A method for offloading vehicle-to-everything (V2X) tasks based on optimal stopping theory

Abstract

This invention relates to a method and system for optimizing and offloading computational tasks in vehicular networks based on optimal stopping theory, belonging to the field of vehicular network technology. The method includes: constructing a vehicular network model based on optimal stopping theory; establishing an objective function that minimizes the expected total offloading cost based on vehicle speed and RSU load; the cost data includes RSU load and observation cost; solving the objective function using optimal stopping theory to calculate a reference value; comparing the observed current RSU load with the calculated reference value to find the optimal stopping time for offloading. This method achieves load balancing for computational tasks in vehicular networks by optimizing and offloading computational tasks, thereby improving the utilization rate of computing resources.

Description

Technical Field

[0001] This invention belongs to the field of vehicle networking technology, and in particular, it is a task offloading method in vehicle networking based on optimal stopping theory. Background Technology

[0002] Offloading strategies for computational tasks in vehicle-to-everything (V2X) networks are a popular research area. Because vehicles have limited computing power, they often need to communicate with Roadside Units (RSUs) to offload computationally intensive tasks. Since different edge servers have different loads, vehicles can leverage their mobility to monitor these servers and offload data to a less loaded RSU. To help vehicles select the least loaded RSU for task offloading, it is necessary to propose a task offloading method based on optimal stopping theory to determine when to offload tasks. Summary of the Invention

[0003] The main objective of this invention is to overcome the shortcomings and deficiencies of the prior art and provide a vehicle network task offloading system and method based on optimal stopping theory. By optimizing the offloading of computing tasks, the system achieves load balancing of task computing in the vehicle network and improves the utilization rate of computing resources.

[0004] According to one aspect of the present invention, the present invention provides a method for optimizing and offloading computational tasks in a vehicle-to-everything (V2X) network based on optimal stopping theory, the method comprising the following steps:

[0005] S1: Construct a vehicle-to-everything (V2X) model based on optimal stopping theory. Based on vehicle speed and RSU load, establish an objective function that minimizes the expected total unloading cost. The total unloading cost includes RSU load and observation cost.

[0006] S2: Solve the objective function using optimal stopping theory to obtain a reference value;

[0007] S3: Based on the observed current RSU load, compare the current load with the calculated reference value to find the optimal stopping time for unloading.

[0008] Preferably, the objective function for minimizing the expected unloading cost includes:

[0009] The objective function for vehicle unloading is defined, and the optimization problem is as follows:

[0010]

[0011] in, x represents the total unloading cost of vehicle i. nThis represents the load on server n, i.e., the total latency spent offloading tasks to the selected server for processing; ΔL represents the distance between adjacent RSUs, where n is the current RSU number, and v i Let be the speed of vehicle i, and c represent the observation cost required to observe one RSU.

[0012] Preferably, the optimal unloading cost of vehicle i at its nth observation is

[0013]

[0014] in, This refers to the unloading cost incurred by stopping observation at this point and selecting the current server. It is the expected cost of continued observation.

[0015] Preferably, if vehicle i has not unloaded by the end of the observation period, it can only unload to the last RSU. The optimal unloading cost for vehicle i in the Nth observation is...

[0016]

[0017] in, The uninstallation cost incurred when the data is unloaded to the Nth server.

[0018] Beneficial effects: This invention constructs a vehicle-to-everything (V2X) model based on optimal stopping theory. Based on vehicle speed and RSU load, it establishes an objective function to minimize the expected total unloading cost in order to find the optimal RSU for task unloading. By using optimal stopping theory to solve this problem, the observed current RSU load is compared with a calculated scalar value to determine the optimal unloading time, thereby achieving load balancing of RSUs in the V2X and improving the efficiency of task unloading.

[0019] The features and advantages of the present invention will become clear from the following accompanying drawings and a detailed description of specific embodiments thereof. Attached Figure Description

[0020] Figure 1 This is a flowchart of a computational task optimization and unloading method in vehicle-to-everything (V2X) networks based on optimal stopping theory.

[0021] Figure 2 This is a cost comparison chart between the proposed algorithm and randomized algorithms and optimal algorithms. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0023] Figure 1 This is a flowchart of a computational task optimization and unloading method in vehicle-to-everything (V2X) networks based on optimal stopping theory. Figure 1 As shown in the figure, this embodiment provides a method for optimizing and offloading computational tasks in vehicle-to-everything (V2X) networks based on optimal stopping theory. The method includes the following steps:

[0024] The optimal RSU load for task offloading is found by using the optimal stopping theory to solve this problem. The observed current RSU load is compared with a certain value to determine the optimal offloading time, thereby achieving load balancing of RSUs in the vehicle network and improving the efficiency of task offloading.

[0025] S1: Construct a vehicle-to-everything (V2X) model based on optimal stopping theory. Based on vehicle speed and RSU load, establish an objective function that minimizes the expected total unloading cost. The total unloading cost includes RSU load and observation cost.

[0026] S2: Solve the objective function using optimal stopping theory to obtain a reference value;

[0027] S3: Based on the observed current RSU load, compare the current load with the calculated reference value to find the optimal stopping time for unloading.

[0028] The method in this embodiment optimizes and offloads computing tasks, thereby achieving load balancing of task computing in the Internet of Vehicles and improving the utilization rate of computing resources.

[0029] In step S1, establishing the objective function that minimizes the expected unloading cost includes:

[0030] The objective function for vehicle unloading is defined, and the optimization problem is as follows:

[0031]

[0032] in, x represents the total unloading cost of vehicle i. n This represents the load on server n, i.e., the total latency spent offloading tasks to the selected server for processing; ΔL represents the distance between adjacent RSUs, where n is the current RSU number, and v i Let be the speed of vehicle i, and c represent the observation cost required to observe one RSU.

[0033] Specifically, a network is constructed consisting of I vehicle terminals and N RSUs. N RSUs equipped with edge servers are deployed along the roadside, and each vehicle travels at a speed v. i While driving on the road, a vehicle generates a computational task requiring unloading and begins observing RSUs sequentially. The entire process can be divided into N observations, and the optimal unloading cost for vehicle i at its nth observation is...

[0034]

[0035] in, This refers to the unloading cost incurred by stopping observation at this point and selecting the current server. It is the expected cost of continued observation.

[0036] If vehicle i has not unloaded by the end of the observation period, it can only unload to the last RSU. The optimal unloading cost for vehicle i in the Nth observation period is...

[0037]

[0038] in, The uninstallation cost incurred when the data is unloaded to the Nth server.

[0039] In step S2, the parameter ξ of the objective function is solved using optimal stopping theory. The specific process is as follows:

[0040] In step S2, to select the optimal value, the vehicle needs to unload when the current unloading cost is lower than the expected future unloading cost:

[0041]

[0042] in, x represents the total unloading cost of vehicle i. n This represents the load on server n, i.e., the total latency spent offloading tasks to the selected server for processing; ΔL represents the distance between adjacent RSUs, where n is the current RSU number, and v i Let be the speed of vehicle i, and c represent the observation cost required to observe one RSU.

[0043] Simplifying the above equation, we can see that x n The following conditions must be met:

[0044]

[0045] For simplicity and convenience in the future, a...

[0046]

[0047] At this point, all we need to do is x n and A comparison is sufficient; Substitute to calculate

[0048]

[0049] Here, the random sequence x n Convert to unknown x:

[0050]

[0051] Where f(x) represents the probability density function of variable x, and F(x) represents the cumulative distribution function of variable x.

[0052] In step S3, the reference value is calculated through the above process. Compare with the vehicle's currently observed RSU load. If The optimal strategy at this point is to stop observation and offload the task to the current server; if Continuing to observe is the best course of action at this point.

[0053] Figure 2 This is a cost comparison chart between the proposed algorithm, the random algorithm, and the optimal algorithm. As can be seen from the chart, the method proposed in this embodiment achieves a lower cost compared to the random unloading method. The algorithm proposed in this paper can achieve a cost close to that of the optimal algorithm.

[0054] This embodiment constructs a vehicle-to-everything (V2X) model based on optimal stopping theory. Based on vehicle speed and RSU load, it establishes an objective function to minimize the expected total unloading cost, solves for the optimal computational task unloading method, and utilizes optimal stopping theory to address this problem. It compares the observed current RSU load with a calculated scalar value to determine the optimal unloading time, achieving load balancing of RSUs in the V2X and improving the utilization of computational resources.

[0055] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. All equivalent structural transformations made under the concept of the present invention using the contents of the present invention specification and drawings, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A method for optimizing and unloading computational tasks in a vehicle-to-everything (V2X) network based on optimal stopping theory, characterized in that, The method includes the following steps: S1: Construct a vehicle-to-everything (V2X) model based on optimal stopping theory, and establish an objective function that minimizes the expected total unloading cost based on vehicle speed and RSU load; The objective function for minimizing the expected computational cost includes: The objective function for vehicle unloading is established, and the optimization formula is as follows: ； in, Indicates vehicle Total uninstallation cost Indicates server The load, that is, the total latency spent on offloading tasks to the selected server for processing; Indicates the distance between adjacent RSUs. This is the current RSU number. For vehicles driving speed, This represents the observation cost required to observe one RSU; S2: Solve the objective function using optimal stopping theory to obtain a reference value; S3: Based on the observed current RSU load, compare the current load with the calculated reference value to find the optimal stopping time for unloading.

2. The method for optimizing and offloading computational tasks in vehicle-to-everything (V2X) networks based on optimal stopping theory according to claim 1, characterized in that, The total offloading cost includes the load and observation costs of the RSU.

3. The method for optimizing and offloading computational tasks in vehicle-to-everything (V2X) networks based on optimal stopping theory according to claim 1, characterized in that, vehicle In its first The optimal unloading cost at the time of the next observation is: ； in, This refers to the unloading cost incurred by stopping observation at this point and selecting the current server. It is the expected cost of continued observation.

4. The method for optimizing and offloading computational tasks in vehicle-to-everything (V2X) networks based on optimal stopping theory according to claim 3, characterized in that, If vehicle If the RSU is not uninstalled by the end of the monitoring period, then uninstallation will be performed until the last RSU is reached. The optimal unloading cost for this observation is: ； in, To uninstall to the The cost of unloading each server.

Images