CN113408659A - Building energy consumption integrated analysis method based on data mining - Google Patents
Building energy consumption integrated analysis method based on data mining Download PDFInfo
- Publication number
- CN113408659A CN113408659A CN202110800904.2A CN202110800904A CN113408659A CN 113408659 A CN113408659 A CN 113408659A CN 202110800904 A CN202110800904 A CN 202110800904A CN 113408659 A CN113408659 A CN 113408659A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- building energy
- data
- analysis
- integrated analysis
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q50/08—Construction
Abstract
The invention provides a building energy consumption integrated analysis method based on data mining, which comprises the following steps: identifying a building energy consumption mode by adopting a Gaussian mixture model; classifying the historical building energy consumption data by adopting a decision tree algorithm; performing outlier analysis on the classified historical building energy consumption data by adopting a local outlier detection algorithm based on density, and identifying abnormal building energy consumption data; finding out building energy consumption influence factors by adopting a gray level correlation analysis algorithm according to the building energy consumption normal data; training the feedforward neural network by using a conjugate gradient method to obtain a building energy consumption integrated analysis prediction model; and predicting the future building energy consumption condition by using a building energy consumption integrated analysis prediction model according to the real-time building energy consumption data. The invention can solve the technical problem that when the building energy consumption is analyzed in the prior art, whether the current building energy consumption data is abnormal or not is only analyzed, and the building energy consumption cannot be predicted.
Description
Technical Field
The invention relates to the technical field of building energy conservation, in particular to a building energy consumption integrated analysis method based on data mining.
Background
According to data statistics in recent years, in the composition of terminal energy consumption in our country, the building energy consumption accounts for more than 33% of the total energy consumption of the district and town, so it is very important to reduce the building energy consumption in order to achieve the goal of conservation-oriented society, and therefore, the analysis of the situation of the building energy consumption is needed. In the field of building energy consumption data analysis, in order to mine more comprehensive information from building energy consumption historical data, an integrated building energy consumption analysis method is gradually started, and a common method is to analyze the building energy consumption through a series of steps such as classification, outlier analysis, correlation analysis, prediction and the like; through the analysis and prediction of the building energy consumption, the method can be used as a reference when implementing a scheme for reducing the building energy consumption.
In the prior art, CN102289585A discloses a public building energy consumption real-time monitoring method based on data mining, which includes the following steps: s1: building an energy consumption mode decision tree; s2: acquiring building energy consumption data in real time; s3: judging whether the current building energy consumption data are energy consumption abnormal points or not, carrying out mode matching on the current building energy consumption data and the affiliated building energy consumption mode judgment tree, and judging whether the current building energy consumption data are outliers or not. According to the technical scheme, the specific energy consumption mode of the building is identified by clustering analysis on historical energy consumption data, the building energy consumption mode decision tree is obtained after data classification, dynamically collected energy consumption data are subjected to mode matching in the real-time building energy consumption monitoring process, outlier analysis is carried out on the dynamically collected energy consumption data and historical data with the same mode, and whether the current building energy consumption data are abnormal or not can be judged.
However, when the above technical scheme is used for analyzing the building energy consumption, only whether the current building energy consumption data is abnormal or not is analyzed, the building energy consumption cannot be predicted, and the actual requirement for comprehensively analyzing and predicting the building energy consumption cannot be met.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a building energy consumption integration analysis method based on data mining, and aims to solve the technical problems that when building energy consumption is analyzed in the prior art, whether the current building energy consumption data is abnormal or not is only analyzed, building energy consumption cannot be predicted, and building energy consumption cannot be comprehensively analyzed and predicted.
The invention adopts the technical scheme that a building energy consumption integrated analysis method based on data mining comprises the following steps:
s1, identifying the building energy consumption mode by adopting a Gaussian mixture model;
s2, classifying the historical building energy consumption data by adopting a decision tree algorithm according to the building energy consumption mode;
s3, performing outlier analysis on the classified historical building energy consumption data by adopting a local outlier detection algorithm based on density, and identifying abnormal building energy consumption data;
s4, deleting the abnormal building energy consumption data from the historical building energy consumption data to obtain normal building energy consumption data;
s5, finding out building energy consumption influence factors by adopting a gray level correlation analysis algorithm according to the normal data of the building energy consumption;
s6, training the artificial neural network by using a conjugate gradient method according to the normal data of the building energy consumption and the influence factors of the building energy consumption to obtain a building energy consumption integrated analysis prediction model;
and S7, predicting the future building energy consumption situation by using the building energy consumption integrated analysis prediction model according to the real-time building energy consumption data.
Further, adopting a Gaussian mixture model to identify the building energy consumption mode, comprising:
s1-1, setting a category value, and randomly initializing the expectation and variance of each single Gaussian distribution and the weight of the single Gaussian distribution in the overall distribution;
s1-2, calculating the probability that each building energy consumption historical data belongs to each Gaussian distribution;
s1-3, calculating a total value according to the weight value and the probability calculated in the step S1-2, wherein the calculation aim is to make the total value maximum;
s1-4, repeating the steps S1-2 and S1-3 until the change amplitude of the total value is smaller than or equal to the amplitude threshold value.
Further, the decision tree algorithm is a C4.5 decision tree algorithm.
Further, performing outlier analysis on the classified historical building energy consumption data, including:
s3-1, inputting the minimum number of data points in the neighborhood;
s3-2, performing neighborhood search on each data point P in the historical building energy consumption data;
s3-3, calculating the local reachable density of the data point P;
s3-4, calculating a local outlier factor of the data point P according to the local reachable density;
and S3-5, determining the data points with the local outlier factors larger than the data anomaly threshold as outliers.
Further, the artificial neural network is a feedforward neural network.
Further, the building energy consumption influencing factors include: the temperature of the wet bulb, the temperature of the dry bulb, the humidity and the wind speed are the working states of holidays and non-holidays.
Further, the building energy consumption integrated analysis prediction model construction method comprises the following steps:
s6-1, constructing a training set and a testing set;
s6-2, setting hyper-parameters of the feedforward neural network, wherein the number of nodes of the hidden layer is 9;
s6-3, using a training set, taking the wet bulb temperature, the dry bulb temperature, the humidity, the wind speed and the working state as input, taking the building energy consumption normal data as output, and using a conjugate gradient method to train the feedforward neural network;
and S6-4, testing the trained feedforward neural network by using a test set, optimizing the hyper-parameters of the feedforward neural network, and obtaining the building energy consumption integrated analysis prediction model.
In a second aspect, a building energy consumption integrated analysis system based on data mining is provided, and comprises a building energy consumption data acquisition module and a building energy consumption integrated analysis prediction module;
the building energy consumption data acquisition module is used for acquiring historical building energy consumption data and real-time building energy consumption data;
and the building energy consumption integration analysis prediction module predicts the future building energy consumption by using the building energy consumption integration analysis prediction model provided by the first aspect.
In a third aspect, an electronic device is provided, including:
one or more processors;
storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the method for building energy consumption integration analysis based on data mining provided by the first aspect.
In a fourth aspect, a computer readable storage medium is provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the method for building energy consumption integration analysis based on data mining provided in the first aspect.
According to the technical scheme, the beneficial technical effects of the invention are as follows:
1. the adoption of the Gaussian mixture model to identify the building energy consumption mode can overcome the defect that other clustering algorithms simply classify the building energy consumption data in a distance mode, and is closer to the actual situation.
2. When the conjugate gradient method is used for carrying out the feedforward neural network parameter training, only the first-order derivation is carried out on the function, and the operations of the second-order derivation of the function and the inversion of the matrix are not needed. Therefore, the defect of low convergence speed caused by only referring to the gradient of the function is avoided, and excessive storage and calculation resources consumed by complex operation are also avoided.
3. The energy consumption of the building can be accurately predicted by using the feedforward neural network, and the effect of comprehensively analyzing and predicting the energy consumption of the building is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
Fig. 1 is a flow chart of a building energy consumption integration analysis method according to embodiment 1 of the present invention;
fig. 2 is a schematic flow chart of building energy consumption integrated analysis prediction model construction according to embodiment 1 of the present invention;
FIG. 3 is a schematic diagram of a feedforward neural network according to embodiment 1 of the present invention;
fig. 4 is a graph showing the comparison effect between the predicted value and the actual value of the building energy consumption in embodiment 1 of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
Example 1
The embodiment provides a building energy consumption integration analysis method based on data mining, which predicts the future building energy consumption situation by using a building energy consumption integration analysis prediction model, and specifically comprises the following steps:
s1, adopting the Gaussian mixture model to identify the building energy consumption mode
The building energy consumption data is closely related to the production and life of human beings, so the distribution of the energy consumption data conforms to Gaussian distribution. The gaussian mixture model is to identify multiple gaussian distribution models corresponding to one object, and display the distribution rule of all data in a weighted manner. Compared with clustering algorithms such as DBSCAN clustering algorithm and K-medoids clustering algorithm, the Gaussian mixture model is closer to the actual situation, and is not only used for classifying the building energy consumption data in a distance mode.
In a specific embodiment, when the gaussian mixture model is used for identifying the building energy consumption mode, the following steps are carried out:
s1-1, setting a category value, and randomly initializing the expectation and variance of each single Gaussian distribution and the weight of the single Gaussian distribution in the overall distribution.
Because the energy consumption difference of the buildings on different dates is larger, for example, the energy consumption of the buildings in the workplace and the field is larger in working days, and the energy consumption is smaller in rest days; the residential buildings have low energy consumption in working days and high energy consumption in rest days; therefore, in a specific embodiment, the category modes of the building energy consumption are divided into 2 types, one type is a holiday mode, and the other type is a non-holiday mode.
And S1-2, calculating the probability that each building energy consumption historical data belongs to each Gaussian distribution, and taking whether the point is close to the center of a certain Gaussian distribution as a measurement standard.
S1-3, calculating a total value according to the weight value and the probability calculated in the step S1-2, wherein the calculation aim is to make the total value maximum.
S1-4, repeating the steps S1-2 and S1-3 until the change amplitude of the total value is smaller than or equal to the amplitude threshold value. In a specific embodiment, to reduce the operation, the total value is not changed greatly, for example, the change amplitude is less than 10%.
By identifying the building energy consumption mode, the building energy consumption historical data can be classified, so that the subsequent data processing result is more accurate and the efficiency is higher.
S2, classifying the historical building energy consumption data by adopting a decision tree algorithm according to the building energy consumption mode
The decision tree algorithm can make feasible classification for large data sources in a short time, and is efficient and accurate. In a specific implementation mode, according to the data characteristics of the building energy consumption, the C4.5 decision tree algorithm can be used for rapidly and effectively classifying the historical data of the building energy consumption. The C4.5 decision tree algorithm uses the information gain rate, by which the optimal grouping variables and partitioning points can be determined for the decision tree, to select attributes.
S3, performing outlier analysis on the classified historical building energy consumption data by adopting a density-based local outlier detection algorithm, and identifying abnormal building energy consumption data
The local outlier detection algorithm represents the degree of abnormality of the object P by an abnormality factor of the object P, and the larger the abnormality factor is, the greater the possibility of abnormality is. In a specific embodiment, the outlier analysis is performed on the classified historical building energy consumption data by the following method:
s3-1, inputting the minimum number of data points in the neighborhood;
s3-2, performing neighborhood search on each data point P in the historical building energy consumption data;
s3-3, calculating the local reachable density of the data point P;
s3-4, calculating a local outlier factor of the data point P according to the local reachable density;
s3-5, determining the data points with the local outlier factors larger than the data anomaly threshold as outliers;
and defining the data corresponding to the cluster points as abnormal building energy consumption data by the method of the step.
S4, deleting the abnormal building energy consumption data from the historical building energy consumption data to obtain the normal building energy consumption data
In a specific embodiment, in order to make the subsequent data analysis result more accurate, the abnormal building energy consumption data needs to be deleted from the historical building energy consumption data, and the normal building energy consumption data is used for subsequent data analysis.
S5, finding out influence factors of building energy consumption by adopting a gray level correlation analysis algorithm according to the normal data of the building energy consumption
The gray level correlation analysis algorithm can reduce the loss caused by information asymmetry, has low requirements on sample data and has high calculation speed. When the gray level correlation analysis is carried out, if the parent factor and the child factor change trends, the synchronous change degree is higher, namely the correlation degree of the parent factor and the child factor is higher. And calculating the association degree of the mother factor and the child factor, wherein the larger the value is, the larger the influence of the child factor on the mother factor is.
In a specific embodiment, the factors influencing the energy consumption of the building mainly comprise the external climate conditions and the working state. The external climate conditions include temperature, humidity, wind speed, etc. The identification of the building energy consumption mode in the operating state according to step S1 can be classified into a holiday mode and a non-holiday mode.
According to the normal data of the building energy consumption, selecting the external climate condition data in the same period as the normal data of the building energy consumption, calculating the correlation degree of the external climate condition and the building energy consumption by adopting a gray level correlation analysis algorithm, selecting the normal data of the building energy consumption as a mother factor and the external climate condition as a child factor, and calculating to obtain the correlation degree of the 4 factors including the wet bulb temperature, the dry bulb temperature, the humidity and the wind speed in the external climate condition and the building energy consumption to be more than 0.6, which shows that the 4 factors have larger influence on the building energy consumption. The wet bulb temperature and the dry bulb temperature are more highly related to the energy consumption of the building than the highest temperature and the lowest temperature of the day.
The method of the step determines the wet bulb temperature, the dry bulb temperature, the humidity, the wind speed and whether the working state is the working state of holidays and non-holidays, and the 5 factors are used as the influence factors of the building energy consumption.
S6, training the artificial neural network by using a conjugate gradient method according to the normal data of the building energy consumption and the influence factors of the building energy consumption to obtain a building energy consumption integrated analysis prediction model
In the implementation, the artificial neural network is a feedforward neural network based on a conjugate gradient method. In the process of solving the neural network parameters by using the conjugate gradient method, only first-order derivation is needed to be carried out on the function, and operations of function second-order derivation and matrix inversion are not needed. Therefore, the defect of low convergence speed caused by only referring to the gradient of the function is avoided, and excessive storage and calculation resources consumed by complex operation are also avoided. Besides the above characteristics, the conjugate gradient method has the advantages of being not easily affected by other factors, high in step convergence, and free of setting of initial values. The method for constructing the building energy consumption integrated analysis prediction model, as shown in fig. 2, specifically comprises the following steps:
s6-1, constructing a training set and a testing set
In a specific embodiment, when the training set and the test set are constructed by using the building energy consumption normal data, the external climate condition data and the working state data, the ratio of the training set to the test set is preferably 3: 1.
S6-2, setting hyper-parameters of feedforward neural network
In a specific embodiment, when the number of nodes of the hidden layer is set to 9, the generated errors of the whole network are small. And initializing the weight according to the number of the nodes of the input layer and the hidden layer. The structure of the feedforward neural network is shown in fig. 3.
S6-3, using a training set, taking the wet bulb temperature, the dry bulb temperature, the humidity, the wind speed and the working state as input, taking the normal data of the building energy consumption as output, and using a conjugate gradient method to train the feedforward neural network
The activation function of the training adopts a Sigmoid function, the mean square error MSE is used as a loss function, and a regular term is added as an additional evaluation standard to prevent overfitting in the training process. Specifically, a learning sample is taken and is transmitted into an input layer in the forward direction; normalizing the sample, and scaling the interval to be within the interval of [0.1,0.9 ]; clustering classification adds operating states (i.e., energy consumption pattern classification); calculating the input and output of each layer of neurons; calculating an output error; training the feedforward neural network by using a conjugate gradient method, and reversely adjusting the weight and the threshold in the network; and (4) iterating for multiple times until the training is completed.
And S6-4, testing the trained feedforward neural network by using a test set, optimizing the hyper-parameters of the feedforward neural network, and obtaining the building energy consumption integrated analysis prediction model.
In order to verify the prediction effect of the model, when the trained feedforward neural network is tested by using a test set, the comparison effect between the predicted value and the true value is shown in fig. 4, and the prediction accuracy is over 90%.
By the method in the step, the building energy consumption integrated analysis prediction model can be obtained.
S7, predicting the future building energy consumption situation by using the building energy consumption integrated analysis prediction model according to the real-time building energy consumption data
The method comprises the steps of obtaining real-time building energy consumption data in a period of time, such as one week, inputting the real-time building energy consumption data in the week into a building energy consumption integrated analysis prediction model, predicting the building energy consumption situation in the future period of time, and obtaining the prediction result of the future building energy consumption as the output of the model.
Through the technical scheme of this embodiment, can carry out comparatively accurate prediction to the building energy consumption through using feedforward neural network, realize carrying out comprehensive analysis and prediction's effect to the building energy consumption.
Example 2
The building energy consumption integrated analysis system based on data mining comprises a building energy consumption data acquisition module and a building energy consumption integrated analysis prediction module;
the building energy consumption data acquisition module is used for acquiring historical building energy consumption data and real-time building energy consumption data;
the building energy consumption integrated analysis and prediction module predicts the future building energy consumption by using the building energy consumption integrated analysis and prediction model provided in embodiment 1.
Example 3
Provided is an electronic device including:
one or more processors;
storage means for storing one or more programs;
when executed by one or more processors, the one or more programs cause the one or more processors to implement the data mining-based building energy consumption integration analysis method provided in embodiment 1.
Example 4
There is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements the data mining-based building energy consumption integration analysis method provided in embodiment 1.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (10)
1. A building energy consumption integrated analysis method based on data mining is characterized by comprising the following steps:
s1, identifying the building energy consumption mode by adopting a Gaussian mixture model;
s2, classifying the historical building energy consumption data by adopting a decision tree algorithm according to the building energy consumption mode;
s3, performing outlier analysis on the classified historical building energy consumption data by adopting a local outlier detection algorithm based on density, and identifying abnormal building energy consumption data;
s4, deleting the abnormal building energy consumption data from the historical building energy consumption data to obtain normal building energy consumption data;
s5, finding out building energy consumption influence factors by adopting a gray level correlation analysis algorithm according to the normal data of the building energy consumption;
s6, training the artificial neural network by using a conjugate gradient method according to the normal data of the building energy consumption and the influence factors of the building energy consumption to obtain a building energy consumption integrated analysis prediction model;
and S7, predicting the future building energy consumption situation by using the building energy consumption integrated analysis prediction model according to the real-time building energy consumption data.
2. The building energy consumption integration analysis method based on data mining as claimed in claim 1, wherein the identifying the building energy consumption pattern by using the Gaussian mixture model comprises:
s1-1, setting a category value, and randomly initializing the expectation and variance of each single Gaussian distribution and the weight of the single Gaussian distribution in the overall distribution;
s1-2, calculating the probability that each building energy consumption historical data belongs to each Gaussian distribution;
s1-3, calculating a total value according to the weight value and the probability calculated in the step S1-2, wherein the calculation aim is to make the total value maximum;
s1-4, repeating the steps S1-2 and S1-3 until the change amplitude of the total value is smaller than or equal to the amplitude threshold value.
3. The data mining-based building energy consumption integration analysis method according to claim 1, wherein the decision tree algorithm is a C4.5 decision tree algorithm.
4. The building energy consumption integrated analysis method based on data mining as claimed in claim 1, wherein the performing of outlier analysis on the classified building energy consumption historical data comprises:
s3-1, inputting the minimum number of data points in the neighborhood;
s3-2, performing neighborhood search on each data point P in the historical building energy consumption data;
s3-3, calculating the local reachable density of the data point P;
s3-4, calculating a local outlier factor of the data point P according to the local reachable density;
and S3-5, determining the data points with the local outlier factors larger than the data anomaly threshold as outliers.
5. The method of claim 1, wherein the artificial neural network is a feedforward neural network.
6. The integrated analysis method for building energy consumption based on data mining as claimed in claim 5, wherein the building energy consumption influence factors include: the temperature of the wet bulb, the temperature of the dry bulb, the humidity and the wind speed are the working states of holidays and non-holidays.
7. The building energy consumption integration analysis method based on data mining as claimed in claim 6, wherein the building energy consumption integration analysis prediction model construction method comprises:
s6-1, constructing a training set and a testing set;
s6-2, setting hyper-parameters of the feedforward neural network, wherein the number of nodes of the hidden layer is 9;
s6-3, using a training set, taking the wet bulb temperature, the dry bulb temperature, the humidity, the wind speed and the working state as input, taking the building energy consumption normal data as output, and using a conjugate gradient method to train the feedforward neural network;
and S6-4, testing the trained feedforward neural network by using a test set, optimizing the hyper-parameters of the feedforward neural network, and obtaining the building energy consumption integrated analysis prediction model.
8. A building energy consumption integrated analysis system based on data mining is characterized by comprising a building energy consumption data acquisition module and a building energy consumption integrated analysis prediction module;
the building energy consumption data acquisition module is used for acquiring historical building energy consumption data and real-time building energy consumption data;
the building energy consumption integrated analysis and prediction module predicts the future building energy consumption by using the building energy consumption integrated analysis and prediction model of any one of claims 1-6.
9. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of data mining based building energy consumption integration analysis of any of claims 1-6.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for integrated analysis of building energy consumption based on data mining of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110800904.2A CN113408659A (en) | 2021-07-15 | 2021-07-15 | Building energy consumption integrated analysis method based on data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110800904.2A CN113408659A (en) | 2021-07-15 | 2021-07-15 | Building energy consumption integrated analysis method based on data mining |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113408659A true CN113408659A (en) | 2021-09-17 |
Family
ID=77686454
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110800904.2A Pending CN113408659A (en) | 2021-07-15 | 2021-07-15 | Building energy consumption integrated analysis method based on data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408659A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116734918A (en) * | 2023-06-05 | 2023-09-12 | 宁夏中昊银晨能源技术服务有限公司 | Indoor environment monitoring system suitable for near zero energy consumption building |
| CN116738856A (en) * | 2023-06-27 | 2023-09-12 | 广州珠江外资建筑设计院有限公司 | Building energy consumption prediction method and system |
| CN116955963A (en) * | 2023-09-19 | 2023-10-27 | 北京英沣特能源技术有限公司 | Heating ventilation energy-saving ladder optimizing control method based on historical data analysis |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289585A (en) * | 2011-08-15 | 2011-12-21 | 重庆大学 | Real-time monitoring method for energy consumption of public building based on data mining |
| CN104484715A (en) * | 2014-11-28 | 2015-04-01 | 江苏大学 | Neural network and particle swarm optimization algorithm-based building energy consumption predicting method |
| CN106250905A (en) * | 2016-07-08 | 2016-12-21 | 复旦大学 | A kind of real time energy consumption method for detecting abnormality of combination colleges and universities building structure feature |
-
2021
- 2021-07-15 CN CN202110800904.2A patent/CN113408659A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289585A (en) * | 2011-08-15 | 2011-12-21 | 重庆大学 | Real-time monitoring method for energy consumption of public building based on data mining |
| CN104484715A (en) * | 2014-11-28 | 2015-04-01 | 江苏大学 | Neural network and particle swarm optimization algorithm-based building energy consumption predicting method |
| CN106250905A (en) * | 2016-07-08 | 2016-12-21 | 复旦大学 | A kind of real time energy consumption method for detecting abnormality of combination colleges and universities building structure feature |
Non-Patent Citations (1)
| Title |
|---|
| 梁家兴: "建筑能耗集成化智能分析方法的优化研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116734918A (en) * | 2023-06-05 | 2023-09-12 | 宁夏中昊银晨能源技术服务有限公司 | Indoor environment monitoring system suitable for near zero energy consumption building |
| CN116738856A (en) * | 2023-06-27 | 2023-09-12 | 广州珠江外资建筑设计院有限公司 | Building energy consumption prediction method and system |
| CN116738856B (en) * | 2023-06-27 | 2024-04-02 | 广州珠江外资建筑设计院有限公司 | Building energy consumption prediction method and system |
| CN116955963A (en) * | 2023-09-19 | 2023-10-27 | 北京英沣特能源技术有限公司 | Heating ventilation energy-saving ladder optimizing control method based on historical data analysis |
| CN116955963B (en) * | 2023-09-19 | 2023-12-08 | 北京英沣特能源技术有限公司 | Heating ventilation energy-saving ladder optimizing control method based on historical data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113408659A (en) | Building energy consumption integrated analysis method based on data mining | |
| CN110335168B (en) | Method and system for optimizing power utilization information acquisition terminal fault prediction model based on GRU | |
| CN110571792A (en) | Analysis and evaluation method and system for operation state of power grid regulation and control system | |
| CN112363896B (en) | Log abnormality detection system | |
| CN112734128A (en) | 7-day power load peak value prediction method based on optimized RBF | |
| CN111814956A (en) | Multi-task learning air quality prediction method based on multi-dimensional secondary feature extraction | |
| CN110598902A (en) | Water quality prediction method based on combination of support vector machine and KNN | |
| CN116383773A (en) | Data center energy efficiency anomaly detection method, system and medium based on self-adaptive prediction interval | |
| CN114169254A (en) | Abnormal energy consumption diagnosis method and system based on short-term building energy consumption prediction model | |
| CN116432123A (en) | Electric energy meter fault early warning method based on CART decision tree algorithm | |
| CN111984514B (en) | Log anomaly detection method based on Prophet-bLSTM-DTW | |
| CN113033898A (en) | Electrical load prediction method and system based on K-means clustering and BI-LSTM neural network | |
| CN114997342B (en) | SCR fault diagnosis method, device, equipment and storage medium | |
| CN113723670B (en) | Photovoltaic power generation power short-term prediction method with variable time window | |
| CN116470491A (en) | Photovoltaic power probability prediction method and system based on copula function | |
| CN116151799A (en) | BP neural network-based distribution line multi-working-condition fault rate rapid assessment method | |
| CN113726559B (en) | Based on artificial intelligence network safety analysis early warning system | |
| CN114912716A (en) | Short-term power load prediction method and system based on bidirectional long-term and short-term memory network | |
| CN114676887A (en) | River water quality prediction method based on graph convolution STG-LSTM | |
| CN114741972A (en) | Construction method of seasonal prediction model of air pollutant concentration | |
| CN113762591A (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM counterstudy | |
| CN116365519B (en) | Power load prediction method, system, storage medium and equipment | |
| Hu et al. | The early warning model of dust concentration in smart construction sites based on long short term memory network | |
| Hong et al. | Drainage network flow anomaly classification based on XGBoost | |
| CN116843080B (en) | Machine learning-based carbon element footprint prediction method and system for urea production |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210917 |