CN114444955A - Key parameter data mining and long-term configuration prediction method and system for comprehensive energy - Google Patents
Key parameter data mining and long-term configuration prediction method and system for comprehensive energy Download PDFInfo
- Publication number
- CN114444955A CN114444955A CN202210113731.1A CN202210113731A CN114444955A CN 114444955 A CN114444955 A CN 114444955A CN 202210113731 A CN202210113731 A CN 202210113731A CN 114444955 A CN114444955 A CN 114444955A
- Authority
- CN
- China
- Prior art keywords
- energy
- hub
- cold
- electric
- gas
- 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
- 238000000034 method Methods 0.000 title claims abstract description 77
- 230000007774 longterm Effects 0.000 title claims abstract description 42
- 238000007418 data mining Methods 0.000 title claims abstract description 14
- 238000005265 energy consumption Methods 0.000 claims abstract description 27
- 238000005457 optimization Methods 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims abstract description 18
- 230000008859 change Effects 0.000 claims abstract description 13
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 125
- 239000001257 hydrogen Substances 0.000 claims description 108
- 229910052739 hydrogen Inorganic materials 0.000 claims description 108
- 239000003345 natural gas Substances 0.000 claims description 62
- 239000007789 gas Substances 0.000 claims description 47
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims description 35
- 238000013527 convolutional neural network Methods 0.000 claims description 25
- 238000010276 construction Methods 0.000 claims description 22
- 230000005611 electricity Effects 0.000 claims description 22
- 238000004519 manufacturing process Methods 0.000 claims description 21
- 238000011161 development Methods 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 15
- 238000005065 mining Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 230000008878 coupling Effects 0.000 claims description 9
- 238000010168 coupling process Methods 0.000 claims description 9
- 238000005859 coupling reaction Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000005485 electric heating Methods 0.000 claims description 2
- 230000000306 recurrent effect Effects 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 5
- 238000012937 correction Methods 0.000 abstract description 3
- 238000001816 cooling Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 229920006395 saturated elastomer Polymers 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 229940049705 immune stimulating antibody conjugate Drugs 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 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
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/067—Enterprise or organisation modelling
-
- 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)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a key parameter data mining and long-term configuration prediction method and system for comprehensive energy, which are characterized in that a key parameter information extraction method is adopted to obtain the latest parameters, and a deep clustering algorithm is used for clustering the parameters of comprehensive energy equipment to construct a comprehensive energy equipment library and an economical quantitative internal optimization configuration model of an energy supply hub; obtaining typical energy use characteristics of different seasons of a reference year; performing optimized combination on the four typical energy hubs by adopting a source-load matching model selection modeling method to obtain a configuration scheme meeting various energy requirements in different seasons; predicting the parameter change trend of typical equipment, and then performing a life cycle curve fitting method by adopting various models to perform long-term prediction on energy consumption requirements; and finally, carrying out optimization combination on the obtained prediction results by adopting a source-load matching model selection modeling method to obtain a long-term prediction configuration scheme. The invention improves the prediction accuracy, and has the advantages of automatic parameter identification and automatic correction, so that the prediction result is more in line with the actual situation.
Description
Technical Field
The invention belongs to the technical field of data mining and long-term configuration prediction, and particularly relates to a method and a system for mining key parameter data for comprehensive energy and predicting long-term configuration.
Background
In recent years, integrated energy systems have become a new focus and leading edge of research. In an integrated energy system, an energy hub is defined as an input-output port model for describing the energy, load, exchange and coupling relationships among networks in a multi-energy system. The coupling matrix describing the input energy and the output load port can briefly represent various coupling relations of conversion, storage, transmission and the like among various forms of energy such as electricity, heat, gas and the like, and plays an important role in planning and operation research of a multi-energy system. In the process of utilizing an energy hub to model a multi-energy system, the equipment parameters are more, the energy input and output relation is complex, and how to optimize the modeling is a current concern; meanwhile, how to improve the prediction accuracy rate in the long-term prediction of the comprehensive energy is also an important research point.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a method and a system for mining key parameter data and predicting long-term configuration for comprehensive energy, aiming at the defects in the prior art, wherein the method and the system are used for automatically extracting, clustering and predicting multi-dimensional input parameters of a model by combining a data mining technology, optimizing and modeling, and establishing an energy supply hub economic quantitative internal optimization configuration model and a source-load matching model, so that the long-term configuration prediction of the comprehensive energy is realized.
The invention adopts the following technical scheme:
the method for mining key parameter data and predicting long-term configuration for comprehensive energy comprises the following steps:
s1, classifying the network information by adopting a convolutional neural network, extracting key parameter information by adopting the convolutional neural network, clustering the key parameter information by adopting a deep clustering method, and constructing an integrated energy device library;
s2, coupling different comprehensive energy devices from the comprehensive energy device library constructed in the step S1, constructing an economical quantitative internal optimization configuration model of the energy supply hub, solving the economical quantitative internal optimization configuration model of the energy supply hub under the condition of maximum profit, and obtaining an optimal selection scheme comprising four energy hubs of an electricity-cold/heat-gas-hydrogen energy hub, an electricity-cold/heat-gas energy hub, an electricity-cold/heat energy hub and an electricity-gas-hydrogen energy hub;
s3, preprocessing the electricity, cold, heat, gas and hydrogen load data of the M year of the reference year by adopting a clustering feature extraction technology, and obtaining typical energy consumption features of different parks and different moments of the M year by clustering;
s4, selecting an optimal selection type scheme of the energy hub obtained in the step S2 to perform optimal energy supply according to the typical energy consumption characteristics of different parks at different times in the Mth year obtained in the step S3 by adopting a park source load matching type selection modeling method, solving a park source load matching model under the condition that the annual cost of the park is lowest, and obtaining the quantity ratio of various energy supply hubs meeting various energy consumption requirements in different seasons; summing the configurations of all the parks to obtain a comprehensive energy configuration scheme of the M year of the corresponding area;
s5, converting the time sequence into a curve shape by using the key parameter information of the equipment in the step S1 and adopting a time sequence prediction method, analyzing by using a convolutional neural network model, and predicting the change trend of the key parameter information of the typical equipment from the M +1 year to the end N year;
s6, forecasting the energy consumption requirement of the garden by adopting a life cycle curve fitting method, and forecasting the development requirement of various energy consumption of the garden from the M +1 year to the end N year;
s7, taking the typical equipment parameter variation trend from the M +1 th year to the N last year predicted in the step S5 and various energy use development demands of the garden from the M +1 th year to the N last year predicted in the step S6 as input parameters, and predicting the regional comprehensive energy long-term allocation scheme from the M +1 th year to the N last year by using the model selection modeling method of garden source load matching in the step S4.
Specifically, in step S1, extracting the key parameter information through the recurrent neural network specifically includes:
preprocessing webpage text data to obtain word vectors, inputting the word vectors into a convolutional neural network for model training, constructing a text classifier, labeling data to be extracted, inputting BIO sequences and the text word vectors into a cyclic neural network for training to obtain an information extraction model, extracting key unstructured data in a text into structured data, and obtaining equipment key parameters including capacity, power, energy conversion efficiency, service life, investment cost, maintenance cost and predicted net residue rate.
Specifically, in step S2, the annual cost of the electric-cooling/heating-gas-hydrogen energy hub includes:
the production and energy purchase cost is as follows:
the fixed construction cost of the energy hub is as follows:
annual revenue for the electricity-cold/heat-gas-hydrogen type energy hub includes:
the energy supply service income of the energy hub is as follows:
the energy hub standby service revenue is:
the income of the power supply service of the electric automobile charging pile is as follows:
the annual cost of an electric-cold/hot-gas type energy hub includes: the production and energy purchase cost is as follows:
the fixed construction cost of the energy hub is as follows:
the annual revenue of an electricity-cold/hot-gas type energy hub includes: the energy supply service income of the energy hub is as follows:
the energy hub standby service revenue is:
the income of the power supply service of the electric automobile charging pile is as follows:
the annual cost of an electric-cold/hot type energy hub includes: the production and energy purchase cost is as follows:
the fixed construction cost of the energy hub is as follows:
annual revenue for an electric-cold/hot energy hub includes: the energy supply service income of the energy hub is as follows:
the energy hub standby service revenue is:
the income of the power supply service of the electric automobile charging pile is as follows:
the annual cost of an electricity-gas-hydrogen type energy hub includes: the production and energy purchase cost is as follows:
the fixed construction cost of the energy hub is as follows:
annual revenue for an electricity-gas-hydrogen type energy hub includes:
the energy supply service income of the energy hub is as follows:
the energy hub standby service revenue is:
the income of the power supply service of the electric automobile charging pile is as follows:
wherein, EH1、EH2、EH3、EH4Respectively an electric-cold/hot-gas-hydrogen type, an electric-cold/hot-gas type, an electric-cold/hot type, and an electric-gas-hydrogen type energy hub; d is the total annual days; n is a radical ofwThe number of typical scenes in different seasons of the year; w is typical scenes of different seasons in different years, namely a summer typical scene, a transition season typical scene and a winter typical scene; t is the sum of time periods in one day; t is the specific time of day; p is a radical ofwThe occurrence probability of scenes corresponding to different seasons; c. Ce、cgPurchase price for external electricity and natural gas;
purchasing electric quantity from an external main network for each energy hub in a t period under a w scene,
the method comprises the steps that natural gas purchase amount of each energy hub in a t-time period under a w scene is shown, I is an energy device type set contained in an electricity-cold/heat-gas-hydrogen type energy hub, GSHP-ground source heat pump, EB-electric heating boiler, ISAC-ice cold storage air conditioner, PV-photovoltaic and E VSE-electric vehicle charging pile; i is the type of energy equipment contained in the electricity-cold/heat-gas-hydrogen type energy hub;
annual initial investment cost of unit capacity and annual fixed maintenance cost of unit capacity corresponding to each energy device; viStandard capacity for each type of equipment;
the configuration number of each device in the type of energy hub; lambdae、λc、λh、λg、
The energy supply prices corresponding to electric energy, cold energy, hot and cold, natural gas and hydrogen energy are provided;
the price of power supply for the charging pile;
for annual electric energy unit capacity backup service prices and annual natural gas unit capacity backup service prices.
Income is served for the power supply of the electric vehicle charging pile;
the electric energy standby service income for each energy hub is received;
income is provided for the natural gas energy standby service of each energy hub;
providing electric energy for each energy hub in t time period in a w scene;
providing cold energy for each energy hub in t time period under w scene;
providing heat energy for each energy junction externally in t time period in w scene;
providing natural gas quantity for each energy hub at t time period in a w scene;
providing hydrogen energy for each energy hub at t time under w scene;
and the power supply amount of the charging pile of the electric automobile at the t time period under the w scene of each energy junction is calculated.
Further, the supply constraints of electric energy, cold energy, heat energy, natural gas and hydrogen energy in the electric-cold/hot-gas-hydrogen type energy hub are as follows:
electric load supply constraint of the electric-cold/hot-gas-hydrogen type energy hub:
electricity-cold/heat-gas-hydrogen type energy hub cold load supply constraint:
electric-cold/hot-gas-hydrogen type energy hub heat load supply constraint:
natural gas load supply constraints of the electricity-cold/heat-gas-hydrogen type energy hub:
hydrogen load supply constraint of the electricity-cold/heat-gas-hydrogen type energy hub:
the following relationship exists for the power balance constraints of electricity and natural gas in an electricity-cold/heat-gas-hydrogen type energy hub in the energy hub:
and (3) power balance constraint:
natural gas balance constraint:
the supply constraints of electric, cold, heat and natural gas demand in an electric-cold/hot-gas type energy hub are as follows:
electric load supply constraint of the electric-cold/hot-gas type energy hub:
electric-cold/hot-gas type energy hub cold load supply constraint:
electric-cold/hot-gas type energy hub heat load supply constraint:
natural gas load supply constraints for an electric-cold/hot-gas type energy hub:
the following relationship exists for the power balance constraints of electricity and natural gas in an electricity-cold/heat-gas type energy hub in the energy hub:
and (3) power balance constraint:
natural gas balance constraint:
the supply of electric, cold and heat energy requirements in an electric-cold/hot type energy hub is constrained as follows:
electric-cold/hot type energy hub electric load supply constraint:
electric-cold/hot type energy hub cold load supply constraint:
electric-cold/hot type energy hub heat load supply constraint:
the following relationship exists for the power balance constraints of electricity and natural gas in an electricity-cold/heat type energy hub in the energy hub:
and (3) power balance constraint:
natural gas balance constraint:
the supply constraints for the electric, natural and hydrogen energy demands in an electricity-gas-hydrogen type energy hub are as follows:
electrical load supply constraint of the electro-gas-hydrogen type energy hub:
natural gas load supply constraint of an electricity-gas-hydrogen type energy hub:
hydrogen load supply constraint of the electro-gas-hydrogen type energy hub:
the following relationship exists for the power balance constraints of electricity and natural gas in an electricity-cold/heat type energy hub in the energy hub:
and (3) power balance constraint:
natural gas balance constraint:
specifically, in step S4, the annual campus cost includes:
energy purchase cost for production of all types of energy hubs in the area:
the construction cost of all types of energy hubs in the area is as follows:
wherein Park is four parks including school Park, industrial Park, residential Park and commercial Park;
purchasing electric quantity from an external main network correspondingly for each type of energy hub in the time period t;
corresponding natural gas purchase amount to each type of energy hub in the t period;
the optimal number of the four energy hubs to be built in different parks is calculated;
the annual total construction cost of the four types of energy hubs;
load requirements corresponding to electric energy in each park time interval;
the load requirements corresponding to the electric vehicle charging piles at all times of the park;
the upper limit ratio of hydrogen energy supply for each park.
Furthermore, electric energy, cold energy, heat energy, natural gas, hydrogen energy and electric automobile charge pile correspond load demand restraint in each season in garden as follows:
campus electrical load supply constraints:
campus cold load supply constraints:
campus heat load supply constraints:
and supply constraint of the garden gas load:
campus hydrogen load supply constraints:
park electric automobile fills electric pile power supply and accords with the demand constraint:
specifically, in step S5, in the time series prediction method, a convolutional neural network model is used to predict the variation trend of the device parameter.
Specifically, in step S6, the fitting of the life cycle curve by using multiple models specifically includes:
selecting three life cycle functions for fitting, inputting the historical energy-consumption demand data of each park into a Bass model, a Gompertz model and a polynomial model, and respectively outputting the prediction results of different models.
Another technical solution of the present invention is a system for mining key parameter data and predicting long-term configuration for integrated energy, including:
the data module is used for classifying the network information by adopting a convolutional neural network, extracting key parameter information by adopting the convolutional neural network, clustering the key parameter information by adopting a deep clustering method and constructing an integrated energy device library;
the solving module is used for coupling different comprehensive energy devices from the comprehensive energy device library constructed by the data module, constructing an economical quantitative internal optimization configuration model of the energy supply hub, solving the economical quantitative internal optimization configuration model of the energy supply hub under the condition of maximum profit, and obtaining an optimal selection scheme comprising an electricity-cold/heat-gas-hydrogen energy hub, an electricity-cold/heat-gas type energy hub, an electricity-cold/heat type energy hub and an electricity-gas-hydrogen type energy hub;
the preprocessing module is used for preprocessing the electricity, cold, heat, gas and hydrogen load data of the M year of the reference year by adopting a clustering feature extraction technology, and obtaining typical energy utilization features of different parks and different moments of the M year by clustering;
the configuration module adopts a model selection modeling method of garden source load matching, selects an optimal model selection scheme of an energy hub obtained by the solving module to perform optimal energy supply according to typical energy consumption characteristics of different parks at different moments in the Mth year obtained by the preprocessing module, and solves the garden source load matching model under the condition of lowest annual cost of the parks to obtain the quantity ratio of various energy supply hubs meeting various energy consumption requirements in different seasons; summing the configurations of all the parks to obtain a comprehensive energy configuration scheme of the M year of the corresponding area;
the conversion module is used for converting the time sequence into a curve shape by using the key parameter information extracted from the data module and adopting a time sequence prediction method, and predicting the variation trend of the key parameter information of the typical equipment from the M +1 year to the end N year by adopting a convolutional neural network model for analysis;
the fitting module is used for predicting the energy utilization requirement of the garden by adopting a life cycle curve fitting method and predicting the development requirement of various types of energy utilization of the garden from the M +1 year to the end N year;
and the prediction module is used for predicting the long-term configuration scheme of the comprehensive energy in the region from the M +1 year to the N year at the end by using the model selection modeling method of the source-load matching of the region of the configuration module, wherein the typical equipment key parameter information change trend from the M +1 year to the N year at the end of the term predicted by the conversion module and various energy use development requirements of the region from the M +1 year to the N year at the end of the term predicted by the fitting module are used as input parameters.
Compared with the prior art, the invention has at least the following beneficial effects:
according to the key parameter data mining and long-term configuration prediction method for the comprehensive energy, the latest parameters are obtained by adopting a key parameter information extraction method, and the parameters of the comprehensive energy equipment are clustered by using a deep clustering algorithm, so that the input parameters of the model are standardized, and the accuracy of the calculation result is improved; then optimizing the model, and constructing an energy supply hub economic quantitative internal optimization configuration model and a source load matching model selection model, so that the calculated result has practical significance; and finally, respectively predicting equipment parameters and energy consumption requirements for a long time by using a time sequence prediction method and a life cycle curve fitting method, and inputting a prediction result into the model selection model to provide a credible reference for equipment model selection and energy supply scheme selection, thereby improving the service profit.
Furthermore, a real-time key parameter information extraction model is provided, and a multi-input text classifier model is constructed by distributing different weights to the data of the title, the keyword and the content and inputting the data into convolutional neural networks with different scales, so that the accuracy of parameter information extraction is higher.
Furthermore, in the constructed energy supply hub economic quantitative internal optimization configuration model, the cost composition of the energy hub is fully considered when the annual cost in the four energy hubs is calculated, the annual cost is divided into two parts including the production energy purchasing cost and the fixed investment cost of the energy hub, and meanwhile, the cost is refined to each device in each part of the cost, so that the model can better meet the actual condition.
Furthermore, in the constraint of the energy supply hub economy quantification internal optimization configuration model, the sum of the electric energy, the cold energy, the hot energy, the gas energy and the hydrogen energy of all devices in the energy hub model is not less than the energy requirements of four energy hubs, and the obtained optimal selection scheme is more reasonable under the condition of meeting the constraint.
Furthermore, in the model selection modeling method for garden source load matching, the annual cost is also fully considered, the annual cost is divided into two parts including the energy purchasing cost and the fixed investment cost of all types of energy hubs in the region, and the calculated structure is more in line with the actual situation.
Furthermore, in the model constraint of the model selection modeling of the garden source load matching, the sum of the electric energy, the cold energy, the hot energy, the gas energy and the hydrogen energy of all energy hubs in the model is ensured to be not less than the actual energy requirement of the garden, and the obtained optimal scheme is more reasonable under the condition of meeting the constraint.
Furthermore, a time series prediction method is adopted to predict the change trend of the typical equipment parameters, the time series is converted into a curve shape, and then a model based on a convolutional neural network is used for analysis to predict the change trend of the typical equipment parameters from the M +1 year to the end N year.
Furthermore, three common life cycle curves are adopted for fitting, and the optimal type selection result under different life cycle curves can be obtained, so that the results are compared and analyzed, and a more comprehensive conclusion is obtained.
In conclusion, the method is based on data mining and prediction algorithms, multiple links are optimized, and compared with the traditional mode, the prediction accuracy is improved; meanwhile, along with the increase of information and the development of time, the model has the advantages of automatic parameter identification and automatic correction, so that the prediction result can better accord with the actual situation.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a general flow chart of a method for comprehensive energy-oriented key parameter data mining and long-term configuration prediction;
FIG. 2 is a diagram of an energy hub (taking an electric-cold/hot-gas-hydrogen energy hub as an example);
FIG. 3 is a detailed view of a multi-input text classifier model in a key parameter information extraction method;
fig. 4 is a summary view of the energy hub benefits in the case of the optimal number of areas in embodiment 1;
FIG. 5 is a graph showing the revenue variation of each region for a 20 year life cycle of each region in example 1;
FIG. 6 is a graph showing the change in cost of each region over a 20-year life cycle of each region in example 1.
Detailed Description
The invention provides a key parameter data mining and long-term configuration prediction method for comprehensive energy, which adopts a key parameter information extraction method to obtain the latest parameters, and uses a deep clustering algorithm to cluster the comprehensive energy equipment parameters to construct a comprehensive energy equipment library; secondly, constructing an economical quantitative internal optimization configuration model of the energy supply hub; then, a clustering feature extraction technology is adopted to obtain typical energy utilization features of different seasons of the reference year; then, a source-load matching model selection modeling method is adopted to carry out optimization combination on the four typical energy hubs to obtain a configuration scheme meeting various energy requirements in different seasons; then predicting the parameter change trend of typical equipment, and then performing long-term prediction on energy consumption requirements by adopting a life cycle curve fitting method of various models; and finally, carrying out optimization combination on the obtained prediction results by adopting a source-load matching model selection modeling method to obtain a long-term prediction configuration scheme. The method is based on data mining and prediction algorithms, multiple links are optimized, and compared with the traditional mode, the prediction accuracy is improved. Meanwhile, along with the increase of information and the development of time, the model has the advantages of automatic parameter identification and automatic correction, so that the prediction result can better accord with the actual situation.
Referring to fig. 1, the method for mining key parameter data and predicting long-term configuration for integrated energy according to the present invention performs optimal configuration of internal integrated energy devices for each type of standardized energy hub in a park, and determines the optimal configuration number of internal energy devices for each type of standardized energy hub; and then, on the basis of the former, the commissioning quantity of the four types of standardized energy hubs in each region is optimized, and the optimal commissioning quantity corresponding to the four types of standardized energy hubs in the school park, the industrial park, the residential park and the commercial park is determined. The method comprises the following steps of carrying out long-term prediction on various equipment parameters and energy consumption development requirements, and obtaining a prediction configuration result by adopting a garden source load matching type selection modeling method for an energy hub optimal configuration scheme and a long-term prediction parameter result, wherein the specific steps are as follows:
s1, providing a key parameter information extraction method based on real-time network information, classifying the network information by adopting a convolutional neural network, extracting the key parameter information by adopting a cyclic neural network, and clustering a large number of equipment parameters by adopting a deep clustering method to construct an integrated energy equipment library;
the method for extracting the key parameter information based on the real-time network information specifically comprises the following steps: preprocessing webpage text data to obtain word vectors, inputting the word vectors into a convolutional neural network for model training, constructing a text classifier, manually labeling data to be extracted, inputting BIO sequences and text word vectors into a cyclic neural network for training to obtain an information extraction model, and finally extracting key unstructured data in a text into structured data to obtain multiple equipment model parameters.
And during clustering, clustering the parameters of various types of equipment by adopting a VaDE algorithm to obtain representative standardized equipment parameters.
The key parameters of the equipment comprise: capacity, power, energy conversion efficiency, lifetime, investment cost, maintenance cost, and projected net residual value rate.
S2, constructing an energy supply hub economic quantitative internal optimization configuration model, coupling different comprehensive energy devices from the comprehensive energy device library obtained in step S1, referring to fig. 3, constructing a model to obtain an optimal selection scheme of four typical energy hubs, including an electricity-cold/hot-gas-hydrogen energy hub, an electricity-cold/hot-gas energy hub, an electricity-cold/hot-energy hub, and an electricity-gas-hydrogen energy hub; solving the model under the condition of maximum profit to obtain an optimal equipment configuration scheme of the energy hub;
in the energy supply hub economic quantitative internal optimization configuration model, aiming at four standardized energy hubs, namely an electric-cold/hot-gas-hydrogen type, an electric-cold/hot-gas type and an electric-cold/hot type, the economic quantitative analysis modeling of each energy hub is as follows:
(1) electric-cold/hot-gas-hydrogen type energy hub
Referring to fig. 2, the annual cost of the electric-cooling/heating-gas-hydrogen type energy hub includes the production and energy purchase cost and the fixed construction cost of the energy hub, which are specifically:
1) the production and energy purchase cost is as follows:
2) the fixed construction cost of the energy hub is as follows:
the annual income of the electricity-cold/heat-gas-hydrogen type energy hub comprises the income of energy hub energy supply service, the income of energy hub standby service and the income of electric automobile charging pile power supply service, and specifically comprises the following steps:
1) the energy supply service income of the energy hub is as follows:
2) the energy hub standby service revenue is:
3) the income of the power supply service of the electric automobile charging pile is as follows:
the supply constraints of the electric energy, cold energy, heat energy, natural gas and hydrogen energy requirements in the electricity-cold/heat-gas-hydrogen type energy hub are as follows:
1) electric load supply constraint of energy hub of electric-cold/hot-gas-hydrogen type:
2) electricity-cold/heat-gas-hydrogen type energy hub cold load supply constraint:
3) electric-cold/hot-gas-hydrogen type energy hub heat load supply constraint:
4) natural gas load supply constraints of the electricity-cold/heat-gas-hydrogen type energy hub:
5) hydrogen load supply constraint of the electricity-cold/heat-gas-hydrogen type energy hub:
the following relationship exists for the power balance constraints of electricity and natural gas in an electricity-cold/heat-gas-hydrogen type energy hub in the energy hub:
1) and (3) power balance constraint:
2) natural gas balance constraint:
(2) electric-cold/hot-gas type energy hub
The annual cost of the electricity-cold/heat-gas type energy hub comprises the production and energy purchase cost and the fixed construction cost of the energy hub, and specifically comprises the following steps:
1) the production and energy purchase cost is as follows:
2) the fixed construction cost of the energy hub is as follows:
the annual income of the electricity-cold/heat-gas type energy hub comprises energy hub energy supply service income, energy hub standby service income and electric automobile charging pile power supply service income, and specifically comprises the following steps:
1) the energy supply service income of the energy hub is as follows:
2) the energy hub standby service revenue is:
3) the income of the power supply service of the electric automobile charging pile is as follows:
the supply constraints of electric, cold, heat and natural gas demand in an electric-cold/hot-gas type energy hub are as follows:
1) electric load supply constraint of the electric-cold/hot-gas type energy hub:
2) electric-cold/hot-gas type energy hub cold load supply constraint:
3) electric-cold/hot-gas type energy hub heat load supply constraint:
4) natural gas load supply constraints for an electric-cold/hot-gas type energy hub:
the following relationship exists for the power balance constraints of electricity and natural gas in an electricity-cold/heat-gas type energy hub in the energy hub:
1) and (3) power balance constraint:
2) natural gas balance constraint:
(3) electric-cold/hot type energy hub
The annual cost of the electricity-cold/heat energy hub comprises the production and energy purchasing cost and the fixed construction cost of the energy hub, and specifically comprises the following steps:
1) the production and energy purchase cost is as follows:
2) the fixed construction cost of the energy hub is as follows:
the annual income of the electricity-cold/hot type energy hub comprises energy hub energy supply service income, energy hub standby service income and electric automobile charging pile power supply service income, and specifically comprises the following steps:
1) the energy supply service income of the energy hub is as follows:
2) the energy hub standby service revenue is:
3) the income of the power supply service of the electric automobile charging pile is as follows:
the supply of electric, cold and heat energy requirements in an electric-cold/hot type energy hub is constrained as follows:
1) electric-cold/hot type energy hub electric load supply constraint:
2) electric-cold/hot type energy hub cold load supply constraint:
3) electric-cold/hot type energy hub heat load supply constraint:
the following relationship exists for the power balance constraints of electricity and natural gas in an electricity-cold/heat type energy hub in the energy hub:
1) and (3) power balance constraint:
2) natural gas balance constraint:
(4) electric-gas-hydrogen type energy hub
The annual cost of the electricity-gas-hydrogen type energy hub comprises the production and energy purchase cost and the fixed construction cost of the energy hub, and specifically comprises the following steps:
1) the production and energy purchase cost is as follows:
2) the fixed construction cost of the energy hub is as follows:
the annual income of the electricity-gas-hydrogen type energy hub comprises energy hub energy supply service income, energy hub standby service income and electric automobile charging pile power supply service income, and specifically comprises the following steps:
1) the energy supply service income of the energy hub is as follows:
2) the energy hub standby service revenue is:
3) the income of the power supply service of the electric automobile charging pile is as follows:
the supply constraints for the electric, natural and hydrogen energy demands in an electricity-gas-hydrogen type energy hub are as follows:
1) electrical load supply constraint of the electro-gas-hydrogen type energy hub:
2) natural gas load supply constraint of an electricity-gas-hydrogen type energy hub:
3) hydrogen load supply constraint of the electro-gas-hydrogen type energy hub:
the following relationship exists for the power balance constraints of electricity and natural gas in an electricity-cold/heat type energy hub in the energy hub:
1) and (3) power balance constraint:
2) natural gas balance constraint:
wherein, EH1、EH2、EH3、EH4Respectively an electric-cold/hot-gas-hydrogen type, an electric-cold/hot-gas type, an electric-cold/hot type, and an electric-gas-hydrogen type energy hub; d is the total annual days; n is a radical ofwThe number of typical scenes in different seasons of the year; w is typical scenes of different seasons in different years, namely a summer typical scene, a transition season typical scene (spring and autumn) and a winter typical scene; t is the sum of time periods in one day; t is the specific time of day; p is a radical ofwThe occurrence probability of scenes corresponding to different seasons; c. Ce、cgPurchase price for external electricity and natural gas;
and purchasing electric quantity from the external main network for each energy hub in the t time period under the w scene.
And the purchase amount of the natural gas of each energy hub in the t period under the w scene. I is a set of energy device types contained in an electricity-cooling/heating-gas-hydrogen type energy hub, specifically: g SHP-ground source heat pump, CCHP-CCHP, EB-electric boiler, ISA C-ice cold storage air conditioner, P2G-P2G, PV-photovoltaic and E VSE-electric vehicle charging pile; i is the type of energy equipment contained in the electricity-cold/heat-gas-hydrogen type energy hub, and the values are as follows: GSHP, CCHP, EB, ISAC, P2G, PV, EVSE;
annual initial investment cost of unit capacity and annual fixed maintenance cost of unit capacity corresponding to each energy device; viStandard capacity for each type of equipment;
the configuration number of each device in the type of energy hub; lambda [ alpha ]e、λc、λh、λg、
The energy supply prices corresponding to electric energy, cold energy, hot and cold, natural gas and hydrogen energy are provided;
supplying power price for the charging pile;
the unit capacity reserve service price of annual electric energy and the unit capacity reserve service price of annual natural gas.
The income is served for supplying power to the electric vehicle charging pile;
for each energyElectric energy standby service income of the hub;
income is provided for the natural gas energy standby service of each energy hub;
providing electric energy for each energy hub in t time period in a w scene;
providing cold energy for each energy hub in t time period under w scene;
providing heat energy for each energy junction externally in t time period in w scene;
providing natural gas quantity for each energy hub at t time period in a w scene;
providing hydrogen energy for each energy hub at t time under w scene;
and the power supply amount of the charging pile of the electric automobile at the t time period under the w scene of each energy junction is calculated.
S3, preprocessing the electricity, cold, heat, gas and hydrogen load data of the Mth year of the reference year by adopting a clustering feature extraction technology, and obtaining typical energy utilization features of four seasons and different moments in different parks through clustering;
and clustering the load data through a deep clustering algorithm to finally obtain the load characteristics of four parks of schools, businesses, residents and industries at different moments in four seasons of spring, summer, autumn and winter.
S4, providing a model selection modeling method for garden source load matching, selecting a certain typical energy hub scheme in the step S2 to perform optimized energy supply according to the typical energy consumption characteristics of different parks at different moments in the M year obtained in the step S3, and solving a garden source load matching model under the condition that annual cost of the parks is lowest to obtain the quantity ratio and the minimum equipment cost of various energy supply hubs meeting various energy consumption requirements in different seasons; further summing the configuration of all parks in the area to obtain a comprehensive energy configuration scheme corresponding to the M year of the area;
the annual cost of the garden comprises the production and energy purchase cost of all types of energy hubs in the area and the construction cost of all types of energy hubs in the area, and specifically comprises the following steps:
1) energy purchase cost for production of all types of energy hubs in the area:
2) the construction cost of all types of energy hubs in the area is as follows:
electric energy, cold energy, heat energy, natural gas, hydrogen energy and electric automobile fill electric pile corresponding load demand restraint in each season in garden as follows:
1) the campus electrical load supply constraints are as follows:
2) campus cold load supply constraints are as follows:
3) the campus heat load supply constraints are as follows:
4) the campus gas load supply constraints are as follows:
5) the campus hydrogen load supply constraints are as follows:
6) park electric automobile fills electric pile power supply and accords with the demand constraint as follows:
wherein Park is four parks including school Park, industrial Park, residential Park and commercial Park;
purchasing electric quantity from an external main network correspondingly for each type of energy hub in the time period t;
corresponding natural gas purchase amount to each type of energy hub in the t period;
the optimal number of the four energy hubs to be built in different parks is calculated;
is a four-class energy hubThe annual total investment cost;
load requirements corresponding to electric energy in each park time interval;
the load requirements corresponding to the electric automobile charging piles at all the time intervals of the park;
the upper limit ratio of hydrogen energy supply for each park.
S5, predicting the parameter variation trend of the equipment by adopting a time series prediction method, acquiring key parameter information of various equipment in the step S1, converting the time series into a curve shape by adopting the time series prediction method, and then applying a model based on a convolutional neural network to analyze to predict the parameter variation trend of the typical equipment from the M +1 year to the end N year;
in the time series prediction method, a convolutional neural network model is adopted to predict the variation trend of the equipment parameters.
S6, adopting multiple models to carry out a life cycle curve fitting method, carrying out long-term prediction on the energy consumption requirements of each garden, and predicting various energy consumption development requirements of the garden from the M +1 year to the end N year;
adopting multiple models to carry out a life cycle curve fitting method, selecting three life cycle functions for fitting, inputting the historical energy consumption demand data of each park into the three models, then respectively outputting the prediction results of the different models, and selecting the function commonly used for life cycle curve fitting by the models, wherein the method comprises the following steps: bass model, Gompertz model, polynomial model.
S7, taking the typical equipment parameter variation trend from the M +1 th year to the N last year predicted in the step S5 and various energy use development demands of the garden from the M +1 th year to the N last year predicted in the step S6 as input parameters, and predicting the regional comprehensive energy long-term allocation scheme from the M +1 th year to the N last year by using the model selection modeling method of garden source load matching in the step S4.
In another embodiment of the present invention, a system for mining and predicting long-term configuration of key parameter data for integrated energy is provided, which can be used to implement the method for mining and predicting long-term configuration of key parameter data for integrated energy described above.
The data module classifies network information by adopting a convolutional neural network, extracts key parameter information by adopting the convolutional neural network, clusters the key parameter information by adopting a deep clustering method and constructs an integrated energy equipment library;
the solving module is used for coupling different comprehensive energy devices from the comprehensive energy device library constructed by the data module, constructing an economical quantitative internal optimization configuration model of the energy supply hub, solving the economical quantitative internal optimization configuration model of the energy supply hub under the condition of maximum profit, and obtaining an optimal selection scheme comprising an electricity-cold/heat-gas-hydrogen energy hub, an electricity-cold/heat-gas type energy hub, an electricity-cold/heat type energy hub and an electricity-gas-hydrogen type energy hub;
the preprocessing module is used for preprocessing the electricity, cold, heat, gas and hydrogen load data of the M year of the reference year by adopting a clustering feature extraction technology, and obtaining typical energy utilization features of different parks and different moments of the M year by clustering;
the configuration module adopts a model selection modeling method of garden source load matching, selects an optimal model selection scheme of an energy hub obtained by the solving module to perform optimal energy supply according to typical energy consumption characteristics of different parks at different moments in the Mth year obtained by the preprocessing module, and solves the garden source load matching model under the condition of lowest annual cost of the parks to obtain the quantity ratio of various energy supply hubs meeting various energy consumption requirements in different seasons; summing the configurations of all the parks to obtain a comprehensive energy configuration scheme of the M year of the corresponding area;
the conversion module is used for converting the time sequence into a curve shape by using the key parameter information extracted from the data module and adopting a time sequence prediction method, and predicting the change trend of the key parameter information of the typical equipment from the M +1 year to the end N year by adopting a convolutional neural network model for analysis;
the fitting module is used for predicting the energy utilization requirement of the garden by adopting a life cycle curve fitting method and predicting the development requirement of various types of energy utilization of the garden from the M +1 year to the end N year;
and the prediction module is used for predicting the long-term configuration scheme of the comprehensive energy in the region from the M +1 year to the N year at the end by using the model selection modeling method of the source-load matching of the region of the configuration module, wherein the typical equipment key parameter information change trend from the M +1 year to the N year at the end of the term predicted by the conversion module and various energy use development requirements of the region from the M +1 year to the N year at the end of the term predicted by the fitting module are used as input parameters.
Example 1
In order to verify the long-term configuration prediction effect of the method, Shaanxi province is selected as the source range of experimental data, 2020 years are taken as a reference year, the deduction period is 20 years, the deduction model is a Bass model, equipment parameters are automatically extracted and long-term predicted, meanwhile, the energy load requirements of an energy hub and a park are subjected to feature extraction and long-term prediction, and finally, a 20-year configuration selection scheme is obtained by solving an energy supply hub economic quantitative internal optimization configuration model and a source-load matching model, so that the long-term configuration prediction of comprehensive energy is realized. The specific results are as follows:
according to the model, the minimum cost of the energy hub is set as an objective function, and the optimal investment number of each region, income of each region and cost of each region in the whole life cycle of 20 years are obtained by combining constraints such as energy supply and demand balance. Wherein the energy hub benefit prediction results under the optimal number of investments in each area in 2040 years are shown in fig. 4.
The results of the revenue and cost per area for the 20 year life cycle are shown in fig. 5 and 6, respectively. As seen in FIG. 5, the income change of each region in Shaanxi province shows S-type change mode: the initial stage of deduction is slowly climbed, the middle stage of deduction is rapidly increased, and the market profit at the final stage of deduction is saturated; the inflection point of the curve occurs around 2030, when the market profit grows the fastest and the profit size is half that at steady state. Specifically, the profit of northern Shaanxi in steady state is about 448054 ten thousand yuan, the profit of Guanzhong region is about 594498 ten thousand yuan, the profit of southern Shaanxi region is about 214032 ten thousand yuan, and the profit scale of each region in steady state is about 2 times of that in initial condition. According to the marginal effect of the economic principle, the market economic scale can continuously tend to be saturated along with the investment inrush of the comprehensive energy market, which shows that the deduction result has certain rationality.
In summary, according to the method and system for mining key parameter data and predicting long-term configuration for comprehensive energy, the modeling process is optimized by automatically extracting model input parameters, the prediction accuracy is improved, and credible reference is provided for equipment type selection and energy supply scheme selection under the comprehensive energy service, so that the service profit is improved.
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (9)
1. The method for mining key parameter data and predicting long-term configuration for comprehensive energy is characterized by comprising the following steps of:
s1, classifying the network information by adopting a convolutional neural network, extracting key parameter information by adopting the convolutional neural network, clustering the key parameter information by adopting a deep clustering method, and constructing an integrated energy device library;
s2, coupling different comprehensive energy devices from the comprehensive energy device library constructed in the step S1, constructing an economical quantitative internal optimization configuration model of the energy supply hub, solving the economical quantitative internal optimization configuration model of the energy supply hub under the condition of maximum profit, and obtaining an optimal selection scheme comprising four energy hubs of an electricity-cold/heat-gas-hydrogen energy hub, an electricity-cold/heat-gas energy hub, an electricity-cold/heat energy hub and an electricity-gas-hydrogen energy hub;
s3, preprocessing the electricity, cold, heat, gas and hydrogen load data of the M year of the reference year by adopting a clustering feature extraction technology, and obtaining typical energy consumption features of different parks and different moments of the M year by clustering;
s4, selecting an optimal selection type scheme of the energy hub obtained in the step S2 to perform optimal energy supply according to the typical energy consumption characteristics of different parks at different times in the Mth year obtained in the step S3 by adopting a park source load matching type selection modeling method, solving a park source load matching model under the condition that the annual cost of the park is lowest, and obtaining the quantity ratio of various energy supply hubs meeting various energy consumption requirements in different seasons; summing the configurations of all the parks to obtain a comprehensive energy configuration scheme of the M year of the corresponding area;
s5, converting the time sequence into a curve shape by using the key parameter information of the equipment in the step S1 and adopting a time sequence prediction method, analyzing by using a convolutional neural network model, and predicting the change trend of the key parameter information of the typical equipment from the M +1 year to the end N year;
s6, forecasting the energy consumption requirement of the garden by adopting a life cycle curve fitting method, and forecasting the development requirement of various energy consumption of the garden from the M +1 year to the end N year;
s7, taking the typical equipment parameter variation trend from the M +1 th year to the N last year predicted in the step S5 and various energy use development demands of the garden from the M +1 th year to the N last year predicted in the step S6 as input parameters, and predicting the regional comprehensive energy long-term allocation scheme from the M +1 th year to the N last year by using the model selection modeling method of garden source load matching in the step S4.
2. The method for mining key parameter data for integrated energy and predicting long-term configuration according to claim 1, wherein in step S1, extracting key parameter information through a recurrent neural network specifically comprises:
preprocessing webpage text data to obtain word vectors, inputting the word vectors into a convolutional neural network for model training, constructing a text classifier, labeling data to be extracted, inputting BIO sequences and the text word vectors into a cyclic neural network for training to obtain an information extraction model, extracting key unstructured data in a text into structured data, and obtaining equipment key parameters including capacity, power, energy conversion efficiency, service life, investment cost, maintenance cost and predicted net residue rate.
3. The method for data mining and long-term deployment prediction of key parameters for integrated energy resources of claim 1, wherein the annual cost of the electric-cold/hot-gas-hydrogen type energy hub in step S2 comprises:
the production and energy purchase cost is as follows:
the fixed construction cost of the energy hub is as follows:
annual revenue for an electricity-cold/heat-gas-hydrogen type energy hub includes:
the energy supply service income of the energy hub is as follows:
the energy hub standby service revenue is:
the income of the power supply service of the electric automobile charging pile is as follows:
the annual cost of an electric-cold/hot-gas type energy hub includes:
the production and energy purchase cost is as follows:
the fixed construction cost of the energy hub is as follows:
the annual revenue of an electricity-cold/hot-gas type energy hub includes:
the energy supply service income of the energy hub is as follows:
the energy hub standby service revenue is:
the income of the power supply service of the electric automobile charging pile is as follows:
the annual cost of an electric-cold/hot type energy hub includes:
the production and energy purchase cost is as follows:
the fixed construction cost of the energy hub is as follows:
annual revenue for an electric-cold/hot energy hub includes:
the energy supply service income of the energy hub is as follows:
the energy hub standby service revenue is:
the income of the power supply service of the electric automobile charging pile is as follows:
the annual cost of an electricity-gas-hydrogen type energy hub includes:
the production and energy purchase cost is as follows:
the fixed construction cost of the energy hub is as follows:
annual revenue for an electricity-gas-hydrogen type energy hub includes:
the energy supply service income of the energy hub is as follows:
the energy hub standby service revenue is:
the income of the power supply service of the electric automobile charging pile is as follows:
wherein, EH1、EH2、EH3、EH4Respectively an electric-cold/hot-gas-hydrogen type, an electric-cold/hot-gas type, an electric-cold/hot type, and an electric-gas-hydrogen type energy hub; d is the annual dayThe sum of the numbers; n is a radical ofwThe number of typical scenes in different seasons of the year; w is typical scenes of different seasons in different years, namely a summer typical scene, a transition season typical scene and a winter typical scene; t is the sum of time periods in one day; t is the specific time of day; p is a radical ofwThe occurrence probability of scenes corresponding to different seasons; c. Ce、cgPurchase price for external electricity and natural gas;
purchasing electric quantity from an external main network for each energy hub in a t period under a w scene,
the method comprises the steps that natural gas purchase amount of each energy hub at t time period under a w scene is shown, I is an energy device type set contained in an electricity-cold/heat-gas-hydrogen type energy hub, GSHP-ground source heat pump, EB-electric heating boiler, ISAC-ice cold storage air conditioner, PV-photovoltaic and EVSE-electric vehicle charging pile; i is the type of energy equipment contained in the electricity-cold/heat-gas-hydrogen type energy hub;
annual initial investment cost of unit capacity and annual fixed maintenance cost of unit capacity corresponding to each energy device; viStandard capacity for each type of equipment;
the configuration number of each device in the type of energy hub; lambda [ alpha ]e、λc、λh、λg、
The energy supply prices corresponding to electric energy, cold energy, hot and cold, natural gas and hydrogen energy are provided;
supplying power price for the charging pile;
a unit capacity backup service price for annual electric energy and a unit capacity backup service price for annual natural gas;
income is served for the power supply of the electric vehicle charging pile;
the electric energy standby service income for each energy hub is received;
income is provided for the natural gas energy standby service of each energy hub;
providing electric energy for each energy hub in t time period in a w scene;
providing cold energy for each energy hub in t time period under w scene;
providing heat energy for each energy junction externally in t time period in w scene;
providing natural gas quantity for each energy hub at t time period in a w scene;
providing hydrogen energy for each energy hub at t time under w scene;
and the power supply amount of the charging pile of the electric automobile at the t time period under the w scene of each energy junction is calculated.
4. The method of claim 3, wherein the supply constraints of the electric energy, cold energy, heat energy, natural gas and hydrogen energy demand in the electric-cold/hot-gas-hydrogen energy hub are as follows:
electric load supply constraint of energy hub of electric-cold/hot-gas-hydrogen type:
electricity-cold/heat-gas-hydrogen type energy hub cold load supply constraint:
electric-cold/hot-gas-hydrogen type energy hub heat load supply constraint:
natural gas load supply constraints of the electricity-cold/heat-gas-hydrogen type energy hub:
hydrogen load supply constraint of the electricity-cold/heat-gas-hydrogen type energy hub:
the following relationship exists for the power balance constraints of electricity and natural gas in an electricity-cold/heat-gas-hydrogen type energy hub in the energy hub:
and (3) power balance constraint:
natural gas balance constraint:
the supply constraints of electric, cold, heat and natural gas demand in an electric-cold/hot-gas type energy hub are as follows:
electric load supply constraint of the electric-cold/hot-gas type energy hub:
electric-cold/hot-gas type energy hub cold load supply constraint:
electric-cold/hot-gas type energy hub heat load supply constraint:
natural gas load supply constraints for an electric-cold/hot-gas type energy hub:
the following relationship exists for the power balance constraints of electricity and natural gas in an electricity-cold/heat-gas type energy hub in the energy hub:
and (3) power balance constraint:
natural gas balance constraint:
the supply of electric, cold and heat energy requirements in an electric-cold/hot type energy hub is constrained as follows:
electric-cold/hot type energy hub electric load supply constraint:
electric-cold/hot type energy hub cold load supply constraint:
electric-cold/hot type energy hub heat load supply constraint:
the following relationship exists for the power balance constraints of electricity and natural gas in an electricity-cold/heat type energy hub in the energy hub:
and (3) power balance constraint:
natural gas balance constraint:
the supply constraints for the electric, natural and hydrogen energy demands in an electricity-gas-hydrogen type energy hub are as follows:
electrical load supply constraint of the electro-gas-hydrogen type energy hub:
natural gas load supply constraint of an electricity-gas-hydrogen type energy hub:
hydrogen load supply constraint of the electro-gas-hydrogen type energy hub:
the following relationships exist for the power balance constraints of electricity and natural gas in an electricity-cold/heat type energy hub in the energy hub:
and (3) power balance constraint:
natural gas balance constraint:
5. the method for data mining and long-term configuration prediction of key parameters for integrated energy according to claim 1, wherein in step S4, the annual campus cost comprises:
energy purchase cost for production of all types of energy hubs in the area:
the construction cost of all types of energy hubs in the area is as follows:
wherein Park is four parks including school Park, industrial Park, residential Park and commercial Park;
purchasing electric quantity from an external main network correspondingly for each type of energy hub in the time period t;
corresponding natural gas purchase amount to each type of energy hub in the t period;
the optimal number of the four energy hubs in different parks is built;
the annual total construction cost of the four types of energy hubs;
load requirements corresponding to electric energy in each park time interval;
the load requirements corresponding to the electric automobile charging piles at all the time intervals of the park;
the upper limit ratio of hydrogen energy supply for each park.
6. The method for data mining and long-term configuration prediction of key parameters for comprehensive energy resources according to claim 5, wherein the corresponding load demands of electric energy, cold energy, heat energy, natural gas, hydrogen energy and electric vehicle charging piles in each season of the park are constrained as follows:
park electrical load supply constraints:
campus cold load supply constraints:
campus heat load supply constraints:
and supply constraint of the garden gas load:
campus hydrogen load supply constraints:
park electric automobile fills electric pile power supply and accords with the demand constraint:
7. the method for data mining and long-term configuration prediction of key parameters for integrated energy according to claim 1, wherein in step S5, the time series prediction method uses a convolutional neural network model to predict the variation trend of the equipment parameters.
8. The method for data mining and long-term configuration prediction of key parameters for integrated energy according to claim 1, wherein in step S6, the life cycle curve fitting using multiple models is specifically:
selecting three life cycle functions for fitting, inputting the historical energy-consumption demand data of each park into a Bass model, a Gompertz model and a polynomial model, and respectively outputting the prediction results of different models.
9. A system for mining and predicting long-term configuration of key parameter data for comprehensive energy is characterized by comprising the following components:
the data module is used for classifying the network information by adopting a convolutional neural network, extracting key parameter information by adopting the convolutional neural network, clustering the key parameter information by adopting a deep clustering method and constructing an integrated energy device library;
the solving module is used for coupling different comprehensive energy devices from the comprehensive energy device library constructed by the data module, constructing an economical quantitative internal optimization configuration model of the energy supply hub, solving the economical quantitative internal optimization configuration model of the energy supply hub under the condition of maximum profit, and obtaining an optimal selection scheme comprising an electricity-cold/heat-gas-hydrogen energy hub, an electricity-cold/heat-gas type energy hub, an electricity-cold/heat type energy hub and an electricity-gas-hydrogen type energy hub;
the preprocessing module is used for preprocessing the electricity, cold, heat, gas and hydrogen load data of the M year of the reference year by adopting a clustering feature extraction technology, and obtaining typical energy utilization features of different parks and different moments of the M year by clustering;
the configuration module adopts a model selection modeling method of garden source load matching, selects an optimal model selection scheme of an energy hub obtained by the solving module to perform optimal energy supply according to typical energy consumption characteristics of different parks at different moments in the Mth year obtained by the preprocessing module, and solves the garden source load matching model under the condition of lowest annual cost of the parks to obtain the quantity ratio of various energy supply hubs meeting various energy consumption requirements in different seasons; summing the configurations of all the parks to obtain a comprehensive energy configuration scheme of the M year of the corresponding area;
the conversion module is used for converting the time sequence into a curve shape by using the key parameter information extracted from the data module and adopting a time sequence prediction method, and predicting the variation trend of the key parameter information of the typical equipment from the M +1 year to the end N year by adopting a convolutional neural network model for analysis;
the fitting module is used for predicting the energy utilization requirement of the garden by adopting a life cycle curve fitting method and predicting the development requirement of various types of energy utilization of the garden from the M +1 year to the end N year;
and the prediction module is used for predicting the long-term configuration scheme of the comprehensive energy in the region from the M +1 year to the N year at the end by using the model selection modeling method of the source-load matching of the region of the configuration module, wherein the typical equipment key parameter information change trend from the M +1 year to the N year at the end of the term predicted by the conversion module and various energy use development requirements of the region from the M +1 year to the N year at the end of the term predicted by the fitting module are used as input parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210113731.1A CN114444955A (en) | 2022-01-30 | 2022-01-30 | Key parameter data mining and long-term configuration prediction method and system for comprehensive energy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210113731.1A CN114444955A (en) | 2022-01-30 | 2022-01-30 | Key parameter data mining and long-term configuration prediction method and system for comprehensive energy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114444955A true CN114444955A (en) | 2022-05-06 |
Family
ID=81371208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210113731.1A Pending CN114444955A (en) | 2022-01-30 | 2022-01-30 | Key parameter data mining and long-term configuration prediction method and system for comprehensive energy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114444955A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116739627A (en) * | 2022-10-25 | 2023-09-12 | 荣耀终端有限公司 | Product sales prediction method and electronic equipment |
-
2022
- 2022-01-30 CN CN202210113731.1A patent/CN114444955A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116739627A (en) * | 2022-10-25 | 2023-09-12 | 荣耀终端有限公司 | Product sales prediction method and electronic equipment |
| CN116739627B (en) * | 2022-10-25 | 2024-06-07 | 荣耀终端有限公司 | Product sales prediction method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109103926A (en) | Photovoltaic power generation based on more Radiation Characteristics year meteorology scenes receives capacity calculation method | |
| CN111681130B (en) | Comprehensive energy system optimal scheduling method considering conditional risk value | |
| CN110729764B (en) | Optimal scheduling method for photovoltaic power generation system | |
| CN113326467B (en) | Multi-target optimization method, storage medium and optimization system for multi-station fusion comprehensive energy system based on multiple uncertainties | |
| CN113991742B (en) | Distributed photovoltaic double-layer collaborative optimization investment decision-making method for power distribution network | |
| CN114792156A (en) | Photovoltaic output power prediction method and system based on curve characteristic index clustering | |
| CN115062930A (en) | Power distribution network source and network load and storage coordination planning method | |
| CN110994606A (en) | Multi-energy power supply capacity configuration method based on complex adaptive system theory | |
| CN111639819A (en) | Multi-stage optimization control method for comprehensive energy park | |
| CN108075471B (en) | Multi-objective constraint optimization power grid scheduling strategy based on stochastic power output prediction | |
| CN116029490A (en) | Optical network storage collaborative planning method considering capacity limitation of distributed resource area | |
| CN115065078A (en) | Energy storage capacity configuration method and system in micro-grid environment | |
| CN115115193A (en) | Low-carbon analysis and optimization planning method for industrial park | |
| CN115021331A (en) | Clean energy-based ground water wind-solar integrated compensation method based on contribution coefficient method | |
| CN114301089A (en) | Energy storage capacity configuration optimization method for wind-solar combined power generation system | |
| CN114444955A (en) | Key parameter data mining and long-term configuration prediction method and system for comprehensive energy | |
| CN112561252B (en) | Reactive power combination evaluation method for power grid in new energy-containing region | |
| CN112653195B (en) | Method for configuring robust optimization capacity of grid-connected micro-grid | |
| CN116780649B (en) | Multi-energy complementary utilization distributed robust optimization operation method | |
| CN113128786A (en) | Wind, light and water complementary capacity and site selection optimization method based on space grid search | |
| CN112598175A (en) | Watershed type virtual power plant scheduling method | |
| CN114662922B (en) | Resident demand response potential evaluation method and system considering photovoltaic uncertainty | |
| CN116562432A (en) | Novel power system planning-oriented source network load storage collaborative planning method and system | |
| CN111126675A (en) | Multi-energy complementary microgrid system optimization method | |
| CN116128154A (en) | Energy optimal configuration method and device for agricultural park comprehensive energy system |
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 |