Unmanned aerial vehicle assisted railway sensing data collection and calculation unloading method and system

Abstract

The invention discloses an unmanned aerial vehicle-assisted railway sensing data collection and calculation unloading method and system, and the method comprises the steps: deciding the flight path of an unmanned aerial vehicle (UAV) and calculating task unloading based on a DRL intelligent algorithm, collecting the sensing data of a wireless sensor network (WSN), and carrying out the task unloading calculation, wSN transmission energy consumption and UAV flight and calculation energy consumption are minimized while a certain real-time requirement of railway environment monitoring data is met. The method can be applied to monitoring of the railway operation environment, certain real-time data collection of the wireless sensor network is guaranteed through deployment flexibility of the UAV, the transmission energy consumption of the wireless sensor network is minimized as much as possible, and meanwhile, the computing load of the UAV is reduced and the life cycle of the whole monitoring system is prolonged by utilizing computing resources of a base station and a high-speed train.

Description

Technical Field

[0001] The present invention belongs to the field of wireless communication technology, and in particular relates to a method and system for collecting and calculating railway sensor data assisted by an unmanned aerial vehicle. Background Art

[0002] With the rapid development of China's railways, effective railway infrastructure and environmental monitoring are particularly important. For environments with difficult geological conditions, where it is not easy to lay and maintain wired backhaul networks, and where certain real-time requirements for information transmission must be guaranteed, wireless sensor networks (WSNs) have become an effective solution for monitoring the railway operating environment. For example, video surveillance cameras, foreign object intrusion monitoring sensors, and disaster monitoring sensors deployed along the line send data to the ground control center through wireless backhaul. WSNs for monitoring the railway operating environment are deployed over a large area to obtain and analyze WSN data to track changes in the railway operating environment. However, the massive amount of monitoring data generated in this process poses a great challenge to the transmission bearer network, and a certain amount of computing power is required to process and calculate the data. The service quality of this process can be measured by the freshness AoI indicator of the calculation results. In the railway WSN scenario, the AoI of data represents the time difference from data acquisition, collection, unloading, calculation to the final result returning to the data fusion center.

[0003] With the advancement of Unmanned Aerial Vehicle (UAV) technology, UAVs are increasingly used in civil and commercial applications, including surveillance, aerial imaging, precision agriculture, smart logistics, disaster response, etc. UAVs have the advantages of rapid deployment, easy programming, and high scalability, and can provide reliable and cost-effective wireless communication solutions for a variety of real-world scenarios. In addition, UAVs can fly to places where the wireless channel conditions of the equipment are good, enabling the equipment to complete data transmission with low energy consumption. Therefore, in the railway wireless sensor network, using UAVs for sensor data collection can effectively reduce the transmission energy consumption of the sensor network and extend the life cycle of the sensor network; through the trajectory control of UAVs, better data transmission channel conditions can be obtained to ensure the reliability of data transmission. In addition, the server carried by the UAV can directly calculate and process the collected data, further improving the latency performance of data processing. However, considering the battery life and limited computing power of the UAV, the UAV can offload part of the data to the BS for processing and calculation. Summary of the invention

[0004] In order to solve the problems of short battery life cycle in railway wireless sensor networks, certain real-time requirements for environmental data, and computational processing of massive monitoring data, the present invention provides a method and system for collecting and computing railway sensor data assisted by drones.

[0005] The invention discloses a method for collecting and offloading calculation of railway sensor data assisted by a UAV. The method is based on a deep reinforcement learning algorithm (DRL) to decide the flight trajectory of the UAV and offload the calculation task. The method collects the sensor data of the wireless sensor network (WSN) and offloads the calculation task. The method can meet the real-time requirements of the railway environmental monitoring data while minimizing the transmission energy consumption of the WSN and the flight and calculation energy consumption of the UAV. The method specifically includes the following steps:

[0006] Data collection phase of WSN: SN (Sensor Node) collects railway environmental data and stores the data in the buffer area; SN sends a data status indication frame to BS (Base Station), which includes the location coordinates of SN, SN buffer queue status, data timestamp, and data priority.

[0007] UAV data collection phase: The base station BS executes the DRL algorithm to make decisions based on the data status of the WSN and the computing power of the UAV, including the UAV data collection flight trajectory and computing task offloading; the BS sends a trajectory indication frame to the UAV, which contains the locations that the UAV needs to arrive at first and then the UAV flies to the corresponding SN position based on the trajectory and sends a wake-up indication frame to the SN, and the SN uploads the sensor data in the buffer area.

[0008] Computational task offloading stage: After completing data collection, the UAV sends a collection completion indication frame to the BS, and the BS sends a task offloading indication frame to the UAV, which includes the offloaded data ratio and the offloaded data type. The offload ratio ranges from 0 to 1. When the BS computing resources are insufficient, the BS offloads part of the task to the train for calculation, and the final calculation results are returned to the BS.

[0009] Algorithm training and execution: The DRL algorithm is executed in the BS. The algorithm's environmental status information includes the location coordinates of the SN, the queue status of the SN buffer, the data timestamp, the data priority, and the computing resources of the UAV. The algorithm's actions include the UAV trajectory and the computing task offloading decision. The algorithm's reward indicators include the freshness of the transmitted data AoI, the transmission energy consumption, and the UAV energy consumption. The algorithm trains the model through historical data or experimental phase data. When the training reaches the preset rounds or meets the preset feedback conditions, the BS uses the trained model for UAV trajectory, data collection, and computing task offloading decisions.

[0010] Furthermore, the data status indication frame is used to inform the BS of the sensor data information of the SN cache area, including the SN location, cache queue status, data timestamp, and data priority; based on this information, the BS executes the DRL algorithm to decide the UAV data collection flight trajectory and computing task offloading.

[0011] Furthermore, the trajectory indication frame is used to control the flight trajectory of the UAV data collection, including the location information of the SNs that the UAV needs to reach first and then. Based on the flight trajectory, the UAV adjusts the speed and direction to fly to the corresponding SN positions first and then, and sends a wake-up indication frame to the corresponding SN, and the SN uploads the sensor data.

[0012] Furthermore, the task offloading indication frame is used to inform the UAV to offload the computing task, including the offloading ratio of the computing task and the type of offloaded data. The UAV sends the computing task to the BS based on the indication. When the BS computing resources are insufficient, the BS offloads part of the task to the train for calculation. After the corresponding device completes the calculation, the calculation results are returned to the BS.

[0013] The present invention provides a UAV-assisted railway sensor data collection and calculation offloading system, which is suitable for the above-mentioned UAV-assisted railway sensor data collection and calculation offloading method, including but not limited to railway WSN constructed by Wi-Fi, Star Flash, ZigBee and Bluetooth communication technologies and gateway equipment for network protocol conversion, as well as UAV, ground BS and high-speed trains. The cellular communication standards used between key equipment include but not limited to 4G and 5G communication technologies.

[0014] Among them, WSN perceives the railway operating environment and sends data status indication frames to the base station. The BS executes the DRL decision algorithm based on this information; the BS sends a trajectory indication frame to the UAV, the UAV flies based on the trajectory, and sends a wake-up indication frame when it arrives at the corresponding SN position, and the SN sends the sensor data to the UAV; after the collection is completed, the UAV flies back to the BS according to the trajectory and informs the BS, the BS sends a task offloading indication frame to the UAV, and the UAV offloads the computing task to the BS. When the BS computing resources are insufficient, the BS offloads part of the task to the train for calculation, and finally all the results are returned to the BS.

[0015] The beneficial technical effects of the present invention are:

[0016] The present invention is aimed at data collection and calculation of wireless sensor networks for railway operation and maintenance environment monitoring. The base station side determines the flight trajectory of the UAV based on the data status of the WSN and the computing resources of the UAV to collect data and unload computing tasks. While meeting the demand for freshness of railway environmental monitoring data, it reduces the data transmission energy consumption of the WSN and the flight and computing energy consumption of the UAV, and extends the life cycle of the WSN network. The present invention provides strong support for future intelligent railway operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the principle architecture of the drone-assisted railway sensor data collection and computation offloading method of the present invention.

[0018] Figure 2 for Figure 1Communication frame timing diagram of UAV data collection and computing task offloading in the scenario.

[0019] Figure 3 for Figure 1 The signaling transmission process between different devices in the scenario. DETAILED DESCRIPTION

[0020] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] The invention discloses a method for collecting and unloading railway sensor data assisted by a drone, which adopts a DRL algorithm to decide UAV trajectory planning, data collection and computing task unloading, and the algorithm is executed in the BS. The communication between the UAV, BS and WSN is based on 5G communication technology, wherein the UAV and BS respectively serve as air and ground communication platforms of the railway environment, providing wireless access, data collection and computing task unloading for the railway WSN; the high-speed train is for ground users to access the BS, and when the BS computing resources are insufficient, some tasks can be unloaded to the train for calculation. The WSN perceives the railway environment, stores the collected data in the cache area, and sends a data status indication frame to the BS, which has a small amount of data and is only used to inform the BS of the current SN sensor data cache situation. The BS executes the DRL algorithm to make a decision based on the data status of the WSN, sends the trajectory decision result to the UAV through the trajectory indication frame, and the UAV flies according to the indicated trajectory and collects the WSN data; after the UAV data collection is completed, the BS sends a task unloading indication frame to the UAV according to the decision result, and the UAV sends some tasks to the BS for calculation according to the instruction, and the calculation results are all returned to the BS. BS acts as a data fusion center to integrate the final calculation results.

[0022] Figure 1 The present invention is a network for the collection and computational offloading of railway sensor data assisted by the drone. The communication technology of the network is based on the 5G cellular network. The UAV and BS serve as air and ground base stations, respectively, for access to the railway WSN and high-speed trains. In the network, the UAV, BS and high-speed trains are equipped with servers with different computing capabilities. The DRL algorithm is executed in the BS, and the model is trained based on historical data or experimental phase data. When the training reaches a preset round or reaches a preset feedback condition, the model parameters are used to decide the UAV flight trajectory and computational task offloading. It should be noted that the deep reinforcement learning model is not limited in this embodiment. The deep reinforcement learning model can be: deep Q learning, deep deterministic policy gradient, proximal policy optimization and other models.

[0023] The railway environment monitoring WSN samples the environment based on different sampling frequencies and transmits data status indication frames to the ground BS. Based on the received data status indication frames and the computing resources of the UAV, the BS decides the flight trajectory and computing task offloading of the UAV to collect data through the DRL model. The BS sends a trajectory indication frame to the UAV, which includes the locations of the SNs that the UAV needs to reach first and then. The UAV flies based on the trajectory and wakes up the specified SN to request the collection of uplink sensor data. After the data collection is completed, it sends a collection completion indication frame to the BS and flies back to the vicinity of the BS. The BS sends a computing task offloading indication frame to the UAV, including the computing task offloading ratio and the offloading data type. The UAV sends the collected data to the BS as instructed. When the BS computing resources are insufficient, the BS can offload part of the tasks to the train for calculation. After the corresponding equipment completes the calculation, the calculation results are returned to the BS, and the BS acts as a data fusion center for data analysis and integration.

[0024] Figure 2 The wireless communication frame timing diagram for the UAV to complete a data collection and computing task offloading process. First, the WSN sends a data status indication frame to the ground BS, which includes the SN location, cache queue status, data timestamp, and data priority information. The data timestamp is the sampling time mark of the data, the cache queue status indicates the amount of data in the SN cache queue, and the data priority indicates the urgency of data collection and calculation; the data timestamp is used to calculate the AoI of the data, which increases linearly with time until the calculation result of the data is returned to the BS, and the AoI decreases to the time difference from sampling, transmission, offloading calculation to the final return to the BS. Then, based on the received sensor data status indication frame and the computing resources of the UAV, the BS executes the DRL algorithm to decide the UAV flight trajectory and computing task offloading; the BS sends a trajectory indication frame to the UAV, which includes the location of the SN that the UAV needs to arrive at first and then. Based on the flight trajectory, the UAV adjusts the speed and direction to fly to the corresponding SN location first and then, and sends a wake-up indication frame to the corresponding SN to request the uplink data of the SN. Then, after the data collection is completed, the UAV flies back to the BS according to the trajectory indication and informs the BS that the data collection is completed. Finally, the BS sends a data computing task offloading indication frame to the UAV, including the computing task offloading ratio and the type of offloaded data. The UAV sends the computing task to the BS based on the indication. When the BS computing resources are insufficient, the BS can offload part of the task to the train for calculation. After the corresponding equipment completes the calculation, the calculation results are returned to the BS, which acts as a data fusion center for data analysis and integration.

[0025] Figure 3The corresponding signaling flow chart is shown in the figure. The SN sends a data status indication frame to the base station, and the UAV informs the BS of its computing resources. The BS executes the DRL decision algorithm based on this information. Then, the BS sends a trajectory indication frame to the UAV. The UAV flies based on the trajectory and sends a wake-up indication frame when it reaches the corresponding SN position. The SN sends the sensor data to the UAV. Finally, after the collection is completed, the UAV flies back to the BS according to the trajectory and informs the BS. The BS sends a task offloading indication frame to the UAV. The UAV offloads the computing task to the BS. When the BS computing resources are insufficient, the BS can offload part of the task to the train for calculation. Finally, all the results are returned to the BS, and the BS calculates the algorithm reward based on the entire process.

[0026] The above description is only part of the embodiments of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the core ideas and principles of the present invention are included in the protection scope of the present invention.

Claims

1. A method for collecting and calculating railway sensor data assisted by a drone, characterized in that: Based on the deep reinforcement learning algorithm DRL, the UAV flight trajectory and computing task offloading are determined, the wireless sensor network WSN sensor data is collected, and the task offloading is performed to minimize the WSN transmission energy consumption and the UAV flight and computing energy consumption while meeting the real-time requirements of railway environmental monitoring data. The specific steps include: Data collection phase of WSN: SN collects railway environment data and stores the data in the buffer area; SN sends a data status indication frame to BS, which includes the location coordinates of SN, SN buffer queue status, data timestamp, and data priority; UAV data collection phase: The base station BS executes the DRL algorithm to make decisions based on the data status of the WSN and the computing power of the UAV, including the flight trajectory of the UAV data collection and the offloading of computing tasks; the BS sends a trajectory indication frame to the UAV, which contains the locations that the UAV needs to reach first and then last. The UAV flies to the corresponding SN position based on the trajectory and sends a wake-up indication frame to the SN, and the SN uploads the sensor data in the buffer area; Computation task offloading stage: After completing data collection, the UAV sends a collection completion indication frame to the BS, and the BS sends a task offloading indication frame to the UAV, which includes the offloading data ratio and the offloading data type. The offloading ratio ranges from 0 to 1. When the BS computing resources are insufficient, the BS offloads part of the task to the train for calculation, and the final calculation results are returned to the BS. Algorithm training and execution: The DRL algorithm is executed in the BS. The algorithm's environmental status information includes the location coordinates of the SN, the queue status of the SN buffer, the data timestamp, the data priority, and the computing resources of the UAV. The algorithm's actions include the UAV trajectory and the computing task offloading decision. The algorithm's reward indicators include the AoI of the transmitted data, the transmission energy consumption, and the UAV energy consumption. The algorithm trains the model through historical data or experimental phase data. When the training reaches the preset rounds or meets the preset feedback conditions, the BS uses the trained model for UAV trajectory, data collection, and computing task offloading decisions.

2. The method for collecting and calculating railway sensor data assisted by an unmanned aerial vehicle according to claim 1, characterized in that: The data status indication frame is used to inform the BS of the sensor data information of the SN cache area, including SN location, cache queue status, data timestamp, and data priority; Based on this information, the BS executes the DRL algorithm to decide the flight trajectory of the UAV data collection and offload the computational tasks.

3. The method for collecting and calculating railway sensor data assisted by an unmanned aerial vehicle according to claim 1, characterized in that: The trajectory indication frame is used to control the flight trajectory of UAV data collection, including the location information of the SNs that the UAV needs to reach first and then. Based on the flight trajectory, the UAV adjusts the speed and direction to fly to the corresponding SN positions first and then sends a wake-up indication frame to the corresponding SN, and the SN uploads the sensor data.

4. The method for collecting and calculating railway sensor data assisted by an unmanned aerial vehicle according to claim 1, characterized in that: The task offloading indication frame is used to inform the UAV to offload the computing task, including the offloading ratio of the computing task and the offloading data type, and the UAV sends the computing task to the BS based on the indication; When the BS computing resources are insufficient, the BS offloads some tasks to the train for computation; After the corresponding device completes the calculation, the calculation results are returned to the BS.

5. A UAV-assisted railway sensor data collection and calculation unloading system, characterized in that: The method for collecting and offloading the sensor data of railways assisted by drones as described in any one of claims 1 to 4 includes but is not limited to railway WSN constructed by Wi-Fi, Starflash, ZigBee and Bluetooth communication technologies and gateway devices for network protocol conversion, as well as UAVs, ground BSs and high-speed trains, and cellular communication standards including but not limited to 4G and 5G communication technologies are used between key devices; Among them, WSN perceives the railway operating environment and sends data status indication frames to the base station. The BS executes the DRL decision algorithm based on this information; the BS sends a trajectory indication frame to the UAV, the UAV flies based on the trajectory, and sends a wake-up indication frame when it arrives at the corresponding SN position, and the SN sends the sensor data to the UAV; after the collection is completed, the UAV flies back to the BS according to the trajectory and informs the BS, the BS sends a task offloading indication frame to the UAV, and the UAV offloads the computing task to the BS. When the BS computing resources are insufficient, the BS offloads part of the task to the train for calculation, and finally all the results are returned to the BS.

Images