A power supply and distribution method and system for a data center
By constructing a feature comparison model and allocating distribution nodes, the problem of poor flexibility in power supply and distribution methods is solved, and the safety and economicality of the power grid are improved.
Patent Information
- Application Number
- CN202111200899.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-10-15
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-10-15
AI Technical Summary
In the prior art, the power supply and distribution methods are poor, and the power resource allocation capacity needs to be improved, resulting in excessive power load in some areas and safety hazards.
By obtaining information from community users, a feature comparison model is constructed, and feature traversal and sorting is performed based on the power consumption time, power consumption time nodes and power consumption characteristics, first- and second-level power distribution nodes are allocated to realize regional power supply and distribution management. Proper load allocation.
It has realized regional key management, intelligent power supply, optimized resource allocation, and improved the safety and economics of the power grid.
Smart Images

Figure CN113839389B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power supply and distribution, and in particular to a power supply and distribution method and system for a data center. Background Art
[0002] The main reason for the current power supply shortage is that the peak load is too high, the peak-valley load difference of the power grid is very large, and the power supply and power grid transmission capacity are limited during peak hours, resulting in a power supply gap during peak hours. In order to alleviate the power supply shortage, various regions are taking active actions, such as starting emergency peak-shifting power restrictions and guiding various production enterprises to appropriately adjust production arrangements. In order to ensure a smooth and orderly power supply and meet power demand, it is necessary to continuously optimize the power grid operation mode and strengthen the power supply capacity of the power grid.
[0003] However, the inventors of this application found that the above technology has at least the following technical problems in the process of implementing the technical solution of the invention in the embodiment of this application:
[0004] In the existing technology, there are technical problems such as poor flexibility in power supply and distribution, the need to improve the power resource allocation capability, excessive power load in some areas, and potential safety hazards. Summary of the invention
[0005] The embodiment of the present application provides a power supply and distribution method and system for a data center, which solves the technical problems in the prior art, such as poor flexibility of power supply and distribution methods, the need to improve the power resource allocation capability, excessive power load in some areas, and potential safety hazards. The technical effects of regional key management, intelligent power supply, optimized resource allocation, and reasonable load allocation are achieved, thereby improving the safety and economy of the power grid.
[0006] In view of the above problems, an embodiment of the present application provides a power supply and distribution method and system for a data center.
[0007] In a first aspect, an embodiment of the present application provides a power supply and distribution method for a data center, wherein the method includes: obtaining user information of a first community, wherein the user information includes the user's family information and power usage habit information; allocating a first-level power distribution node according to the user information, and obtaining a first-level power distribution node allocation result; obtaining basic information of a first user, wherein the first user is a user of the first community, and obtaining the first user's historical power usage information according to the basic information; constructing a first feature comparison model, wherein the first feature comparison model includes power usage duration features, power usage time node features, and power usage power features, and performing feature traversal on the first user's historical power usage information based on the first feature comparison model to obtain a first feature traversal result; obtaining a feature value label of the first user according to the first feature traversal result, and performing feature value sorting based on the feature value label to obtain a first sorting result; obtaining a second-level power distribution node allocation result based on the first sorting result, and performing regional power supply and distribution management through the first-level power distribution node allocation result and the second-level power distribution node allocation result.
[0008] On the other hand, an embodiment of the present application provides a power supply and distribution system for a data center, wherein the system includes: a first obtaining unit, the first obtaining unit is used to obtain user information of a first community, wherein the user information includes the user's family information and electricity usage habit information; a second obtaining unit, the second obtaining unit is used to allocate a first-level distribution node according to the user information, and obtain a first-level distribution node allocation result; a third obtaining unit, the third obtaining unit is used to obtain basic information of a first user, wherein the first user is a user of the first community, and the historical electricity usage information of the first user is obtained according to the basic information; a first construction unit, the first construction unit is used to construct a first A feature comparison model, wherein the first feature comparison model includes a power consumption duration feature, a power consumption time node feature, and a power consumption power feature, and based on the first feature comparison model, a feature traversal is performed on the historical power consumption information of the first user to obtain a first feature traversal result; a fourth acquisition unit, wherein the fourth acquisition unit is used to obtain a feature value label of the first user according to the first feature traversal result, and to sort the feature values based on the feature value label to obtain a first sorting result; a first management unit, wherein the first management unit is used to obtain a secondary distribution node allocation result based on the first sorting result, and to perform regional power supply and distribution management through the primary distribution node allocation result and the secondary distribution node allocation result.
[0009] In a third aspect, an embodiment of the present application provides a power supply and distribution system for a data center, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods described in the first aspect when executing the program.
[0010] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
[0011] Due to obtaining user information of the first community, wherein the user information includes the user's family information and electricity usage habit information; allocating the first-level distribution node according to the user information, and obtaining the first-level distribution node allocation result; obtaining the basic information of the first user, wherein the first user is a user of the first community, and obtaining the historical electricity usage information of the first user according to the basic information; constructing a first feature comparison model, wherein the first feature comparison model includes electricity usage duration characteristics, electricity usage time node characteristics, and electricity usage power characteristics, performing feature traversal on the historical electricity usage information of the first user based on the first feature comparison model, and obtaining a first feature traversal result; obtaining the feature value label of the first user according to the first feature traversal result, and sorting the feature values based on the feature value label to obtain a first sorting result; obtaining the second-level distribution node allocation result based on the first sorting result, and performing a technical solution for regional power supply and distribution management through the first-level distribution node allocation result and the second-level distribution node allocation result, the embodiment of the present application provides a power supply and distribution method and system for a data center, thereby achieving the technical effects of regional key management, intelligent power supply, optimized resource allocation, and reasonable load allocation, thereby improving the safety and economy of the power grid.
[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] Figure 1 A schematic diagram of a flow chart of a power supply and distribution method for a data center according to an embodiment of the present application;
[0014] Figure 2 A schematic diagram of a flow chart of obtaining a first feature comparison model in a power supply and distribution method for a data center according to an embodiment of the present application;
[0015] Figure 3 A schematic diagram of a process of updating a first initial model of a power supply and distribution method for a data center according to an embodiment of the present application;
[0016] Figure 4 A schematic diagram of a flow chart of performing time period cluster analysis on power consumption information in a power supply and distribution method for a data center according to an embodiment of the present application;
[0017] Figure 5 A schematic diagram of a flow chart of adding a non-fixed secondary power distribution node in a power supply and distribution method for a data center according to an embodiment of the present application;
[0018] Figure 6 A schematic diagram of a flow chart of analyzing the behavior habits of a second user in a power supply and distribution method of a data center according to an embodiment of the present application;
[0019] Figure 7 A schematic diagram of a flow chart of evaluating the power supply pressure of a first community in a power supply and distribution method of a data center according to an embodiment of the present application;
[0020] Figure 8 This is a schematic diagram of the structure of a power supply and distribution system of a data center in an embodiment of the present application;
[0021] Fig. 9 It is a schematic diagram of the structure of an exemplary electronic device according to an embodiment of the present application.
[0022] Explanation of the reference numerals: first obtaining unit 11 , second obtaining unit 12 , third obtaining unit 13 , first constructing unit 14 , fourth obtaining unit 15 , first managing unit 16 , electronic device 300 , memory 301 , processor 302 , communication interface 303 , bus architecture 304 . DETAILED DESCRIPTION
[0023] The embodiment of the present application provides a power supply and distribution method and system for a data center, which solves the technical problems in the prior art, such as poor flexibility of power supply and distribution methods, the need to improve the power resource allocation capability, excessive power load in some areas, and potential safety hazards. The technical effects of regional key management, intelligent power supply, optimized resource allocation, and reasonable load allocation are achieved, thereby improving the safety and economy of the power grid.
[0024] Application Overview
[0025] The main reason for the current power supply shortage is that the peak load is too high, the peak-to-valley load difference of the power grid is very large, and the power supply and transmission capacity of the power grid are limited during peak hours, resulting in a power supply gap during the peak power consumption period. In order to alleviate the power supply shortage, various regions are taking active actions, such as starting emergency peak-shifting power restrictions and guiding various production enterprises to appropriately adjust production arrangements. In order to ensure smooth and orderly power supply and meet power demand, it is necessary to continuously optimize the power grid operation mode and strengthen the power supply capacity of the power grid. However, in the existing technology, due to the poor flexibility of the power supply and distribution mode, the power resource allocation capacity needs to be improved, the power load in some areas is too large, and there are technical problems such as safety hazards.
[0026] In response to the above technical problems, the overall idea of the technical solution provided by this application is as follows:
[0027] An embodiment of the present application provides a power supply and distribution method for a data center, wherein the method includes: obtaining user information of a first community, wherein the user information includes the user's family information and power usage habit information; allocating a first-level power distribution node according to the user information, and obtaining a first-level power distribution node allocation result; obtaining basic information of a first user, wherein the first user is a user of the first community, and obtaining historical power usage information of the first user according to the basic information; constructing a first feature comparison model, wherein the first feature comparison model includes power usage duration features, power usage time node features, and power usage power features, and performing feature traversal on the historical power usage information of the first user based on the first feature comparison model to obtain a first feature traversal result; obtaining a feature value label of the first user according to the first feature traversal result, and performing feature value sorting based on the feature value label to obtain a first sorting result; obtaining a second-level power distribution node allocation result based on the first sorting result, and performing regional power supply and distribution management through the first-level power distribution node allocation result and the second-level power distribution node allocation result.
[0028] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.
[0029] Embodiment 1
[0030] like Figure 1 As shown, an embodiment of the present application provides a power supply and distribution method for a data center, wherein the method includes:
[0031] S100: Obtaining user information of a first community, wherein the user information includes family information and electricity usage habit information of the user;
[0032] S200: Allocate a primary power distribution node according to the user information to obtain a primary power distribution node allocation result;
[0033] S300: Obtain basic information of a first user, wherein the first user is a user of the first community, and obtain historical electricity usage information of the first user according to the basic information;
[0034] Specifically, user information of the first community is obtained, wherein the user information includes the user's family information and electricity usage habit information, the first community is any community that needs power supply and distribution, the user's family information includes the number, gender, and age of the user's family members, and the electricity usage habit information includes the electricity usage time interval, the power usage range, etc. The first-level distribution node is allocated according to the user information, and the first-level distribution node allocation result is obtained. The first-level distribution node is the first node under the bus, which can carry a large power consumption. When the power node level increases, that is, the node becomes level 2, level 3, etc., as the level increases, the power decreases successively. The node is a virtual node, which may include a fixed node and a non-fixed node. The fixed node refers to a node that always exists, and the non-fixed node is a node that only appears at a specific time point. The basic information of the first user is obtained, wherein the first user is a user of the first community, and the historical electricity usage information of the first user is obtained according to the basic information. The basic information includes the historical electricity usage information of the first user's family within a certain time range. According to the first-level distribution node allocation result, the location, quantity and level of the distribution nodes in the first community can be mastered, so as to facilitate regional key management.
[0035] S400: constructing a first feature comparison model, wherein the first feature comparison model includes a power usage duration feature, a power usage time node feature, and a power usage power feature, and performing feature traversal on the historical power usage information of the first user based on the first feature comparison model to obtain a first feature traversal result;
[0036] Specifically, a first feature comparison model is constructed, which includes a power usage duration feature, a power usage time node feature, and a power usage power feature. The historical power usage information of the first user is input into the first feature comparison model for traversal operation, that is, all power usage duration features, power usage time node features, and power usage power features in the historical power usage information of the first user are accessed once to obtain the first feature traversal result. This can achieve in-depth analysis and processing of historical information, make reasonable use of historical data, and achieve the effect of mastering the power usage rules of users.
[0037] S500: Obtaining a feature value label of the first user according to the first feature traversal result, and sorting feature values based on the feature value label to obtain a first sorting result;
[0038] S600: Obtain a secondary power distribution node allocation result based on the first sorting result, and perform regional power supply and distribution management through the primary power distribution node allocation result and the secondary power distribution node allocation result.
[0039] Specifically, the characteristic value label of the first user is obtained according to the first characteristic traversal result, and the characteristic value is sorted based on the characteristic value label to obtain the first sorting result. The characteristic value label is used to mark the characteristic value, and contains the characteristic information of the power consumption duration, the characteristic information of the power consumption time node, and the characteristic information of the power consumption. Further, the characteristic value is sorted, and the characteristic value is sorted from large to small or from small to large to obtain the first sorting result. The secondary distribution node allocation result is obtained based on the first sorting result. The secondary distribution node allocation result is obtained on the basis of in-depth analysis of the user's historical power consumption information. Regional power supply and distribution management is performed through the primary distribution node allocation result and the secondary distribution node allocation result. Intelligent power supply and reasonable load allocation can be achieved through characteristic analysis and characteristic value sorting.
[0040] Further, such as Figure 2 As shown, the embodiment of the present application also includes:
[0041] S610: Obtain a first initial model, wherein the first initial model is obtained through a first collaboration system;
[0042] S620: Obtain first user data of a first community, and perform decentralized processing on the first user data of the first community to obtain a first processing result;
[0043] S630: Calculate the covariance matrix of the first processing result to obtain eigenvalues and eigenvectors of the covariance matrix;
[0044] S640: Projecting the first user data onto the feature vector according to the sorting result of the feature value to obtain a first training data set;
[0045] S650: Training the first initial model using the first training data set to generate first model parameters;
[0046] S660: Obtain the first feature comparison model through the first model parameters.
[0047] Specifically, a first initial model is obtained, wherein the first initial model is obtained through a first collaborative system, first user data of a first community is obtained, the first user data is electricity consumption data of a first user, and the first user data of the first community is decentralized to obtain a first processing result. Decentralization is a process relative to centralization. Decentralization does not mean no center, but rather that nodes can freely choose and decide the center. In a decentralized system, anyone can become a center.
[0048] The covariance matrix of the first processing result is operated to obtain the eigenvalues and eigenvectors of the covariance matrix; each element of the covariance matrix is the covariance between each vector element, and the covariance matrix represents the energy distribution of the sample set in each direction in the original n-dimensional space. By finding the eigenvector of the covariance matrix, what is actually found are some specific directions in the original n-dimensional space, where the energy of the sample set is concentrated, and the size of the eigenvalue reflects the energy size of the sample set in this direction. According to the sorting result of the eigenvalue, the first user data is projected onto the eigenvector to obtain the first training data set, and the first initial model is trained by the first training data set. The first initial model is a neural network model, and further, the first model parameters are generated. The reliability of data analysis can be improved, thereby mastering the characteristics of user data.
[0049] Further, such as Figure 3 As shown, the embodiment of the present application also includes:
[0050] S671: Send the first model parameter to the first collaboration system;
[0051] S672: Obtain a first feedback parameter of the first collaborative system, wherein the first feedback parameter is obtained by integrating a plurality of model parameters by the first collaborative system, and the plurality of model parameters include the first model parameter;
[0052] S673: Update the first initial model according to the first feedback parameter to obtain the first feature comparison model.
[0053] Specifically, the first model parameter is sent to the first collaborative system to obtain the first feedback parameter of the first collaborative system. The first collaborative system obtains the first feedback parameter by integrating multiple model parameters, and the multiple model parameters include the first model parameter. The first initial model is updated according to the first feedback parameter to obtain the first feature comparison model. The first initial model is a neural network model. Neural Networks (NN) is a complex neural network system formed by a large number of simple processing units (called neurons) that are widely interconnected. It reflects many basic characteristics of human brain functions and is a highly complex nonlinear dynamic learning system. The neural network model is described based on the mathematical model of neurons. The first feedback parameter is supervised learning, so that the first initial model processes the input information more accurately, and the first feature comparison model obtained is more reasonable and accurate.
[0054] Further, such as Figure 4As shown, the obtaining of user information of the first community, wherein the user information includes the user's family information and electricity usage habit information, step S100 includes:
[0055] S110: Obtaining electricity consumption information of the first community in a first period;
[0056] S120: Clustering electricity consumption in a time period according to the electricity consumption information to obtain a first clustering result;
[0057] S130: Obtaining power consumption location distribution information of the first clustering result according to the power consumption information;
[0058] S140: Using the first clustering result and the power consumption location distribution information as the user information.
[0059] Specifically, the electricity consumption information of the first community within the first period is obtained. The first period is a time period. The length of the first period is determined according to the amount of data it contains. The electricity consumption of the time period is clustered according to the electricity consumption information. Cluster analysis refers to the process of classifying data into different classes or clusters. Objects in the same cluster have great similarities, while objects in different clusters have great differences. Objects with similar electricity consumption information within the time period are grouped into one category, such as grouping electricity consumption information on working days from Monday to Friday into one category, and grouping electricity consumption information on rest days on Saturday and Sunday into one category, thereby obtaining the first clustering result. The electricity consumption location distribution information of the first clustering result is obtained according to the electricity consumption information, and the relative position between each information in a category is obtained according to the distance between each information as the electricity consumption location. The first clustering result and the electricity consumption location distribution information are used as the user information. Through cluster analysis, data is analyzed from the perspective of information similarity, which can make the obtained user information more scientific and reliable.
[0060] Further, such as Figure 5 As shown, the embodiment of the present application also includes:
[0061] S710: Obtaining a behavior habit coefficient of the first user according to the first feature traversal result;
[0062] S720: Obtaining a first behavior habit coefficient threshold;
[0063] S730: Determine whether the behavior habit coefficient has a time node that meets the first behavior habit coefficient threshold;
[0064] S740: When the behavior habit coefficient has a time node that meets the first behavior habit coefficient threshold, add a non-fixed secondary power distribution node to the time node;
[0065] S750: Perform regional power supply and distribution management through the primary power distribution node allocation result, the secondary power distribution node allocation result and the non-fixed secondary power distribution node.
[0066] Specifically, the behavior habit coefficient of the first user is obtained according to the first feature traversal result, and the first behavior habit coefficient threshold is obtained, which may be the maximum value of the first behavior habit coefficient. It is determined whether the behavior habit coefficient has a time node that meets the first behavior habit coefficient threshold. When the behavior habit coefficient has a time node that meets the first behavior habit coefficient threshold, a non-fixed secondary distribution node is added to the time node. That is, it is determined whether the first behavior habit coefficient exceeds the first behavior habit coefficient threshold. If it exceeds, the corresponding time node is obtained, and a non-fixed secondary distribution node is added to the time node. The secondary distribution node is a non-fixed node, that is, it is active. Regional power supply and distribution management is performed through the first-level distribution node allocation result, the second-level distribution node allocation result and the non-fixed secondary distribution node. Setting a non-fixed secondary distribution node can increase the flexibility of the distribution node, can timely regulate abnormal power usage, and realize regional management.
[0067] Further, such as Figure 6 The embodiment of the present application also includes:
[0068] S751: Obtaining a behavior habit coefficient of a second user, wherein the second user is a user at a first distance from the first user;
[0069] S752: Determine whether the behavior habit coefficient of the second user at the time node meets the first behavior habit coefficient threshold;
[0070] S753: When the conditions are met, the non-fixed secondary distribution node is shared with the second user.
[0071] Specifically, the behavior habit coefficient of the second user is obtained, the second user is a user with a first distance from the first user, that is, the second user is a neighbor of the first user, and it is determined whether the behavior habit coefficient of the second user meets the first behavior habit coefficient threshold at the time node, that is, when the behavior habit coefficient of the first user meets the first behavior habit coefficient threshold. If it is satisfied, the non-fixed secondary distribution node is shared with the second user, that is, when the behavior habit coefficient of the first user meets the first behavior habit coefficient threshold, if the behavior habit coefficient of the second user with a distance from him also meets the first behavior habit coefficient threshold, then the two share the non-fixed secondary distribution node, which improves the configuration efficiency of the distribution node and alleviates the pressure on electricity consumption.
[0072] Further, such as Figure 7 The embodiment of the present application also includes:
[0073] S754: Obtaining distribution location and distribution time information of non-fixed secondary distribution nodes;
[0074] S755: Performing a position concentration analysis according to the distribution positions to obtain a first analysis result;
[0075] S756: Perform time density analysis according to the distribution time information to obtain a second analysis result;
[0076] S757: Evaluate the power supply pressure of the first community according to the first analysis result and the second analysis result to obtain a first evaluation result;
[0077] S758: Providing off-peak electricity usage reminders to users of the non-fixed secondary distribution node based on the first evaluation result.
[0078] Specifically, the distribution location and distribution time information of the non-fixed secondary distribution node are obtained, and the location concentration analysis is performed according to the distribution location to obtain the first analysis result. From the first analysis result, the concentration and distribution location of users with high power consumption can be observed. The time density analysis is performed according to the distribution time information to obtain the second analysis result. According to the second analysis result, the time node of peak power consumption can be grasped, thereby grasping the power consumption pattern. According to the first analysis result and the second analysis result, the power supply pressure of the first community is evaluated to obtain the first evaluation result. If users with high power consumption are concentrated in the first community and there are multiple peak power consumption time nodes, then the power supply pressure of the first community is relatively large. According to the first evaluation result, users of the non-fixed secondary distribution node are reminded to use electricity at off-peak times. In order to solve the problem of high power consumption and excessive load on the power grid, users who configure the non-fixed secondary distribution node are reminded and it is recommended to use electricity at off-peak times, so as to optimize resource allocation and improve the safety and economy of the power grid.
[0079] In summary, the power supply and distribution method and system for a data center provided by the embodiments of the present application have the following technical effects:
[0080] 1. Due to obtaining user information of the first community, wherein the user information includes the user's family information and electricity usage habit information; allocating the first-level distribution node according to the user information, and obtaining the first-level distribution node allocation result; obtaining the basic information of the first user, wherein the first user is a user of the first community, and obtaining the historical electricity usage information of the first user according to the basic information; constructing a first feature comparison model, wherein the first feature comparison model includes electricity usage duration characteristics, electricity usage time node characteristics, and electricity usage power characteristics, and performing feature traversal on the historical electricity usage information of the first user based on the first feature comparison model to obtain a first feature traversal result; obtaining the feature value label of the first user according to the first feature traversal result, and performing feature value sorting based on the feature value label to obtain a first sorting result; obtaining the second-level distribution node allocation result based on the first sorting result, and performing a regional power supply and distribution management technical solution through the first-level distribution node allocation result and the second-level distribution node allocation result. The embodiment of the present application provides a power supply and distribution method and system for a data center, thereby achieving the technical effects of regional key management, intelligent power supply, optimized resource allocation, and reasonable load allocation, thereby improving the safety and economy of the power grid.
[0081] 2. Due to the reasonable configuration of non-fixed secondary distribution nodes, a peak-shifting electricity consumption reminder mechanism is established to achieve regional key management and improve the technical effect of power grid safety and economy.
[0082] Embodiment 2
[0083] Based on the same inventive concept as the power supply and distribution method of a data center in the aforementioned embodiment, Figure 8 As shown, an embodiment of the present application provides a power supply and distribution system for a data center, wherein the system includes:
[0084] A first obtaining unit 11, the first obtaining unit 11 is used to obtain user information of the first community, wherein the user information includes family information and electricity usage habit information of the user;
[0085] A second obtaining unit 12, the second obtaining unit 12 is used to allocate the primary distribution node according to the user information and obtain the primary distribution node allocation result;
[0086] A third obtaining unit 13, the third obtaining unit 13 is used to obtain basic information of a first user, wherein the first user is a user of the first community, and obtain historical electricity usage information of the first user according to the basic information;
[0087] A first construction unit 14, the first construction unit 14 is used to construct a first feature comparison model, wherein the first feature comparison model includes a power consumption duration feature, a power consumption time node feature, and a power consumption power feature, and based on the first feature comparison model, perform feature traversal on the historical power consumption information of the first user to obtain a first feature traversal result;
[0088] A fourth obtaining unit 15, the fourth obtaining unit 15 is used to obtain a feature value label of the first user according to the first feature traversal result, and perform feature value sorting based on the feature value label to obtain a first sorting result;
[0089] The first management unit 16 is used to obtain a secondary power distribution node allocation result based on the first sorting result, and perform regional power supply and distribution management through the primary power distribution node allocation result and the secondary power distribution node allocation result.
[0090] Furthermore, the system comprises:
[0091] a fifth obtaining unit, the fifth obtaining unit being used to obtain a first initial model, wherein the first initial model is obtained through the first collaborative system;
[0092] a sixth obtaining unit, the sixth obtaining unit being used to obtain first user data of the first community, and to perform decentralized processing on the first user data of the first community to obtain a first processing result;
[0093] a seventh obtaining unit, the seventh obtaining unit being used to operate the covariance matrix of the first processing result to obtain eigenvalues and eigenvectors of the covariance matrix;
[0094] an eighth obtaining unit, configured to project the first user data onto the feature vector according to a result of sorting the feature values, so as to obtain a first training data set;
[0095] a first generating unit, the first generating unit being configured to train the first initial model using the first training data set to generate first model parameters;
[0096] A ninth obtaining unit, wherein the ninth obtaining unit is used to obtain the first feature comparison model through the first model parameters.
[0097] Furthermore, the system comprises:
[0098] A first sending unit, configured to send the first model parameter to the first collaboration system;
[0099] a tenth obtaining unit, the tenth obtaining unit being configured to obtain a first feedback parameter of the first collaborative system, wherein the first feedback parameter is obtained by integrating a plurality of model parameters of the first collaborative system, and the plurality of model parameters include the first model parameter;
[0100] An eleventh obtaining unit, the eleventh obtaining unit is used to update the first initial model according to the first feedback parameter to obtain the first feature comparison model.
[0101] Furthermore, the system comprises:
[0102] a twelfth obtaining unit, the twelfth obtaining unit being used to obtain electricity usage information of the first community in a first period;
[0103] a thirteenth obtaining unit, the thirteenth obtaining unit being configured to perform power consumption clustering in a time period according to the power consumption information to obtain a first clustering result;
[0104] a fourteenth obtaining unit, the fourteenth obtaining unit being configured to obtain power consumption location distribution information of the first clustering result according to the power consumption information;
[0105] A first execution unit, wherein the first execution unit is configured to use the first clustering result and the power consumption location distribution information as the user information.
[0106] Furthermore, the system comprises:
[0107] a fifteenth obtaining unit, the fifteenth obtaining unit being used to obtain a behavior habit coefficient of the first user according to the first feature traversal result;
[0108] A sixteenth obtaining unit, the sixteenth obtaining unit is used to obtain a first behavior habit coefficient threshold;
[0109] A first judgment unit, the first judgment unit is used to judge whether the behavior habit coefficient has a time node that meets the first behavior habit coefficient threshold;
[0110] A second execution unit, the second execution unit being configured to add a non-fixed secondary power distribution node to a time node when the behavior habit coefficient has a time node that satisfies the first behavior habit coefficient threshold;
[0111] A third execution unit, the third execution unit is used to perform regional power supply and distribution management through the primary power distribution node allocation result, the secondary power distribution node allocation result and the non-fixed secondary power distribution node.
[0112] Furthermore, the system comprises:
[0113] a seventeenth obtaining unit, the seventeenth obtaining unit being used to obtain a behavior habit coefficient of a second user, wherein the second user is a user having a first distance from the first user;
[0114] a second judgment unit, the second judgment unit being used to judge whether the behavior habit coefficient of the second user at the time node meets the first behavior habit coefficient threshold;
[0115] A fourth execution unit, wherein the fourth execution unit is configured to share the non-fixed secondary distribution node with the second user when the condition is met.
[0116] Furthermore, the system comprises:
[0117] An eighteenth obtaining unit, the eighteenth obtaining unit being used to obtain distribution position and distribution time information of a non-fixed secondary distribution node;
[0118] a nineteenth obtaining unit, the nineteenth obtaining unit being configured to perform a position concentration analysis according to the distribution positions to obtain a first analysis result;
[0119] a twentieth obtaining unit, the twentieth obtaining unit being used to perform time density analysis according to the distribution time information to obtain a second analysis result;
[0120] a twenty-first obtaining unit, the twenty-first obtaining unit being configured to evaluate the power supply pressure of the first community according to the first analysis result and the second analysis result to obtain a first evaluation result;
[0121] A fifth execution unit, wherein the fifth execution unit is used to remind users of the non-fixed secondary power distribution node to use electricity at off-peak hours according to the first evaluation result.
[0122] Exemplary Electronic Devices
[0123] Reference below Fig. 9 To describe the electronic device of the embodiment of the present application,
[0124] Based on the same inventive concept as the power supply and distribution method of a data center in the aforementioned embodiment, the embodiment of the present application further provides a power supply and distribution system for a data center, comprising: a processor, the processor is coupled to a memory, the memory is used to store a program, when the program is executed by the processor, the system executes the method described in any one of the first aspects
[0125] The electronic device 300 includes: a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. The communication interface 303, the processor 302, and the memory 301 may be interconnected via the bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0126] The processor 302 may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.
[0127] The communication interface 303 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), wired access networks, etc.
[0128] The memory 301 may be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via the bus architecture 304. The memory may also be integrated with the processor.
[0129] The memory 301 is used to store computer-executable instructions for executing the solution of the present application, and the execution is controlled by the processor 302. The processor 302 is used to execute the computer-executable instructions stored in the memory 301, thereby realizing a power supply and distribution method for a data center provided in the above embodiment of the present application.
[0130] Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application code, which is not specifically limited in the embodiments of the present application.
[0131] An embodiment of the present application provides a power supply and distribution method for a data center, wherein the method includes: obtaining user information of a first community, wherein the user information includes the user's family information and power usage habit information; allocating a first-level power distribution node according to the user information, and obtaining a first-level power distribution node allocation result; obtaining basic information of a first user, wherein the first user is a user of the first community, and obtaining historical power usage information of the first user according to the basic information; constructing a first feature comparison model, wherein the first feature comparison model includes power usage duration features, power usage time node features, and power usage power features, and performing feature traversal on the historical power usage information of the first user based on the first feature comparison model to obtain a first feature traversal result; obtaining a feature value label of the first user according to the first feature traversal result, and performing feature value sorting based on the feature value label to obtain a first sorting result; obtaining a second-level power distribution node allocation result based on the first sorting result, and performing regional power supply and distribution management through the first-level power distribution node allocation result and the second-level power distribution node allocation result.
[0132] Those of ordinary skill in the art will appreciate that the various digital numbers such as the first and second involved in the present application are only for the convenience of description, and are not used to limit the scope of the embodiments of the present application, nor do they represent the order of precedence. "And / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one" refers to one or more. At least two refers to two or more. "At least one", "any one" or similar expressions refer to any combination of these items, including any combination of single items (individuals) or plural items (individuals). For example, at least one item (individual, kind) of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.
[0133] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server, data center, etc. that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.
[0134] The various illustrative logic units and circuits described in the embodiments of the present application can be implemented or operated by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or the design of any combination of the above functions. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any traditional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of computing devices, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration to implement.
[0135] The method or steps of the method described in the embodiments of the present application can be directly embedded in hardware, a software unit executed by a processor, or a combination of the two. The software unit can be stored in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC, and the ASIC can be arranged in a terminal. Optionally, the processor and the storage medium can also be arranged in different components in the terminal. These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0136] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include these modifications and variations.
Claims
1. A power supply and distribution method for a data center, wherein: The method comprises: Obtaining user information of the first community, wherein the user information includes family information and electricity usage habit information of the user; Allocate the primary power distribution node according to the user information to obtain the primary power distribution node allocation result; Obtaining basic information of a first user, wherein the first user is a user of the first community, and obtaining historical electricity usage information of the first user according to the basic information; Constructing a first feature comparison model, wherein the first feature comparison model includes a power consumption duration feature, a power consumption time node feature, and a power consumption power feature, and performing a feature traversal on the historical power consumption information of the first user based on the first feature comparison model to obtain a first feature traversal result; Obtaining a feature value label of the first user according to the first feature traversal result, and sorting feature values based on the feature value label to obtain a first sorting result; A secondary power distribution node allocation result is obtained based on the first sorting result, and regional power supply and distribution management is performed through the primary power distribution node allocation result and the secondary power distribution node allocation result.
2. The method of claim 1, wherein: The method further comprises: Obtaining a first initial model, wherein the first initial model is obtained through a first collaborative system; Obtaining first user data of a first community, performing decentralized processing on the first user data of the first community, and obtaining a first processing result; Performing operations on the covariance matrix of the first processing result to obtain eigenvalues and eigenvectors of the covariance matrix; According to the sorting result of the feature values, projecting the first user data onto the feature vector to obtain a first training data set; Training the first initial model using the first training data set to generate first model parameters; The first feature comparison model is obtained through the first model parameters.
3. The method of claim 2, wherein: The method further comprises: sending the first model parameter to the first collaboration system; Obtaining a first feedback parameter of the first collaborative system, wherein the first feedback parameter is obtained by integrating a plurality of model parameters of the first collaborative system, and the plurality of model parameters include the first model parameter; The first initial model is updated according to the first feedback parameter to obtain the first feature comparison model.
4. The method of claim 1, wherein: The obtaining of user information of the first community, wherein the user information includes family information and electricity usage habit information of the user, further includes: Obtaining electricity consumption information of the first community in a first period; Performing power consumption clustering in a time period according to the power consumption information to obtain a first clustering result; Obtaining electricity usage location distribution information of the first clustering result according to the electricity usage information; The first clustering result and the power consumption location distribution information are used as the user information.
5. The method of claim 1, wherein: The method further comprises: Obtaining a behavior habit coefficient of the first user according to the first feature traversal result; Obtaining a first behavioral habit coefficient threshold; Determine whether the behavior habit coefficient has a time node that meets the first behavior habit coefficient threshold; When the behavior habit coefficient has a time node that meets the first behavior habit coefficient threshold, adding a non-fixed secondary power distribution node to the time node; Regional power supply and distribution management is performed through the primary power distribution node allocation result, the secondary power distribution node allocation result and the non-fixed secondary power distribution node.
6. The method of claim 5, wherein: The method further comprises: Obtaining a behavior habit coefficient of a second user, wherein the second user is a user at a first distance from the first user; Determining whether the behavior habit coefficient of the second user at the time node meets the first behavior habit coefficient threshold; When the condition is satisfied, the non-fixed secondary distribution node is shared by the second user.
7. The method of claim 6, wherein: The method further comprises: Obtaining the distribution location and distribution time information of non-fixed secondary distribution nodes; Performing a position concentration analysis according to the distribution positions to obtain a first analysis result; Performing time density analysis according to the distribution time information to obtain a second analysis result; Evaluate the power supply pressure of the first community according to the first analysis result and the second analysis result to obtain a first evaluation result; According to the first evaluation result, users of the non-fixed secondary distribution node are reminded of off-peak electricity consumption.
8. A power supply and distribution system for a data center, wherein: The system comprises: a first obtaining unit, the first obtaining unit being used to obtain user information of the first community, wherein the user information includes family information and electricity usage habit information of the user; a second obtaining unit, the second obtaining unit being configured to perform allocation of the primary distribution node according to the user information, and obtain an allocation result of the primary distribution node; a third obtaining unit, the third obtaining unit being configured to obtain basic information of a first user, wherein the first user is a user of the first community, and to obtain historical electricity usage information of the first user according to the basic information; A first construction unit, the first construction unit is used to construct a first feature comparison model, wherein the first feature comparison model includes a power consumption duration feature, a power consumption time node feature, and a power consumption power feature, and based on the first feature comparison model, a feature traversal is performed on the historical power consumption information of the first user to obtain a first feature traversal result; a fourth obtaining unit, the fourth obtaining unit being configured to obtain a feature value label of the first user according to the first feature traversal result, and to sort feature values based on the feature value label to obtain a first sorting result; A first management unit, wherein the first management unit is used to obtain a secondary power distribution node allocation result based on the first sorting result, and perform regional power supply and distribution management through the primary power distribution node allocation result and the secondary power distribution node allocation result.
9. A power supply and distribution system for a data center, comprising: A processor, the processor is coupled to a memory, the memory is used to store a program, when the program is executed by the processor, the system is enabled to execute the method according to any one of claims 1 to 7.
