connectivity prediction. According to vehicle density and traffic flow, a vehicular network connectivity prediction model was presented based on Nakagami distribution. The Nakagami distribution was used to describe the fading channel in the signal transmission process. Form expression of the inter-vehicle connectivity probability was also derived with power probability density function and signal to noise ratio of received signals.Simulation results show that connectivity probability can be well improved with larger ratio of vehicles which transmit signals before the ratio reaches the maximum.However,negative effect will take place on vehicular connectivity when the ratio exceeds the maximum value.

The inter-vehicle transmission interference is one of the key factors to impact the communication performance of vehicular Ad Hoc networks. When vehicles send signals at the same time, it will inevitably have an impact on the surrounding vehicles, which has a negative effect on network connectivity prediction. According to vehicle density and traffic flow, a vehicular network connectivity prediction model was presented based on Nakagami distribution. The Nakagami distribution was used to describe the fading channel in the signal transmission process. Form expression of the inter-vehicle connectivity probability was also derived with power probability density function and signal to noise ratio of received signals.Simulation results show that connectivity probability can be well improved with larger ratio of vehicles which transmit signals before the ratio reaches the maximum.However,negative effect will take place on vehicular connectivity when the ratio exceeds the maximum value.

Recently，with the rapid development of vehicular communication technology，IoV（internet of vehicles）as one of the applications of IoT（internet of things），is attracting more and more attention as well as its basic applications.The algorithm of predicting the connectivity probability based on highway model was proposed.Also，the joint distribution of vehicles on highway was studied，and the equation calculating the boundaries of connectivity probability on one road segment was analyzed quantitatively.The diagram presenting the relationship between the connectivity probability on one road segment and the average number of vehicles in each tuple was depicted by Rstudio.As a consequence，the model of connectivity probability on one path was achieved by calculating the products of the connectivity probability on all road segments along one path.The analysis result shows that the connectivity probability on one path can be improved by increasing the communication range or the density of vehicles.

Recently，with the rapid development of vehicular communication technology，IoV（internet of vehicles）as one of the applications of IoT（internet of things），is attracting more and more attention as well as its basic applications.The algorithm of predicting the connectivity probability based on highway model was proposed.Also，the joint distribution of vehicles on highway was studied，and the equation calculating the boundaries of connectivity probability on one road segment was analyzed quantitatively.The diagram presenting the relationship between the connectivity probability on one road segment and the average number of vehicles in each tuple was depicted by Rstudio.As a consequence，the model of connectivity probability on one path was achieved by calculating the products of the connectivity probability on all road segments along one path.The analysis result shows that the connectivity probability on one path can be improved by increasing the communication range or the density of vehicles.

An enhanced neighbor information-based multi-hop broadcast protocol（ENIMBP）in highway scenarios was proposed, which calculated the forwarding waiting time by using vehicle neighbor information as well as position, speed and direction to select the optimal forwarding vehicle. In order to calculate the forwarding waiting time, ENIMBP employed position information for vehicles which with different distance to the broadcasting vehicle, while used speed and direction in addition for those with the same distance to the broadcasting vehicle. ENIMBP is a good solution to segmentation problem and hidden／exposed node problem in highway scenarios. Simulation results show that ENIMBP can significantly reduce the end to end delay in a sparse network, while maintaining a high packet delivery ratio.

An enhanced neighbor information-based multi-hop broadcast protocol（ENIMBP）in highway scenarios was proposed, which calculated the forwarding waiting time by using vehicle neighbor information as well as position, speed and direction to select the optimal forwarding vehicle. In order to calculate the forwarding waiting time, ENIMBP employed position information for vehicles which with different distance to the broadcasting vehicle, while used speed and direction in addition for those with the same distance to the broadcasting vehicle. ENIMBP is a good solution to segmentation problem and hidden／exposed node problem in highway scenarios. Simulation results show that ENIMBP can significantly reduce the end to end delay in a sparse network, while maintaining a high packet delivery ratio.

In order to improve the broadcast reception rate in VANET, the conclusion that the relationship between collision probability and minimum contention window size and the relationship between expiration probability and minimum window size were reached by building Markov model. According to this conclusion, a minimum contention window size adjustment back-off algorithm called CEB was proposed, it is on the basis of the relative size between the number of expiration beacons and pre-set threshold. Simulations were done to compare the performance of CEB, RBEB and BEB, and the results show that the performance of the new proposed algorithm is better than that of RBEB and BEB.

In order to improve the broadcast reception rate in VANET, the conclusion that the relationship between collision probability and minimum contention window size and the relationship between expiration probability and minimum window size were reached by building Markov model. According to this conclusion, a minimum contention window size adjustment back-off algorithm called CEB was proposed, it is on the basis of the relative size between the number of expiration beacons and pre-set threshold. Simulations were done to compare the performance of CEB, RBEB and BEB, and the results show that the performance of the new proposed algorithm is better than that of RBEB and BEB.

The location-based routing protocol RBVT-R was analyzed. Aiming at the defects of RBVT-R routing protocol during the process of routing establishment and packet forwarding, an improved algorithm of RBVT-R was proposed. This method has improved the flooding mechanism by attaining road traffic density independently during the process of routing establishment. A packet forwarding scheme based on direction and location forecast was proposed during the process of packet forwarding, and had solved the problem of repeated transmission of packets in the same section. The simulation results show that the proposed improvement strategy can effectively enhance the average packet delivery ratio and end-to-end delay.

The location-based routing protocol RBVT-R was analyzed. Aiming at the defects of RBVT-R routing protocol during the process of routing establishment and packet forwarding, an improved algorithm of RBVT-R was proposed. This method has improved the flooding mechanism by attaining road traffic density independently during the process of routing establishment. A packet forwarding scheme based on direction and location forecast was proposed during the process of packet forwarding, and had solved the problem of repeated transmission of packets in the same section. The simulation results show that the proposed improvement strategy can effectively enhance the average packet delivery ratio and end-to-end delay.

In order to solve the periodic broadcast scalability of IEEE 802.11p-based VANET on control channel, a minimum contention window adjustment algorithm based on neighbor nodes number estimation was proposed. First of all, in order to minimize the collision probability, the relationship between minimum contention window（CWmin）and active node number n was deduced on the basis of Markov model IEEE 802.11 broadcast backoff. Then minimum contention window was adjusted dynamically by estimating the number of neighbor nodes in real time. Finally, the proposed algorithm and the original's fixed CWmin method were compared by simulation, and the results show that the proposed algorithm is superior to the original method in broadcast reception rate.

In order to solve the periodic broadcast scalability of IEEE 802.11p-based VANET on control channel, a minimum contention window adjustment algorithm based on neighbor nodes number estimation was proposed. First of all, in order to minimize the collision probability, the relationship between minimum contention window（CWmin）and active node number n was deduced on the basis of Markov model IEEE 802.11 broadcast backoff. Then minimum contention window was adjusted dynamically by estimating the number of neighbor nodes in real time. Finally, the proposed algorithm and the original's fixed CWmin method were compared by simulation, and the results show that the proposed algorithm is superior to the original method in broadcast reception rate.