Dynamic quantity management method based on cloud computing network elements

Abstract

The invention relates to a number dynamic management method based on a cloud computing network element. The method comprises the following steps: intelligently predicting the number of tourists in a set urban landscape area in a future night time interval at a cloud computing network element end by adopting an AI number prediction model corresponding to the set urban landscape area; and determining the ratio of the number of turned-on street lamps of the set urban landscape area in the future night time interval at the cloud computing network element end according to the intelligent prediction result. According to the invention, the AI quantity prediction model aiming at the set urban landscape area can be adopted at the cloud computing network element end to intelligently predict the number of tourists in the set urban landscape area in the future night time interval according to the number of passing tourists in the set urban landscape area and the associated information of various landscapes; and the number of the street lamps which are turned on uniformly at intervals in the future night time interval in the urban landscape area is dynamically regulated and set, so that dynamic management of each urban landscape area is realized at the cloud computing network element end.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of cloud computing, in particular to a dynamic management method based on the number of cloud computing network elements. BACKGROUND

[0002] The resource data on the cloud computing system is very large, and the resource information updates quickly. To obtain accurate and reliable dynamic information, an effective approach is needed to ensure the speed of information. The cloud computing system can effectively deploy dynamic information and has a resource monitoring function, which is conducive to managing the load and use of resources. As the "blood" of resource management, resource monitoring plays a key role in the overall system performance. If the system resource supervision is not in place and the information lacks reliability, other subsystems will reference incorrect information, which will inevitably have an adverse impact on the allocation of system resources. In the resource monitoring process, configuration and supervision activities can be carried out by deploying an agent program on each cloud computing server, such as connecting each cloud resource server through a monitoring server, and then sending the resource usage to the database in a periodic unit. The monitoring server analyzes all resources by synthesizing the effective information in the database to evaluate the availability of resources and maximize the effectiveness of resource information.

[0003] The cloud computing system monitors and controls the system operation and management of various application fields. For example, it is desirable to use the advantages of the cloud computing system in monitoring and control to perform intelligent dynamic management of each city landscape area to ensure the normal operation of the city landscape area while meeting the demand for energy saving. Specifically, it is desirable to dynamically regulate the number of evenly spaced streetlights according to the number of tourists in the future night time interval of each city landscape area. However, the difficulty of the present technical solution lies in the accurate and stable acquisition of the number of tourists in the future night time interval of each city landscape area. SUMMARY

[0004] To solve the technical problems in the related field, the present application provides a dynamic management method based on the number of cloud computing network elements. By using an AI number prediction model for a set city landscape area on the cloud computing network element side, the number of tourists in the future night time interval of the set city landscape area is intelligently predicted based on the past number of tourists and various landscape-related information of the set city landscape area. Then, the number of evenly spaced streetlights in the future night time interval of the set city landscape area is dynamically regulated according to the intelligently predicted number of tourists in the future night time interval of the set city landscape area. Thus, the dynamic management of each city landscape area is realized on the cloud computing network element side, taking into account the operation demand of the scenic area and the energy saving and emission reduction demand.

[0005] According to the present application, a dynamic management method based on the number of cloud computing network elements is provided, which comprises: Capture the various landscape-related information of the set urban landscape area and the respective number of tourists corresponding to each of the future night time intervals before the future night time interval at the cloud computing network element end of the set urban landscape area, and the various landscape-related information of the set urban landscape area is the area of the set urban landscape area, the peak number of tourists, the number of surrounding other landscape areas and the number of surrounding residents; At the cloud computing network element end, the AI quantity prediction model corresponding to the set urban landscape area is used to intelligently predict the number of tourists in the set urban landscape area in the future night time interval according to the various landscape-related information of the set urban landscape area, the respective number of tourists corresponding to each of the future night time intervals before the future night time interval, the interval length of each night time interval and the total number of residents in the set city; At the cloud computing network element end, the AI quantity prediction model corresponding to the set urban landscape area is used to intelligently predict the number of tourists in the set urban landscape area in the future night time interval according to the various landscape-related information of the set urban landscape area, the respective number of tourists corresponding to each of the future night time intervals before the future night time interval, the interval length of each night time interval and the total number of residents in the set city; Wherein, the AI quantity prediction model corresponding to the set urban landscape area is a radial basis neural network after multiple learning, and the number of times of learning of the radial basis neural network is positively correlated with the area of the set urban landscape area, and the number of night time intervals before the future night time interval is proportional to the number of surrounding other landscape areas of the set urban landscape area.

[0006] Therefore, the present application has at least the following three important invention points: Invention point A: at the cloud computing network element end, the AI quantity prediction model corresponding to the set urban landscape area is used to intelligently predict the number of tourists in the set urban landscape area in the future night time interval according to the various landscape-related information of the set urban landscape area, the respective number of tourists corresponding to each of the future night time intervals before the future night time interval, the interval length of each night time interval and the total number of residents in the set city, and the number of street lamps turned on in the set urban landscape area in the future night time interval is dynamically determined based on the intelligently predicted number of tourists, thereby improving the dynamic management capability of the set urban landscape area; Invention point B: the AI quantity prediction model corresponding to the set urban landscape area is introduced to perform intelligent prediction of the number of tourists in the set urban landscape area in the future night time interval, the AI quantity prediction model corresponding to the set urban landscape area is a radial basis neural network after multiple learning, and the number of times of learning of the radial basis neural network is positively correlated with the area of the set urban landscape area, and the number of night time intervals before the future night time interval is proportional to the number of surrounding other landscape areas of the set urban landscape area, thereby designing different AI quantity prediction models for different urban landscape areas; The application point C: introducing a plurality of basic information including the landscape-related information of the city landscape area, the number of tourists corresponding to each of the night time intervals before the future night time interval of the city landscape area, the interval length of each night time interval, and the total number of residents of the city, to participate in the intelligent prediction of the number of tourists in the future night time interval of the city landscape area. The landscape-related information of the city landscape area is the area of the city landscape area, the peak number of tourists, the number of surrounding other landscape areas, and the number of surrounding residents. The sufficient and comprehensive selection of the above basic information ensures the stability and effectiveness of the intelligent prediction result. DETAILED DESCRIPTION

[0007] The embodiment of the cloud computing network element quantity dynamic management method of the application will be described in detail below.

[0008] Embodiment A of the application The cloud computing network element quantity dynamic management method according to the embodiment A of the application specifically includes the following steps: Capture the landscape-related information of the city landscape area and the number of tourists corresponding to each of the night time intervals before the future night time interval of the city landscape area at the cloud computing network element end. The landscape-related information of the city landscape area is the area of the city landscape area, the peak number of tourists, the number of surrounding other landscape areas, and the number of surrounding residents. Specifically, a plurality of different cloud computing nodes are used at the cloud computing network element end to capture the landscape-related information of the city landscape area and the number of tourists corresponding to each of the night time intervals before the future night time interval of the city landscape area. An AI number prediction model corresponding to the city landscape area is used at the cloud computing network element end to intelligently predict the number of tourists in the future night time interval of the city landscape area according to the landscape-related information of the city landscape area, the number of tourists corresponding to each of the night time intervals before the future night time interval of the city landscape area, the interval length of each night time interval, and the total number of residents of the city. The number of open street lamps in the future night time interval of the city landscape area is determined according to the number of tourists in the future night time interval of the city landscape area at the cloud computing network element end. Specifically, the number of open street lamps in the future night time interval of the city landscape area is determined according to the number of tourists in the future night time interval of the city landscape area at the cloud computing network element end, which includes: when a certain time interval is within the night operating time segment of the city landscape area, it is judged that the certain time interval belongs to the night time interval. The AI quantity prediction model corresponding to the city landscape area is a radial basis neural network after multiple learning, and the number of times of learning of the radial basis neural network is positively correlated with the area of the city landscape area, and the number of night time intervals before the future night time interval is positively correlated with the number of other landscape areas around the city landscape area. The number of street lamps turned on in the future night time interval is determined according to the number of tourists in the future night time interval of the city landscape area at the cloud computing network element, and the number of street lamps turned on in the future night time interval of the city landscape area is monotonically positively correlated with the number of tourists in the future night time interval of the city landscape area. The number of street lamps turned on in the future night time interval of the city landscape area is determined according to the number of tourists in the future night time interval of the city landscape area at the cloud computing network element, and the number of street lamps turned on in the future night time interval of the city landscape area is the ratio of the number of street lamps turned on in the future night time interval of the city landscape area to the total number of street lamps in the city landscape area.

[0009] Embodiment B of the present application Compared with embodiment A of the present application, the number dynamic management method based on the cloud computing network element according to embodiment B of the present application further comprises the following steps: The product of the number of street lamps turned on in the future night time interval of the city landscape area and the total number of street lamps in the city landscape area is taken as the number of street lamps turned on in the future night time interval of the city landscape area at the cloud computing network element to perform the opening control of the plurality of street lamps uniformly spaced in the future night time interval. The product of the number of street lamps turned on in the future night time interval of the city landscape area and the total number of street lamps in the city landscape area is taken as the number of street lamps turned on in the future night time interval of the city landscape area at the cloud computing network element to perform the opening control of the plurality of street lamps uniformly spaced in the future night time interval, and the number of the plurality of street lamps uniformly spaced is equal to the number of street lamps turned on in the future night time interval of the city landscape area.

[0010] Embodiment C of the present application Compared with embodiment A of the present application, the number dynamic management method based on the cloud computing network element according to embodiment C of the present application further comprises the following steps: Receiving the ratio of the number of street lamps turned on in the future night time interval in the set city landscape area, and wirelessly transmitting the ratio of the number of street lamps turned on in the future night time interval in the set city landscape area to the handheld terminal of the field staff in the set city landscape area through the mobile communication network; Specifically, receiving the ratio of the number of street lamps turned on in the future night time interval in the set city landscape area, and wirelessly transmitting the ratio of the number of street lamps turned on in the future night time interval in the set city landscape area to the handheld terminal of the field staff in the set city landscape area through the mobile communication network includes that the mobile communication network is based on a time division duplex communication mechanism.

[0011] Next, the specific steps of the cloud computing network element quantity dynamic management method of the application will be further described.

[0012] In the cloud computing network element quantity dynamic management method according to any embodiment of the application: Capturing the various landscape-related information of the set city landscape area and capturing the various tourist numbers corresponding to each night time interval before the future night time interval at the cloud computing network element, the various landscape-related information of the set city landscape area being the area of the set city landscape area, the peak tourist number, the number of surrounding other landscape areas, and the number of surrounding residents, including: the number of surrounding other landscape areas of the set city landscape area being the number of other landscape areas covered by a circle with the center of the area of the set city landscape area as the center and a set radius value as the radius of the circle; Specifically, the number of surrounding other landscape areas of the set city landscape area being the number of other landscape areas covered by a circle with the center of the area of the set city landscape area as the center and a set radius value as the radius of the circle includes that the set radius value is a fixed value, and its value range is between 10 kilometers and 50 kilometers; Wherein, the AI quantity prediction model corresponding to the set city landscape area is a radial basis neural network after multiple learning, and the number of times of learning of the radial basis neural network is positively correlated with the area of the set city landscape area, and the number of night time intervals of each night time interval before the future night time interval is proportional to the number of surrounding other landscape areas of the set city landscape area, including: using a numerical mapping formula to represent the numerical mapping relationship between the number of times of learning of the radial basis neural network and the area of the set city landscape area positively correlated; The numerical mapping formula is used to represent the numerical mapping relationship between the number of radial basis neural network learning and the area of the set city landscape area positively correlated, including: in the numerical mapping formula, the area of the set city landscape area is the input content of the numerical mapping formula, and the number of radial basis neural network learning positively correlated with the area of the set city landscape area is the output content of the numerical mapping formula. In the cloud computing network element, the landscape correlation information of the set city landscape area and the number of tourists corresponding to each night time interval before the future night time interval are captured, and the landscape correlation information of the set city landscape area includes the area of the set city landscape area, the peak number of tourists, the number of surrounding other landscape areas, and the number of surrounding residents.

[0013] In the cloud computing network element-based quantity dynamic management method according to any embodiment of the present application: In the cloud computing network element, the landscape correlation information of the set city landscape area and the number of tourists corresponding to each night time interval before the future night time interval are captured, and the landscape correlation information of the set city landscape area includes the area of the set city landscape area, the peak number of tourists, the number of surrounding other landscape areas, and the number of surrounding residents. In the cloud computing network element, the landscape correlation information of the set city landscape area and the number of tourists corresponding to each night time interval before the future night time interval are captured, and the landscape correlation information of the set city landscape area includes the area of the set city landscape area, the peak number of tourists, the number of surrounding other landscape areas, and the number of surrounding residents.

[0014] In addition, in the cloud computing network element quantity dynamic management method, the landscape correlation information of the set city landscape area and the tourist quantity corresponding to each night time interval before the future night time interval of the set city landscape area are captured at the cloud computing network element end, and the landscape correlation information of the set city landscape area includes the area of the set city landscape area, the peak tourist quantity, the number of surrounding other landscape areas and the number of surrounding residents.

[0015] The cloud computing network element quantity dynamic management method of the present application can solve the technical problem that the cloud computing system in the prior art is difficult to realize dynamic management of each city landscape area by using the AI quantity prediction model for the set city landscape area to intelligently predict the tourist quantity of the set city landscape area in the future night time interval according to the past tourist quantity and the landscape correlation information of the set city landscape area, and then dynamically regulating the number of street lamps of the set city landscape area that are turned on at uniform intervals in the future night time interval.

[0016] Although the present application has been described with reference to the preferred embodiments, it will be apparent to those skilled in the art that various changes and modifications can be made to the present application without departing from the spirit and scope thereof. Therefore, various changes, modifications and equivalents of the present application are covered by the contents of the appended claims and their equivalents.

Claims

1. A method for dynamically managing the number of cloud computing network elements, characterized in that, The method comprises: capturing, at the cloud computing network element, landscape-related information of a set urban landscape area and capturing the number of tourists corresponding to each of the future night time intervals before the future night time interval at the cloud computing network element, wherein the landscape-related information of the set urban landscape area comprises the area size of the set urban landscape area, the peak number of tourists, the number of surrounding other landscape areas, and the number of surrounding residents; using an AI quantity prediction model corresponding to the set urban landscape area to intelligently predict the number of tourists in the future night time interval of the set urban landscape area according to the landscape-related information of the set urban landscape area, the number of tourists corresponding to each of the future night time intervals before the future night time interval, the interval length of each night time interval, and the total number of residents in the set city at the cloud computing network element; determining the proportion of the number of street lamps turned on in the future night time interval of the set urban landscape area according to the number of tourists in the future night time interval of the set urban landscape area at the cloud computing network element; wherein the AI quantity prediction model corresponding to the set urban landscape area is a radial basis neural network after multiple learning, and the number of times of learning of the radial basis neural network is positively correlated with the area size of the set urban landscape area, and the number of night time intervals before the future night time interval is proportional to the number of surrounding other landscape areas of the set urban landscape area.

2. The quantity dynamic management method based on the cloud computing network element according to claim 1, wherein: determining the proportion of the number of street lamps turned on in the future night time interval of the set urban landscape area according to the number of tourists in the future night time interval of the set urban landscape area at the cloud computing network element comprises: determining that the proportion of the number of street lamps turned on in the future night time interval of the set urban landscape area is monotonically positively correlated with the number of tourists in the future night time interval of the set urban landscape area; wherein determining the proportion of the number of street lamps turned on in the future night time interval of the set urban landscape area according to the number of tourists in the future night time interval of the set urban landscape area at the cloud computing network element further comprises: determining that the proportion of the number of street lamps turned on in the future night time interval of the set urban landscape area is the ratio of the number of street lamps turned on in the future night time interval of the set urban landscape area to the total number of street lamps in the set urban landscape area.

3. The method for dynamically managing the number of cloud computing network elements according to claim 2, wherein, The method further comprises: multiplying the proportion of the number of street lamps turned on in the future night time interval of the set urban landscape area and the total number of street lamps in the set urban landscape area to obtain the number of street lamps turned on in the future night time interval of the set urban landscape area for performing the on-off control of the plurality of street lamps uniformly spaced in the future night time interval at the cloud computing network element. The product of the set city landscape area in the future night time interval The number of open road lamps accounts for the total number of road lamps in the set city landscape area is taken as the number of open road lamps in the set city landscape area in the future night time interval to perform the opening control of the plurality of evenly spaced road lamps in the future night time interval, including: the number of evenly spaced road lamps is equal to the number of open road lamps in the set city landscape area in the future night time interval.

4. The method for dynamically managing the number of cloud computing network elements according to claim 2, wherein, The method further comprises: Receiving the number of open road lamps in the set city landscape area in the future night time interval accounts for, and transmitting the number of open road lamps in the set city landscape area in the future night time interval accounts for to the handheld terminal of the field staff of the set city landscape area through the mobile communication network.

5. The number dynamic management method based on the cloud computing network element according to any one of claims 2-4, characterized in that: Capturing each item of landscape-related information of the set city landscape area and capturing each tourist number corresponding to each night time interval before the future night time interval at the cloud computing network element, each item of landscape-related information of the set city landscape area is the area of the set city landscape area, the peak number of tourists, the number of surrounding other landscape areas, and the number of surrounding residents, including: the number of surrounding other landscape areas of the set city landscape area is the number of other landscape areas covered by a circle with the area center of the set city landscape area as the center and the set radius value as the radius.

6. The number dynamic management method based on the cloud computing network element according to claim 5, characterized in that: The AI number prediction model corresponding to the set city landscape area is a radial basis neural network after multiple learning, and the number of times of learning of the radial basis neural network is positively correlated with the area of the set city landscape area, and the number of night time intervals before the future night time interval is positively correlated with the number of surrounding other landscape areas of the set city landscape area, including: a numerical mapping formula is used to represent the numerical mapping relationship between the number of times of learning of the radial basis neural network and the area of the set city landscape area positively correlated; Wherein, the numerical mapping formula is used to represent the numerical mapping relationship between the number of times of learning of the radial basis neural network and the area of the set city landscape area positively correlated, including: in the numerical mapping formula, the area of the set city landscape area is the input content of the numerical mapping formula, and the number of times of learning of the radial basis neural network positively correlated with the area of the set city landscape area is the output content of the numerical mapping formula.

7. The number dynamic management method based on the cloud computing network element according to claim 5, characterized in that: Capture the various landscape-related information of the set urban landscape area and the respective number of tourists corresponding to each of the future night time intervals before the future night time interval at the cloud computing network element end. The various landscape-related information of the set urban landscape area is the area of the set urban landscape area, the peak number of tourists, the number of surrounding other landscape areas, and the number of surrounding residents. The future night time interval before each of the night time intervals and the future night time interval form a complete night time section, and the interval length of each night time interval is the same.

8. The cloud computing network element-based dynamic management method according to any one of claims 2-4, characterized in that: Intelligently predict the number of tourists in the set urban landscape area in the future night time interval by using the AI quantity prediction model corresponding to the set urban landscape area according to the various landscape-related information of the set urban landscape area, the respective number of tourists corresponding to each of the future night time intervals before the future night time interval, the interval length of each night time interval, and the total number of residents in the set city at the cloud computing network element end.

9. The cloud computing network element-based dynamic management method according to claim 8, characterized in that: Intelligently predict the number of tourists in the set urban landscape area in the future night time interval by using the AI quantity prediction model corresponding to the set urban landscape area according to the various landscape-related information of the set urban landscape area, the respective number of tourists corresponding to each of the future night time intervals before the future night time interval, the interval length of each night time interval, and the total number of residents in the set city at the cloud computing network element end further includes: executing the AI quantity prediction model corresponding to the set urban landscape area to obtain the number of tourists in the set urban landscape area in the future night time interval output by the AI quantity prediction model corresponding to the set urban landscape area.