CN115423301B - Intelligent electric power energy management and control method, device and system based on Internet of things - Google Patents
Intelligent electric power energy management and control method, device and system based on Internet of things Download PDFInfo
- Publication number
- CN115423301B CN115423301B CN202211052303.9A CN202211052303A CN115423301B CN 115423301 B CN115423301 B CN 115423301B CN 202211052303 A CN202211052303 A CN 202211052303A CN 115423301 B CN115423301 B CN 115423301B
- Authority
- CN
- China
- Prior art keywords
- electric energy
- data
- community
- energy consumption
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000005265 energy consumption Methods 0.000 claims abstract description 157
- 238000012544 monitoring process Methods 0.000 claims abstract description 69
- 238000013528 artificial neural network Methods 0.000 claims abstract description 22
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000005457 optimization Methods 0.000 claims abstract description 19
- 238000011217 control strategy Methods 0.000 claims abstract description 10
- 238000007726 management method Methods 0.000 claims description 75
- 238000004364 calculation method Methods 0.000 claims description 30
- 230000005611 electricity Effects 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 27
- 238000012360 testing method Methods 0.000 claims description 18
- 238000004140 cleaning Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000000513 principal component analysis Methods 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 230000002354 daily effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004134 energy conservation Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000006855 networking Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013506 data mapping Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005316 response function Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/35—Utilities, e.g. electricity, gas or water
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Environmental & Geological Engineering (AREA)
- Water Supply & Treatment (AREA)
- Toxicology (AREA)
- Public Health (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of energy management and control, solves the technical problem of inaccurate community electric power energy consumption prediction, and particularly relates to an electric power energy intelligent management and control method based on the Internet of things, which comprises the following steps: obtaining a predicted value of total electric energy consumption through an electric energy consumption prediction model according to the effective temperature data of the current day, the community resident data and the date type data; calculating the actual value of the total consumption of the electric energy according to the collected real-time monitoring data set; and calculating an electric energy consumption prediction error according to the electric energy total consumption actual value and the electric energy total consumption predicted value, sending early warning information according to the prediction error, and adopting a corresponding electric energy management and control strategy. According to the invention, the electric energy consumption prediction model with high stability and high prediction precision is constructed by adopting the gray neural network and the ant colony optimization algorithm, and the electric energy consumption prediction model is continuously optimized by using the cleaned database, so that the prediction precision is improved, and the intelligent management and control of the electric energy of communities are facilitated.
Description
Technical Field
The invention relates to the technical field of energy management and control, in particular to an intelligent electric power energy management and control method, device and system based on the Internet of things.
Background
Along with the development of the Internet of things technology, the Internet of things technology and energy management and control are combined, so that the use of community electric energy is controlled efficiently, safely and intelligently, the community energy consumption level is reduced, and the energy conservation and emission reduction of the whole society and the community energy consumption cost are very necessary.
At present, the existing intelligent energy management and control method is usually based on historical data for analysis to realize intelligent management of power energy production and consumption, but the traditional power energy consumption prediction method is very slow to process aiming at massive historical data, often takes a long time, even sometimes causes prediction distortion due to poor stability of a prediction model, so that power energy cannot be reasonably managed and controlled, and the power energy utilization rate is low.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent electric power energy management and control method, device and system based on the Internet of things, which solve the technical problem of inaccurate community electric power energy consumption prediction and achieve the purposes of reducing electric power energy consumption and improving the utilization rate on the premise of fully meeting and perfecting the electric power energy consumption requirements of communities.
In order to solve the technical problems, the invention provides the following technical scheme: an intelligent electric power energy management and control method based on the Internet of things comprises the following steps:
s1, calculating effective current day temperature data according to current day meteorological data of a community in an area position;
s2, acquiring community resident data and date type data, wherein the date type data comprises holidays and workdays;
s3, obtaining a total electric energy consumption predicted value of the current day of the community through a pre-built electric energy consumption predicted model according to the current day effective temperature data, the community resident data and the date type data, wherein the electric energy consumption predicted model is built according to a historical data set stored in a database;
s4, acquiring a real-time monitoring data set acquired by the electric energy data acquisition equipment, wherein the real-time monitoring data comprises household energy monitoring data, corridor lighting energy monitoring data and street lamp energy monitoring data;
s5, calculating the actual value of the total electric energy consumption of the community on the same day according to the real-time monitoring data set;
s6, calculating an electric energy consumption prediction error according to the electric energy total consumption actual value and the electric energy total consumption prediction value;
s7, judging whether the prediction error is within a preset range, and if the prediction error is within the preset range, judging that the electric energy consumption of the community is normal; if the prediction error is not in the preset range, judging that the community electric energy consumption is abnormal and sending early warning information to an energy management and control center;
S8, adopting a corresponding energy management and control strategy according to the early warning information energy management and control center.
Further, between the steps S6 and S7, the method further includes:
s9, cleaning the data in the database according to the prediction error;
and S10, continuously optimizing the electric energy consumption prediction model according to the cleaned database.
Further, the step S3 specifically includes:
s31, constructing an electric energy consumption prediction model according to a historical energy sample set stored in a database;
s32, obtaining a predicted value of the total consumption of the electric energy of the current day of the community by adopting the electric energy consumption prediction model according to the current day effective temperature data, the community resident data and the date type data.
Further, the step S31 specifically includes:
s311, acquiring a historical energy sample set which is processed by a principal component analysis algorithm and stored in a database, wherein each historical sample in the historical energy sample set consists of historical daily effective temperature data, historical date type data, historical daily community resident data and historical daily total electric energy consumption;
s312, randomly dividing the historical energy sample set into a training sample set and a test sample set according to a preset proportion;
S313, determining the topological structure of the gray neural network according to the data characteristics of the training sample set so as to obtain an initial prediction model;
s314, training and optimizing the initial prediction model through a training sample set according to the mapping relation between the weight bias of the initial prediction model and the ant colony optimization algorithm to obtain an optimal electric energy consumption prediction model;
s315, testing and verifying the performance of the electric energy consumption prediction model by adopting a test sample set.
Further, the step S9 specifically includes:
when the prediction error is not in the preset range, uploading the effective temperature data of the current day, the date type data and the real-time monitoring data set to a database, and removing dirty data in the database;
and uploading the effective temperature data of the current day, the date type data and the real-time monitoring data set to a database when the prediction error is in a preset range, and eliminating repeated historical data, wherein the collection time interval of the repeated historical data is larger than a time threshold value, in the database.
Further, the expression of the output value of the electric energy consumption prediction model is:
in the above, W f The predicted value of the total consumption of the electric energy on the same day of the community is that m is the number of community electricity utilization units and n is the influence The number of factor indexes of total consumption of community electric energy, x j For the j-th power consumption unit, alpha ij For the weight of the jth power consumption unit in the ith factor index, F τ Is of date type, and τ has values of 1 and 0 representing workdays and holidays, respectively.
The invention also provides a technical scheme that: electric power energy intelligence management and control device based on thing networking includes:
the effective temperature calculation module is used for calculating the effective temperature data of the current day according to the weather data of the current day of the position of the area where the community is located;
the system comprises a first acquisition module, a second acquisition module and a first storage module, wherein the first acquisition module is used for acquiring community resident data and date type data, and the date type data comprises holidays and workdays;
the predicted value calculation module is used for obtaining a predicted value of the total electric energy consumption of the current day of the community through a pre-built electric energy consumption prediction model according to the current day effective temperature data, the community resident data and the date type data, wherein the electric energy consumption prediction model is built according to a historical data set stored in a database;
the second acquisition module is used for acquiring a real-time monitoring data set acquired by the electric energy data acquisition equipment, wherein the real-time monitoring data comprises household energy monitoring data, corridor lighting energy monitoring data and street lamp energy monitoring data;
The actual value calculation module is used for calculating the actual value of the total electric energy consumption of the community on the same day according to the real-time monitoring data set;
the prediction error calculation module is used for calculating an electric energy consumption prediction error according to the electric energy total consumption actual value and the electric energy total consumption predicted value;
the judging module is used for judging whether the prediction error is in a preset range, and if the prediction error is in the preset range, judging that the community electric energy consumption is normal; if the prediction error is not in the preset range, judging that the community electric energy consumption is abnormal and sending early warning information to an energy management and control center;
and the intelligent management and control module is used for adopting a corresponding energy management and control strategy according to the early warning information energy management and control center.
Further, the method further comprises the following steps:
the database cleaning module is used for cleaning the data in the database according to the prediction error e;
and the prediction model optimization module is used for continuously optimizing the electric energy consumption prediction model according to the cleaned database.
The invention also provides another technical scheme: a system of an intelligent electric power energy management and control method based on the Internet of things comprises the following steps: the system comprises electric energy data acquisition equipment, computer equipment and an energy management and control center;
The electric energy data acquisition equipment is used for acquiring electric energy consumption data of communities and transmitting the electric energy consumption data to the computer equipment;
the computer equipment establishes data transmission with the energy management and control center, and comprises at least one processor, a memory and a database, wherein the computer equipment is used for receiving a real-time monitoring data set acquired by the electric energy data acquisition equipment and uploading the real-time monitoring data set to the database, and then the processor is used for calling and running an executable instruction in the memory to calculate the predicted value of the total electric energy consumption of the community on the same day according to the received real-time monitoring data set;
the energy management and control center is used for displaying community electricity consumption information and sending out an alarm to remind management and control center staff.
Further, the electric energy data acquisition equipment comprises a plurality of internet of things sensors which are deployed on site and used for acquiring electric energy consumption, and a power supply module used for providing electric energy required by the operation of the internet of things sensors.
By means of the technical scheme, the invention provides an intelligent electric power energy management and control method, device and system based on the Internet of things, which at least have the following beneficial effects:
1. According to the invention, the topological structure of the gray neural network is used as an initial prediction model according to the gray relevance among indexes affecting the electric energy factors, then the initial prediction model is trained and optimized according to a training sample set extracted from a database and an ant colony optimization algorithm, so that an optimal electric energy consumption prediction model is obtained, the stability of the electric energy consumption prediction model is improved, the data can be rapidly processed, the output electric energy consumption prediction value can be ensured to be more accurate, the supply and detailed use conditions of electric energy of each link of a community can be conveniently monitored in real time, visual and scientific basis is provided for energy conservation and consumption reduction, and intelligent management and control are performed according to a scientific energy efficiency evaluation method and an evaluation standard.
2. According to the invention, collected data are processed and analyzed according to the error between the predicted value and the actual monitored value of the electric energy consumption prediction model, dirty data stored in the database are cleaned according to the analysis result, valuable data are reserved, the cleaned database is used for optimizing the electric energy consumption prediction model, and maintenance personnel in an energy management and control center are not required to monitor and optimize the electric energy consumption prediction model, so that the accuracy of the electric energy consumption predicted value is improved, the calculated amount of the prediction process is reduced, the prediction speed is improved, and the method has higher social value and application prospect.
3. According to the invention, the electric energy consumption prediction model with high stability and high prediction precision is constructed by adopting the gray neural network and the ant colony optimization algorithm, and the electric energy consumption prediction model is continuously optimized by using the cleaned database without monitoring and optimizing by maintenance personnel of an energy management and control center, so that the optimization efficiency and the prediction precision are improved, the electric energy consumption is reduced on the premise of fully meeting and perfecting the electric energy consumption requirement of the community, and the electric energy utilization rate is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a flow chart of an intelligent control method for electric power energy according to a first embodiment of the invention;
FIG. 2 is a flowchart of step S3 of the intelligent control method of electric power energy source of the present invention;
FIG. 3 is a flow chart of the method for intelligently controlling the electric energy source for constructing the electric energy consumption prediction model;
FIG. 4 is a topology diagram of a gray neural network of the intelligent control method of electric power energy sources of the present invention;
FIG. 5 is a schematic block diagram of an intelligent control device for electric power energy according to a first embodiment of the present invention;
FIG. 6 is a flowchart of an intelligent control method for electric power energy according to a second embodiment of the present invention;
FIG. 7 is a schematic block diagram of an intelligent control device for electric power energy according to a second embodiment of the present invention;
fig. 8 is a schematic block diagram of the intelligent control system for electric power energy of the present invention.
In the figure: 101. an effective temperature calculation module; 102. a first acquisition module; 103. a predictive value calculation module; 104. a second acquisition module; 105. an actual value calculation module; 106. a prediction error calculation module; 107. a judging module; 108. an intelligent management and control module; 109. a database cleaning module; 110. a predictive model optimization module; 100. an electric energy data acquisition device; 200. a computer device; 300. and an energy management and control center.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. Therefore, the implementation process of how to apply the technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in a method of implementing an embodiment described above may be implemented by a program to instruct related hardware, and thus the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Summary of the application
The electric power energy consumption of the community mainly comprises community household electricity consumption, corridor lighting electricity consumption and street lamp electricity consumption, wherein the community household electricity consumption is an important factor affecting the community electric power energy consumption, the starting and stopping of an air conditioner are main factors of the community household electricity consumption, and the method is oriented to massive historical data, and is poor in stability of a prediction model and easy to cause predicted value distortion. Therefore, the method and the system obtain the predicted value of the total consumption of the electric energy of the community through the electric energy consumption prediction model according to the effective temperature, the number of the residents of the community and the date type, collect a real-time monitoring data set through the electric energy data collection device based on the Internet of things technology, aggregate the actual value of the total consumption of the electric energy of the community, compare the actual value of the total consumption of the electric energy of the community with the predicted value of the total consumption of the electric energy of the community, clean a database for constructing the electric energy consumption prediction model according to comparison results, retain valuable data, continuously optimize the electric energy consumption prediction model, enhance the prediction precision of the prediction model, reduce operation time, facilitate energy management and control personnel to adopt an optimal management and control strategy according to the predicted value of the more accurate electric energy consumption, and achieve the purpose of reducing electric energy consumption on the premise of meeting the requirements of the use of the community.
Example 1
Referring to fig. 1-4, an intelligent control method for electric power energy based on internet of things according to a first embodiment of the invention is shown, comprising the following steps:
s1, calculating effective current day temperature data according to current day meteorological data of the area position of the community.
Specifically, weather data of the current day can be obtained according to weather forecast of a city where a community to be controlled for electric power energy is located, and air temperature data and air relative humidity data of the current day are extracted from the weather data of the current day, wherein the air temperature is marked as T, the air relative humidity is marked as R, and the effective temperature data of the current day is marked as T a When R is>0.13T 2 -13.5T+363 and T>At 30, T a The calculation formula of (2) is as follows:
T a ＝32.99+0.00515T 2 -0.02314TR+0.00001T 3 R
otherwise the first set of parameters is selected,
T a ＝4.00+0.7664T-0.00087R 2 -0.00024T 2 R+0.00006TR 2 +0.00001T 3 R
wherein the effective temperature data T of the same day a And air temperature T are in units of deg.c.
It should be noted that, in general, a community resident decides whether to start or stop an air conditioner according to his own indoor feeling, and for this reason, the embodiment does not consider the wind speed when calculating the effective temperature on the same day.
S2, acquiring community resident data and date type data, wherein the date type data comprises holidays and workdays.
Specifically, factor indexes influencing the consumption of the community electric power energy are very many and too complex, so that three main factor indexes, namely effective temperature in the same day room, the number of community households and whether the current household number is holidays or not, are extracted by adopting a principal component analysis algorithm (PCA for short), and in the embodiment, the current household number in the community can be obtained through community property investigation, and whether the current day is holidays or not can be obtained according to a calendar table.
S3, obtaining a predicted value of the total electric energy consumption of the community on the same day through a pre-constructed electric energy consumption prediction model according to the effective temperature data of the current day, the community resident data and the date type data. As shown in fig. 2, the method specifically comprises the following steps:
s31, constructing an electric energy consumption prediction model according to a historical energy sample set stored in a database, wherein the specific construction steps are as follows, as shown in fig. 3:
s311, acquiring a historical energy sample set which is processed by a principal component analysis algorithm and stored in a database.
Specifically, the data before the current day collected by the data collection device is processed and analyzed and then stored in the database, so as to form a sample set of historical energy consumption of the community, and in this embodiment, the number of the historical energy consumption sample sets is 200.
It should be noted that, factor indexes affecting the consumption of electric power energy of the community are very many and too complex, so that three main impact indexes are extracted by adopting a principal component analysis algorithm (PCA for short), namely, each history sample in the obtained history energy sample set is composed of history day effective temperature data, history date type data, history day community resident data and history day electric energy total consumption, wherein the history day electric energy total consumption is an actual value of the electric energy total consumption of the community on the history day.
S312, the historical energy use sample set is randomly divided into a training sample set and a test sample set according to a preset proportion.
In this embodiment, 200 samples in the historical energy sample set are randomly divided into a training sample set and a test sample set according to a ratio of 4:1, that is, 160 training samples are contained in the training sample set, and 40 test samples are contained in the test sample set.
S313, determining the topological structure of the gray neural network according to the data characteristics of the training sample set so as to obtain an initial prediction model.
It should be noted that the gray neural network is a hybrid model in which a gray model and a neural network model are fused; the modeling idea of the gray neural network model is that a time response function of a gray differential equation proposed based on a gray theory is mapped into an expanded neural network, so that parameters of the gray differential equation and each weight of the neural network are mutually corresponding, then the neural network is trained, when the network converges, corresponding equation parameters are extracted from the trained neural network, a whitened differential equation is obtained, and the total consumption of community electric energy can be predicted by using the whitened differential equation. Wherein, the expression of the time response function is:
In the above expression, t represents the number of input parameters, a represents the development coefficient of the gray model, and b represents the amount of feedback.
In this embodiment, according to the data features of 160 training samples in the training sample set, the topology structure of the gray neural network can be formed in the neural network mapped by the foregoing method, as shown in fig. 4, and four layers are total: l1, L2, L3 and L4 are respectively an input layer, an hidden layer 1, a hidden layer 2 and an output layer, t represents the serial number of an input parameter, and x n (t) represents network input parameters, ω 11 、ω 2i 、ω 3i (i=1, 2, …, n) represents the connection weight of each neural unit of the network, y represents the predicted value of the network, and n represents the number of the predicted factor indexes of the total consumption of the community electric energy.
The t value is input into the L1 layer node, and the nodes of the L2 layer, the L3 layer and the L4 layer are calculated, wherein the activation function of the neuron of the L2 layer is a Sigmoid function:
the excitation function of the neurons of the other layers is taken as a linear function f (x) =x, and then calculated according to the neural network topology, a gray differential equation can be mapped into the topology of a neural network.
As can be seen from FIG. 4, the initial prediction model constructed by the method introduces factor indexes influencing the consumption of electric energy of communities as input variables of the model in the L3 layer, considers the effect of the factor indexes influencing the total consumption of electric energy of communities on the prediction value, and simultaneously has the weight omega of the network 21 ,ω 22 ,…,ω 2n Different variables are respectively given, and the weights can be adjusted to different degrees during training, but because the initial weights and the bias of the initial prediction model constructed based on the gray neural network have great randomization, the initial prediction model is easy to fall into local optimum during training, and related parameters cannot be further adjusted, so that the problems of low convergence speed, low prediction precision, poor stability and the like of the initial prediction model are caused, and therefore, the initial prediction model needs to be trained and optimized by adopting an ant colony optimization algorithm according to a training sample set so as to obtain the optimal electric energy consumption prediction model.
And S314, training and optimizing the initial prediction model through a training sample set according to the mapping relation between the weight bias of the initial prediction model and the ant colony optimization algorithm to obtain an optimal electric energy consumption prediction model.
Specifically, according to the data characteristics of the training sample set, initial ant colony algorithm parameters are generated randomly, the weight and node bias of each node connection of the gray neural network are generated, the generated gray neural networks are encoded to correspond to ant individuals in the ant colony algorithm, then initial groups of the ant colony optimization algorithm are generated, after the initial groups are formed, optimization processing is carried out on each individual in the groups, and an optimal electric energy consumption prediction model is output after the iteration times are reached.
In this embodiment, the initial ant colony algorithm parameters: the number of ant individuals is M ant The maximum iteration number is I max The learning rate is mu, an optimal electric energy consumption prediction model is obtained after the initial prediction model is trained, and the expression of the output value of the electric energy consumption prediction model is as follows:
in the above, W f The method is characterized in that the method is used for predicting the total consumption of electric energy of a community on the same day, m is the number of community electricity utilization units, n is the number of factor indexes influencing the total consumption of the electric energy of the community, and x j For the j-th power consumption unit, alpha ij For the weight of the jth power consumption unit in the ith factor index, F τ Is of date type, and τ has values of 1 and 0 representing workdays and holidays, respectively.
S315, testing and verifying the performance of the electric energy consumption prediction model by adopting a test sample set.
Specifically, 40 test samples in the test sample set are input into the electric energy consumption prediction model for testing, and the accuracy of the electric energy consumption prediction model is verified.
S32, obtaining a predicted value of the total electric energy consumption of the community on the same day by adopting an electric energy consumption prediction model according to the effective temperature data of the current day, the resident data of the community and the date type data.
Specifically, the obtained effective temperature data of the dayThe community resident data and date type data are input into an electric energy consumption prediction model, and after a series of processing of the electric energy consumption prediction model, the electric energy total consumption prediction value W of the community on the same day can be obtained f At this time, the community can schedule and store energy of electric power according to the predicted value of the total consumption of electric energy, so that normal living demands of residents in the community are ensured, and the waste of electric power and energy can be avoided.
And S4, acquiring a real-time monitoring data set acquired by the electric energy data acquisition equipment.
Specifically, by adopting the electric energy data acquisition equipment deployed on the sensing layer of the internet of things to acquire the time electricity consumption of each electricity consumption unit of the community on the same day, namely, a real-time monitoring data set, in the embodiment, the community electricity consumption units can be divided into household electricity consumption, corridor lighting electricity consumption and community street lamp electricity consumption, and therefore, the real-time monitoring data comprises household energy monitoring data, corridor lighting energy monitoring data and street lamp energy monitoring data.
And S5, calculating the actual value of the total electric energy consumption of the community on the same day according to the real-time monitoring data set.
Specifically, household energy monitoring data, corridor lighting energy monitoring data and street lamp energy monitoring data acquired by the electric energy data acquisition equipment are accumulated, and the actual value of the total electric energy consumption of the community on the same day can be obtained and recorded as W.
And S6, calculating an electric energy consumption prediction error according to the electric energy total consumption actual value and the electric energy total consumption prediction value.
Specifically, according to the actual value W of the total consumption of the electric energy and the predicted value W of the total consumption of the electric energy f The electric energy consumption prediction error can be obtained, and if the electric energy consumption prediction error is set as e, the expression is
S7, judging whether the prediction error e is in a preset range, and if the prediction error e is in the preset range, judging that the electric energy consumption of the community is normal; if the prediction error e is not in the preset range, the community electric energy consumption is judged to be abnormal, and early warning information is sent to the energy management and control center.
In the embodiment, the preset range is set to be 0-0.03, and if the prediction error e is within the preset range, the community electric energy consumption is judged to be normal, namely, only continuous monitoring is needed and regulation is not needed; if the prediction error e is not in the preset range, the community electric energy consumption is judged to be abnormal, namely, early warning information is required to be sent to the energy management and control center through a network, and the early warning information is that overload occurs to the total community electric energy consumption or the total community electric energy consumption is far lower than a predicted value.
And S8, adopting a corresponding energy management and control strategy according to the early warning information energy management and control center.
Specifically, a worker in the energy management and control center adopts a corresponding management and control strategy according to the received early warning information, if the received early warning information is overload of the total consumption of electric energy of the community, the worker detects whether each electricity utilization unit has electricity stealing and leakage, if the electricity stealing and leakage does not occur, the electricity consumption prediction model is required to be optimized, and the electricity utilization units are managed and controlled, so that the consumption of electric energy is reduced.
For example, the lighting lamp of the central square in the community can be intelligently controlled according to the traffic flow, so that the consumption of electric power and energy is reduced, the intelligent control method is that the monitoring camera is used for capturing the image of the target area and transmitting the image of the target area to the target detector through the Internet of things, the human-shaped targets in the image of the target area are extracted through the target detector, the human-shaped targets are counted according to the human-shaped targets, when the human-shaped targets are larger than or equal to the traffic flow threshold value, the lighting lamp is turned on, when the human-shaped targets are smaller than the traffic flow threshold value, the lighting lamp is turned off, and the lighting lamp and the street lamp are controlled by different circuits, so that the consumption of electric power and energy is reduced on the premise that the travel and play demands of residents in the community are met, and the purpose of intelligent control of the electric power and energy is achieved.
Referring to fig. 5, this embodiment further provides a technical solution: electric power energy intelligence management and control device based on thing networking includes:
the effective temperature calculating module 101, the effective temperature calculating module 101 is used for calculating the effective temperature data of the current day according to the weather data of the current day of the position of the area where the community is located;
the first acquisition module 102, the first acquisition module 102 is configured to acquire community resident data and date type data, where the date type data includes holidays and workdays;
The predicted value calculation module 103, the predicted value calculation module 103 is used for obtaining a predicted value of the total electric energy consumption of the current day of the community through a pre-built electric energy consumption prediction model according to the effective temperature data of the current day, the household data of the community and the date type data, wherein the electric energy consumption prediction model is built according to a historical data set stored in a database;
the second acquisition module 104 is configured to acquire a real-time monitoring data set acquired by the electric energy data acquisition device, where the real-time monitoring data includes household energy monitoring data, corridor lighting energy monitoring data and street lamp energy monitoring data;
the actual value calculation module 105, the actual value calculation module 105 is used for calculating the actual value of the total electric energy consumption of the community on the same day according to the real-time monitoring data set;
the prediction error calculation module 106, the prediction error calculation module 106 is configured to calculate an electric energy consumption prediction error according to the electric energy total consumption actual value and the electric energy total consumption predicted value;
the judging module 107 is configured to judge whether the prediction error is within a preset range, and if the prediction error is within the preset range, judge that the community electric energy consumption is normal; if the prediction error is not in the preset range, judging that the community electric energy consumption is abnormal and sending early warning information to an energy management and control center;
The intelligent management and control module 108, the intelligent management and control module 108 is used for adopting a corresponding energy management and control strategy according to the early warning information energy management and control center.
According to the embodiment, the topological structure of the gray neural network is used as an initial prediction model according to the gray relevance among indexes affecting the electric energy factors, then the initial prediction model is trained and optimized according to a training sample set extracted from a database and an ant colony optimization algorithm, so that an optimal electric energy consumption prediction model is obtained, the stability of the electric energy consumption prediction model is improved, the electric energy consumption prediction model can be enabled to process data rapidly, the output electric energy consumption prediction value can be ensured to be more accurate, the supply and detailed use conditions of electric energy of all links of a community can be monitored in real time conveniently, visual and scientific basis is provided for energy conservation and consumption reduction, and intelligent management and control are carried out according to a scientific energy efficiency evaluation method and an evaluation standard.
Example two
Referring to fig. 2-4 and fig. 6, a power energy intelligent control method based on the internet of things according to a second embodiment of the present invention is shown, where the power energy intelligent control method according to the second embodiment includes steps in the power energy intelligent control method according to the first embodiment, and compared with the power energy intelligent control method according to the first embodiment, the second embodiment further includes steps S9 and S10, as shown in fig. 6.
And S9, cleaning the data in the database according to the prediction error.
Specifically, when the prediction error e is not within the preset range, the effective temperature data and date type data of the current day and the real-time monitoring data set are uploaded to the database, and in addition, the prediction value output by the electric energy consumption prediction model is lower in precision, that is, dirty data stored in the database needs to be removed, so that the prediction precision of the electric energy consumption prediction model can be improved, the prediction time is shortened, and the stability of the electric energy consumption prediction model is enhanced.
In this embodiment, the idea of removing dirty data in the database is to perform descriptive statistical analysis on data similar to the effective temperature data and date type data in the database, perform data cleaning on the ETL workflow according to a preset data mapping rule, and remove the dirty data stored in the database, where the data mapping rule refers to whether the difference between the daily electricity consumption data of the household stored in the database and the average value of the daily electricity consumption data of the household collected by the current electric energy data collection device is within a threshold range or not under the condition of the same effective temperature and date type, and if not, the difference indicates that the data is erroneous data and needs to be removed in time.
Specifically, when the prediction error e is within a preset range, uploading the effective temperature data of the current day, the date type data and the real-time monitoring data set to a database, and eliminating historical data which are the same as the uploaded data in the database and have time intervals larger than a time threshold value, namely eliminating repeated data in the database.
Because the electric energy data acquisition equipment monitors electric equipment and acquires data every day, repeated data are required to be cleaned in time for massive data, data redundancy is reduced, stability of an electric energy consumption prediction model is further improved, and prediction speed is improved.
And S10, continuously optimizing the electric energy consumption prediction model according to the cleaned database.
Specifically, the community resident electricity consumption is related to the effective temperature and date type of the current day, and is also related to a plurality of factor indexes such as personnel constitution, economic level and the like of resident families, so that partial data sample sets are extracted from the cleaned database to continuously optimize the electric energy consumption prediction model, the output value of the electric energy consumption prediction model is more in line with the current community electricity consumption requirement, and the intelligent management and control of the community electric energy source are conveniently realized by the energy management and control center.
Referring to fig. 7, this embodiment further provides a technical solution: electric power energy intelligence management and control device based on thing networking includes:
the effective temperature calculating module 101, the effective temperature calculating module 101 is used for calculating the effective temperature data of the current day according to the weather data of the current day of the position of the area where the community is located;
the first acquisition module 102, the first acquisition module 102 is configured to acquire community resident data and date type data, where the date type data includes holidays and workdays;
the predicted value calculation module 103, the predicted value calculation module 103 is used for obtaining a predicted value of the total electric energy consumption of the current day of the community through a pre-built electric energy consumption prediction model according to the effective temperature data of the current day, the household data of the community and the date type data, wherein the electric energy consumption prediction model is built according to a historical data set stored in a database;
the second acquisition module 104 is configured to acquire a real-time monitoring data set acquired by the electric energy data acquisition device, where the real-time monitoring data includes household energy monitoring data, corridor lighting energy monitoring data and street lamp energy monitoring data;
the actual value calculation module 105, the actual value calculation module 105 is used for calculating the actual value of the total electric energy consumption of the community on the same day according to the real-time monitoring data set;
The prediction error calculation module 106, the prediction error calculation module 106 is configured to calculate an electric energy consumption prediction error according to the electric energy total consumption actual value and the electric energy total consumption predicted value;
the judging module 107 is configured to judge whether the prediction error is within a preset range, and if the prediction error is within the preset range, judge that the community electric energy consumption is normal; if the prediction error is not in the preset range, judging that the community electric energy consumption is abnormal and sending early warning information to an energy management and control center;
the intelligent management and control module 108, the intelligent management and control module 108 is used for adopting a corresponding energy management and control strategy according to the early warning information energy management and control center;
the database cleaning module 109 is configured to clean data in the database according to the prediction error e;
the prediction model optimization module 110, the prediction model optimization module 110 is configured to continuously optimize the electric energy consumption prediction model according to the cleaned database.
According to the embodiment, the collected data are processed and analyzed according to the error between the predicted value and the actual monitoring value of the electric energy consumption prediction model, dirty data stored in the database are cleaned according to the analysis result, and valuable data are reserved, so that the operation amount of the electric energy consumption prediction model is reduced, the prediction speed is improved, the accuracy of the predicted value is further improved, and the method has high social value and application prospect.
Referring to fig. 8, this embodiment further provides a technical solution: an intelligent power energy management and control system based on the Internet of things comprises: the system comprises an electric energy data acquisition device 100, a computer device 200 and an energy management and control center 300;
the electric energy data acquisition equipment 100 establishes data communication with the computer equipment 200, the electric energy data acquisition equipment 100 is used for acquiring electric energy consumption data of communities and transmitting the electric energy consumption data to the computer equipment 200, and the electric energy data acquisition equipment 100 comprises a plurality of internet of things sensors which are deployed on site and are used for acquiring electric energy consumption, and a power supply module which is used for providing electric energy required by the operation of the internet of things sensors;
the computer device 200 establishes data transmission with the energy management and control center 300, and the computer device 200 comprises at least one processor, a memory and a database, and is used for receiving the real-time monitoring data set collected by the electric energy data collection device 100 and uploading the real-time monitoring data set to the database, and then calling and running executable instructions in the memory through the processor to calculate the predicted value of the total electric energy consumption of the community on the current day according to the received real-time monitoring data set;
the energy management and control center 300 is used for displaying community electricity consumption information and sending an alarm to remind management and control center staff.
The internet of things can be used for realizing communication in a large range in the intelligent management and control system of the electric power energy, real-time monitoring data collected by the internet of things sensor which is arranged on the sensing layer of the internet of things and used for collecting electric energy are convenient to transfer data information from an industrial network to the Internet through the transmission layer, and the data are transmitted to the data monitoring center to be compared with the predicted value, so that intelligent management and control of the electric power energy are realized, and the application range is enlarged.
The electric power energy intelligent management and control system based on the internet of things is used for realizing a corresponding electric power energy intelligent management and control method based on the internet of things in the method embodiments, and has the beneficial effects of the corresponding method embodiments, and is not described herein.
According to the invention, the electric energy consumption prediction model with high stability and high prediction precision is constructed by adopting the gray neural network and the ant colony optimization algorithm, and the electric energy consumption prediction model is continuously optimized by using the cleaned database without monitoring and optimizing by maintenance personnel of an energy management and control center, so that the optimization efficiency and the prediction precision are improved, the electric energy consumption is reduced on the premise of fully meeting and perfecting the electric energy consumption requirement of the community, and the electric energy utilization rate is improved.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other. For each of the above embodiments, since it is substantially similar to the method embodiment, the description is relatively simple, and reference should be made to the description of the method embodiment for relevant points.
The foregoing embodiments have been presented in a detail description of the invention, and are presented herein with a particular application to the understanding of the principles and embodiments of the invention, the foregoing embodiments being merely intended to facilitate an understanding of the method of the invention and its core concepts; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (5)
1. The intelligent electric power energy management and control method based on the Internet of things is characterized by comprising the following steps of:
s1, calculating effective current day temperature data according to current day meteorological data of a community in an area position;
s2, acquiring community resident data and date type data, wherein the date type data comprises holidays and workdays;
S3, obtaining a predicted value of the total electric energy consumption of the current day of the community through an electric energy consumption prediction model according to the current day effective temperature data, the community resident data and the date type data, wherein a specific calculation process of the predicted value of the total electric energy consumption of the current day of the community comprises the following steps of;
s31, constructing an electric energy consumption prediction model according to a historical energy sample set stored in a database;
s32, obtaining a total consumption predicted value of the electric energy on the current day of the community by adopting the electric energy consumption prediction model according to the current day effective temperature data, the community resident data and the date type data, wherein the expression of the output value of the electric energy consumption prediction model is as follows:
in the above-mentioned method, the step of,
predictive value of total consumption of electric energy for the current day of the community, < >>
For the number of community electricity utilization units, +.>
For the number of factor indexes affecting the total consumption of community electric energy, < ->
Is->
Personal electric unit->
Is->
The individual power consumption units are at the->
Weight of individual factor index, ++>
Is of date type and->
Values of 1 and 0 respectively represent workdays and holidays;
the specific process for constructing the electric energy consumption prediction model comprises the following steps:
s311, acquiring a historical energy sample set which is processed by a principal component analysis algorithm and stored in a database;
S312, randomly dividing the historical energy sample set into a training sample set and a test sample set according to a preset proportion;
s313, determining the topological structure of the gray neural network according to the data characteristics of the training sample set so as to obtain an initial prediction model;
s314, training and optimizing the initial prediction model through a training sample set according to the mapping relation between the weight bias of the initial prediction model and the ant colony optimization algorithm to obtain an optimal electric energy consumption prediction model;
s315, testing and verifying the electric energy consumption prediction model by adopting a test sample set;
s4, acquiring a real-time monitoring data set acquired by the electric energy data acquisition equipment, wherein the real-time monitoring data comprises household energy monitoring data, corridor lighting energy monitoring data and street lamp energy monitoring data;
s5, calculating the actual value of the total electric energy consumption of the community on the same day according to the real-time monitoring data set;
s6, calculating an electric energy consumption prediction error according to the electric energy total consumption actual value and the electric energy total consumption prediction value;
s7, judging whether the prediction error is within a preset range, and if the prediction error is within the preset range, judging that the electric energy consumption of the community is normal; if the prediction error is not in the preset range, judging that the community electric energy consumption is abnormal and sending early warning information to an energy management and control center;
S8, adopting a corresponding energy management and control strategy according to the early warning information energy management and control center;
wherein, between step S6 and S7, further comprises:
s9, cleaning the data in the database according to the prediction error;
and S10, continuously optimizing the electric energy consumption prediction model according to the cleaned database.
2. The intelligent control method for electric power source according to claim 1, wherein in step S9, the method specifically comprises the steps of:
when the prediction error is not in the preset range, uploading the effective temperature data of the current day, the date type data and the real-time monitoring data set to a database, and removing dirty data in the database;
and uploading the effective temperature data of the current day, the date type data and the real-time monitoring data set to a database when the prediction error is in a preset range, and eliminating repeated historical data, wherein the collection time interval of the repeated historical data is larger than a time threshold value, in the database.
3. An apparatus for applying the intelligent management and control method for electric power energy based on the internet of things according to any one of claims 1-2, comprising:
the effective temperature calculation module (101), the effective temperature calculation module (101) is used for calculating the effective temperature data of the current day according to the weather data of the current day of the position of the area where the community is located;
A first acquisition module (102), the first acquisition module (102) being configured to acquire community household data and date type data, wherein the date type data includes holidays and workdays;
the predicted value calculation module (103), the predicted value calculation module (103) is used for obtaining a predicted value of the total electric energy consumption of the current day of the community through an electric energy consumption prediction model according to the current day effective temperature data, the community resident data and the date type data, and a specific calculation process of the predicted value of the total electric energy consumption of the current day of the community comprises the following steps of;
constructing an electric energy consumption prediction model according to a historical energy sample set stored in a database;
and obtaining a total electric energy consumption predicted value of the current day of the community by adopting the electric energy consumption prediction model according to the current day effective temperature data, the community resident data and the date type data, wherein the expression of the output value of the electric energy consumption prediction model is as follows:
in the above-mentioned method, the step of,
predictive value of total consumption of electric energy for the current day of the community, < >>
For the number of community electricity utilization units, +.>
For the number of factor indexes affecting the total consumption of community electric energy, < ->
Is->
Personal electric unit->
Is->
The individual power consumption units are at the->
Weight of individual factor index, ++ >
Is of date type and->
Values of 1 and 0 respectively represent workdays and holidays;
the specific process for constructing the electric energy consumption prediction model comprises the following steps:
acquiring a historical energy consumption sample set which is processed by a principal component analysis algorithm and stored in a database;
randomly dividing the historical energy consumption sample set into a training sample set and a test sample set according to a preset proportion;
determining the topological structure of the gray neural network according to the data characteristics of the training sample set to obtain an initial prediction model;
according to the mapping relation between the weight bias of the initial prediction model and the ant colony optimization algorithm, training and optimizing the initial prediction model through a training sample set to obtain an optimal electric energy consumption prediction model;
testing and verifying the electric energy consumption prediction model by adopting a test sample set;
the second acquisition module (104) is used for acquiring a real-time monitoring data set acquired by the electric energy data acquisition equipment, wherein the real-time monitoring data comprises household energy monitoring data, corridor lighting energy monitoring data and street lamp energy monitoring data;
the actual value calculation module (105) is used for calculating the actual value of the total electric energy consumption of the community on the same day according to the real-time monitoring data set;
A prediction error calculation module (106), wherein the prediction error calculation module (106) is used for calculating an electric energy consumption prediction error according to the electric energy total consumption actual value and the electric energy total consumption predicted value;
the judging module (107), the judging module (107) is used for judging whether the prediction error is in a preset range, if so, judging that the community electric energy consumption is normal; if the prediction error is not in the preset range, judging that the community electric energy consumption is abnormal and sending early warning information to an energy management and control center;
the intelligent management and control module (108), the intelligent management and control module (108) is used for adopting a corresponding energy management and control strategy according to the early warning information energy management and control center;
further comprises:
the database cleaning module (109) is used for cleaning the data in the database according to the prediction error;
and the prediction model optimization module (110) is used for continuously optimizing the electric energy consumption prediction model according to the cleaned database.
4. A system for applying the intelligent management and control method for electric power energy based on the internet of things according to any one of claims 1-2, comprising: the system comprises electric energy data acquisition equipment (100), computer equipment (200) and an energy management and control center (300);
The electric energy data acquisition equipment (100) is in data communication with the computer equipment (200), and the electric energy data acquisition equipment (100) is used for acquiring electric energy consumption data of communities and transmitting the electric energy consumption data to the computer equipment (200);
the computer equipment (200) establishes data transmission with the energy management and control center (300), and the computer equipment (200) comprises at least one processor, a memory and a database, and is used for receiving a real-time monitoring data set acquired by the electric energy data acquisition equipment (100) and uploading the real-time monitoring data set to the database, and then calling and running executable instructions in the memory through the processor to calculate a predicted value of the total electric energy consumption of the community on the same day according to the received real-time monitoring data set;
the energy management and control center (300) is used for displaying community electricity consumption information and sending out an alarm to remind management and control center staff.
5. The system of claim 4, wherein the electrical energy data collection device (100) comprises a plurality of internet of things sensors deployed in the field for collecting electrical energy usage, and a power supply module for providing electrical energy required by the internet of things sensors when in operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211052303.9A CN115423301B (en) | 2022-09-01 | 2022-09-01 | Intelligent electric power energy management and control method, device and system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211052303.9A CN115423301B (en) | 2022-09-01 | 2022-09-01 | Intelligent electric power energy management and control method, device and system based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115423301A CN115423301A (en) | 2022-12-02 |
| CN115423301B true CN115423301B (en) | 2023-04-25 |
Family
ID=84200914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211052303.9A Active CN115423301B (en) | 2022-09-01 | 2022-09-01 | Intelligent electric power energy management and control method, device and system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115423301B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116070795B (en) * | 2023-03-29 | 2023-07-11 | 山东历控能源有限公司 | Intelligent energy management and control method and system based on Internet of things |
| CN116455079B (en) * | 2023-05-04 | 2024-04-26 | 奥斯塔娜(常州)电子有限公司 | Big data-based electricity consumption integrated safety supervision system and method |
| CN117369813B (en) * | 2023-10-13 | 2024-06-21 | 湖北华中电力科技开发有限责任公司 | Visual display method of energy consumption monitoring index system based on data center |
| CN117318051B (en) * | 2023-11-28 | 2024-02-06 | 江苏清智云能综合能源服务有限公司 | Intelligent energy storage management and control system and method based on Internet of things technology |
| CN118446423A (en) * | 2024-05-16 | 2024-08-06 | 国网安徽省电力有限公司营销服务中心 | Intelligent power supply scheme generation method and system based on mobile terminal on-diagram operation |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521674A (en) * | 2011-12-07 | 2012-06-27 | 福建省电力有限公司 | Computer generating method for short-term load forecasting in summer in power consumer electricity-utilization information acquisition system |
| CN103065201A (en) * | 2012-12-19 | 2013-04-24 | 福建省电力有限公司 | Electric load prediction method used for electric power based on factors of temperature and festivals and holidays |
| CN105243449A (en) * | 2015-10-13 | 2016-01-13 | 北京中电普华信息技术有限公司 | Method and device for correcting prediction result of electricity selling amount |
| CN105260803A (en) * | 2015-11-06 | 2016-01-20 | 国家电网公司 | Power consumption prediction method for system |
| CN108492134A (en) * | 2018-03-07 | 2018-09-04 | 国网四川省电力公司 | The big data user power utilization behavior analysis system integrated based on multicycle regression tree |
| CN109726862A (en) * | 2018-12-24 | 2019-05-07 | 深圳供电局有限公司 | User daily electric quantity mode prediction method |
| CN109754113A (en) * | 2018-11-29 | 2019-05-14 | 南京邮电大学 | Load forecasting method based on dynamic time warping Yu length time memory |
| CN110610280A (en) * | 2018-10-31 | 2019-12-24 | 山东大学 | Short-term prediction method, model, device and system for power load |
| CN112422640A (en) * | 2020-10-30 | 2021-02-26 | 苏州中行泰科技有限公司 | Intelligent integrated management and control system for building energy system |
| CN112598155A (en) * | 2020-11-23 | 2021-04-02 | 国网浙江海宁市供电有限公司 | Load increase and decrease estimation method and system for transformer substation |
-
2022
- 2022-09-01 CN CN202211052303.9A patent/CN115423301B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521674A (en) * | 2011-12-07 | 2012-06-27 | 福建省电力有限公司 | Computer generating method for short-term load forecasting in summer in power consumer electricity-utilization information acquisition system |
| CN103065201A (en) * | 2012-12-19 | 2013-04-24 | 福建省电力有限公司 | Electric load prediction method used for electric power based on factors of temperature and festivals and holidays |
| CN105243449A (en) * | 2015-10-13 | 2016-01-13 | 北京中电普华信息技术有限公司 | Method and device for correcting prediction result of electricity selling amount |
| CN105260803A (en) * | 2015-11-06 | 2016-01-20 | 国家电网公司 | Power consumption prediction method for system |
| CN108492134A (en) * | 2018-03-07 | 2018-09-04 | 国网四川省电力公司 | The big data user power utilization behavior analysis system integrated based on multicycle regression tree |
| CN110610280A (en) * | 2018-10-31 | 2019-12-24 | 山东大学 | Short-term prediction method, model, device and system for power load |
| CN109754113A (en) * | 2018-11-29 | 2019-05-14 | 南京邮电大学 | Load forecasting method based on dynamic time warping Yu length time memory |
| CN109726862A (en) * | 2018-12-24 | 2019-05-07 | 深圳供电局有限公司 | User daily electric quantity mode prediction method |
| CN112422640A (en) * | 2020-10-30 | 2021-02-26 | 苏州中行泰科技有限公司 | Intelligent integrated management and control system for building energy system |
| CN112598155A (en) * | 2020-11-23 | 2021-04-02 | 国网浙江海宁市供电有限公司 | Load increase and decrease estimation method and system for transformer substation |
Non-Patent Citations (4)
| Title |
|---|
| Zhendong Zang等."Application of ARIMA and Markov Combination Model in Medium and Long Term Electricity Forecasting".《2019 IEEE 3rd International Electrical and Energy Conference (CIEEC)》.2020,全文. * |
| 徐江等."基于主成分分析和正则化神经网络的电力负荷预测方法".《内蒙古电力技术》.2021,第33-37页. * |
| 王捷等."蚁群灰色神经网络组合模型在电力负荷预测中的应用".《电力系统保护与控制》.2009,第48-52页. * |
| 黄震."基于机器学习算法的短期电力负荷预测研究".《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》.2021,C042-1766. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115423301A (en) | 2022-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115423301B (en) | Intelligent electric power energy management and control method, device and system based on Internet of things | |
| Catalao et al. | Hybrid wavelet-PSO-ANFIS approach for short-term wind power forecasting in Portugal | |
| CN109086913B (en) | Power system transient stability assessment method and system based on deep learning | |
| CN111275270A (en) | Method for predicting regional electrical fire risk based on edge calculation and neural network | |
| CN104399682B (en) | A kind of photovoltaic power station component cleans intelligent decision early warning system | |
| CN105930955A (en) | Deep learning-based charging network operation situation analysis method and apparatus | |
| CN105320184B (en) | Building Indoor Environment intelligent monitor system | |
| CN106765959A (en) | Heat-air conditioner energy-saving control method based on genetic algorithm and depth B P neural network algorithms | |
| KR101173823B1 (en) | System and method for predicting an energy consumption of multi-family housing | |
| CN109471370B (en) | Behavior prediction and control method and system based on exhaust fan operation data | |
| CN109492790A (en) | Wind turbines health control method based on neural network and data mining | |
| CN106405352A (en) | Equivalent salt deposit density (ESDD) prediction and early warning system for power insulator surface contaminant | |
| CN117634826B (en) | Intelligent building state monitoring management system based on cloud computing and multidimensional data | |
| CN116307641A (en) | Digital power plant-oriented resource collaborative scheduling management method and system | |
| CN115630709A (en) | Method for dynamically analyzing and optimizing AI energy consumption threshold of data center | |
| CN114897241A (en) | Intelligent building energy efficiency supervision and prediction method based on digital twins | |
| CN111612227A (en) | Load prediction method based on K-means clustering and bat optimization neural network | |
| CN117314191A (en) | Comprehensive energy system operation strategy rolling generation method and system | |
| CN117808183A (en) | Multi-objective path optimization method and system considering fault priority | |
| CN110533300B (en) | Intelligent decision-making system for transformer based on game set pair cloud | |
| CN116664095B (en) | Security inspection prediction method based on deep learning | |
| CN117390944A (en) | Substation operation condition simulation system | |
| CN117311422A (en) | Method and system for regulating and controlling internal environment of greenhouse for crop planting | |
| CN116435989A (en) | Novel method, device and system for predicting Internet of things state of power system equipment | |
| CN116305741B (en) | Updating method and device for digital twin model of power equipment |
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 |