CN117114252A - Comprehensive energy intelligent management method based on Internet of things - Google Patents
Comprehensive energy intelligent management method based on Internet of things Download PDFInfo
- Publication number
- CN117114252A CN117114252A CN202311384207.9A CN202311384207A CN117114252A CN 117114252 A CN117114252 A CN 117114252A CN 202311384207 A CN202311384207 A CN 202311384207A CN 117114252 A CN117114252 A CN 117114252A
- Authority
- CN
- China
- Prior art keywords
- energy
- abnormal
- information
- membership
- energy information
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 33
- 230000002159 abnormal effect Effects 0.000 claims abstract description 200
- 239000013598 vector Substances 0.000 claims abstract description 75
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000004044 response Effects 0.000 claims abstract description 10
- 230000005856 abnormality Effects 0.000 claims description 49
- 238000005265 energy consumption Methods 0.000 claims description 44
- 230000000694 effects Effects 0.000 claims description 35
- 238000011156 evaluation Methods 0.000 claims description 30
- 238000000034 method Methods 0.000 claims description 12
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 8
- 239000003345 natural gas Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
-
- 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
- G06F18/2337—Non-hierarchical techniques using fuzzy logic, i.e. fuzzy clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Fuzzy Systems (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of energy management, in particular to a comprehensive energy intelligent management method based on the Internet of things, which comprises the following steps: collecting abnormal energy utilization information of at least one energy source in historical time; performing fuzzy clustering processing on all abnormal energy information by using a fuzzy clustering algorithm to obtain membership vectors of the abnormal energy information, wherein the membership vectors comprise membership of each abnormal cause of the abnormal energy information; collecting real-time energy utilization information of energy, and acquiring predicted consumption at future time based on the real-time energy utilization information; in response to the predicted consumption being in an abnormal state, calculating a target membership vector of the energy based on the real-time energy information and membership vectors of each abnormal energy information; and determining the abnormal reason of the abnormal state based on the target membership vector. According to the technical scheme, the abnormal reasons can be accurately positioned when the consumption is in an abnormal state, and the accurate management of energy sources is realized.
Description
Technical Field
The application relates to the technical field of energy management, in particular to a comprehensive energy intelligent management method based on the Internet of things.
Background
With the rapid increase of global energy demand, various energy sources such as electric energy, natural gas and the like are widely applied to various fields. In order to avoid waste of energy, energy management plays an important role.
Currently, patent document with grant publication No. CN102314548B discloses an energy management method of estimating an operation state of each energy consumption device by detecting a change in total energy consumption amount per unit time using a gauge and then comparing the change with previously input energy consumption amounts per unit time of each energy consumption device; then, the consumption time and the power consumption amount of each energy consumption device can be detected, thereby predicting the current or future energy consumption cost.
However, although the above method can estimate the operation state of each energy consumption device, when the operation state is in an abnormal state, the current or future energy consumption cost cannot be accurately predicted, and the cause of the abnormal state cannot be located, and accurate management of energy cannot be realized.
Disclosure of Invention
In order to solve the technical problems, the application provides a comprehensive energy intelligent management method based on the Internet of things, which monitors the state of energy consumption and accurately locates the cause of abnormality when the consumption is in the abnormal state so as to realize the accurate management of energy.
The application provides a comprehensive energy intelligent management method based on the Internet of things, which comprises the following steps: collecting abnormal energy consumption information of at least one energy source in historical time, wherein the abnormal energy consumption information comprises a time sequence of energy consumption in a set time period under an abnormal consumption state, and the energy source at least comprises electric energy; performing fuzzy clustering processing on all abnormal energy information by using a fuzzy clustering algorithm to obtain membership vectors of each abnormal energy information, wherein the membership vectors comprise membership of the abnormal energy information belonging to each abnormal type, and one abnormal type corresponds to one abnormal reason; acquiring real-time energy utilization information of the energy, and acquiring predicted consumption of the energy at a future moment based on the real-time energy utilization information; responding to the predicted consumption in an abnormal state, and calculating a target membership vector of the energy based on the real-time energy information and membership vectors of each abnormal energy information; determining an abnormal reason of the abnormal state based on the target membership vector, and realizing intelligent management of energy sources; wherein the calculating the target membership vector of the energy based on the real-time energy information and the membership vector of each abnormal energy information includes: calculating the similarity of the real-time energy information and each abnormal energy information, and taking the abnormal energy information with the similarity larger than a similarity threshold value as target energy information; the main abnormality cause of each abnormal energy information is acquired to calculate the tendency of each abnormality cause, wherein the main abnormality cause is the abnormality cause corresponding to the abnormality type of the membership maximum value, and the tendency satisfies the relation:
wherein,the main abnormality cause in the energy information for all targets is abnormality cause +>Quantity of->For the amount of all target energy information, +.>The main abnormality cause in all abnormal energy information is abnormality cause +>Quantity of->For abnormality cause->Is a tendency of (2); calculating a target membership vector of the energy based on the tendency of each abnormal cause and the target energy consumption information, wherein the target membership vector comprises target membership of each abnormal cause, and the target membership satisfies a relation:
wherein,for abnormality cause->Tendency of (A)>For the sum of the tendencies of all abnormality causes, +.>For the amount of all target energy information, +.>Energy information for object->Similarity of->Energy information for object->Cause of abnormality in middle energizer->Membership of->For abnormality cause->Target membership of (a).
In one embodiment, the performing fuzzy clustering on all the abnormal energy information by using the fuzzy clustering algorithm to obtain the membership vector of each abnormal energy information includes: setting the number of initial categories as 2, and carrying out fuzzy clustering treatment on all abnormal energy information to obtain a membership initial vector of each piece of abnormal energy information, wherein the membership initial vector comprises initial membership of the abnormal energy information to each initial category; calculating a clustering effect evaluation index based on the membership degree initial vector of each piece of abnormal energy information; updating the number of the initial categories with a set step length, repeatedly executing fuzzy clustering processing and calculating corresponding clustering effect evaluation indexes; iteratively updating the number of the initial categories, and drawing a clustering effect evaluation index curve, wherein the abscissa of the clustering effect evaluation index curve is the number of the initial categories, and the ordinate is the clustering effect evaluation index; and obtaining inflection points of the clustering effect evaluation index curve, taking the number of initial categories corresponding to the inflection points as the target number of abnormal types, and enabling the membership initial vector obtained when fuzzy clustering processing is carried out on the target number to correspond to the membership vector.
In one embodiment, the cluster effect evaluation index satisfies the relation:
wherein the method comprises the steps ofFor the number of all abnormal energy information,/>for the number of all initial categories +.>Is abnormal energy information->For the initial category->Is>And the clustering effect evaluation index is the clustering effect evaluation index which is in negative correlation with the clustering effect.
In one embodiment, the acquiring real-time energy information of the energy source, and acquiring the predicted consumption of the energy source at a future time based on the real-time energy information includes: the real-time energy utilization information comprises the current time and the energy consumption of a set number of times before the current time, wherein the current time and the set number of times before the current time correspond to the set time period; and inputting the real-time energy utilization information into a trained time sequence prediction network to obtain the predicted consumption of the energy source at the future moment.
In one embodiment, the similarity between the real-time energy information and the abnormal energy information satisfies the relationship:
wherein,for real-time energy information and abnormal energy information +.>Similarity of->For real-time energy information and abnormal energy information +.>Is a DTW distance of (c).
In one embodiment, said responding to said predicted consumption being in an abnormal state comprises: calculating the average value of all energy consumption in the real-time energy consumption informationAnd standard deviation->The method comprises the steps of carrying out a first treatment on the surface of the Based on the average->And the standard deviation->Calculating a normal interval, wherein the normal interval is +.>The method comprises the steps of carrying out a first treatment on the surface of the In response to the predicted consumption being within the normal interval, the predicted consumption is in a normal state; in response to the predicted consumption being not within the normal interval, the predicted consumption is in an abnormal state.
In one embodiment, in response to the predicted consumption being in an abnormal state, the real-time energy information is used as a new piece of abnormal energy information for determining the cause of the abnormality in the abnormal state next time.
In one embodiment, the determining the abnormal cause of the abnormal state based on the target membership vector, implementing intelligent management of energy includes: and checking each abnormal reason according to the order of the target membership from high to low.
The technical scheme of the application has the following beneficial technical effects:
according to the technical scheme provided by the application, firstly, the membership vector of each abnormal energy information in the history time is determined based on a fuzzy clustering algorithm, wherein the membership vector can accurately reflect the possibility of each abnormal cause of the abnormal energy information; and predicting the predicted consumption amount at the future time according to the real-time energy consumption information to judge whether the state is abnormal, and accurately positioning the abnormal reason causing the abnormal state according to the real-time energy consumption information and the membership degree vector of each abnormal energy consumption information when the predicted consumption amount is in the abnormal state, so as to realize the accurate management of energy.
Further, in the fuzzy clustering process, the number of the abnormal types is determined by using the clustering effect evaluation index, so that the self-adaptive determination of the number of the abnormal types is realized, the membership degree of each abnormal energy information belonging to each abnormal type is further obtained, and the possibility of each abnormal cause of the abnormal energy information is further obtained.
Further, the target membership vector includes target membership of each abnormal cause, and when the target membership vector is calculated, similarity between the real-time energy information and each abnormal energy information is considered, and tendency of the real-time energy information to be in an abnormal state due to each abnormal cause in the history time is considered, so that accuracy of the target membership vector is improved.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the application are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a flow chart of an integrated energy intelligent management method based on the Internet of things according to an embodiment of the application;
FIG. 2 is a flowchart of performing fuzzy clustering on all abnormal energy information by using a fuzzy clustering algorithm to obtain membership vectors of each abnormal energy information according to an embodiment of the present application;
fig. 3 is a flowchart of calculating a target membership vector of the energy source based on the real-time energy information and membership vectors of each abnormal energy information according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be understood that when the terms "first," "second," and the like are used in the claims, the specification and the drawings of the present application, they are used merely for distinguishing between different objects and not for describing a particular sequential order. The terms "comprises" and "comprising" when used in the specification and claims of the present application are taken to specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
According to a first aspect of the application, the application provides an integrated energy intelligent management method based on the Internet of things. The system is used for an Internet of things architecture, and the Internet of things architecture comprises an acquisition terminal of at least one energy source. Fig. 1 is a flowchart of an integrated energy intelligent management method based on the internet of things according to an embodiment of the present application. As shown in fig. 1, the test method 100 includes steps S101 to S105, which are described in detail below.
S101, acquiring abnormal energy information of at least one energy source in historical time, wherein the abnormal energy information comprises a time sequence of energy consumption in a set time period under an abnormal consumption state, and the energy source at least comprises electric energy.
In one embodiment, for any one of the energy consumption devices in the history time, when the energy consumption device is in an abnormal state, a time sequence of the energy consumption amount of the energy consumption device in a set time period is collected as an abnormal energy consumption information. The energy consumption is the consumption of electric energy in unit time, and the set time period is 1 minute.
Illustratively, the energy consuming device is a lighting fixtureIf it is at the momentWhen it is determined that the lighting device is in an abnormal state, time +.>The time series of the power consumption of the lighting device in the previous 1 minute is used as an abnormal power consumption data.
In other embodiments, the set time period may also be the time of the last day. The energy source also includes water and natural gas. The collection of the energy consumption can be obtained through a corresponding collection terminal, for example, the electric energy consumption, the water consumption and the natural gas consumption are sequentially collected through an electric energy meter, a water meter and a natural gas meter.
S102, performing fuzzy clustering processing on all abnormal energy information by using a fuzzy clustering algorithm to obtain membership vectors of each abnormal energy information, wherein the membership vectors comprise membership of the abnormal energy information belonging to each abnormal type, and one abnormal type corresponds to one abnormal reason.
In one embodiment, for one abnormal energy information, the reasons for the occurrence of the abnormal state are more than one, so that the embodiment of the application adopts a fuzzy clustering algorithm to perform fuzzy clustering processing on all abnormal energy information to obtain the membership degree of the abnormal energy information belonging to each abnormal type.
Specifically, please refer to fig. 2, which is a flowchart of performing fuzzy clustering processing on all abnormal energy information by using a fuzzy clustering algorithm to obtain membership vectors of each abnormal energy information according to an embodiment of the present application. The fuzzy clustering processing of all the abnormal energy information by using the fuzzy clustering algorithm to obtain membership vectors of each abnormal energy information comprises the following steps: s201, setting the number of initial categories as 2, and carrying out fuzzy clustering treatment on all abnormal energy information to obtain a membership initial vector of each piece of abnormal energy information, wherein the membership initial vector comprises initial membership of the abnormal energy information to each initial category; s202, calculating a clustering effect evaluation index based on the membership initial vector of each piece of abnormal energy information; s203, updating the number of the initial categories with a set step length, repeatedly executing fuzzy clustering processing and calculating corresponding clustering effect evaluation indexes; s204, iteratively updating the number of the initial categories, and drawing a clustering effect evaluation index curve, wherein the abscissa of the clustering effect evaluation index curve is the number of the initial categories, and the ordinate is the clustering effect evaluation index; s205, obtaining inflection points of the clustering effect evaluation index curve, taking the number of initial categories corresponding to the inflection points as the target number of abnormal types, and enabling membership initial vectors obtained when fuzzy clustering processing is carried out on the target number to correspond to membership vectors.
Wherein the set step length is 1.
Wherein, the clustering effect evaluation index satisfies the relation:
wherein the method comprises the steps ofFor the number of all abnormal energy information, +.>For the number of all initial categories +.>Is abnormal energy information->For the initial category->Is>And the clustering effect evaluation index is the clustering effect evaluation index which is in negative correlation with the clustering effect. Wherein (1)>Can reflect abnormal energy information->The larger the value of the entropy of the corresponding membership initial vector is, the more the class of the abnormal energy information cannot be accurately judged, and the worse the clustering effect is.
In one embodiment, the fuzzy clustering algorithm is a fuzzy C-means clustering algorithm, and in the process of performing fuzzy clustering processing on all abnormal energy information to obtain the membership degree initial vector of each abnormal energy information, the distance between the abnormal energy information and the clustering center needs to be calculated. The fuzzy C-means clustering algorithm is a common technical means for those skilled in the art, and will not be described herein.
It can be appreciated that in the fuzzy C-means clustering algorithm, the clustering center of each initial category can be obtained, and the clustering effect evaluation index can also be the sum of the DTW distances among all the clustering centers.
In other embodiments, the fuzzy clustering algorithm may also be a PCM fuzzy clustering algorithm.
In one embodiment, after determining the number of the abnormal types, performing fuzzy clustering processing on all abnormal energy information according to the number of the abnormal types to obtain a clustering center of each abnormal type, wherein the clustering center is standard abnormal energy information corresponding to the abnormal type. The cluster center of each anomaly type is marked for the anomaly reason of the anomaly type by combining experience, and one anomaly type corresponds to one anomaly reason.
In this way, in the fuzzy clustering process, the number of the abnormal types is determined by using the clustering effect evaluation index, so that the self-adaptive determination of the number of the abnormal types is realized, the membership degree of each abnormal energy information belonging to each abnormal type is further obtained, and the possibility of each abnormal cause of the abnormal energy information is further obtained.
S103, collecting real-time energy utilization information of the energy, and acquiring the predicted consumption of the energy at the future moment based on the real-time energy utilization information.
In one embodiment, collecting real-time energy consumption information of the energy, where the real-time energy consumption information includes a current time and a set number of times before the current time, where the current time and the set number of times before the current time correspond to the set time period; inputting the real-time energy utilization information into a trained time sequence prediction network to obtain the predicted consumption of the energy source at the future moment; the time sequence prediction network can be realized by adopting a LSTM, TCN, RNN cyclic neural network.
And S104, responding to the predicted consumption in an abnormal state, and calculating a target membership vector of the energy based on the real-time energy information and the membership vector of each abnormal energy information.
In one embodiment, after obtaining the consumption of the energy source at a future time, it may be determined whether the predicted consumption is abnormal, which is described in detail below. The responding to the predicted consumption being in an abnormal state includes: calculating the average value of all energy consumption in the real-time energy consumption informationAnd standard deviation->The method comprises the steps of carrying out a first treatment on the surface of the Based on the average->And the standard deviation->Calculating a normal interval, wherein the normal interval is +.>The method comprises the steps of carrying out a first treatment on the surface of the In response to the predicted consumption being within the normal interval, the predicted consumption is in a normal state; in response to the predicted consumption being not within the normal interval, the predicted consumption is in an abnormal state.
It is understood that the criterion for judging whether the predicted consumption is abnormal isCriteria.
In one embodiment, please refer to fig. 3, which is a flowchart of calculating a target membership vector of the energy source based on the real-time energy information and the membership vector of each abnormal energy information according to an embodiment of the present application. The calculating the target membership vector of the energy based on the real-time energy information and the membership vector of each abnormal energy information comprises: s301, calculating the similarity of the real-time energy information and each piece of abnormal energy information, and taking the abnormal energy information with the similarity larger than a similarity threshold value as target energy information; s302, acquiring main abnormality reasons of each abnormal energy information to calculate tendency of each abnormality reason, wherein the main abnormality reasons are abnormality reasons corresponding to abnormality types with membership maximum values, and the tendency satisfies a relation:
wherein,the main abnormality cause in the energy information for all targets is abnormality cause +>Quantity of->For the amount of all target energy information, +.>The main abnormality cause in all abnormal energy information is abnormality cause +>Quantity of->For abnormality cause->Is a tendency of (2); s303, calculating a target membership vector of the energy based on the tendency of each abnormal cause and the target energy consumption information, wherein the target membership vector comprises the target membership of each abnormal cause, and the target membership satisfies the relation:
wherein,for abnormality cause->Tendency of (A)>For the sum of the tendencies of all abnormality causes, +.>For the amount of all target energy information, +.>Energy information for object->Similarity of->Energy information for object->Cause of abnormality in middle energizer->Membership of->For abnormality cause->Target membership of (a).
The similarity between the real-time energy information and each abnormal energy information can be obtained according to the DTW distance, when the DTW distance between the real-time energy information and the abnormal energy information is larger, the similarity between the real-time energy information and the abnormal energy information is smaller, and the similarity threshold value is 0.8, for example, the similarity between the real-time energy information and the abnormal energy information satisfies the relation:
wherein,for real-time energy information and abnormal energy information +.>Similarity of->For real-time energy information and abnormal energy information +.>Is a DTW distance of (c).
Wherein, in the calculation formula of the tendency,in all target energy information corresponding to the real-time energy information, the abnormality cause is +>Frequency which is the main cause of anomalies; />For characterising the cause of abnormality->Resulting in real-time energy usage information and all targetsThe likelihood of using energy information; tendency->The larger the value, the more the abnormality cause is in the history time>The greater the probability that the real-time energy information is in an abnormal state.
Thus, the target membership vector of the energy is obtained, the target membership vector comprises the target membership of each abnormal cause, the similarity between the real-time energy utilization information and each abnormal energy utilization information is considered when the target membership vector is calculated, and the tendency of the real-time energy utilization information to be in an abnormal state due to each abnormal cause in the historical time is considered, so that the accuracy of the target membership vector is improved.
S105, determining an abnormal reason of the abnormal state based on the target membership vector, and realizing intelligent management of energy.
In one embodiment, the target membership vector includes target membership for each anomaly cause, the greater the target membership, the greater the likelihood that the corresponding anomaly cause will result in an energy consumption anomaly. The method for intelligently managing the energy source based on the abnormal reason of the abnormal state determined by the target membership vector comprises the following steps: and (3) checking each abnormal reason according to the sequence of the target membership from large to small, so as to realize intelligent management of energy.
In one embodiment, in response to the predicted consumption being in an abnormal state, the real-time energy information is used as a new piece of abnormal energy information for determining the cause of the abnormality in the abnormal state next time.
The technical principle and implementation details of the comprehensive energy intelligent management method based on the Internet of things are introduced through the specific embodiments. According to the technical scheme provided by the application, firstly, the membership vector of each abnormal energy information in the history time is determined based on a fuzzy clustering algorithm, wherein the membership vector can accurately reflect the possibility of each abnormal reason corresponding to the abnormal energy information; and predicting the predicted consumption amount at the future time according to the real-time energy consumption information to judge whether the state is abnormal, and accurately positioning the abnormal reason causing the abnormal state according to the real-time energy consumption information and the membership degree vector of each abnormal energy consumption information when the predicted consumption amount is in the abnormal state, so as to realize the accurate management of energy.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the claims. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (8)
1. The comprehensive energy intelligent management method based on the Internet of things is characterized by comprising the following steps of:
collecting abnormal energy consumption information of at least one energy source in historical time, wherein the abnormal energy consumption information comprises a time sequence of energy consumption in a set time period under an abnormal consumption state, and the energy source at least comprises electric energy;
performing fuzzy clustering processing on all abnormal energy information by using a fuzzy clustering algorithm to obtain membership vectors of each abnormal energy information, wherein the membership vectors comprise membership of the abnormal energy information belonging to each abnormal type, and one abnormal type corresponds to one abnormal reason;
acquiring real-time energy utilization information of the energy, and acquiring predicted consumption of the energy at a future moment based on the real-time energy utilization information;
responding to the predicted consumption in an abnormal state, and calculating a target membership vector of the energy based on the real-time energy information and membership vectors of each abnormal energy information;
determining an abnormal reason of the abnormal state based on the target membership vector, and realizing intelligent management of energy sources;
wherein the calculating the target membership vector of the energy based on the real-time energy information and the membership vector of each abnormal energy information includes:
calculating the similarity of the real-time energy information and each abnormal energy information, and taking the abnormal energy information with the similarity larger than a similarity threshold value as target energy information; the main abnormality cause of each abnormal energy information is acquired to calculate the tendency of each abnormality cause, wherein the main abnormality cause is the abnormality cause corresponding to the abnormality type of the membership maximum value, and the tendency satisfies the relation:
wherein,the main abnormality cause in the energy information for all targets is abnormality cause +>Quantity of->For the amount of all target energy information, +.>The main abnormality cause in all abnormal energy information is abnormality cause +>Quantity of->For abnormality cause->Is a tendency of (2); calculating a target membership vector of the energy based on the tendency of each abnormal cause and the target energy consumption information, wherein the target membership vector comprises target membership of each abnormal cause, and the target membership satisfies a relation:
wherein,for abnormality cause->Tendency of (A)>For the sum of the tendencies of all abnormality causes, +.>For the amount of all target energy information, +.>Energy information for object->Similarity of->Energy information for object->Cause of abnormality in middle energizer->Membership of->For abnormality cause->Target membership of (a).
2. The comprehensive energy intelligent management method based on the internet of things according to claim 1, wherein the performing fuzzy clustering processing on all abnormal energy information by using the fuzzy clustering algorithm to obtain the membership vector of each abnormal energy information comprises:
setting the number of initial categories as 2, and carrying out fuzzy clustering treatment on all abnormal energy information to obtain a membership initial vector of each piece of abnormal energy information, wherein the membership initial vector comprises initial membership of the abnormal energy information to each initial category;
calculating a clustering effect evaluation index based on the membership degree initial vector of each piece of abnormal energy information;
updating the number of the initial categories with a set step length, repeatedly executing fuzzy clustering processing and calculating corresponding clustering effect evaluation indexes;
iteratively updating the number of the initial categories, and drawing a clustering effect evaluation index curve, wherein the abscissa of the clustering effect evaluation index curve is the number of the initial categories, and the ordinate is the clustering effect evaluation index;
and obtaining inflection points of the clustering effect evaluation index curve, taking the number of initial categories corresponding to the inflection points as the target number of abnormal types, and enabling the membership initial vector obtained when fuzzy clustering processing is carried out on the target number to correspond to the membership vector.
3. The comprehensive energy intelligent management method based on the internet of things according to claim 2, wherein the clustering effect evaluation index satisfies the relation:
wherein the method comprises the steps ofFor the number of all abnormal energy information, +.>For the number of all initial categories +.>Is abnormal energy information->For the initial category->Is>And the clustering effect evaluation index is the clustering effect evaluation index which is in negative correlation with the clustering effect.
4. The comprehensive energy intelligent management method based on the internet of things according to claim 1, wherein the collecting the real-time energy information of the energy and obtaining the predicted consumption of the energy at a future time based on the real-time energy information comprises:
the real-time energy utilization information comprises the current time and the energy consumption of a set number of times before the current time, wherein the current time and the set number of times before the current time correspond to the set time period;
and inputting the real-time energy utilization information into a trained time sequence prediction network to obtain the predicted consumption of the energy source at the future moment.
5. The comprehensive energy intelligent management method based on the internet of things according to claim 1, wherein the similarity of the real-time energy information and the abnormal energy information satisfies a relation:
wherein,for real-time energy information and abnormal energy information->Similarity of->For real-time energy information and abnormal energy information +.>Is a DTW distance of (c).
6. The comprehensive energy intelligent management method based on the Internet of things of claim 1, wherein said responding to said predicted consumption being in an abnormal state comprises:
calculating the average value of all energy consumption in the real-time energy consumption informationAnd standard deviation->；
Based on the average valueAnd the standard deviation->Calculating a normal interval, wherein the normal interval is +.>；
In response to the predicted consumption being within the normal interval, the predicted consumption is in a normal state;
in response to the predicted consumption being not within the normal interval, the predicted consumption is in an abnormal state.
7. The comprehensive energy intelligent management method based on the internet of things according to claim 6, wherein the real-time energy information is used as a new piece of abnormal energy information for determining the cause of the abnormality next time in response to the predicted consumption being in the abnormality state.
8. The comprehensive energy intelligent management method based on the internet of things according to claim 1, wherein the determining the abnormal cause of the abnormal state based on the target membership vector, implementing the intelligent management of the energy comprises: and checking each abnormal reason according to the order of the target membership from high to low.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311384207.9A CN117114252A (en) | 2023-10-24 | 2023-10-24 | Comprehensive energy intelligent management method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311384207.9A CN117114252A (en) | 2023-10-24 | 2023-10-24 | Comprehensive energy intelligent management method based on Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117114252A true CN117114252A (en) | 2023-11-24 |
Family
ID=88798760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311384207.9A Pending CN117114252A (en) | 2023-10-24 | 2023-10-24 | Comprehensive energy intelligent management method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117114252A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504607A (en) * | 2014-09-04 | 2015-04-08 | 国家电网公司 | Method for diagnosing photovoltaic power station faults on the basis of fuzzy clustering algorithm |
| US20190205774A1 (en) * | 2018-01-02 | 2019-07-04 | International Business Machines Corporation | Fast detection of energy consumption anomalies in buildings |
| CN112307435A (en) * | 2020-10-30 | 2021-02-02 | 三峡大学 | Method for judging and screening abnormal electricity consumption based on fuzzy clustering and trend |
| CN112488242A (en) * | 2020-12-18 | 2021-03-12 | 深圳供电局有限公司 | Power metering terminal anomaly detection method and device, computer equipment and medium |
| CN113033414A (en) * | 2021-03-26 | 2021-06-25 | 深圳供电局有限公司 | Power consumption data anomaly detection method and device, computer equipment and storage medium |
| CN116796271A (en) * | 2023-06-19 | 2023-09-22 | 天津三源电力信息技术股份有限公司 | Resident energy abnormality identification method |
-
2023
- 2023-10-24 CN CN202311384207.9A patent/CN117114252A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504607A (en) * | 2014-09-04 | 2015-04-08 | 国家电网公司 | Method for diagnosing photovoltaic power station faults on the basis of fuzzy clustering algorithm |
| US20190205774A1 (en) * | 2018-01-02 | 2019-07-04 | International Business Machines Corporation | Fast detection of energy consumption anomalies in buildings |
| CN112307435A (en) * | 2020-10-30 | 2021-02-02 | 三峡大学 | Method for judging and screening abnormal electricity consumption based on fuzzy clustering and trend |
| CN112488242A (en) * | 2020-12-18 | 2021-03-12 | 深圳供电局有限公司 | Power metering terminal anomaly detection method and device, computer equipment and medium |
| CN113033414A (en) * | 2021-03-26 | 2021-06-25 | 深圳供电局有限公司 | Power consumption data anomaly detection method and device, computer equipment and storage medium |
| CN116796271A (en) * | 2023-06-19 | 2023-09-22 | 天津三源电力信息技术股份有限公司 | Resident energy abnormality identification method |
Non-Patent Citations (1)
| Title |
|---|
| 王化祥 编著: "《智能信息处理 第2版》", 天津：天津大学出版社, pages: 241 - 243 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108198408B (en) | Self-adaptive anti-electricity-stealing monitoring method and system based on electricity information acquisition system | |
| KR101941854B1 (en) | System and method of estimating load with null data correction | |
| CN112684401B (en) | Method and system for processing operation error data of electric energy meter in light-load station area | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| CN106598822A (en) | Abnormal data detection method and device applied to capacity estimation | |
| CN110298765B (en) | Power distribution network power consumption abnormality detection method based on objective correlation factors | |
| CN112101765A (en) | Abnormal data processing method and system for operation index data of power distribution network | |
| CN114879070A (en) | Battery state evaluation method and related equipment | |
| CN114076841A (en) | Electricity stealing behavior identification method and system based on electricity utilization information data | |
| CN107274025B (en) | System and method for realizing intelligent identification and management of power consumption mode | |
| CN111626360B (en) | Method, apparatus, device and storage medium for detecting boiler fault type | |
| CN115202802A (en) | Alarm threshold determination method, device, equipment, storage medium and alarm system | |
| CN112418522A (en) | Industrial heating furnace steel temperature prediction method based on three-branch integrated prediction model | |
| CN117114252A (en) | Comprehensive energy intelligent management method based on Internet of things | |
| CN111310121A (en) | New energy output probability prediction method and system | |
| CN115935212A (en) | Adjustable load clustering method and system based on longitudinal trend prediction | |
| CN114157486B (en) | Communication flow data abnormity detection method and device, electronic equipment and storage medium | |
| CN115935285A (en) | Multi-element time series anomaly detection method and system based on mask map neural network model | |
| CN106816871B (en) | State similarity analysis method for power system | |
| CN111222550B (en) | User electricity consumption behavior determining method and device | |
| CN106156470B (en) | Time series abnormity detection and labeling method and system | |
| CN114331688A (en) | Method and device for detecting batch operation state of bank counter system business | |
| KR20210016980A (en) | Server and method for estimating used amount of missed data in advanced metering infrastructure system | |
| CN116739532B (en) | Energy project management method, system, terminal equipment and storage medium | |
| CN117647697B (en) | Knowledge graph-based fault positioning method and system for electric power metering assembly line |
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 |