CN113434690B - Clustering algorithm-based electricity utilization prediction evaluation method, device, system and medium - Google Patents
Clustering algorithm-based electricity utilization prediction evaluation method, device, system and medium Download PDFInfo
- Publication number
- CN113434690B CN113434690B CN202110983999.6A CN202110983999A CN113434690B CN 113434690 B CN113434690 B CN 113434690B CN 202110983999 A CN202110983999 A CN 202110983999A CN 113434690 B CN113434690 B CN 113434690B
- Authority
- CN
- China
- Prior art keywords
- power
- preset
- clustering
- electrical appliance
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a clustering algorithm-based electricity utilization prediction evaluation method, a device, a system and a medium, which are used for collecting actual operation parameters of a target electric appliance and storing the actual operation parameters into a preset database by responding to electric appliance addition operation input by a user; based on the influence of preset factors on the electricity consumption of the target electrical appliance, clustering the collected electrical appliances in a preset database to obtain a clustering result of the target electrical appliance under the corresponding preset factors; calculating the predicted power consumption of the target electrical appliance under the preset factors according to the clustering result and the actual operation parameters; and carrying out power utilization evaluation on the target electrical appliance according to the predicted power consumption, and generating an optimal power utilization strategy of the target electrical appliance according to the evaluation result and the clustering result. Through clustering processing based on preset factors, the predicted power consumption and actual environment factors can be closely related in the process of predicting and evaluating the power consumption, accurate predicted power consumption is obtained, a reliable optimal power utilization strategy is further obtained, and the accuracy of power consumption prediction and power utilization suggestion is effectively improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a clustering algorithm-based power utilization prediction evaluation method, device, system and medium.
Background
With the popularization and use of various household appliances, people depend on various household appliances at present and are difficult to form good electricity utilization habits, so that the electricity consumption of a plurality of families is greatly increased, and common users lack electricity consumption calculation capacity of the various household appliances, so that the electricity expense of the families is often confused.
Even if some users can predict the household electricity consumption according to the power on the electric appliance nameplate and adjust the electricity consumption habit based on the prediction result, the electricity consumption of various household appliances under different influence factors can be correspondingly changed, so that the mode of predicting and adjusting the electricity consumption habit through the power on the electric appliance nameplate is not accurate, the accurate electricity consumption prediction is difficult to realize, and the reliability of the electricity consumption suggestion is further reduced.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention provides a method, an apparatus, a system and a medium for power consumption prediction evaluation based on a clustering algorithm, which aims to improve the accuracy of power consumption prediction and provide a reliable power consumption strategy to save power consumption.
The technical scheme of the invention is as follows:
a power utilization prediction evaluation method based on a clustering algorithm comprises the following steps:
responding to an electric appliance adding operation input by a user, acquiring actual operation parameters of a target electric appliance and storing the actual operation parameters into a preset database;
based on the influence of preset factors on the power consumption of the target electrical appliance, clustering the electrical appliances collected in the preset database to obtain a clustering result of the target electrical appliance under the corresponding preset factors;
calculating the predicted power consumption of the target electrical appliance under the preset factors according to the clustering result and the actual operation parameters;
and carrying out power utilization evaluation on the target electrical appliance according to the predicted power consumption, and generating an optimal power utilization strategy of the target electrical appliance according to an evaluation result and the clustering result.
In one embodiment, the collecting and storing actual operating parameters of the target electrical appliance in a preset database in response to an electrical appliance adding operation input by a user includes:
responding to an electric appliance adding operation input by a user, and triggering and displaying a corresponding guide interface on a display screen;
receiving the electric appliance name, the brand model, the service life and the daily average running time of the target electric appliance input by a user on the guide interface;
and calling corresponding rated power in a preset parameter library according to the electric appliance name and the brand model of the target electric appliance to obtain the actual operation parameters of the target electric appliance and store the actual operation parameters in a preset database.
In an embodiment, the clustering, based on the influence of a preset factor on the power consumption of the target electrical appliance, the electrical appliances collected in the preset database to obtain a clustering result of the target electrical appliance under the corresponding preset factor includes:
acquiring output power of electric appliances of corresponding types which are acquired in advance when preset factors change according to the types of the electric appliances which are acquired in the preset database;
constructing a corresponding power prediction function according to the output power, the corresponding rated power and the preset factor;
clustering the power prediction function according to a preset clustering algorithm to obtain a plurality of clustering centers;
and identifying the clustering center to which the target electrical appliance belongs under the preset factors to obtain a corresponding clustering result.
In one embodiment, the constructing a corresponding power prediction function according to the output power, the corresponding rated power and the preset factor includes:
calculating a power parameter K according to the rated power corresponding to the output power, wherein K = P/Pr, wherein P is the output power, and Pr is the rated power;
and taking the preset factors as independent variables, and taking the power parameters as dependent variables to construct corresponding power prediction functions.
In one embodiment, the calculating the predicted power consumption of the target electrical appliance under the preset factor according to the clustering result and the actual operation parameter includes:
confirming the clustering center of the target electrical appliance according to the clustering result;
obtaining a predicted value of the preset factor according to a predicted time period, and calling a power parameter corresponding to the predicted value according to a power prediction function corresponding to the clustering center;
calculating the predicted power consumption W of the target electrical appliance under the preset factors according to the power parameters, the rated power, the average daily operation time and the predicted time period,
In one embodiment, the performing power consumption assessment on the target electrical appliance according to the predicted power consumption and generating an optimal power consumption strategy of the target electrical appliance according to an assessment result and the clustering result includes:
determining whether the predicted power consumption is greater than a preset threshold;
when the predicted power consumption is larger than the preset threshold value, calling the power prediction function corresponding to the clustering center where the target electrical appliance is located under the preset factor;
and extracting the optimal value of the preset factor in the power prediction function corresponding to the clustering center, and generating the optimal power utilization strategy of the target electrical appliance according to the optimal value of the preset factor.
In one embodiment, after the power consumption of the target electrical appliance is evaluated according to the predicted power consumption, and an optimal power consumption strategy of the target electrical appliance is generated according to the evaluation result and the clustering result, the method further includes:
collecting simulated operation parameters of the target electrical appliance in response to a prediction updating operation input by a user based on the optimal power utilization strategy;
and recalculating the simulated power consumption of the target electrical appliance under the prediction factor according to the clustering result and the simulated operation parameters.
The invention further provides a power consumption prediction and evaluation device based on the clustering algorithm, which comprises:
the acquisition module is used for responding to the electric appliance adding operation input by a user, acquiring the actual operation parameters of the target electric appliance and storing the actual operation parameters into a preset database;
the clustering module is used for clustering the collected electric appliances in the preset database based on the electricity utilization influence of preset factors on the target electric appliance to obtain a clustering result of the target electric appliance under the corresponding preset factors;
the prediction module is used for calculating the predicted power consumption of the target electrical appliance under the preset factors according to the clustering result and the actual operation parameters;
and the evaluation module is used for carrying out power utilization evaluation on the target electrical appliance according to the predicted power consumption and generating an optimal power utilization strategy of the target electrical appliance according to an evaluation result and the clustering result.
The invention further provides a power utilization prediction evaluation system based on a clustering algorithm, which comprises at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the above-described clustering algorithm-based electricity usage prediction evaluation method.
Yet another embodiment of the present invention provides a non-transitory computer-readable storage medium storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform the above-described clustering algorithm-based electricity prediction assessment method.
Has the advantages that: the invention discloses a power consumption prediction evaluation method, a device, a system and a medium based on a clustering algorithm.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
fig. 1 is a flowchart of a power consumption prediction evaluation method based on a clustering algorithm according to an embodiment of the present invention;
FIG. 2 is a power prediction function curve diagram of the electricity consumption prediction evaluation method based on the clustering algorithm according to the embodiment of the present invention;
fig. 3 is a block diagram of a power consumption prediction and evaluation apparatus based on a clustering algorithm according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a hardware structure of the electricity consumption prediction and evaluation system based on the clustering algorithm according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and effects of the present invention clearer and clearer, the present invention is described in further detail below. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flowchart illustrating an embodiment of a power consumption prediction evaluation method based on a clustering algorithm according to the present invention. The electricity consumption prediction and evaluation method based on the clustering algorithm provided by the embodiment is suitable for predicting and evaluating household electricity consumption of residents and generating electricity consumption suggestions to save electricity, and is applied to terminal equipment, and optionally, a system consisting of the terminal equipment, a network and a server, wherein the network is a medium for providing a communication link between the terminal equipment and the server, and can comprise various connection types, such as a wired connection type, a wireless communication link type, an optical fiber cable type and the like; the operating system on the terminal device may include an apple IOS system, an android system, a microsoft operating system, or another operating system, the terminal device is connected to the server through the network to implement interaction, so as to perform operations such as receiving or sending data, and may specifically be various electronic devices having a display screen and supporting web browsing, including but not limited to a smart phone, a tablet computer, a portable computer, a desktop server, and the like. As shown in fig. 1, the method specifically includes the following steps:
and S100, responding to the electric appliance adding operation input by the user, acquiring the actual operation parameters of the target electric appliance and storing the actual operation parameters into a preset database.
In this embodiment, the power consumption prediction evaluation may be performed through an application program pre-installed on the terminal device, or a corresponding power consumption prediction evaluation interface may be entered through a platform such as a wechat public number, a wechat applet, or the like, or a browser may jump to a designated link to enter the power consumption prediction evaluation interface, which is not limited in this embodiment. When a user triggers the power utilization prediction and evaluation function and enters a corresponding power utilization prediction and evaluation interface, the method can perform electric appliance adding operation according to the use condition of the electric appliances in the current household, acquire the actual operation parameters of the target electric appliances in the current household according to the electric appliance adding operation input by the user and store the actual operation parameters into a preset database, namely, the preset database containing the actual operation parameters of multiple target electric appliances can be quickly established according to a large number of electric appliance adding operations input by the user, a detailed data base is provided for power utilization analysis of various electric appliances, and the accuracy of power utilization prediction is improved.
In one embodiment, the collecting and storing actual operating parameters of the target electrical appliance in a preset database in response to an electrical appliance adding operation input by a user includes:
responding to an electric appliance adding operation input by a user, and triggering and displaying a corresponding guide interface on a display screen;
receiving the electric appliance name, the brand model, the service life and the daily average running time of the target electric appliance input by a user on the guide interface;
and calling corresponding rated power in a preset parameter library according to the electric appliance name and the brand model of the target electric appliance to obtain the actual operation parameters of the target electric appliance and store the actual operation parameters in a preset database.
In this embodiment, when a user inputs an electrical appliance adding operation on the power consumption prediction and evaluation interface, the corresponding guide interface may be triggered when the electrical appliance adding operation is detected, and the guide interface is displayed on a display screen of the terminal device to guide the user to perform detailed actual operation parameter filling, the user may input data such as an electrical appliance name, a brand model, a service life, a daily average operation duration and the like of a target electrical appliance on the guide interface according to the use condition of the electrical appliance in a home, specifically, the guide interface may be sequentially displayed in a progressive manner, for example, a name filling interface is displayed first, after the user selects a corresponding electrical appliance name through a text input or a drop-down box, the user jumps to the filling interface of the brand model through a jump link (for example, clicking a "next" button and the like), and similarly, after selecting a corresponding brand model through a text input or a drop-down box, other guide interfaces are sequentially displayed, until the user completes the filling of all the actual operation parameters; alternatively, the guidance interface may also adopt a one-time display mode, for example, a parameter form is set on the guidance interface, and the guidance user fills in each cell in the parameter form to complete filling in of the actual operation parameter, which may be specifically selected according to actual requirements, and this embodiment does not limit this.
After receiving the electric appliance name and the brand model of the target electric appliance filled by the user, calling corresponding rated power in a preset parameter library according to the electric appliance name and the brand model, so as to obtain the actual operation parameters of the target electric appliance and store the actual operation parameters in a preset database, in the embodiment, the actual operation parameters of the target electric appliance include but are not limited to the electric appliance name, the brand model, the service life, the average daily operation time length and the rated power, because a common user has no good knowledge of the electric parameters of the target electric appliance, in order to avoid the incapability of subsequent power consumption prediction and evaluation caused by the incapability of filling the rated power of the target electric appliance, in the embodiment, a parameter library is constructed by acquiring the electric appliance model and the rated power of each large brand on the market in advance, so that the user can directly search and call the existing rated power in the parameter library only by intuitively inputting the electric appliance name and the brand model, the parameter filling difficulty of the target electric appliance is reduced, and the parameter acquisition efficiency is improved.
Optionally, if the transfer fails, that is, at this time, the rated power corresponding to the currently received name and brand model of the electrical appliance is not stored in the parameter base, at this time, a photographing prompt may be output on the display screen to prompt a user to acquire a nameplate image of the target electrical appliance through a camera of the terminal device, after the nameplate image acquired by the camera is received, the nameplate image is subjected to text recognition to obtain the corresponding rated power, and the name, brand model and corresponding rated power of the electrical appliance are stored in the parameter base, so that other users can transfer the electrical appliance, and through the electrical appliance adding operation of different users in the using process, the coverage rate of data stored in the parameter base is continuously improved, and the obtaining efficiency of the actual operating parameters is improved.
S200, based on the influence of preset factors on the electricity consumption of the target electrical appliance, clustering the electrical appliances collected in the preset database to obtain a clustering result of the target electrical appliance under the corresponding preset factors.
In this embodiment, because different environmental factors have different influences on the operating state of the target electrical appliance, and further influence the power consumption of the target electrical appliance, for example, the change of the external temperature can directly influence the output power of most electrical appliances and further influence the power consumption, in order to achieve accurate power consumption prediction, based on the influence of the preset factors on the power consumption of the target electrical appliance, the cluster processing is performed on the massive electrical appliances collected in the prediction database, and the cluster result of the target electrical appliance added by the current user under each preset factor is obtained, the cluster processing is specifically a machine learning method, which involves grouping of data points, a group of data points is given, each data point can be divided into a specific group by a corresponding cluster algorithm, so that the obtained cluster result is a plurality of groups, and the data points in the same group should have similar attributes and/or characteristics, the data points in different groups should have highly different attributes and/or characteristics, and taking the preset factor of temperature as an example, different target appliances (e.g., variable frequency air conditioner and fixed frequency air conditioner) belonging to the same air conditioner may be clustered into different groups under the condition of temperature change, that is, the temperature has different power utilization effects on different air conditioners, while different kinds of target appliances (e.g., water heater and refrigerator) may be clustered into the same group under the condition of temperature change, which means that the temperature has highly similar power utilization effects on different kinds of target appliances in the group.
The specific preset factors can be determined according to actual conditions, including but not limited to temperature, season, service life, humidity, altitude and the like, so that a user can obtain clustering results under different preset factors through clustering after the target electrical appliance is added, the predicted power consumption can be closely related to actual environmental factors in the process of predicting and evaluating the power consumption, and the accuracy and reliability of predicting the power consumption of the target electrical appliance are effectively improved.
In an embodiment, the clustering, based on the influence of a preset factor on the power consumption of the target electrical appliance, the electrical appliances collected in the preset database to obtain a clustering result of the target electrical appliance under the corresponding preset factor includes:
acquiring output power of electric appliances of corresponding types which are acquired in advance when preset factors change according to the types of the electric appliances which are acquired in the preset database;
constructing a corresponding power prediction function according to the output power, the corresponding rated power and the preset factor;
clustering the power prediction function according to a preset clustering algorithm to obtain a plurality of clustering centers;
and identifying the clustering center to which the target electrical appliance belongs under the preset factors to obtain a corresponding clustering result.
In this embodiment, when clustering processing is performed on the power consumption influence of a target electrical appliance based on different preset factors, output power of electrical appliances of corresponding pre-collected categories when the preset factors change is obtained according to the categories of the electrical appliances collected in a preset database, that is, output power of various electrical appliances is generally affected when different preset factors change, so that output power of electrical appliances of different categories when the preset factors change is tested in advance and data is collected, for example, electrical appliances in the preset database can be divided into different categories according to working principles, such as variable frequency air conditioners, fixed frequency air conditioners, central air conditioners, direct cooling refrigerators, air cooling refrigerators, solar water heaters, air energy water heaters, electric water heaters and the like, output power of electrical appliances of different categories is tested in advance, and a plurality of test electrical appliances of different brands and different models can be selected for testing under each category, the accuracy of the test data is improved, the output power of each test electrical appliance is collected as the test data when the preset factors change, and the collected test data is stored in a corresponding database for flexible and efficient calling during clustering.
And then constructing a responsive power prediction function according to the acquired output power which changes along with the change of the preset factors, the rated power of the corresponding test electric appliance and the preset factors, namely, expressing the change of the relation between the output power and the rated power of each type of electric appliance under the influence of different preset factors through the power prediction function so as to represent the correlation between the environmental factors and the output power. Then, clustering the constructed power prediction function according to a preset clustering algorithm to obtain a plurality of clustering centers, specifically, clustering algorithms such as K-means (K mean) clustering, mean shift clustering, density-based clustering and the like can be adopted to perform clustering processing on the power prediction functions of all types of electric appliances, so that the electric appliances of different types can be clustered and grouped according to the influence commonality of preset factors, namely when the clustering processing is performed based on the preset factors, the power prediction functions of the electric appliances belonging to the same clustering center have the same or similar characteristics, which indicates that the preset factors have the same or similar influence results on the output power of the electric appliances of the same clustering center, when the subsequent power consumption prediction is performed, the type of the target electric appliance is obtained according to the name and brand model of the target electric appliance input by a user, and the category, the type, the power of the target electric appliance is obtained according to the type, the power prediction of the target electric appliance, The method comprises the steps that the cluster centers of the electric appliance names and the brand models which belong to the electric appliance names and the brand models under all preset factors are identified, namely the cluster centers obtained by clustering under all the preset factors all contain corresponding electric appliance types, names and brand models of test electric appliances, and the types, the electric appliance names and the brand models of target electric appliances are matched with the electric appliance types, the names and the brand models of the test electric appliances contained in all the cluster centers, so that corresponding clustering results can be obtained conveniently and efficiently.
In one embodiment, the constructing a corresponding power prediction function according to the output power, the corresponding rated power and the preset factor includes:
calculating a power parameter K according to the rated power corresponding to the output power, wherein K = P/Pr, wherein P is the output power, and Pr is the rated power;
and taking the preset factors as independent variables, and taking the power parameters as dependent variables to construct corresponding power prediction functions.
In this embodiment, when constructing the power prediction function, please refer to fig. 2 together, the power prediction function of the response is constructed by using the preset factor as the independent variable and the power parameter K as the dependent variable according to the output power tested and collected in advance, wherein the power parameter K is the ratio of the corresponding output power P when the preset factor is changed and the rated power Pr of the currently tested electric appliance, i.e. K = P/Pr, as shown in fig. 2, when the preset factor is the temperature, the temperature T is the dependent variable according to the output power obtained by the test, the power parameter K is the independent variable to construct the corresponding power prediction function, and further obtain the corresponding power prediction curve, wherein the curve 1 is the power prediction curve of the air conditioner when the temperature is changed, the curve 2 is the power prediction curve of the water heater when the temperature is changed, and the curve 3 is the power prediction curve of the refrigerator when the temperature is changed, specifically, the power prediction function may be constructed to obtain a continuous function or a discrete function according to whether the output power obtained by the test is continuous, which is not limited in this embodiment.
Specifically, when clustering is performed, taking a K-means clustering algorithm as an example, under the influence of a certain preset factor, a power prediction function of a plurality of test electrical appliances under the change of the preset factor can be randomly selected as an initial clustering center, the distance between each power prediction function to be processed and each initial clustering center is respectively calculated for the power prediction functions to be processed of the other test electrical appliances, when the distance between the power prediction function to be processed and any one initial clustering center is smaller than the preset distance, the preset clustering standard is considered to be satisfied, the power prediction function to be processed which satisfies the preset clustering standard is distributed to the group corresponding to the initial clustering center with the smallest distance, then, the clustering center of each group is updated, namely, the power prediction function to be processed which is contained in each group and the initial clustering centers are recalculated to obtain a new clustering center, the method specifically comprises the steps of calculating an average value of distances between power prediction functions to be processed in each group and an initial clustering center, taking the power prediction functions to be processed, which are closest to the average value, in each group as a new clustering center of the corresponding group, continuously and circularly performing iteration updating on the clustering centers until a preset iteration number is reached, outputting a final clustering center, realizing clustering processing on the power prediction functions of all electrical appliances, obtaining a plurality of groups distinguished by the clustering centers, distinguishing the change characteristics of output power of the electrical appliances under the influence of preset factors, and facilitating subsequent efficient and accurate power consumption prediction.
S300, calculating the predicted power consumption of the target electrical appliance under the preset factors according to the clustering result and the actual operation parameters.
In the embodiment, after the clustering result of each electric appliance under the corresponding preset factor is obtained by clustering, since the clustering result represents the power change of the target appliance under the influence of the electricity consumption of the corresponding preset factors, therefore, the predicted power consumption under the preset factors is comprehensively calculated by combining the clustering result of the target electrical appliance and the actual operation parameters filled by the user, namely, the environmental influence factors are closely related to the actual operation parameters based on the clustering processing, so that the calculated predicted power consumption can include the power consumption influence of the preset factors on the target electrical appliance in the actual use condition, compared with the conventional power consumption calculation directly carried out through the rated power of the target electrical appliance, the accuracy of the predicted power consumption is obviously improved, and a user can calculate the corresponding predicted power consumption expense through the accurate predicted power consumption, when the electric charge is compared, the situation that the electric charge is disfigured due to overlarge deviation and the like can not occur.
In one embodiment, the calculating the predicted power consumption of the target electrical appliance under the preset factor according to the clustering result and the actual operation parameter includes:
confirming the clustering center of the target electrical appliance according to the clustering result;
obtaining a predicted value of the preset factor according to a predicted time period, and calling a power parameter corresponding to the predicted value according to a power prediction function corresponding to the clustering center;
calculating the predicted power consumption W of the target electrical appliance under the preset factors according to the power parameters, the rated power, the average daily operation time and the predicted time period,
In this embodiment, when calculating the predicted power consumption, first determining the cluster center of the target electrical appliance according to the cluster result, that is, a plurality of groups and a plurality of cluster centers obtained by clustering under the preset factors, where the target electrical appliance is assigned to one of the groups corresponding to the cluster center, and each cluster center corresponds to a power prediction function as a common characteristic function of power changes of the electrical appliances in the group, so as to obtain the predicted value of the corresponding preset factor according to the prediction time period input by the user, and obtain the corresponding power parameter through the predicted value, where the power parameter is the power prediction function corresponding to the cluster center where the target electrical appliance is located, and the X-axis value is the Y-axis value corresponding to the power prediction function when the predicted value is obtained, for example, when the user wants to predict the predicted power consumption in the future month, the predicted value of the preset factor in the future month is obtained, taking the temperature as an example, the temperature value of the geographical position in the future month can be obtained according to the geographical position input by the user or the automatically obtained geographical position, and the power parameters corresponding to different temperatures in the future month are called through the power prediction function corresponding to the clustering center of the target electrical appliance under the influence of the temperature so as to reflect the influence of the temperature change of each day on the output power of the target electrical appliance. Then, the presetting of the target electrical appliance under the preset factors can be calculated according to the power parameters, the rated power, the average daily operation time and the prediction time periodThe electricity consumption W is measured, and the electricity consumption,
where j is the number of predetermined factors,
is the power parameter corresponding to the predicted value of the jth preset factor, n is the number of the target electrical appliances,
is the rated power of the ith target appliance,
the average daily running time of the ith target electrical appliance is, and N is the number of days contained in the preset time period. In the predicted power consumption obtained through the calculation of the clustering result and the actual operation parameters, the superposition influence of different preset factors in the prediction period on the output power of the target electrical appliance is reflected, so that when the household power consumption is predicted, the power consumption of all the electrical appliances under the influence of different preset factors in the prediction period can be comprehensively and completely considered, a user can clearly and accurately know the accurate predicted value of the household power consumption under the influence of the current power consumption habit and the external environment factors, and the transparency degree of the user on the knowledge channel of the household power consumption and the data acquisition is widened.
S400, power utilization evaluation is carried out on the target electrical appliance according to the predicted power consumption, and an optimal power utilization strategy of the target electrical appliance is generated according to an evaluation result and the clustering result.
In the embodiment, after the power consumption of the target electrical appliance input by the user is predicted, the power consumption of the target electrical appliance used in the household of the user is estimated according to the predicted power consumption obtained through calculation, so that whether waste exists according to the current power consumption habit input by the user or not is known, if the waste exists, the situation indicates that some bad power consumption habits or old electrical appliances consuming more power possibly exist in the target electrical appliance used by the user in daily life, and the like.
In one embodiment, the performing power consumption assessment on the target electrical appliance according to the predicted power consumption and generating an optimal power consumption strategy of the target electrical appliance according to an assessment result and the clustering result includes:
determining whether the predicted power consumption is greater than a preset threshold;
when the predicted power consumption is larger than the preset threshold value, calling the power prediction function corresponding to the clustering center where the target electrical appliance is located under the preset factor;
and extracting the optimal value of the preset factor in the power prediction function corresponding to the clustering center, and generating the optimal power utilization strategy of the target electrical appliance according to the optimal value of the preset factor.
In this embodiment, when power consumption evaluation is performed, the predicted power consumption is compared with a preset threshold, where the preset threshold may be obtained by calculation according to an average of daily average power consumptions of all users in the system, that is, the average of the daily average power consumptions of all users is calculated first, and then the average is multiplied by days when the predicted power consumptions are calculated to obtain the preset threshold, that is, whether the predicted power consumption of the current user exceeds the average of the actual power consumptions of all users is determined, if yes, situations such as power consumption waste caused by overlong operation time, overlong service life and the like exist in actual operation parameters input by the current user are evaluated, at this time, according to a clustering result, a power prediction function corresponding to a clustering center where the target electrical appliance is located under various preset factors is retrieved, and power consumption changes of the target electrical appliance under the influence of different factors are obtained through the power prediction function, the optimal values of the preset factors in the power prediction function are extracted, and the optimal power utilization strategy of the target electric appliance is generated according to the optimal values of the preset factors, so that the targeted power utilization optimization suggestions can be provided according to the actual electric appliance use condition and the big data clustering result of the user and aiming at the power utilization habits of different users, and the targeted and personalized power utilization saving suggestions are realized, for example, the electric appliance sensitive to temperature change can be recommended to the user to close the corresponding electric appliance, such as a water heater, when the temperature is low, the heat preservation power consumption is very large in 24 hours; the electrical appliance with a large influence on aging can extract an optimal annual limit value according to a power prediction function corresponding to a clustering center, specifically, a Y-axis numerical value of the power prediction function, namely a sudden increase position of a power parameter, can be obtained firstly, namely when the value of the power parameter increased along with the increase of the service life exceeds a threshold value, the sudden increase is considered to occur, the optimal service life of the electrical appliance is positioned according to an X-axis numerical value of the power prediction function corresponding to the sudden increase position, a user is recommended to replace the electrical appliance when the service life of the electrical appliance exceeds the optimal service life, an electricity utilization strategy optimization suggestion with accurate data support is realized, and the reliability of the electricity utilization suggestion is improved to help the user to save electricity.
In one embodiment, after the power consumption of the target electrical appliance is evaluated according to the predicted power consumption, and an optimal power consumption strategy of the target electrical appliance is generated according to the evaluation result and the clustering result, the method further includes:
collecting simulated operation parameters of the target electrical appliance in response to a prediction updating operation input by a user based on the optimal power utilization strategy;
and recalculating the simulated power consumption of the target electrical appliance under the prediction factor according to the clustering result and the simulated operation parameters.
In this embodiment, when the predicted power consumption of the user is large and there is waste, the system automatically pushes the corresponding optimal power utilization policy to provide a power saving reference for the daily power utilization of the user, at this time, the user may perform power utilization prediction again based on the power utilization policy, for example, click a preset simulation link on the current interface to perform prediction update operation, click the simulation link to display a new power utilization simulation interface on the display screen, the user may input a corresponding simulation operation parameter of the target electrical appliance on the power utilization simulation interface according to the previously output optimal power utilization policy, that is, the simulation operation parameter is a parameter modified according to the optimal power utilization policy, similarly, the influence of the preset factor on the target electrical appliance is reflected according to the clustering result, and the simulation operation parameter of the target electrical appliance after modification is combined to recalculate the simulation power consumption of the target electrical appliance, that is in this embodiment, through the change of the simulation power consumption habit, the specific circuit numerical value that good power consumption habit can save is directly perceived to show the user, and the visual numerical value that converts the power consumption habit of difference into the quantization to the contrast intensity and the nature directly perceived of power consumption under the reinforcing different use habits.
According to the method embodiment, the actual operation parameters of the target electrical appliance are collected and stored in the preset database, the target electrical appliance in the preset database is subjected to clustering processing according to the preset factors, then the corresponding predicted power consumption is calculated according to the clustering result and the actual operation parameters, the optimal power consumption strategy is generated, the predicted power consumption can be closely related to the actual environment factors in the process of predicting and evaluating the power consumption through the clustering processing based on the preset factors, the accurate predicted power consumption is obtained, the reliable optimal power consumption strategy is further obtained, and the accuracy of power consumption prediction and power consumption suggestion is effectively improved.
It should be noted that, a certain order does not necessarily exist between the above steps, and those skilled in the art can understand, according to the description of the embodiments of the present invention, that in different embodiments, the above steps may have different execution orders, that is, may be executed in parallel, may also be executed interchangeably, and the like.
Another embodiment of the present invention provides a power consumption prediction and evaluation apparatus based on a clustering algorithm, as shown in fig. 3, the apparatus 300 includes:
the acquisition module 11 is used for responding to an electric appliance adding operation input by a user, acquiring actual operation parameters of a target electric appliance and storing the actual operation parameters into a preset database;
the clustering module 12 is configured to perform clustering processing on the collected electric appliances in the preset database based on the influence of preset factors on the power consumption of the target electric appliance, so as to obtain a clustering result of the target electric appliance under the corresponding preset factors;
the prediction module 13 is configured to calculate a predicted power consumption of the target electrical appliance under the preset factor according to the clustering result and the actual operation parameter;
and the evaluation module 14 is configured to perform power utilization evaluation on the target electrical appliance according to the predicted power consumption, and generate an optimal power utilization strategy of the target electrical appliance according to an evaluation result and the clustering result.
The acquisition module 11, the clustering module 12, the prediction module 13 and the evaluation module 14 are connected in sequence, the module referred to in the present invention refers to a series of computer program instruction segments capable of completing a specific function, and is more suitable for describing the execution process of the electricity consumption prediction evaluation based on the clustering algorithm than a program, and the specific implementation of each module refers to the corresponding method embodiment, and is not described herein again.
Another embodiment of the present invention provides a power consumption prediction and evaluation system based on a clustering algorithm, as shown in fig. 4, the system 10 includes:
one or more processors 110 and a memory 120, where one processor 110 is illustrated in fig. 4, the processor 110 and the memory 120 may be connected by a bus or other means, and fig. 4 illustrates a connection by a bus as an example.
The memory 120 is a non-volatile computer-readable storage medium, and can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions corresponding to the electricity consumption prediction evaluation method based on the clustering algorithm in the embodiment of the present invention. The processor 110 executes various functional applications and data processing of the system 10 by executing the non-volatile software programs, instructions and units stored in the memory 120, namely, implements the electricity consumption prediction evaluation method based on the clustering algorithm in the above method embodiment.
The memory 120 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the system 10, and the like. Further, the memory 120 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 120 optionally includes memory located remotely from processor 110, which may be connected to system 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more units are stored in the memory 120, and when executed by the one or more processors 110, perform the electricity prediction evaluation method based on the clustering algorithm in any of the above-described method embodiments, for example, performing the above-described method steps S100 to S400 in fig. 1.
Embodiments of the present invention provide a non-transitory computer-readable storage medium storing computer-executable instructions for execution by one or more processors, e.g., to perform method steps S100-S400 of fig. 1 described above.
By way of example, non-volatile storage media can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), electrically erasable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in many forms such as Synchronous RAM (SRAM), dynamic RAM, (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The disclosed memory components or memory of the operating environment described herein are intended to comprise one or more of these and/or any other suitable types of memory.
In summary, in the electricity consumption prediction evaluation method, apparatus, system and medium based on the clustering algorithm disclosed by the present invention, the method collects the actual operation parameters of the target electrical appliance and stores them in the preset database by responding to the electrical appliance addition operation input by the user; based on the influence of preset factors on the electricity consumption of the target electrical appliance, clustering the collected electrical appliances in a preset database to obtain a clustering result of the target electrical appliance under the corresponding preset factors; calculating the predicted power consumption of the target electrical appliance under the preset factors according to the clustering result and the actual operation parameters; and carrying out power utilization evaluation on the target electrical appliance according to the predicted power consumption, and generating an optimal power utilization strategy of the target electrical appliance according to the evaluation result and the clustering result. Through clustering processing based on preset factors, the predicted power consumption and actual environment factors can be closely related in the process of predicting and evaluating the power consumption, accurate predicted power consumption is obtained, a reliable optimal power utilization strategy is further obtained, and the accuracy of power consumption prediction and power utilization suggestion is effectively improved.
Of course, it will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program, which may be stored in a non-volatile computer-readable storage medium, and the computer program may include the processes of the above method embodiments when executed. The storage medium may be a memory, a magnetic disk, a floppy disk, a flash memory, an optical memory, etc.
It is to be understood that the invention is not limited to the examples described above, but that modifications and variations may be effected thereto by those of ordinary skill in the art in light of the foregoing description, and that all such modifications and variations are intended to be within the scope of the invention as defined by the appended claims.
Claims (8)
1. A power utilization prediction evaluation method based on a clustering algorithm is characterized by comprising the following steps:
responding to an electric appliance adding operation input by a user, acquiring actual operation parameters of a target electric appliance and storing the actual operation parameters into a preset database;
based on the influence of preset factors on the power consumption of the target electrical appliance, clustering the electrical appliances collected in the preset database to obtain a clustering result of the target electrical appliance under the corresponding preset factors;
calculating the predicted power consumption of the target electrical appliance under the preset factors according to the clustering result and the actual operation parameters;
carrying out power utilization evaluation on the target electrical appliance according to the predicted power consumption, and generating an optimal power utilization strategy of the target electrical appliance according to an evaluation result and the clustering result;
the method comprises the following steps of clustering collected electric appliances in a preset database based on the power utilization influence of preset factors on the target electric appliance to obtain the clustering result of the target electric appliance under the corresponding preset factors, wherein the clustering result comprises the following steps:
acquiring output power of the pre-acquired testing electric appliances of corresponding categories when preset factors change according to the categories of the electric appliances acquired in the preset database;
constructing a corresponding power prediction function according to the output power, the rated power of the corresponding test electric appliance and the preset factors, wherein the power prediction function is used for representing the change of the relation between the output power and the rated power of each type of test electric appliance under the influence of different preset factors;
clustering the power prediction function according to a preset clustering algorithm to obtain a plurality of clustering centers, and clustering and grouping the test electric appliances of different types according to the influence generality of preset factors;
identifying a clustering center to which the target electrical appliance belongs under the preset factors to obtain a corresponding clustering result;
the constructing of the corresponding power prediction function according to the output power, the rated power of the corresponding test electrical appliance and the preset factor includes:
calculating a power parameter K, K = P/Pr according to the output power and the rated power of the corresponding test electrical appliance, wherein P is the output power, and Pr is the rated power of the test electrical appliance;
and taking the preset factors as independent variables, and taking the power parameters as dependent variables to construct corresponding power prediction functions.
2. The electricity consumption prediction and evaluation method based on the clustering algorithm as claimed in claim 1, wherein the step of collecting and storing the actual operation parameters of the target electrical appliance in a preset database in response to the electrical appliance adding operation input by the user comprises:
responding to an electric appliance adding operation input by a user, and triggering and displaying a corresponding guide interface on a display screen;
receiving the electric appliance name, the brand model, the service life and the daily average running time of the target electric appliance input by a user on the guide interface;
and calling corresponding rated power in a preset parameter library according to the electric appliance name and the brand model of the target electric appliance to obtain the actual operation parameters of the target electric appliance and store the actual operation parameters in a preset database.
3. The electricity consumption prediction evaluation method based on the clustering algorithm as claimed in claim 2, wherein the calculating the predicted electricity consumption of the target electrical appliance under the preset factors according to the clustering result and the actual operation parameters comprises:
confirming the clustering center of the target electrical appliance according to the clustering result;
obtaining a predicted value of the preset factor according to a predicted time period, and calling a power parameter corresponding to the predicted value according to a power prediction function corresponding to the clustering center;
calculating the predicted power consumption W of the target electrical appliance under the preset factors according to the power parameters, the rated power of the target electrical appliance, the daily average running time and the predicted time period,
4. The electricity utilization prediction evaluation method based on the clustering algorithm according to claim 3, wherein the performing the electricity utilization evaluation on the target electrical appliance according to the predicted electricity utilization amount and generating the optimal electricity utilization strategy of the target electrical appliance according to the evaluation result and the clustering result comprises:
determining whether the predicted power consumption is greater than a preset threshold;
when the predicted power consumption is larger than the preset threshold value, calling the power prediction function corresponding to the clustering center where the target electrical appliance is located under the preset factor;
and extracting the optimal value of the preset factor in the power prediction function corresponding to the clustering center, and generating the optimal power utilization strategy of the target electrical appliance according to the optimal value of the preset factor.
5. The electricity consumption prediction evaluation method based on the clustering algorithm according to claim 4, wherein after the electricity consumption evaluation is performed on the target electrical appliance according to the predicted electricity consumption and the optimal electricity consumption strategy of the target electrical appliance is generated according to the evaluation result and the clustering result, the method further comprises:
collecting simulated operation parameters of the target electrical appliance in response to a prediction updating operation input by a user based on the optimal power utilization strategy;
and recalculating the simulated power consumption of the target electrical appliance under the prediction factor according to the clustering result and the simulated operation parameters.
6. An electricity consumption prediction evaluation device based on a clustering algorithm is characterized by comprising:
the acquisition module is used for responding to the electric appliance adding operation input by a user, acquiring the actual operation parameters of the target electric appliance and storing the actual operation parameters into a preset database;
the clustering module is used for clustering the collected electric appliances in the preset database based on the electricity utilization influence of preset factors on the target electric appliance to obtain a clustering result of the target electric appliance under the corresponding preset factors;
the power control module is specifically used for acquiring the output power of the pre-acquired test electric appliance of the corresponding category when the preset factor changes according to the category of the acquired electric appliance in the preset database;
constructing a corresponding power prediction function according to the output power, the rated power of the corresponding test electric appliance and the preset factors, wherein the power prediction function is used for representing the change of the relation between the output power and the rated power of each type of test electric appliance under the influence of different preset factors;
clustering the power prediction function according to a preset clustering algorithm to obtain a plurality of clustering centers, and clustering and grouping the test electric appliances of different types according to the influence generality of preset factors;
identifying a clustering center to which the target electrical appliance belongs under the preset factors to obtain a corresponding clustering result;
the prediction module is used for calculating the predicted power consumption of the target electrical appliance under the preset factors according to the clustering result and the actual operation parameters;
specifically, the method is used for calculating a power parameter K, K = P/Pr according to the output power and the rated power of the corresponding test electrical appliance, wherein P is the output power, and Pr is the rated power of the test electrical appliance;
taking the preset factors as independent variables and the power parameters as dependent variables to construct corresponding power prediction functions;
and the evaluation module is used for carrying out power utilization evaluation on the target electrical appliance according to the predicted power consumption and generating an optimal power utilization strategy of the target electrical appliance according to an evaluation result and the clustering result.
7. A power usage prediction evaluation system based on a clustering algorithm, the system comprising at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for electricity prediction assessment based on clustering algorithm of any of claims 1-5.
8. A non-transitory computer-readable storage medium having stored thereon computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform the method for electricity prediction assessment based on clustering algorithm of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110983999.6A CN113434690B (en) | 2021-08-25 | 2021-08-25 | Clustering algorithm-based electricity utilization prediction evaluation method, device, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110983999.6A CN113434690B (en) | 2021-08-25 | 2021-08-25 | Clustering algorithm-based electricity utilization prediction evaluation method, device, system and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113434690A CN113434690A (en) | 2021-09-24 |
| CN113434690B true CN113434690B (en) | 2022-02-08 |
Family
ID=77806219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110983999.6A Active CN113434690B (en) | 2021-08-25 | 2021-08-25 | Clustering algorithm-based electricity utilization prediction evaluation method, device, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113434690B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN106779253A (en) * | 2017-02-17 | 2017-05-31 | 广东电网有限责任公司电力科学研究院 | The term load forecasting for distribution and device of a kind of meter and photovoltaic |
| CN106777005A (en) * | 2016-12-07 | 2017-05-31 | 国网天津市电力公司 | User power utilization behavior analysis method based on big data technological improvement clustering algorithm |
| CN108776939A (en) * | 2018-06-07 | 2018-11-09 | 上海电气分布式能源科技有限公司 | The analysis method and system of user power utilization behavior |
| WO2018209913A1 (en) * | 2017-05-18 | 2018-11-22 | 华南理工大学 | Distribution network station area power shortage prediction method based on voltage quality |
| CN110601374A (en) * | 2019-10-21 | 2019-12-20 | 国网电子商务有限公司 | Power utilization management system and power utilization data monitoring method |
| CN111428745A (en) * | 2020-01-03 | 2020-07-17 | 中国电力科学研究院有限公司 | Clustering analysis-based low-voltage user electricity utilization feature extraction method |
| CN112072635A (en) * | 2019-06-11 | 2020-12-11 | 上海芯联芯智能科技有限公司 | Intelligent power supply and utilization system and method and intelligent power utilization system |
| CN112766570A (en) * | 2021-01-19 | 2021-05-07 | 国网湖北省电力有限公司武汉供电公司 | Fusion mining and multivariate application method for resident massive fine-grained electricity consumption data |
| US11070056B1 (en) * | 2020-03-13 | 2021-07-20 | Dalian University Of Technology | Short-term interval prediction method for photovoltaic power output |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2594181A1 (en) * | 2004-12-30 | 2006-07-06 | Proventys, Inc. | Methods, systems, and computer program products for developing and using predictive models for predicting a plurality of medical outcomes, for evaluating intervention strategies, and for simultaneously validating biomarker causality |
-
2021
- 2021-08-25 CN CN202110983999.6A patent/CN113434690B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN106777005A (en) * | 2016-12-07 | 2017-05-31 | 国网天津市电力公司 | User power utilization behavior analysis method based on big data technological improvement clustering algorithm |
| CN106779253A (en) * | 2017-02-17 | 2017-05-31 | 广东电网有限责任公司电力科学研究院 | The term load forecasting for distribution and device of a kind of meter and photovoltaic |
| WO2018209913A1 (en) * | 2017-05-18 | 2018-11-22 | 华南理工大学 | Distribution network station area power shortage prediction method based on voltage quality |
| CN108776939A (en) * | 2018-06-07 | 2018-11-09 | 上海电气分布式能源科技有限公司 | The analysis method and system of user power utilization behavior |
| CN112072635A (en) * | 2019-06-11 | 2020-12-11 | 上海芯联芯智能科技有限公司 | Intelligent power supply and utilization system and method and intelligent power utilization system |
| CN110601374A (en) * | 2019-10-21 | 2019-12-20 | 国网电子商务有限公司 | Power utilization management system and power utilization data monitoring method |
| CN111428745A (en) * | 2020-01-03 | 2020-07-17 | 中国电力科学研究院有限公司 | Clustering analysis-based low-voltage user electricity utilization feature extraction method |
| US11070056B1 (en) * | 2020-03-13 | 2021-07-20 | Dalian University Of Technology | Short-term interval prediction method for photovoltaic power output |
| CN112766570A (en) * | 2021-01-19 | 2021-05-07 | 国网湖北省电力有限公司武汉供电公司 | Fusion mining and multivariate application method for resident massive fine-grained electricity consumption data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113434690A (en) | 2021-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110868241B (en) | Underground cable fault early warning method and device based on multiple models | |
| US20180260920A1 (en) | Method and system for determining energy management strategies | |
| CN104864548A (en) | Air conditioner operating control method and system | |
| US9928467B2 (en) | Apparatus for forecasting water demand | |
| CN102953936A (en) | Unit commitment for wind power generation | |
| CN110866634A (en) | Underground cable fault early warning method and device based on model selection | |
| CN112104505B (en) | Application recommendation method, device, server and computer readable storage medium | |
| WO2016147298A1 (en) | Recommendation device, recommendation method, and computer program | |
| CN112580187A (en) | Dry-type transformer overheating early warning method and device, computer equipment and storage medium | |
| CN115034519A (en) | Method and device for predicting power load, electronic equipment and storage medium | |
| CN109839889A (en) | Equipment recommendation system and method | |
| WO2022039675A1 (en) | Method and apparatus for forecasting weather, electronic device and storage medium thereof | |
| CN112801154A (en) | Behavior analysis method and system for solitary old people | |
| CN115681821A (en) | Automatic odorizing control method for intelligent gas equipment management and Internet of things system | |
| CN108667877B (en) | Method and device for determining recommendation information, computer equipment and storage medium | |
| CN101142559B (en) | Monitoring computer-controlled processes and systems | |
| US20200389026A1 (en) | Electric power generation prediction method based on expected value calculation, electric power generation prediction system based on expected value calculation, and electric power generation prediction program based on expected value calculation | |
| CN113434690B (en) | Clustering algorithm-based electricity utilization prediction evaluation method, device, system and medium | |
| KR102009290B1 (en) | Apparatus and method for analyzing buildings | |
| CN112906896A (en) | Information processing method and device and computing equipment | |
| CN111472941A (en) | Fan state judgment method and device and storage medium | |
| CN113479032B (en) | Parking air conditioner control method and system | |
| KR20230093874A (en) | Boiler management apparatus and method for generating prediction model of boiler based on big-data | |
| KR102542488B1 (en) | Method and Apparatus for Predicting Appliance Power Usage State Using Non Intrusive Load Monitoring Based on Long-Short Term Memory | |
| CN115801845B (en) | Industrial Internet data acquisition method and related equipment based on edge calculation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |