Data Center Computing Power Network Resource Scheduling Method

Abstract

The present invention discloses a method for scheduling computing power network resources in a data center, belonging to the technical field of cloud data processing. It includes obtaining the total number of passenger vehicles in a preset city, dividing the preset city into areas, obtaining the number of passenger vehicles in each divided area at different time periods, where different time periods are distinguished by each hour as a time period; obtaining the travel information requests sent by clients in the preset city area, the information requests including the departure place and the destination, and obtaining the network signal quality data of the preset city area. It also includes obtaining the network signal quality data of preset passenger vehicles in the preset city area; through data analysis and scheduling technology, the present invention can calculate the change of the network signal quality data of the preset passenger vehicles in the preset city area, and can also collect the change of the network signal quality data of the departure place in each travel information request to be received by the preset passenger vehicles in the preset city area, so as to provide predictive analysis for passenger vehicles and improve the operation service efficiency.

Description

Technical Field

[0001] The present invention relates to the field of cloud data processing technology, and in particular to a method for scheduling computing power network resources in a data center. Background Art

[0002] In recent years, the widespread application of cloud computing in the field of information technology has brought new challenges and opportunities to the scheduling and optimization of data center network resources. The research on the scheduling and optimization methods of data center network resources for cloud computing has become a hot topic in the industry and academia. The essence of this research is the service of computing resources that can be freely scheduled on demand. In the future, corporate customers and individual users will not only need networks and clouds, but also need to flexibly schedule computing tasks to the right place. Among them, the Internet of Vehicles industry has a wide range of use for computing network resource scheduling services, because its intelligent driving technology has high requirements for low latency and computing task scheduling. It is necessary to quickly switch computing nodes with the high-speed movement of vehicles, and according to the specific business applications initiated by different vehicles, and then based on the needs of different businesses, uniformly arrange and schedule applications and network capabilities to each computing node, forming a wide-area computing network service chain. In this computing network service chain, there are many beneficiaries, including the rapidly developing same-city taxi-hailing system, which can analyze user needs and the location of passenger drivers in real time through advanced intelligent algorithms to achieve rapid matching. However, for passenger vehicles that constantly shuttle through the city, their passenger vehicle networks sometimes change due to the location of the vehicles, among which network delay is one of the changes. The reasons for this situation include vehicle computer freezes, insufficient network traffic, vehicle network antenna failure, and surrounding interference signals. These problems will lead to unstable network connections for passenger vehicles, resulting in network delays and / or reduced network quality. If this happens, the passenger end will not be able to receive the taxi information request sent by the client in time, thereby increasing the customer's taxi waiting time and reducing the customer's service experience. The existing computing resource scheduling method applied to the same-city taxi system is difficult to calculate the network signal status of the passenger vehicle in time according to its driving route, resulting in difficulty in scheduling resources for subsequent orders according to the orders being executed by the passenger vehicle. This is not only not conducive to improving the operational efficiency of passenger vehicles for travel services, but also easily leads to an increase in invalid orders, which in turn leads to an increase in the driver's complaint rate, which is not conducive to the service improvement of the same-city taxi operation. Summary of the invention

[0003] In view of the above problems existing in the existing cloud data processing technology field, the present invention is proposed.

[0004] Therefore, one of the objectives of the present invention is to provide a data center computing power network resource scheduling method. Through data analysis and scheduling technology, it calculates the change in network signal quality data of preset passenger vehicles in a preset urban area, and then predicts whether the preset passenger vehicles that receive travel information requests can complete travel orders. It can also collect the change in network signal quality data of the departure locations from all travel information requests to be received by the preset passenger vehicles in the preset urban area, calculate its change pattern, and then provide predictive analysis for the passenger vehicles, enabling them to make order-taking decisions faster and improving the operation service efficiency.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] A data center computing power network resource scheduling method, comprising the following steps:

[0007] Obtain the total number of passenger vehicles in a preset city, divide the preset city into areas, and obtain the number of passenger vehicles in each divided area at different time periods. The different time periods are distinguished by each hour as a time period;

[0008] Obtain travel information requests sent by the client in the preset urban area. The information requests include the departure location and the destination, and obtain the network signal quality data of the preset urban area. It also includes obtaining the network signal quality data of the preset passenger vehicles in the preset urban area;

[0009] Collect the movement data of the preset passenger vehicles in the preset urban area, analyze their real-time driving routes based on the movement data of the preset passenger vehicles, obtain the change in network signal quality data based on the analyzed real-time driving routes, and classify the change in network signal quality data;

[0010] Preset a safety threshold based on the network signal quality that can receive travel information requests sent by the client in real time. When the network signal quality of the preset passenger vehicle is lower than the safety threshold, it is determined that the preset passenger vehicle cannot receive travel information requests sent by the client in a timely manner, and a low-quality network signal warning is issued. Otherwise, no determination is made;

[0011] When it is determined that the preset passenger vehicle cannot receive travel information requests sent by the client in a timely manner, obtain other passenger vehicles that are not in the order-taking state around the preset passenger vehicle, distinguish the passenger vehicles, and at the same time obtain the network signal quality of the passenger vehicles and conduct a network signal quality comparison.

[0012] As a preferred embodiment of the present invention, the method includes: obtaining other passenger vehicles around the preset passenger vehicle that are not in the order-taking state, where the other passenger vehicles include passenger vehicles within a range of 1 to 3 kilometers from the preset passenger vehicle, and differentiating the passenger vehicles in two ways. One of the ways includes: dividing the passenger vehicles into θ1, θ2,..., θ n , where n represents the nth passenger vehicle. When it is determined that the preset passenger vehicle cannot receive the travel information request sent by the client in a timely manner, the passenger vehicle closest to the client is preferentially recommended to the client who sent the travel information request.

[0013] As a preferred embodiment of the present invention, the other way to differentiate the passenger vehicles includes sorting the network signal quality of the passenger vehicles in descending order based on the distance from the preset passenger vehicle. When it is determined that the preset passenger vehicle cannot receive the travel information request sent by the client in a timely manner, the passenger vehicle with the highest network signal quality strength is preferentially recommended to the client who sent the travel information request.

[0014] As a preferred embodiment of the present invention, the method of grading the change in network signal quality data includes grading according to the collected signal strength data, as follows:

[0015] dBm signal strength numerical range Corresponding signal quality -40～-60 Very good -60～-70 Good -70～-80 Average -80～-90 Slightly weak -90～-100 Weak -100～-110 Poor Below -110 Very poor

[0016] When the passenger vehicle with the highest network signal quality strength travels towards the client, calculate the time required for the passenger vehicle to reach the location of the client, and collect the network signal quality of the passenger vehicle every 2 to 4 seconds within this time. When the collected network signal quality is lower than the "good" level, locate the passenger vehicle to obtain its location data, and at the same time, based on the location data, obtain other passenger vehicles that are not in the order-taking state and are closest to the passenger vehicle, and designate the passenger vehicle as a replacement passenger vehicle, and recommend the replacement passenger vehicle to the client to complete the travel order.

[0017] As a preferred embodiment of the present invention, when collecting the network signal quality of the passenger vehicle every 2 to 4 seconds, obtain the change rule of the network signal quality of the passenger vehicle changing from "very good" level to lower than the "good" level, collect the median data of this change process in the change rule, and preset a critical threshold based on the median data. When calculating the time required for any passenger vehicle to reach the location of the client in the future period, if the change in the network signal quality of the passenger vehicle exceeds the critical threshold, it is determined that the network signal quality of the passenger vehicle will be lower than the "good" level; otherwise, it is not determined.

[0018] As a preferred embodiment of the present invention, it is as follows: In the preset urban area, count each travel information request to be received by the preset passenger vehicle, obtain the departure location from each travel information request, and at the same time analyze the network signal quality of the departure location. If the network signal quality of a certain departure location is lower than the level of good, it is determined that when the preset passenger vehicle travels towards the departure location, its network signal quality will change to the level of general and / or slightly weak, and cancel pushing the corresponding travel information request to the passenger vehicle; otherwise, it is not determined.

[0019] As a preferred embodiment of the present invention, it is as follows: When the network signal quality of a certain departure location is lower than the level of good, analyze the change characteristics of the network signal quality within 2 to 3 months at the departure location, and generate a data set. Divide the test set, validation set, and training set of the network signal quality change in the data set; at the same time, collect the network signal quality data that is closest to the level of general within the analyzed time period, and based on the network signal quality data, collect the tenth network signal quality data closest to this data. Preset a risk threshold based on the network signal quality data. When the network signal quality data at the departure location changes beyond the risk threshold in the future period, it is determined that the network signal quality at the departure location will be lower than the level of good, and a warning notice is sent to the passenger vehicle outside the departure location; otherwise, it is not determined.

[0020] As a preferred embodiment of the present invention, it is as follows: Divide the tenth network signal quality data collected within the time period into several evaluation indicators, count the network signal strength represented by the tenth network signal quality data within the time period, assign different network signal strengths to different evaluation index data, perform normalization processing on the data, and calculate the weight of each evaluation index.

[0021] A terminal includes a processor, an input interface, an output interface, and a memory. Among them, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 8.

[0022] A computer-readable storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 8.

[0023] Beneficial effects:

[0024] Through data analysis and scheduling technology, the present invention calculates the change in network signal quality data of preset passenger vehicles in a preset urban area, and then predicts whether the preset passenger vehicle that receives a travel information request can complete a travel order. Moreover, based on the calculated change result of the network signal quality data of the preset passenger vehicle, the network signal quality intensity of other surrounding passenger vehicles can be analyzed, so as to recommend a preferred passenger vehicle to the customer who sends a travel information request to complete the travel service. On this basis, the change in network signal quality data of the departure location can also be collected from all travel information requests to be received by the preset passenger vehicle in the preset urban area, and its change rule can be calculated, so as to provide predictive analysis for the passenger vehicle, enabling it to make a pick-up decision faster and improving the operation service efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. Among them:

[0026] Figure 1 It is a schematic flowchart of the method of the embodiment of the present invention;

[0027] Figure 2 It is a schematic structural diagram of the process of the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the embodiments of the present invention with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the described embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present invention.

[0029] Since the existing computing power resource scheduling method applied to the same-city taxi system is difficult to calculate the network signal situation of a passenger vehicle in a timely manner according to its driving route, it is difficult to perform resource scheduling for subsequent pick-ups based on the order situation that the passenger vehicle is currently executing. This not only is not conducive to improving the operation efficiency of the passenger vehicle for travel services, but also easily leads to an increase in invalid orders, and then leads to an increase in the driver's complaint rate, which is not conducive to the improvement of the service of the same-city taxi operation.

[0030] Based on this, the present invention proposes a data center computing power network resource scheduling method. Through data analysis and scheduling technology, it calculates the change in network signal quality data of preset passenger vehicles in a preset urban area, and then predicts whether the preset passenger vehicles that receive travel information requests can complete travel orders. It can also collect the change in network signal quality data of the departure locations from all travel information requests to be received by the preset passenger vehicles in the preset urban area, and calculate its change pattern, so as to provide predictive analysis for passenger vehicles, enabling them to make order-taking decisions faster and improving the operation service efficiency.

[0031] The following further specifically describes this solution through embodiments in combination with the accompanying drawings.

[0032] Refer to Figures 1 to 2 , which is an embodiment of the present invention. This embodiment provides a data center computing power network resource scheduling method, including the following steps:

[0033] S10: Obtain the total number of passenger vehicles in the preset city, divide the preset city into areas, and obtain the number of passenger vehicles in each divided area at different time periods. The different time periods are distinguished by each hour as a time period;

[0034] S20: Obtain the travel information requests sent by the client in the preset urban area. The information requests include the departure place and the destination, and obtain the network signal quality data of the preset urban area. It also includes obtaining the network signal quality data of the preset passenger vehicles in the preset urban area;

[0035] S30: Collect the movement data of the preset passenger vehicles in the preset urban area, analyze their real-time driving routes based on the movement data of the preset passenger vehicles, obtain the change in network signal quality data based on the analyzed real-time driving routes, and classify the change in network signal quality data;

[0036] Specifically in this embodiment, classifying the change in network signal quality data includes classifying according to the collected signal strength data, as specifically shown below:

[0037] dBm signal strength numerical range Corresponding signal quality -40～-60 Very good -60～-70 Good -70～-80 Average -80～-90 Slightly weak -90～-100 Weak -100～-110 Poor Below -110 Very poor

[0038] When the passenger vehicle with the highest network signal quality strength travels towards the customer, calculate the time required for the passenger vehicle to reach the location where the customer is, and collect the network signal quality of the passenger vehicle at intervals of every 2 - 4 seconds within the time. When the collected network signal quality is lower than the level of good, locate the passenger vehicle to obtain its location data. At the same time, based on the location data, obtain the other passenger vehicles that are not in the order-taking state and are closest to the passenger vehicle, and designate the passenger vehicle as a substitute passenger vehicle, and recommend the substitute passenger vehicle to the customer to complete the travel order;

[0039] On the basis described above, in this embodiment, when collecting the network signal quality of passenger vehicles in a period of every 2 to 4 seconds, the change rule of the network signal quality of passenger vehicles changing from very good level to lower than good level is obtained. The median data of this change process is collected from the change rule, and a critical threshold is preset based on the median data. When calculating the time required for any passenger vehicle to reach the location of the customer in a future period, if the change in the network signal quality of the passenger vehicle exceeds the critical threshold, it is determined that the network signal quality of the passenger vehicle will be lower than the good level; otherwise, it is not determined.

[0040] Meanwhile, in this embodiment, the travel information requests to be received by each preset passenger vehicle are counted in a preset urban area, the departure location is obtained from each travel information request, and the network signal quality of the departure location is analyzed at the same time. If the network signal quality of a certain departure location is lower than the good level, it is determined that when the preset passenger vehicle travels towards the departure location, its network signal quality will change to a general and / or slightly weak level, and the corresponding travel information request is cancelled from being pushed to the passenger vehicle; otherwise, it is not determined.

[0041] It should be emphasized in this embodiment that when the network signal quality of a certain departure location is lower than the good level, the change characteristics of the network signal quality within 2 to 3 months of the departure location are analyzed, and a data set is generated. The test set, validation set, and training set of the network signal quality change are divided in the data set. At the same time, the network signal quality data closest to the general level in the analyzed time period is collected, and the tenth network signal quality data closest to this data is collected based on the network signal quality data. A risk threshold is preset based on the network signal quality data. When the change in the network signal quality data of the departure location in a future period exceeds the risk threshold, it is determined that the network signal quality of the departure location will be lower than the good level, and a warning notice is sent to the passenger vehicles outside the departure location; otherwise, it is not determined.

[0042] Further, the tenth network signal quality data collected within the time period is divided into several evaluation indicators, the network signal strength represented by the tenth network signal quality data within the time period is counted, different network signal strengths are given different evaluation index data, the data is normalized, and the weight of each evaluation index is calculated.

[0043] S40: A safety threshold is preset based on the network signal quality that can receive the travel information request sent by the client in real time. When the network signal quality of the preset passenger vehicle is lower than the safety threshold, it is determined that the preset passenger vehicle cannot receive the travel information request sent by the client in time, and a low-quality network signal warning is issued; otherwise, it is not determined.

[0044] S50: When it is determined that the preset passenger vehicle cannot receive the travel information request sent by the client in time, obtain other passenger vehicles in the vicinity of the preset passenger vehicle that are not in the order-taking state, distinguish the passenger vehicles, and at the same time obtain the network signal quality of the passenger vehicles and perform a comparison of the network signal quality;

[0045] It should be noted in this embodiment that other passenger vehicles include passenger vehicles within a range of 1 to 3 kilometers from the preset passenger vehicle. There are two ways to distinguish the passenger vehicles. One way includes: dividing the passenger vehicles into θ1, θ2,..., θ according to the distance from the preset passenger vehicle. n , where n represents the nth passenger vehicle. When it is determined that the preset passenger vehicle cannot receive the travel information request sent by the client in time, the passenger vehicle closest to the client who sent the travel information request will be recommended first;

[0046] On the above basis, another way to distinguish the passenger vehicles in this embodiment includes sorting the network signal quality of the passenger vehicles in order of strength based on the distance from the preset passenger vehicle. When it is determined that the preset passenger vehicle cannot receive the travel information request sent by the client in time, the passenger vehicle with the highest network signal quality strength will be recommended first to the client who sent the travel information request.

[0047] A terminal includes a processor, an input interface, an output interface, and a memory. Among them, the memory is used to store a computer program, and the computer program includes program instructions. The processor is configured to call the program instructions to execute the method according to any one of claims 1 to 8.

[0048] A computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 8.

[0049] In summary, through data analysis and scheduling technology, the present invention calculates the change in the network signal quality data of the preset passenger vehicle in the preset urban area, and then predicts whether the preset passenger vehicle that receives the travel information request can complete the travel order. Moreover, based on the calculated change result of the network signal quality data of the preset passenger vehicle, the network signal quality strength of other passenger vehicles around it can be analyzed, and then the priority passenger vehicle can be recommended to the client who sent the travel information request to complete the travel service. On this basis, the change in the network signal quality data of the departure location can also be collected from all the travel information requests to be received by the preset passenger vehicle in the preset urban area, and its change law can be calculated, so as to provide predictive analysis for the passenger vehicle, enabling it to make an order-taking decision faster and improving the operation service efficiency.

[0050] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered by the scope of the claims of the present invention.

Claims

1. A method for scheduling computing power network resources in a data center, characterized in that, It includes the following steps: Obtain the total number of passenger vehicles in a preset city, divide the preset city into areas, and obtain the number of passenger vehicles in each divided area at different times. The different times are distinguished by each hour as a time period; Obtain the travel information requests sent by the client in the areas of the preset city. The information requests include the departure place and the destination, and obtain the network signal quality data of the areas of the preset city. It also includes obtaining the network signal quality data of the preset passenger vehicles in the areas of the preset city; Collect the movement data of the preset passenger vehicles in the areas of the preset city, analyze their real-time driving routes based on the movement data of the preset passenger vehicles, obtain the change of the network signal quality data based on the analyzed real-time driving routes, and classify the change of the network signal quality data; Preset a safety threshold based on the network signal quality that can receive the travel information requests sent by the client in real time. When the network signal quality of the preset passenger vehicle is lower than the safety threshold, it is determined that the preset passenger vehicle cannot receive the travel information requests sent by the client in time, and a low-quality network signal warning is issued. Otherwise, it is not determined; When it is determined that the preset passenger vehicle cannot receive the travel information requests sent by the client in time, obtain other passenger vehicles that are not in the order-taking state around the preset passenger vehicle, distinguish the passenger vehicles, and at the same time obtain the network signal quality of the passenger vehicles and conduct a comparison of the network signal quality; 2. The data center computing power network resource scheduling method according to claim 1, wherein Obtain other passenger vehicles around the preset passenger vehicle that are not in the order-taking state. The other passenger vehicles include passenger vehicles within a range of 1 to 3 kilometers from the preset passenger vehicle, and the passenger vehicles are distinguished in two ways. One of the ways includes: dividing the passenger vehicles into groups according to the distance from the preset passenger vehicle, , where, represents the th passenger vehicle. When it is determined that the preset passenger vehicle cannot receive the travel information request sent by the client in time, the passenger vehicle closest to the client who sent the travel information request is preferentially recommended to the client.

3. The data center computing power network resource scheduling method according to claim 2, wherein Another way to distinguish the passenger vehicles includes sorting the network signal quality of the passenger vehicles in order of strength based on the distance from the preset passenger vehicle. When it is determined that the preset passenger vehicle cannot receive the travel information requests sent by the client in time, the passenger vehicle with the highest network signal quality strength is preferentially recommended to the customer who sent the travel information request; 4. The data center computing power network resource scheduling method according to claim 3, wherein Classifying the change of the network signal quality data includes classifying it according to the collected signal strength data, specifically as follows: When the passenger vehicle with the highest network signal quality strength travels towards the customer, calculate the time required for the passenger vehicle to reach the location where the customer is, and collect the network signal quality of the passenger vehicle at intervals of every 2 - 4 seconds within this time. When the collected network signal quality is lower than the good level, locate the passenger vehicle, obtain its location data, and at the same time, based on the location data, obtain other passenger vehicles that are not in the order-taking state and are closest to the passenger vehicle, and designate the passenger vehicle as a substitute passenger vehicle, and recommend the substitute passenger vehicle to the customer to complete the travel order.

5. The data center computing power network resource scheduling method according to claim 4, wherein When collecting the network signal quality of the passenger vehicle in a period of every 2 to 4 seconds, obtain the change rule of the network signal quality of the passenger vehicle changing from a very good level to a level lower than the good level. Collect the median data of this change process in the change rule, and preset a critical threshold based on the median data. When calculating the time required for any passenger vehicle to reach the location of the customer in a future period, if the change in the network signal quality of the passenger vehicle exceeds the critical threshold, it is determined that the network signal quality of the passenger vehicle will be lower than the good level; otherwise, it is not determined.

6. The data center computing power network resource scheduling method according to claim 5, wherein, Statistically analyze each pending travel information request of the preset passenger vehicle in the area of the preset city, obtain the departure location in each travel information request, and at the same time analyze the network signal quality of the departure location. If the network signal quality of a certain departure location is lower than the good level, it is determined that when the preset passenger vehicle travels to the departure location, its network signal quality will change to a general and / or slightly weak level, and cancel the push of the corresponding travel information request to the passenger vehicle; otherwise, it is not determined.

7. The data center computing power network resource scheduling method according to claim 6, wherein, When the network signal quality of a certain departure location is lower than the good level, analyze the change characteristics of the network signal quality within 2 to 3 months of the departure location and generate a data set. Divide the test set, validation set, and training set of the network signal quality change in the data set; at the same time, collect the network signal quality data that is closest to the general level in the analyzed time period, and based on the network signal quality data, collect the tenth network signal quality data closest to this data. Preset a risk threshold based on the network signal quality data. When the change in the network signal quality data of the departure location in a future period exceeds the risk threshold, it is determined that the network signal quality of the departure location will be lower than the good level, and an early warning notice is sent to the passenger vehicles outside the departure location; otherwise, it is not determined.

8. The data center computing power network resource scheduling method according to claim 7, wherein, Divide the tenth network signal quality data collected in the time period into several evaluation indicators, statistically analyze the network signal strength represented by the tenth network signal quality data in the time period, assign different network signal strengths to different evaluation index data, perform normalization processing on the data, and calculate the weight of each evaluation index.

9. A terminal, characterized in that, It includes a processor, an input interface, an output interface, and a memory. Among them, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by the processor, the processor is caused to execute the method according to any one of claims 1 to 8.

Images