CN111695792A - Subway illumination system abnormal energy consumption analysis method based on multi-attribute clustering - Google Patents
Subway illumination system abnormal energy consumption analysis method based on multi-attribute clustering Download PDFInfo
- Publication number
- CN111695792A CN111695792A CN202010473632.5A CN202010473632A CN111695792A CN 111695792 A CN111695792 A CN 111695792A CN 202010473632 A CN202010473632 A CN 202010473632A CN 111695792 A CN111695792 A CN 111695792A
- Authority
- CN
- China
- Prior art keywords
- attribute
- data
- clustering
- energy consumption
- cluster
- 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.)
- Granted
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 105
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 61
- 238000005286 illumination Methods 0.000 title claims abstract description 27
- 238000004458 analytical method Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 49
- 239000011159 matrix material Substances 0.000 claims abstract description 29
- 239000013598 vector Substances 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000009467 reduction Effects 0.000 claims abstract description 12
- 238000010606 normalization Methods 0.000 claims abstract description 11
- 230000008859 change Effects 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 230000001186 cumulative effect Effects 0.000 claims description 6
- 238000000638 solvent extraction Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The invention relates to a method for analyzing abnormal energy consumption of a subway lighting system based on multi-attribute clustering, which comprises the following steps: corresponding the energy consumption data of the lighting system with respective equipment attributes to form an energy consumption analysis multi-attribute value system; converting the attribute of each non-numerical illumination system into a numerical type, carrying out normalization processing on each attribute, converting the attribute into an attribute value, and establishing a vector of each attribute value to all data; reducing the dimension of a multi-attribute value system of the data, and carrying out Kmeans clustering on the data matrix after dimension reduction; sequentially comparing the distance from each main component in the remaining data which is not subjected to clustering operation to each clustering center, summing the distances from the main attribute of each lighting device to each cluster, and distributing the data to the cluster of the clustering center closest to the main attribute of each lighting device to obtain k clusters; calculating the principal component mean values of all the points in each cluster, and taking the principal component mean values as the mass center until the change of the cluster center tends to be stable to form k clusters; based on the k clusters formed, analysis of the results was performed.
Description
Technical Field
The invention relates to the field of rail transit, in particular to abnormal energy consumption analysis of a subway station illumination system based on multi-attribute clustering.
Background
With the rapid development of the urbanization process in China, the urban rail transit construction is also rapidly developed. The subway generated in compliance with the era gradually becomes an important transportation tool for citizens to go out, and therefore huge energy consumption is brought. The subway mainly uses electricity as energy, but the power consumption of the subway is extremely high, and like in first-line cities such as Beijing, Shanghai and Shenzhen, the power consumption of the subway accounts for more than 30% of the operation cost, the power consumption per year is about 1 hundred million KWh, and the electricity cost is huge. Independent lighting systems are arranged in subway stations and sections to provide convenient and comfortable light sources for passengers and workers. According to GB50034-2004 architectural lighting design standard, GB50016-2006 architectural design fire-proof standard, GB/T162752008 urban rail transit lighting and other related policy and regulations and documents clearly stipulate that the subway lighting system accounts for 14.2% -16.1% of the average equipment load of the subway station, and under the actual condition, the subway lighting system accounts for 20% -30% of the average equipment load of the subway station, and the first-line city accounts for more obviously. Although the subway system has been developed to the intelligent stage, the problem of excessive energy consumption of the lighting system still cannot be solved well.
The load grade, the function, the power supply and distribution mode, the power consumption power, the power supply time and the like of the lighting system equipment are basic attributes influencing the energy consumption of the lighting system, and are basic elements for providing comfortable light sources for passengers and workers, ensuring the normal illumination of the subway and timely processing the occurrence of emergency situations. Therefore, the method can find the abnormal energy consumption of the subway lighting system in time, especially the abnormal conditions of interval work lighting, safety lighting and emergency lighting, and is an important task for guaranteeing the normal operation of the subway.
However, according to the current equipment and equipment technical conditions of the subway station, in the operation and maintenance of the lighting system, the lighting system is mostly based on regular manual detection and random manual monitoring, such energy consumption abnormity judgment has certain limitation, on one hand, the fact that equipment energy consumption abnormity is found in time cannot be guaranteed, on the other hand, specific equipment with abnormal energy consumption is difficult to accurately locate, and the consumed time is long, so that the practical energy-saving effect is not achieved, a specific effective algorithm is used, historical lighting energy consumption is analyzed from a background, abnormal energy consumption is found out, the equipment is controlled in a targeted manner, the energy-saving effect is obvious, and the operation and maintenance cost can be reduced.
The term "abnormal energy consumption" means that the energy consumption data are completely independent in all the energy consumption data sets, and the energy consumption data are not randomly biased but generated by completely different mechanisms. The subway lighting system has the characteristics of randomness, complexity and periodicity due to abnormal energy consumption. The method for monitoring the abnormal energy consumption of the subway lighting system has high uncertainty, and has the problems that the abnormal energy consumption condition of the lighting system is difficult to accurately detect and an accurate abnormal energy consumption detection mathematical model is difficult to establish in the subway operation process.
Anomaly detection is widely used in various application fields, including disease monitoring, equipment state monitoring, building energy consumption, network intrusion and other fields. The monitoring method of the energy consumption abnormity comprises a regression method, a k-nearest neighbor (KNN), an entropy method and a clustering method. Clustering is the most common anomaly monitoring method and is very sensitive to abnormal points in data. The category of the clustering algorithm can be defined according to the classification of the devices of the lighting system, but has no accuracy; the clustering center is selected randomly, so that the time complexity of judging the abnormal energy consumption is increased, and the situation is more serious under the condition of larger data volume. In addition, for the subway lighting system, due to different attributes among the devices, the abnormal state of the subway lighting system cannot be simply detected from the energy consumption value, and the abnormal energy consumption analysis is carried out by integrating multiple attributes.
Disclosure of Invention
The invention aims to provide a method for analyzing abnormal energy consumption of a subway lighting system based on multi-attribute clustering, which is used for solving the problems in the prior art.
The invention discloses a method for analyzing abnormal energy consumption of a subway lighting system based on multi-attribute clustering, which comprises the following steps of: and corresponding the energy consumption data of the lighting system with the respective equipment attributes to form an energy consumption analysis multi-attribute value system A ═ a1，a2，...，aiWhere i denotes the number of illumination system attributes, aiRepresenting an attribute name; converting the attribute of each non-numerical illumination system into a numerical type, carrying out normalization processing on each attribute, converting the attribute into an attribute value, and establishing a vector of each attribute value to all data; reducing the dimension of a multi-attribute value system of the data, constructing a principal component parameter system which comprises a plurality of principal component data, determining the number k of clusters according to an inflection point method, selecting k pieces of equipment data as cluster centers of initial clustering of Kmeans, and carrying out Kmeans clustering on a data matrix after dimension reduction; sequentially comparing the distance from each main component in the remaining data which is not subjected to clustering operation to each clustering center, summing the distances from the main attribute of each lighting device to each cluster, and distributing the data to the cluster of the clustering center closest to the main attribute of each lighting device to obtain k clusters; calculating the principal component mean values of all the points in each cluster, and taking the principal component mean values as the mass center until the change of the cluster center tends to be stable to form k clusters; based on the k clusters formed, analysis of the results was performed.
According to an embodiment of the method for analyzing the abnormal energy consumption of the subway illumination system based on the multi-attribute clustering, the attributes of the illumination system comprise: the device Type, the device Power P, the load Level, the Power supply and distribution mode Power, the energy consumption EC, the Time and the service life Age.
According to an embodiment of the method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering, the analyzing according to the result comprises the following steps: data which are not allocated to any cluster are abnormal data, and energy consumption of corresponding equipment is abnormal; and bringing abnormal equipment into a daily important monitoring range.
According to an embodiment of the method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering, the step of converting each non-numerical lighting system attribute into the numerical value includes the steps of setting a certain numerical value to represent each type of the non-numerical lighting system attribute, and correspondingly converting each type into the numerical value.
According to an embodiment of the method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering, the method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering comprises the following steps of: and after the initial division, a plurality of pieces of data belong to the same cluster, each cluster is used as one piece of data, each attribute column is averaged, so that the plurality of pieces of data are converted into one piece of data to form new data until the change of the cluster center tends to be stable, and k clusters are formed.
According to an embodiment of the method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering, the step of converting the non-numerical attributes into numerical attributes comprises the following steps: the first level, the second level and the third level are respectively corresponding to 1, 2 and 3, and the centralized power supply, the distributed power supply and the hybrid power supply of the power supply and distribution mode are respectively corresponding to 0, 1 and 2.
According to an embodiment of the method for analyzing the abnormal energy consumption of the subway illumination system based on the multi-attribute clustering, disclosed by the invention, the data of each attribute are subjected to normalization processing, vectors of each attribute to all data are established, and a multi-attribute matrix M of illumination system equipment is establishedniThe normalization processing formula includes:
wherein, Value represents a certain attribute Value corresponding to each device of the energy consumption data, and refers to a Value corresponding to the device under the attribute, and all devices have multiple values under the attributeminMinimum of all values in the representation, ValuemaxRepresenting the maximum of all values in the attribute column and n representing the lighting system device number.
According to an embodiment of the method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering, the dimensionality reduction of the multi-attribute value system of the data and the construction of the principal component matrix comprise the following steps:
1) assuming that the lighting system has n devices, each having i attributes, an original matrix M of n × i is constructed from the obtained vectors of each attribute for all datan×iEach row representing a lighting device and each column representing an attribute, calculating a mean vector of the attributes of the original matrix
2) Solving an original matrix Mn×iOf the covariance matrix Sn×n＝Cov(X)；
3) Solving eigenvalues and eigenvectors of the covariance matrix;
4) calculating principal component contribution rate and cumulative contribution rate, taking j principal components with cumulative contribution rate more than 90%, constituting new attribute data, forming principal component parameter system MC ═ { MC ═ MC [ ()1，mc2，...，mcj}。
According to an embodiment of the method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering, the step of performing Kmeans clustering on the data matrix after the dimensionality reduction comprises the following steps: determining the number k of clusters according to an inflection point method; each piece of data of all the equipment is regarded as a node, one piece of data is randomly selected as a first cluster center point, the data which is most dissimilar to the piece of data is selected as a second cluster center point, the number play which is most dissimilar to the first two pieces of data is selected as a third cluster center point, and the like is carried out until k cluster center points are selected; partitioning and extracting the principal component data according to principal component columns to form principal component column vector spaces, clustering the principal component column vector spaces, and clustering similar principal components in the same class; sequentially comparing the distance from each principal component in the residual data to each clustering center, summing the distances from the principal attributes of each lighting device to each cluster, distributing the data to the cluster of the clustering center closest to the data to obtain k clusters, calculating the mean value of each principal component of all points in each cluster, and taking the mean value of the principal components as the centroid; until the change of the cluster center tends to be stable, and final k cluster classes and isolated points are formed.
According to an embodiment of the method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering, the step of performing Kmeans clustering on the data matrix after the dimensionality reduction comprises the following steps: and (3) in the principal component parameter system, dividing and extracting the principal component data in each attribute column to form a principal component column vector space, clustering the principal component column vector space, and clustering similar principal components in the same class.
According to the method for analyzing the abnormal energy consumption of the subway illumination system based on the multi-attribute clustering, the energy consumption data of the illumination system in the subway operation process and the energy consumption attributes of various illumination devices can be acquired in real time through the energy management system of the rail transit company, and the abnormal energy consumption behavior in the operation process can be detected through clustering analysis on the main attributes of the illumination system, so that the accuracy and timeliness of the detection of the abnormal energy consumption of the subway illumination system in the prior art are improved, energy conservation and emission reduction are realized for the subway operation company, and the benefit is increased.
Drawings
Fig. 1 is a flowchart illustrating an embodiment of an abnormal energy consumption analysis method for a subway lighting system based on multi-attribute clustering according to the present invention.
Detailed Description
In order to make the objects, contents, and advantages of the present invention clearer, the following detailed description of the embodiments of the present invention will be made in conjunction with the accompanying drawings and examples.
The invention discloses a method for analyzing abnormal energy consumption of a subway lighting system based on multi-attribute clustering, which comprises the following steps of: and corresponding the energy consumption data of the lighting system with the respective equipment attributes to form an energy consumption analysis multi-attribute value system A ═ a1，a2，...，aiH (i represents the number of attributes of the lighting system), A represents that the energy consumption of the lighting system comes from a plurality of devices, each device is influenced by multiple aspects, and the multiple aspects are formed into an attribute set of energy consumption data, aiTo representOne attribute name includes, for example, a device model, device Power, and the like, specifically including a device model Type, a device Power P, a load Level, a Power supply and distribution mode Power, an energy consumption EC, a Time, and a service life Age;
converting a non-numerical attribute of each piece of data (such as { equipment model, equipment power, load level, …, energy consumption value }) into a numerical type, wherein the equipment in the lighting system has multiple attributes, such as the equipment power is numerical, and if the power supply and distribution mode (centralized power supply, distributed power supply and hybrid power supply) is the non-numerical attribute, converting the non-numerical attribute into numerical data which respectively correspond to (0, 1 and 2), normalizing the attribute data, converting the attribute data into an attribute value convenient to process, converting the non-numerical data into the numerical data, and normalizing the data; it is meant by an attribute value. For example, before numerical conversion, {1100w, centralized power supply, …, 50}, after conversion, a vector of each attribute to all data is established for {1100w,0, …, 50 };
the method is characterized in that a multi-attribute value system of data after the normalization processing of the equipment energy consumption multi-attribute data in the lighting system is subjected to dimension reduction, namely each piece of energy consumption data is composed of a plurality of attribute values, and each attribute column is subjected to the normalization processing, so that the problems that some data are too large and some data are too small, the attribute dimension is reduced, and a principal component parameter system MC (major component parameter) is constructed as { MC (MC) } m1，mc2，...，mcjThe lighting system is composed of a plurality of devices, the energy consumption of the lighting system is influenced by various attributes, but the related attributes are excessive, the time complexity is increased, the dimension reduction processing is carried out on the lighting system, the attribute which has small influence on the energy consumption is deleted, and the rest attributes have large influence on the energy consumption to form the main attribute, namely the main component;
determining the number k of clusters according to an inflection point method;
selecting k lighting system energy consumption data subjected to normalization processing and dimension reduction processing as cluster centers of kmeans initial clustering; dividing and extracting the data principal component data in each attribute column according to the principal component columns, wherein each attribute column is the principal component column, and forming a principal component column vector space to cluster the principal component column vector space, and clustering similar principal components in the same class;
the method specifically comprises the following steps: firstly, selecting k pieces of energy consumption data as a cluster center, taking data of a main component column as a data set, clustering the data set, and classifying the data set and the data of the cluster center into one class, which indicates that the data is also in the cluster. For example, the data set is { a, b, c, d, e, f }, where { a, b, c } is an initial cluster center, and is clustered, and the result of the partitioning is { a, d, e }, { b, f }, and { c }, where d, e and a are in the same cluster.
And sequentially comparing the distances from each principal component in the residual data (only one attribute column is subjected to clustering operation each time, the residual data is the attribute columns which are not subjected to clustering), to each clustering center, wherein one energy consumption data is from a plurality of attributes, and the attribute columns are divided, so that one data is divided according to different attributes and possibly divided into different clusters, and therefore, the judgment is carried out based on the sum of the distances from all the attributes to each cluster. This is calculated according to a common distance formula for clustering, such as Euclidean distance, and the smaller the distance, the greater the probability that the data is attributed to the cluster. Summing the distances from the main attribute of each lighting device to each cluster, and distributing data to the cluster of the cluster center closest to the main attribute to obtain k clusters; and dividing the energy consumption data of all the devices into different classes through clustering, wherein the data in the same class form a set, namely a cluster. Clusters belong to the definition inherent to clustering algorithms.
For each cluster, calculating each principal component mean value of all points in the cluster and taking the principal component mean value as a centroid, specifically comprising: and when the clustering is not finished, executing for multiple times until the partitioning result is stable. And for each cluster, converting the plurality of data in each cluster into one data, namely averaging each attribute column to form new data. Until the change of the cluster center tends to be stable, forming the final k clusters;
and finally, analyzing, wherein the data which is not distributed into any cluster is abnormal data, namely the corresponding equipment has abnormal energy consumption.
The device is brought into a daily key monitoring range, and is purposefully adjusted and overhauled, so that the device can be gradually used normally.
Fig. 1 is a flowchart illustrating an embodiment of an abnormal energy consumption analysis method for a subway lighting system based on multi-attribute clustering, and as shown in fig. 1, the abnormal energy consumption analysis method for a subway lighting system based on multi-attribute clustering of the present invention includes:
s101, selecting a subway station operation station from an energy management system household energy consumption analysis module of the company, selecting month data, extracting lighting system data from a database, and displaying the lighting system data on a household energy consumption analysis interface; selecting a trend graph to display on a household energy consumption analysis interface, and visually acquiring the energy consumption EC of each lighting device in the station every daymd(m denotes a certain lighting device, d denotes the day of the current month);
s102, acquiring the special attributes of each lighting device of the lighting system, such as power, load grade, power supply and distribution mode and the like;
s103, carrying out EC (energy consumption data) on each item of the lighting systemmdCorresponding to respective device attributes, forming an energy consumption analysis multi-attribute value system A ═ { EC, Type, P, Level, Power, Time, Age … }, wherein the device Type, the device Power P, the load Level, the Power supply and distribution mode, the Time, the service life Age and the like;
s104, analyzing and abstracting the multiple attributes of each piece of data, converting the non-numerical attributes into numerical attributes, respectively corresponding the conforming levels (primary level, secondary level and tertiary level) to (1, 2 and 3), respectively corresponding the power supply and distribution modes (centralized power supply, distributed power supply and mixed power supply) to (0, 1 and 2), normalizing the attribute data, establishing vectors of each attribute to all data, and establishing a lighting system equipment multiple attribute matrix Mni(n denotes a lighting system device);
wherein, the normalization processing formula is as follows:
wherein, Value represents a certain attribute Value corresponding to each device of the energy consumption data, and refers to a Value corresponding to the device under the attribute, and all devices have multiple values under the attributeminMinimum of all values in the representation, ValuemaxRepresents the maximum of all values in the attribute column
S105: carrying out PCA dimension reduction on the multi-attribute value system, and setting the original multi-attribute value system A as { a }1，a2，...，aiUpdating (i represents the number of attributes of the illumination system) to a principal component parameter system MC ═ MC1，mc2，...，mcjJ represents the number of lighting system principal components (j < i), and a lighting system equipment principal component matrix MC is establishednj(n denotes a lighting system device). The specific process is as follows:
1) assuming that the lighting system has n devices, each having i attributes, an n × i original matrix M is constructed from the vectors of each attribute obtained in step 4 for all datan×iEach row representing a lighting device and each column representing an attribute, calculating a mean vector of the attributes of the original matrix
2) Solving an original matrix Mn×iOf the covariance matrix Sn×n＝Cov(X)；
3) Solving eigenvalues and eigenvectors of the covariance matrix;
4) calculating principal component contribution rate and cumulative contribution rate, taking j principal components with cumulative contribution rate more than 90%, constituting new attribute data, forming principal component parameter system MC ═ { MC ═ MC [ ()1，mc2，...，mcj}；
S106: performing Kmeans clustering on the data matrix after dimensionality reduction to obtain a clustering result C ═ { C ═ C1，C2，...，Ck}∪{CeIn which C is1，C2，...，CkRepresents the clustering result, CeIs a set of nodes that do not belong to each cluster, i.e., a set of outliers. The specific process is as follows:
5) determining the number k of clusters according to an inflection point method (elbow rule);
6) initial central device selection. Each piece of data of all the equipment is regarded as a node, a piece of data is randomly selected as a first cluster center point, then the data which is most dissimilar to the piece of data is selected as a second cluster center point, then the number play which is most dissimilar to the first two pieces of data is selected as a third cluster center point, and the like until k cluster center points are selected;
7) partitioning and extracting the principal component data according to principal component columns to form principal component column vector spaces, clustering the principal component column vector spaces, and clustering similar principal components in the same class;
8) sequentially comparing the distance from each principal component in the residual data to each clustering center, summing the distances from the principal attributes of each lighting device to each cluster, and distributing the data to the cluster of the clustering center closest to the data to obtain k clusters;
9) and for each cluster, calculating each principal component mean value of all points in the cluster, taking the principal component mean value as a centroid, and repeatedly executing 4) until the change of the cluster center tends to be stable, so as to form final k clusters and isolated points, namely data of abnormal energy consumption of the lighting system, thereby achieving the purpose of finding abnormal energy consumption.
The energy management system collects energy consumption data in the subway operation process in real time, and establishes a multi-attribute value system of the energy consumption of the illumination system according to the collected energy consumption data of the illumination system and the characteristics of each illumination device. And reducing the dimension of the multi-attribute value system, establishing a principal component parameter system, classifying the principal component parameter system by using a clustering algorithm to obtain a final energy consumption analysis result, and finding abnormal energy consumption. The method is not only suitable for the subway lighting system, but also suitable for air conditioner energy consumption analysis, water pump energy consumption analysis and the like, and has strong accuracy, applicability and expansibility.
According to the subway illumination system abnormal energy consumption analysis method based on the multi-attribute clustering, abnormal energy consumption events can be found in real time and accurately, the time and specific equipment of the abnormal energy consumption are determined, maintenance personnel can maintain the subway illumination system timely, the calculation method is simple and reliable, and reliable guarantee is provided for safe operation of the subway, safe traveling of passengers and the like. The invention has strong practicability in the energy-saving aspect of the rail transit subway. The invention can effectively realize the function of detecting the abnormal energy consumption of the lighting system.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A subway illumination system abnormal energy consumption analysis method based on multi-attribute clustering comprises the following steps:
and corresponding the energy consumption data of the lighting system with the respective equipment attributes to form an energy consumption analysis multi-attribute value system A ═ a1，a2，...，aiWhere i denotes the number of illumination system attributes, aiRepresenting an attribute name;
converting the attribute of each non-numerical illumination system into a numerical type, carrying out normalization processing on each attribute, converting the attribute into an attribute value, and establishing a vector of each attribute value to all data;
reducing the dimension of a multi-attribute value system of the data, constructing a principal component parameter system which comprises a plurality of principal component data, determining the number k of clusters according to an inflection point method, selecting k pieces of equipment data as cluster centers of initial clustering of Kmeans, and carrying out Kmeans clustering on a data matrix after dimension reduction;
sequentially comparing the distance from each main component in the remaining data which is not subjected to clustering operation to each clustering center, summing the distances from the main attribute of each lighting device to each cluster, and distributing the data to the cluster of the clustering center closest to the main attribute of each lighting device to obtain k clusters; calculating the principal component mean values of all the points in each cluster, and taking the principal component mean values as the mass center until the change of the cluster center tends to be stable to form k clusters;
based on the k clusters formed, analysis of the results was performed.
2. The method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering as claimed in claim 1, wherein the lighting system attributes comprise: the device Type, the device Power P, the load Level, the Power supply and distribution mode Power, the energy consumption EC, the Time and the service life Age.
3. The method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering as claimed in claim 1, wherein the analyzing according to the result comprises: data which are not allocated to any cluster are abnormal data, and energy consumption of corresponding equipment is abnormal; and bringing abnormal equipment into a daily important monitoring range.
4. The method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering as claimed in claim 1, wherein said converting each non-numerical lighting system attribute into a numerical value includes setting a certain numerical value to represent each type of the non-numerical lighting system attribute, and correspondingly converting each type into a numerical value.
5. The method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering as claimed in claim 1, wherein calculating the principal component mean values of all the points in the cluster and taking the principal component mean values as the centroid comprises: and after the initial division, a plurality of pieces of data belong to the same cluster, each cluster is used as one piece of data, each attribute column is averaged, so that the plurality of pieces of data are converted into one piece of data to form new data until the change of the cluster center tends to be stable, and k clusters are formed.
6. The method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering of claim 1, wherein the converting the non-numerical attributes into numerical attributes comprises: the first level, the second level and the third level are respectively corresponding to 1, 2 and 3, and the centralized power supply, the distributed power supply and the hybrid power supply of the power supply and distribution mode are respectively corresponding to 0, 1 and 2.
7. The method for analyzing the abnormal energy consumption of the subway illumination system based on the multi-attribute clustering as claimed in claim 1, wherein the data normalization process is performed on each attribute, the vector of each attribute to all data is established, and the multi-attribute matrix M of the illumination system equipment is establishedniThe normalization processing formula includes:
wherein, Value represents a certain attribute Value corresponding to each device of the energy consumption data, and refers to a Value corresponding to the device under the attribute, and all devices have multiple values under the attributeminMinimum of all values in the representation, ValuemaxRepresenting the maximum of all values in the attribute column and n representing the lighting system device number.
8. The method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering as claimed in claim 1, wherein the reducing the dimensions of the multi-attribute value system of the data and constructing the principal component matrix comprises:
1) assuming that the lighting system has n devices, each having i attributes, an original matrix M of n × i is constructed from the obtained vectors of each attribute for all datan×iEach row representing a lighting device and each column representing an attribute, calculating a mean vector of the attributes of the original matrix
2) Solving an original matrix Mn×iOf the covariance matrix Sn×n＝Cov(X)；
3) Solving eigenvalues and eigenvectors of the covariance matrix;
4) calculating principal component contribution rate and cumulative contribution rate, taking j principal components with cumulative contribution rate more than 90%, constituting new attribute data, forming principal component parameter system MC ═ { MC ═ MC [ ()1，mc2，...，mcj}。。
9. The method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering as claimed in claim 1, wherein said performing Kmeans clustering on the reduced-dimension data matrix comprises:
determining the number k of clusters according to an inflection point method;
each piece of data of all the equipment is regarded as a node, one piece of data is randomly selected as a first cluster center point, the data which is most dissimilar to the piece of data is selected as a second cluster center point, the number play which is most dissimilar to the first two pieces of data is selected as a third cluster center point, and the like is carried out until k cluster center points are selected;
partitioning and extracting the principal component data according to principal component columns to form principal component column vector spaces, clustering the principal component column vector spaces, and clustering similar principal components in the same class;
sequentially comparing the distance from each principal component in the residual data to each clustering center, summing the distances from the principal attributes of each lighting device to each cluster, distributing the data to the cluster of the clustering center closest to the data to obtain k clusters, calculating the mean value of each principal component of all points in each cluster, and taking the mean value of the principal components as the centroid; until the change of the cluster center tends to be stable, and final k cluster classes and isolated points are formed.
10. The method for analyzing the abnormal energy consumption of the subway lighting system based on the multi-attribute clustering as claimed in claim 1, wherein said performing Kmeans clustering on the reduced-dimension data matrix comprises: and (3) in the principal component parameter system, dividing and extracting the principal component data in each attribute column to form a principal component column vector space, clustering the principal component column vector space, and clustering similar principal components in the same class.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010473632.5A CN111695792B (en) | 2020-05-29 | 2020-05-29 | Subway illumination system abnormal energy consumption analysis method based on multi-attribute clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010473632.5A CN111695792B (en) | 2020-05-29 | 2020-05-29 | Subway illumination system abnormal energy consumption analysis method based on multi-attribute clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111695792A true CN111695792A (en) | 2020-09-22 |
| CN111695792B CN111695792B (en) | 2023-08-01 |
Family
ID=72478763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010473632.5A Active CN111695792B (en) | 2020-05-29 | 2020-05-29 | Subway illumination system abnormal energy consumption analysis method based on multi-attribute clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695792B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112131388A (en) * | 2020-09-28 | 2020-12-25 | 范馨月 | Abnormal data detection method containing text type data types |
| CN116893297A (en) * | 2023-09-11 | 2023-10-17 | 常州旭泰克系统科技有限公司 | Method and system for monitoring energy consumption of rotating equipment |
| CN116991219A (en) * | 2023-09-26 | 2023-11-03 | 北京国电通网络技术有限公司 | Abnormal production state monitoring method, device, electronic equipment and medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060259360A1 (en) * | 2005-05-16 | 2006-11-16 | Manyworlds, Inc. | Multiple Attribute and Behavior-based Advertising Process |
| CN102789599A (en) * | 2012-07-06 | 2012-11-21 | 西北工业大学 | Operation shop bottleneck recognition method based on cluster analysis and multiple attribute decision making |
| CN103913630A (en) * | 2014-04-18 | 2014-07-09 | 上海电科智能系统股份有限公司 | Centralized electric energy measuring and energy consumption analyzing system for rail transit |
| CN104570083A (en) * | 2013-10-29 | 2015-04-29 | 中国石油天然气集团公司 | Multi-dimensional seismic attribute-based automatic geologic body identification method |
| CN105446139A (en) * | 2015-12-18 | 2016-03-30 | 华南理工大学 | Construction energy consumption analysis method and construction energy consumption analysis system based on BP neural network |
| CN105764162A (en) * | 2016-05-10 | 2016-07-13 | 江苏大学 | Wireless sensor network abnormal event detecting method based on multi-attribute correlation |
| CN105825323A (en) * | 2016-03-10 | 2016-08-03 | 山东建筑大学 | Building energy consumption main influence factor analysis method based on big data |
| CN106570581A (en) * | 2016-10-26 | 2017-04-19 | 东北电力大学 | Attribute association based load prediction system and method in energy Internet environment |
| CN108304978A (en) * | 2018-05-08 | 2018-07-20 | 国网江西省电力有限公司经济技术研究院 | A kind of mid-term Electric Power Load Forecast method based on data clusters theory |
| CN108549754A (en) * | 2018-03-29 | 2018-09-18 | 中交隧道局电气化工程有限公司 | Tramcar system energy consumption analysis method based on control figure |
| CN109214522A (en) * | 2018-07-17 | 2019-01-15 | 西安交通大学 | One kind being based on multiattribute equipment performance degradation assessment method |
| CN109858832A (en) * | 2019-02-25 | 2019-06-07 | 合肥工业大学 | A kind of more attribute green Index grading Coordination Evaluation methods |
| CN110727257A (en) * | 2019-08-27 | 2020-01-24 | 华润置地控股有限公司 | Equipment operation diagnosis method and device based on K-means clustering algorithm |
-
2020
- 2020-05-29 CN CN202010473632.5A patent/CN111695792B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060259360A1 (en) * | 2005-05-16 | 2006-11-16 | Manyworlds, Inc. | Multiple Attribute and Behavior-based Advertising Process |
| CN102789599A (en) * | 2012-07-06 | 2012-11-21 | 西北工业大学 | Operation shop bottleneck recognition method based on cluster analysis and multiple attribute decision making |
| CN104570083A (en) * | 2013-10-29 | 2015-04-29 | 中国石油天然气集团公司 | Multi-dimensional seismic attribute-based automatic geologic body identification method |
| CN103913630A (en) * | 2014-04-18 | 2014-07-09 | 上海电科智能系统股份有限公司 | Centralized electric energy measuring and energy consumption analyzing system for rail transit |
| CN105446139A (en) * | 2015-12-18 | 2016-03-30 | 华南理工大学 | Construction energy consumption analysis method and construction energy consumption analysis system based on BP neural network |
| CN105825323A (en) * | 2016-03-10 | 2016-08-03 | 山东建筑大学 | Building energy consumption main influence factor analysis method based on big data |
| CN105764162A (en) * | 2016-05-10 | 2016-07-13 | 江苏大学 | Wireless sensor network abnormal event detecting method based on multi-attribute correlation |
| CN106570581A (en) * | 2016-10-26 | 2017-04-19 | 东北电力大学 | Attribute association based load prediction system and method in energy Internet environment |
| CN108549754A (en) * | 2018-03-29 | 2018-09-18 | 中交隧道局电气化工程有限公司 | Tramcar system energy consumption analysis method based on control figure |
| CN108304978A (en) * | 2018-05-08 | 2018-07-20 | 国网江西省电力有限公司经济技术研究院 | A kind of mid-term Electric Power Load Forecast method based on data clusters theory |
| CN109214522A (en) * | 2018-07-17 | 2019-01-15 | 西安交通大学 | One kind being based on multiattribute equipment performance degradation assessment method |
| CN109858832A (en) * | 2019-02-25 | 2019-06-07 | 合肥工业大学 | A kind of more attribute green Index grading Coordination Evaluation methods |
| CN110727257A (en) * | 2019-08-27 | 2020-01-24 | 华润置地控股有限公司 | Equipment operation diagnosis method and device based on K-means clustering algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 王林: "基于多属性决策TOPSIS的簇头选择", 《计算机工程》, vol. 45, no. 01, pages 45 - 49 * |
| 边宇: "应用GIS的城市照明规划系统", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 04, pages 038 - 51 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112131388A (en) * | 2020-09-28 | 2020-12-25 | 范馨月 | Abnormal data detection method containing text type data types |
| CN112131388B (en) * | 2020-09-28 | 2024-02-06 | 范馨月 | Abnormal data detection method containing text data types |
| CN116893297A (en) * | 2023-09-11 | 2023-10-17 | 常州旭泰克系统科技有限公司 | Method and system for monitoring energy consumption of rotating equipment |
| CN116893297B (en) * | 2023-09-11 | 2024-01-12 | 常州旭泰克系统科技有限公司 | Method and system for monitoring energy consumption of rotating equipment |
| CN116991219A (en) * | 2023-09-26 | 2023-11-03 | 北京国电通网络技术有限公司 | Abnormal production state monitoring method, device, electronic equipment and medium |
| CN116991219B (en) * | 2023-09-26 | 2024-01-12 | 北京国电通网络技术有限公司 | Abnormal production state monitoring method, device, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111695792B (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695792B (en) | Subway illumination system abnormal energy consumption analysis method based on multi-attribute clustering | |
| CN111429027B (en) | Regional power transmission network operation multidimensional analysis method based on big data | |
| Sheu | Dynamic relief-demand management for emergency logistics operations under large-scale disasters | |
| CN112488371B (en) | Pipeline intelligent early warning method and system based on big data | |
| CN109446243B (en) | Method for detecting power generation abnormity of photovoltaic power station based on big data analysis | |
| CN113344408B (en) | Processing method for multi-scale situation awareness process of civil aviation traffic control operation | |
| CN112445844B (en) | Financial data management control system of big data platform | |
| Jiang et al. | Electrical-STGCN: An electrical spatio-temporal graph convolutional network for intelligent predictive maintenance | |
| CN103914482B (en) | Centralized Monitoring event influence property based on CMDB determines method | |
| CN115796390A (en) | Data-driven building energy consumption abnormity diagnosis method and system | |
| CN109460915A (en) | It is a kind of based on big data driving city elevator intelligent send work checking system | |
| CN114118730A (en) | Compliance detection method for business process of power enterprise | |
| Zhang et al. | ARIMA Model‐Based Fire Rescue Prediction | |
| CN110097126B (en) | Method for checking important personnel and house missing registration based on DBSCAN clustering algorithm | |
| CN112991093A (en) | Electricity stealing detection method and system based on edge calculation | |
| Benyao et al. | Elevator Traffic Pattern Recognition Based on Density Peak Clustering | |
| CN113822473B (en) | Traction energy consumption reasonable interval prediction method based on multidimensional data | |
| Novikova et al. | Soft measurements of qualitative integral indicators for monitoring quantitative dataset | |
| CN116719665B (en) | Intelligent judging and identifying method for abnormal state of meteorological numerical mode | |
| Fitriana et al. | Identification of Characteristics of Covid-19 Infection Using the K-Means Clustering Method | |
| CN112257923B (en) | Heavy overload early warning method and device and electronic equipment | |
| 서정욱 | Daily Activity Pattern Recognition considering Spatial Distance based on National Household Travel Survey Data | |
| Yajuan et al. | Study on prediction model of building construction safety accidents based on GA-SVM | |
| Ge et al. | MRM: Site Selection via Mutil-round Meanshift for Global Fairness | |
| Liu et al. | Elevator Group Usage Risk Assessment Model using IoT Platform Information |
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 |