Editor's Note
Guest Editor
Article List
2024, 22(9):925-932.
DOI: 10.11805/TKYDA2024082
Abstract:
Artificial Intelligence of Things(AIoT), as a deep integration of artificial intelligence and IoT technologies, has rapidly emerged as an important development direction for the new generation of information technology. To fully explore the potential of AIoT technology, this paper focuses on the application and development of AIoT technology in the field of intelligent connected vehicles. It delves into the integrated system architecture of AIoT and intelligent connected vehicles, systematically reviews the latest technological applications of AIoT in this field, and provides strategic recommendations for leveraging AIoT technology to promote the advancement and development of intelligent connected vehicle technology.
Artificial Intelligence of Things(AIoT), as a deep integration of artificial intelligence and IoT technologies, has rapidly emerged as an important development direction for the new generation of information technology. To fully explore the potential of AIoT technology, this paper focuses on the application and development of AIoT technology in the field of intelligent connected vehicles. It delves into the integrated system architecture of AIoT and intelligent connected vehicles, systematically reviews the latest technological applications of AIoT in this field, and provides strategic recommendations for leveraging AIoT technology to promote the advancement and development of intelligent connected vehicle technology.
2024, 22(9):933-943.
DOI: 10.11805/TKYDA2024112
Abstract:
Narrow Band Internet of Things(NB-IoT), as a low-power wide area network technology, is specially designed to connect a large number of low-power devices. The low-orbit satellite IoT based on this technology has lower transmission loss and delay, and can achieve seamless coverage of the earth through constellations. However, low-orbit satellites are highly dynamic and face QoS requirements from different users. These factors greatly affect the throughput performance of existing resource scheduling algorithms. In response to these challenges, this paper proposes a high-throughput NB-IoT low-orbit satellite IoT resource scheduling algorithm by comprehensively considering satellite channel characteristics, reliability and delay requirements between different users, and differential Doppler caused by high satellite dynamics in a scenario where a large number of IoT users request wireless resources and time-frequency resources are limited. Simulation results show that compared with existing methods, the resource scheduling algorithm proposed in this paper shows significant performance improvement in system throughput.
Narrow Band Internet of Things(NB-IoT), as a low-power wide area network technology, is specially designed to connect a large number of low-power devices. The low-orbit satellite IoT based on this technology has lower transmission loss and delay, and can achieve seamless coverage of the earth through constellations. However, low-orbit satellites are highly dynamic and face QoS requirements from different users. These factors greatly affect the throughput performance of existing resource scheduling algorithms. In response to these challenges, this paper proposes a high-throughput NB-IoT low-orbit satellite IoT resource scheduling algorithm by comprehensively considering satellite channel characteristics, reliability and delay requirements between different users, and differential Doppler caused by high satellite dynamics in a scenario where a large number of IoT users request wireless resources and time-frequency resources are limited. Simulation results show that compared with existing methods, the resource scheduling algorithm proposed in this paper shows significant performance improvement in system throughput.
2024, 22(9):944-951.
DOI: 10.11805/TKYDA2024023
Abstract:
Aiming at the traffic surge problem caused by massive smart device access in Power Internet of Things(PIoT), a resource scheduling strategy of Mobile Edge Computing(MEC) with delay and energy consumption equalization is proposed. Considering the channel conditions, the safety temperature protection mechanism of electric equipment and the energy consumption of equipment, the energy consumption model and thermal power consumption constraints on the equipment side are constructed based on the Landaer principle. Under the premise of ensuring queue stability, the long-term average time energy consumption of the system is minimized by jointly optimizing the task offloading decision, transmission power and computational resource allocation. To solve this stochastic optimization problem, Lyapunov theory is introduced to transform the problem into a deterministic optimization problem for each time slot. Simulation results show that this strategy is able to reduce the system energy consumption relative to the baseline scheme and achieve an equilibrium between energy consumption and delay.
Aiming at the traffic surge problem caused by massive smart device access in Power Internet of Things(PIoT), a resource scheduling strategy of Mobile Edge Computing(MEC) with delay and energy consumption equalization is proposed. Considering the channel conditions, the safety temperature protection mechanism of electric equipment and the energy consumption of equipment, the energy consumption model and thermal power consumption constraints on the equipment side are constructed based on the Landaer principle. Under the premise of ensuring queue stability, the long-term average time energy consumption of the system is minimized by jointly optimizing the task offloading decision, transmission power and computational resource allocation. To solve this stochastic optimization problem, Lyapunov theory is introduced to transform the problem into a deterministic optimization problem for each time slot. Simulation results show that this strategy is able to reduce the system energy consumption relative to the baseline scheme and achieve an equilibrium between energy consumption and delay.
2024, 22(9):952-958.
DOI: 10.11805/TKYDA2024034
Abstract:
Wireless Sensor Network(WSN) in the power system can sense and collect the status of the working equipment and environmental data in real time, which is an important technology to promote the development of smart grid. Aiming at the special requirements of network survival time, transmission delay, and transmission packet loss rate of WSN in substation scenarios, a WSN routing scheme based on reinforcement learning is proposed. The sending process of packets in WSN is abstracted as a Markov Decision Process(MDP), the rewards are reasonably set according to the optimization objective, and the optimal routing solution method based on Q-learning is given. Simulation results and numerical analysis show that the proposed scheme outperforms the benchmark scheme in terms of network survival time, transmission delay, and packet loss rate.
Wireless Sensor Network(WSN) in the power system can sense and collect the status of the working equipment and environmental data in real time, which is an important technology to promote the development of smart grid. Aiming at the special requirements of network survival time, transmission delay, and transmission packet loss rate of WSN in substation scenarios, a WSN routing scheme based on reinforcement learning is proposed. The sending process of packets in WSN is abstracted as a Markov Decision Process(MDP), the rewards are reasonably set according to the optimization objective, and the optimal routing solution method based on Q-learning is given. Simulation results and numerical analysis show that the proposed scheme outperforms the benchmark scheme in terms of network survival time, transmission delay, and packet loss rate.
2024, 22(9):959-966.
DOI: 10.11805/TKYDA2023410
Abstract:
In pedestrian positioning methods, the strapdown inertial navigation system requires processing data from the Inertial Measurement Unit(IMU) sensors, and the position of the pedestrian is obtained after algorithmic processing, thus placing high demands on the real-time performance and low power consumption of the chip. Since most pedestrian positioning algorithms are developed based on floating-point sensor data, the terminal device is generally required to handle floating-point data. The fifth-generation Reduced Instruction Set Computer(RISC-V) architecture, as an open-source architecture, can save on architectural licensing fees and has a wide range of applications in the field of the Internet of Things. Moreover, its floating-point(F) and vector(V) high-performance extension instructions can well meet the real-time requirements of pedestrian positioning algorithms. In response to the specific performance requirements of the pedestrian positioning system, a System on Chip (SoC) for pedestrian positioning based on a floating-point core vector processor optimized RISC-V architecture is proposed and verified in actual systems. A performance comparison analysis with several quasi-32-bit architecture RISC-V processors and standard processor schemes of algorithm-specific IPs (locate_IP) generated by High-Level Synthesis(HLS) components shows that the design has achieved a 34-fold improvement in performance and a 5.6-fold improvement in energy efficiency, meeting the requirements of micro terminals.
In pedestrian positioning methods, the strapdown inertial navigation system requires processing data from the Inertial Measurement Unit(IMU) sensors, and the position of the pedestrian is obtained after algorithmic processing, thus placing high demands on the real-time performance and low power consumption of the chip. Since most pedestrian positioning algorithms are developed based on floating-point sensor data, the terminal device is generally required to handle floating-point data. The fifth-generation Reduced Instruction Set Computer(RISC-V) architecture, as an open-source architecture, can save on architectural licensing fees and has a wide range of applications in the field of the Internet of Things. Moreover, its floating-point(F) and vector(V) high-performance extension instructions can well meet the real-time requirements of pedestrian positioning algorithms. In response to the specific performance requirements of the pedestrian positioning system, a System on Chip (SoC) for pedestrian positioning based on a floating-point core vector processor optimized RISC-V architecture is proposed and verified in actual systems. A performance comparison analysis with several quasi-32-bit architecture RISC-V processors and standard processor schemes of algorithm-specific IPs (locate_IP) generated by High-Level Synthesis(HLS) components shows that the design has achieved a 34-fold improvement in performance and a 5.6-fold improvement in energy efficiency, meeting the requirements of micro terminals.
2025, 23(5):434-445.
DOI: 10.11805/TKYDA2024170
Abstract:
Low-Earth Orbit(LEO) satellites have the characteristic of global coverage. The Long Range(LoRa) network based on LEO satellite Internet of Things(IoT) has become a research hotspot. To address the floor effect issue of LoRa modulation schemes in LEO satellite channels, two differential LoRa demodulation strategies are proposed for the differential LoRa modulation scheme. Firstly, a closed-form expression for the Symbol Error Rate(SER) is derived under the LEO satellite channel with dynamic Doppler frequency shift, illustrating the floor effect issue of LoRa modulation in LEO satellite channels. Subsequently, the derived closed-form SER expression is validated using Monte Carlo simulations, and the Bit Error Rate(BER) performance of LoRa modulation and the proposed differential LoRa modulation is evaluated. Simulation results show that compared with the LoRa modulation scheme, differential LoRa modulation and the proposed differential LoRa demodulation strategies can effectively improve the BER performance of LEO satellite IoT under dynamic Doppler frequency offset scenarios.
Low-Earth Orbit(LEO) satellites have the characteristic of global coverage. The Long Range(LoRa) network based on LEO satellite Internet of Things(IoT) has become a research hotspot. To address the floor effect issue of LoRa modulation schemes in LEO satellite channels, two differential LoRa demodulation strategies are proposed for the differential LoRa modulation scheme. Firstly, a closed-form expression for the Symbol Error Rate(SER) is derived under the LEO satellite channel with dynamic Doppler frequency shift, illustrating the floor effect issue of LoRa modulation in LEO satellite channels. Subsequently, the derived closed-form SER expression is validated using Monte Carlo simulations, and the Bit Error Rate(BER) performance of LoRa modulation and the proposed differential LoRa modulation is evaluated. Simulation results show that compared with the LoRa modulation scheme, differential LoRa modulation and the proposed differential LoRa demodulation strategies can effectively improve the BER performance of LEO satellite IoT under dynamic Doppler frequency offset scenarios.
2025, 23(5):461-467.
DOI: 10.11805/TKYDA2024045
Abstract:
With the continuous expansion and increasing complexity of modern power grids, there is a need for a technology that can integrate and process multi-source information to meet the demands of large-scale and highly complex information processing. This is essential to enhance the efficiency and security of power grid operations. To this end, a multi-source information fusion method for power grid operation based on fuzzy sets is designed. The collection of multi-source information for power grid operation is implemented through various sensors, including electric sensors, pressure sensors, and humidity sensors. The data collection methods of these sensors inevitably introduce noise into the collected data. To address this, wavelet denoising methods are employed to reduce noise and extract effective information from the power grid operation data. A multi-source information fusion method combining the fuzzy similarity matrix in fuzzy set theory and the Dempster-Shafer(D-S) evidence theory is designed to achieve the fusion of multi-source information in power grid operation. Experimental test results indicate that as the number of data types increases, the maximum confidence level of this method is in a growth phase. The maximum confidence level of multi-source information fusion reaches 0.94, demonstrating that the fusion results are reliable and applicable to the fusion of various types of data. After adding noise levels of 5 dB, 10 dB, 15 dB, 20 dB, and 25 dB, the maximum confidence level of multi-source information fusion using the designed method only experiences a minimal decrease. This indicates that the method has good robustness in multi-source information fusion. Additionally, the high information entropy values suggest that the fused information is richer in content.
With the continuous expansion and increasing complexity of modern power grids, there is a need for a technology that can integrate and process multi-source information to meet the demands of large-scale and highly complex information processing. This is essential to enhance the efficiency and security of power grid operations. To this end, a multi-source information fusion method for power grid operation based on fuzzy sets is designed. The collection of multi-source information for power grid operation is implemented through various sensors, including electric sensors, pressure sensors, and humidity sensors. The data collection methods of these sensors inevitably introduce noise into the collected data. To address this, wavelet denoising methods are employed to reduce noise and extract effective information from the power grid operation data. A multi-source information fusion method combining the fuzzy similarity matrix in fuzzy set theory and the Dempster-Shafer(D-S) evidence theory is designed to achieve the fusion of multi-source information in power grid operation. Experimental test results indicate that as the number of data types increases, the maximum confidence level of this method is in a growth phase. The maximum confidence level of multi-source information fusion reaches 0.94, demonstrating that the fusion results are reliable and applicable to the fusion of various types of data. After adding noise levels of 5 dB, 10 dB, 15 dB, 20 dB, and 25 dB, the maximum confidence level of multi-source information fusion using the designed method only experiences a minimal decrease. This indicates that the method has good robustness in multi-source information fusion. Additionally, the high information entropy values suggest that the fused information is richer in content.
2025, 23(5):468-475.
DOI: 10.11805/TKYDA2024063
Abstract:
With the large-scale development of renewable energy and the high proportion of massive terminals connected to the grid, the network load in the next generation smart grid will be further intensified, which brings unprecedented and great challenges to the power sensing network for real-time data collection and processing, and whole-domain information monitoring. At the same time, the sensor nodes have the problems of difficult energy replenishment as well as limited computational resources, and the traditional network structure will be difficult to meet the needs of the next generation grid, so it is of practical significance to study how to improve the energy efficiency of power sensor network. A Mobile Edge Computing(MEC) assisted computing offloading scheme for power sensor network is proposed to optimize the nodes' task processing latency and energy consumption under limited computational resources, by modeling the optimization problem as a Markov Decision Process(MDP) and solving the problem using Double Deep Q Network(DDQN) algorithm to minimize the total system overhead. Simulation results show that the proposed scheme outperforms the benchmark scheme in terms of delay, energy consumption and convergence performance.
With the large-scale development of renewable energy and the high proportion of massive terminals connected to the grid, the network load in the next generation smart grid will be further intensified, which brings unprecedented and great challenges to the power sensing network for real-time data collection and processing, and whole-domain information monitoring. At the same time, the sensor nodes have the problems of difficult energy replenishment as well as limited computational resources, and the traditional network structure will be difficult to meet the needs of the next generation grid, so it is of practical significance to study how to improve the energy efficiency of power sensor network. A Mobile Edge Computing(MEC) assisted computing offloading scheme for power sensor network is proposed to optimize the nodes' task processing latency and energy consumption under limited computational resources, by modeling the optimization problem as a Markov Decision Process(MDP) and solving the problem using Double Deep Q Network(DDQN) algorithm to minimize the total system overhead. Simulation results show that the proposed scheme outperforms the benchmark scheme in terms of delay, energy consumption and convergence performance.
2025, 23(5):482-488.
DOI: 10.11805/TKYDA2024383
Abstract:
With the rapid development of Internet of Things(IoT), big data, and Artificial Intelligence(AI) technologies, massive amounts of data are being generated and utilized on an unprecedented scale. These data contain a large amount of sensitive information, and how to securely store sensitive data has become a realistic problem that needs to be solved. The existing data storage schemes usually focus on the direct protection of sensitive data, while ignoring the leakage risks associated with explicit and implicit associations between sensitive and non-sensitive data. The explicit and implicit relationships among data are deeply analyzed from the perspective of information entropy, and a method is proposed to quickly assess the explicit and implicit relationships and predict the leakage risk of sensitive data. By introducing the information Lift Ratio(LR) and the Probability of Information Control(PIC), the method can effectively identify the influence of non-sensitive data on the risk of sensitive data leakage. In the simulation experiments, the maximum single-attribute LR in the Statistical Property Dataset(SPD) is 0.308, and the joint-attribute LR can be up to 0.891, and the predicted value of the sensitive data leakage risk is significantly improved, up to 23.2%. The simulation results show that the method can effectively identify and cope with the security risks caused by explicit and implicit relationships, thus significantly improving the overall security level of sensitive data storage.
With the rapid development of Internet of Things(IoT), big data, and Artificial Intelligence(AI) technologies, massive amounts of data are being generated and utilized on an unprecedented scale. These data contain a large amount of sensitive information, and how to securely store sensitive data has become a realistic problem that needs to be solved. The existing data storage schemes usually focus on the direct protection of sensitive data, while ignoring the leakage risks associated with explicit and implicit associations between sensitive and non-sensitive data. The explicit and implicit relationships among data are deeply analyzed from the perspective of information entropy, and a method is proposed to quickly assess the explicit and implicit relationships and predict the leakage risk of sensitive data. By introducing the information Lift Ratio(LR) and the Probability of Information Control(PIC), the method can effectively identify the influence of non-sensitive data on the risk of sensitive data leakage. In the simulation experiments, the maximum single-attribute LR in the Statistical Property Dataset(SPD) is 0.308, and the joint-attribute LR can be up to 0.891, and the predicted value of the sensitive data leakage risk is significantly improved, up to 23.2%. The simulation results show that the method can effectively identify and cope with the security risks caused by explicit and implicit relationships, thus significantly improving the overall security level of sensitive data storage.
2025, 23(5):446-452.
DOI: 10.11805/TKYDA2024336
Abstract:
With the vigorous construction of the digital new power system, the traditional power communication network is gradually transforming into a more robust, resilient, and multi-service-bearing all-time and all-domain communication network.To address the issue of difficult-to-guarantee deterministic latency for time-sensitive services due to the simultaneous access of multiple types of terminal services and massive data transmission in the all-time and all-domain communication network, a deterministic latency guarantee technology is proposed for all-time and all-domain communication networks based on Time-Sensitive Networking(TSN).Firstly, based on the analysis of the characteristics, importance, periodicity, and latency requirements of various types of services in the all-time and all-domain power communication network, the corresponding service models are established and prioritized. Then, a traffic scheduling mechanism based on TSN perception and shaping is proposed to ensure that the calculation of the gate control schedule meets the deterministic low-latency transmission of time-sensitive flows within the transmission cycle. To achieve the goal of minimizing end-to-end latency, a combined algorithm based on genetic algorithm and tabu search algorithm is employed to calculate the gate control list of time-sensitive flows. The average end-to-end latency is reduced by 15% compared with single optimization algorithm, and the latency jitter of time-sensitive flows is controlled at about 2 μs. This improves the scheduling performance and provides strong support for the stable and safe operation of the all-time and all-domain power communication network.
With the vigorous construction of the digital new power system, the traditional power communication network is gradually transforming into a more robust, resilient, and multi-service-bearing all-time and all-domain communication network.To address the issue of difficult-to-guarantee deterministic latency for time-sensitive services due to the simultaneous access of multiple types of terminal services and massive data transmission in the all-time and all-domain communication network, a deterministic latency guarantee technology is proposed for all-time and all-domain communication networks based on Time-Sensitive Networking(TSN).Firstly, based on the analysis of the characteristics, importance, periodicity, and latency requirements of various types of services in the all-time and all-domain power communication network, the corresponding service models are established and prioritized. Then, a traffic scheduling mechanism based on TSN perception and shaping is proposed to ensure that the calculation of the gate control schedule meets the deterministic low-latency transmission of time-sensitive flows within the transmission cycle. To achieve the goal of minimizing end-to-end latency, a combined algorithm based on genetic algorithm and tabu search algorithm is employed to calculate the gate control list of time-sensitive flows. The average end-to-end latency is reduced by 15% compared with single optimization algorithm, and the latency jitter of time-sensitive flows is controlled at about 2 μs. This improves the scheduling performance and provides strong support for the stable and safe operation of the all-time and all-domain power communication network.
2025, 23(5):429-433.
DOI: 10.11805/TKYDA2024382
Abstract:
In recent years, the rapid development of smart terminals and wireless networks has led to an exponential growth in the number of terminal devices and data volumes in the power IoT. These data resources have become important assets for power enterprises, significantly enhancing the smart sensing,internal control capabilities, and customer service efficiency of the power grid. However, as critical national infrastructure, power data is vulnerable to cyber-attacks and theft. If leaked, it could cause significant security risks and economic losses. Therefore, power enterprises must strengthen data security protection to address the security issues in data exchange, sharing, and mining. A cloud-edge collaborative intelligent grid data security sharing scheme is proposed, combining zero-knowledge proof technology with a secret sharing scheme to achieve fine-grained access control and privacy protection for user access requests. Finally, the simulation results show that the total time required to perform distributed data access verification in this paper is no more than 48 ms, indicating that the algorithm has a good performance.
In recent years, the rapid development of smart terminals and wireless networks has led to an exponential growth in the number of terminal devices and data volumes in the power IoT. These data resources have become important assets for power enterprises, significantly enhancing the smart sensing,internal control capabilities, and customer service efficiency of the power grid. However, as critical national infrastructure, power data is vulnerable to cyber-attacks and theft. If leaked, it could cause significant security risks and economic losses. Therefore, power enterprises must strengthen data security protection to address the security issues in data exchange, sharing, and mining. A cloud-edge collaborative intelligent grid data security sharing scheme is proposed, combining zero-knowledge proof technology with a secret sharing scheme to achieve fine-grained access control and privacy protection for user access requests. Finally, the simulation results show that the total time required to perform distributed data access verification in this paper is no more than 48 ms, indicating that the algorithm has a good performance.
2025, 23(5):453-460.
DOI: 10.11805/TKYDA2024061
Abstract:
In the downlink collaborative transmission process of the power Internet of Things(IoT), it is necessary to optimize the effective capacity of the system while ensuring low-latency communication, in order to continuously provide high-quality services to users. A Quality of Service(QoS)-Guaranteed strategy is proposed based on Remote Radio Heads(RRH) Collaboration(QG-RRHC). A two-layer power IoT network model based on Orthogonal Frequency Division Multiple Access(OFDMA) is designed. By introducing the theory of effective capacity, a distributed RRH collaborative transmission scheme for QoS guarantee is studied, which collaboratively serves the downlink data transmission on different subcarriers. Additionally, a heuristic optimization algorithm based on Lagrange duality is proposed to solve the joint optimization problem. Simulation results demonstrate that compared with other benchmark algorithms, the proposed strategy can significantly enhance the system's effective capacity and achieve the performance close to the optimal.
In the downlink collaborative transmission process of the power Internet of Things(IoT), it is necessary to optimize the effective capacity of the system while ensuring low-latency communication, in order to continuously provide high-quality services to users. A Quality of Service(QoS)-Guaranteed strategy is proposed based on Remote Radio Heads(RRH) Collaboration(QG-RRHC). A two-layer power IoT network model based on Orthogonal Frequency Division Multiple Access(OFDMA) is designed. By introducing the theory of effective capacity, a distributed RRH collaborative transmission scheme for QoS guarantee is studied, which collaboratively serves the downlink data transmission on different subcarriers. Additionally, a heuristic optimization algorithm based on Lagrange duality is proposed to solve the joint optimization problem. Simulation results demonstrate that compared with other benchmark algorithms, the proposed strategy can significantly enhance the system's effective capacity and achieve the performance close to the optimal.
2025, 23(5):476-481.
DOI: 10.11805/TKYDA2024247
Abstract:
With the rapid development of the energy Internet, new power services such as vehicle-network interaction have increasingly stringent requirements on service quality, which brings many challenges to the power terminal access network. To address the problem of resource waste and network performance degradation caused by the overlapping coverage of multiple communication technologies and a wide range of communication methods in terminal access network, a Communication Method Selection algorithm based on Random Forest(RF-CMS) is proposed, which intelligently categorizes a large number of diverse new electric power services and selects the most suitable communication methods for them through Random Forest mode. Then, the Multi-Agent Proximal Policy Optimization(MAPPO) algorithm is employed to dynamically allocate routes for the power services from the viewpoint of traffic loading and communication quality to ensure that various terminal service data (e. g., measurement information, control information) can be transmitted timely and accurately in the access network. The effectiveness of the proposed algorithm is validated by comparing it with the routing algorithm based solely on MAPPO in terms of average end-to-end delay and load balancing degree.
With the rapid development of the energy Internet, new power services such as vehicle-network interaction have increasingly stringent requirements on service quality, which brings many challenges to the power terminal access network. To address the problem of resource waste and network performance degradation caused by the overlapping coverage of multiple communication technologies and a wide range of communication methods in terminal access network, a Communication Method Selection algorithm based on Random Forest(RF-CMS) is proposed, which intelligently categorizes a large number of diverse new electric power services and selects the most suitable communication methods for them through Random Forest mode. Then, the Multi-Agent Proximal Policy Optimization(MAPPO) algorithm is employed to dynamically allocate routes for the power services from the viewpoint of traffic loading and communication quality to ensure that various terminal service data (e. g., measurement information, control information) can be transmitted timely and accurately in the access network. The effectiveness of the proposed algorithm is validated by comparing it with the routing algorithm based solely on MAPPO in terms of average end-to-end delay and load balancing degree.
