CN112613899A - Energy supply amount ratio presetting method and device, electronic equipment and storage medium - Google Patents
Energy supply amount ratio presetting method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112613899A CN112613899A CN202011438939.8A CN202011438939A CN112613899A CN 112613899 A CN112613899 A CN 112613899A CN 202011438939 A CN202011438939 A CN 202011438939A CN 112613899 A CN112613899 A CN 112613899A
- Authority
- CN
- China
- Prior art keywords
- price
- data
- energy sources
- energy
- various energy
- 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 37
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000005265 energy consumption Methods 0.000 claims abstract description 19
- 238000006243 chemical reaction Methods 0.000 claims abstract description 13
- 238000003062 neural network model Methods 0.000 claims description 48
- 238000012549 training Methods 0.000 claims description 32
- 238000012360 testing method Methods 0.000 claims description 28
- 230000015654 memory Effects 0.000 claims description 19
- 238000007781 pre-processing Methods 0.000 claims description 15
- 239000002994 raw material Substances 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 230000001502 supplementing effect Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 abstract description 6
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical group C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 18
- 210000002569 neuron Anatomy 0.000 description 16
- 239000001257 hydrogen Substances 0.000 description 13
- 229910052739 hydrogen Inorganic materials 0.000 description 13
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 12
- 239000003345 natural gas Substances 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 7
- 238000004140 cleaning Methods 0.000 description 6
- 230000007787 long-term memory Effects 0.000 description 5
- 230000006403 short-term memory Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 210000004027 cell Anatomy 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000026058 directional locomotion Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 150000002431 hydrogen Chemical class 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method and a device for presetting an energy supply amount ratio, electronic equipment and a storage medium. The method comprises the following steps: constructing price prediction models of various energy sources; respectively predicting the prices of various energy sources after a period of time in the future by using price prediction models of various energy sources; constructing a consumption prediction model of various energy sources; predicting the consumption of various energy sources after a period of time in the future by using a consumption prediction model of various energy sources; and determining the energy supply ratio according to the predicted price and the predicted consumption of each energy source and the energy price ratio conversion relation among the energy sources so as to minimize the total energy consumption cost. The method predicts the price and the consumption of each energy source through the constructed prediction model, and distributes the energy supply quantity according to the predicted price and the predicted consumption of each energy source and the conversion relation of the energy price ratio among each energy source, so that the total energy consumption cost is the lowest, the optimal distribution of various energy sources is realized, and the energy cost for users is minimized.
Description
Technical Field
The application relates to the technical field of energy management and control, in particular to a method and a device for presetting energy supply ratio, electronic equipment and a storage medium.
Background
The energy center adopts an automation, informatization technology and a centralized management mode, implements dynamic monitoring and digital management on energy scheduling and distribution, improves and optimizes energy ratio balance, and realizes a systematic energy-saving and consumption-reducing management and control integrated system. The energy center is used for dispatching and distributing different energy sources for regional users, and comprises an electric energy center, a heat energy center and a hydrogen energy center, wherein the electric energy center adopts the electric energy obtained by regional distributed solar power generation and the electric energy provided by a power grid as raw materials, and also comprises the electric energy obtained by medium and long term electric power transaction and regional electric power spot transaction; the raw material of the heat energy center is natural gas and is also obtained through medium and long term and spot transaction; the feedstock for hydrogen energy centers is hydrogen, primarily from concentrated solar power plants or other hydrogen-producing plants, and there are also long-term and off-the-shelf transactions involving hydrogen energy. The energy center is a revolution of the traditional energy station, is based on the traditional energy architecture, takes data and AI technology as the center, takes guidance on energy utilization as a link, and realizes the optimal operation of energy supply economy.
Under the background of innovation of the energy industry, the setting of scheduling and allocation of various energy sources through an energy center is a new commercial operation mode of the energy industry, and is also a unique path for realizing an energy supply win-win balance point, the purchase price and the sale price of the energy sources are used as controllable resources, the energy center is used for purchasing the energy source raw materials in stock ratio, and the demand side is used for predicting and scheduling transaction, so that the energy supply enters an optimal operation state, which is one of the hot spots in the current energy management and control field. How to realize the optimal scheme of presetting the energy supply ratio is one of key technical problems to be solved at present.
Disclosure of Invention
The application aims to provide an energy supply amount ratio presetting method and device, electronic equipment and a storage medium. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
According to an aspect of an embodiment of the present application, there is provided an energy supply amount ratio presetting method, including:
constructing price prediction models of various energy sources;
respectively predicting the prices of various energy sources after a period of time in the future by using the price prediction models of various energy sources;
constructing a consumption prediction model of various energy sources;
predicting the consumption of various energy sources after a period of time in the future by using the consumption prediction model of various energy sources;
and determining the energy supply ratio according to the predicted price and the predicted consumption of each energy source after a period of time in the future and the conversion relation of the energy price ratio among the energy sources so as to minimize the total energy consumption cost.
Further, the constructing of the price prediction model of various energy sources includes:
collecting historical price data of various energy sources;
preprocessing the historical price data;
respectively establishing a neural network model aiming at various energy sources;
dividing the preprocessed historical price data into training set data and testing set data;
and training the neural network model by using the training set data, testing the trained neural network model by using the test set data until the trained neural network model meets the preset requirement, and obtaining price prediction models of various energy sources.
Further, the historical price data includes: the maximum price, the minimum price, the opening price, the closing price, the technical index dissimilarity moving average line, the trend index, the random index, the variation rate index and the raw material price after a corresponding period of time in the raw material futures trading of several days.
Further, the preprocessing the historical price data includes: and performing dimension reduction processing on the historical price data, then removing abnormal data with large noise, supplementing missing data and deleting repeated data.
Further, the constructing of the usage prediction model of various energy sources includes:
collecting historical consumption data of various energy sources;
preprocessing the historical usage data;
respectively establishing a neural network model aiming at various energy sources;
dividing the preprocessed historical usage data into training set data and testing set data;
and training the neural network model by using the training set data, testing the trained neural network model by using the test set data until the trained neural network model meets the preset requirement, and obtaining the consumption prediction model of each energy source.
Further, the preprocessing the historical usage data includes: and performing dimension reduction processing on the historical usage data, then removing abnormal data with large noise, supplementing missing data and deleting repeated data.
According to another aspect of the embodiments of the present application, there is provided an energy supply amount ratio presetting device, including:
the construction module is used for constructing price prediction models of various energy sources;
the forecasting module is used for respectively forecasting the prices of various energy sources after a period of time in the future by utilizing the price forecasting models of various energy sources;
the construction module is also used for constructing a consumption prediction model of various energy sources;
the prediction module is also used for predicting the consumption of various energy sources after a period of time in the future by utilizing the consumption prediction model of various energy sources;
and the optimization solving module is used for determining the energy supply amount ratio according to the predicted price and the predicted consumption of each energy source after a period of time in the future and the energy price ratio conversion relation among the energy sources so as to minimize the total energy consumption cost.
According to another aspect of the embodiments of the present application, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the energy supply ratio presetting method.
According to another aspect of embodiments of the present application, there is provided a computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the energy supply ratio presetting method described above.
The technical scheme provided by one aspect of the embodiment of the application can have the following beneficial effects:
according to the energy supply ratio presetting method provided by the embodiment of the application, the price and the consumption of each energy source after a period of time in the future are predicted through the constructed prediction model, and the energy supply ratio is distributed according to the predicted price and the predicted consumption of each energy source and the energy price ratio conversion relation among the energy sources, so that the total energy consumption cost is the lowest, the optimal distribution of various energy sources is realized, the energy consumption requirement is met, and the energy consumption cost of a user is minimized.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the application, or may be learned by the practice of the embodiments. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 shows a flowchart of an energy supply ration presetting method according to an embodiment of the present application;
FIG. 2 shows a flowchart of step S10 in FIG. 1;
FIG. 3 shows a schematic structural diagram of a long-and-short-term memory neural network model;
FIG. 4 shows a schematic of the structure of a neuron element;
FIG. 5 shows a flowchart of step S30 in FIG. 1;
fig. 6 is a block diagram illustrating an energy supply ratio presetting apparatus according to an embodiment of the present application;
fig. 7 shows a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It will be understood by those within the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The energy center operation system carries out information interaction with various information systems and platforms, a unified general information model is adopted to model information (a unified information model CIM is adopted to model an organization structure, energy utilization equipment, energy utilization information, energy price information and the like, a digital model is established for various information and put into the operation system), information exchange is carried out with an ERP and EMS system of an energy center, a natural gas international future data release platform, a regional power market spot-stock transaction system, a hydrogen energy transaction platform, a hydrogen energy production factory information system, a user side demand management system and the like, and historical data of raw material price and consumption, user side energy utilization information and the like are obtained. Raw material prices may come from third party systems, such as natural gas international futures data publishing platforms; the usage data comes from energy centers and energy metering equipment at the user end.
As shown in fig. 1, an embodiment of the present application provides a method for presetting an energy supply ratio, including the following steps:
and S10, constructing price prediction models of various energy sources.
As shown in fig. 2, in some embodiments, step S10 includes:
s101, collecting historical price data of various energy sources.
Historical price data for a certain energy source includes: the maximum price, the minimum price, the opening price, the closing price, the technical Index MACD (Moving Average conversion and conversion, iso-Moving Average), the DMI (Directional Movement Index), the KDJ (random Index), the ROC (change rate Index) and the price of the raw material after a corresponding period of time (e.g. 90 days, 100 days, etc.) in the raw material futures transaction for several days. The corresponding period of time can be selected according to actual needs, for example, values of 90 days, 100 days, 120 days, etc. can be selected.
Generally, the energy sources commonly used at present comprise three types of natural gas, electric energy and hydrogen energy. Prices for various energy sources are collected, and the prices come from trading platforms of different energy sources. Historical price data may be obtained by interfacing with third party raw materials trading systems.
User end energy consumption information, user requirements, planning data and the like; the consumption information of the raw materials is acquired by energy monitoring equipment installed in an energy center and then transmitted to an operation system, and the energy consumption data, the demand data and the plan data of the user side are in butt joint with the energy consumption monitoring and operation management system of the user side, and the information is obtained from the user side.
And S102, preprocessing the historical price data.
The pretreatment step comprises: a data cleaning step and a data storage step. The step of data cleaning comprises the steps of arranging the acquired data into a data format which is easy to process, removing abnormal data with large noise, supplementing missing data and deleting repeated data. The data storage comprises the step of storing the data subjected to data cleaning into a relational database. Missing data can be supplemented by methods such as K-value padding. In some embodiments, the sorting of the obtained data into a more manageable data format may include performing dimensionality reduction on historical price data through principal component analysis, and the like.
S103, establishing a neural network model aiming at various energy sources respectively.
Specifically, a long-term and short-term memory neural network model or other neural network models may be adopted, and the long-term and short-term memory neural network model is preferably adopted in this embodiment. The optimal time window, the number of hidden layer neural network units and other algorithm parameters can be found through a particle swarm optimization algorithm, and a neural network model is established.
As shown in fig. 3 and 4, the long-term and short-term memory neural network model includes a plurality of neuron units connected in sequence, and each neuron unit (i.e., LSTM unit) includes an input gate, a forgetting gate, and an output gate.
The forgetting gate is used for deciding which information to discard, and the input is the calculation result h of the last neuron unitt-1And the current input vector xtWhen the two are connected and pass through a forget gate (sigmoid is used for determining which information is reserved and which information is discarded), a 0-1 vector gamma is generatedf t(dimension and output vector C of last neuron element)t-1Same), r |)f tAnd Ct-1After the dot multiplication, the information reserved after the last neuron unit is calculated is obtained.
An input gate for indicating information to be saved or updated, as shown in the above figure as ht-1And xtThe connection vector of (a), a result gamma obtained after passing through the sigmoid layeri tThis is the result of the output of the input gate. But the nerve is next calculatedThe output result of the meta-cell, i.e. the update state C of the new celltWherein, in the step (A),
Ct＝Ct-1·Γf t+Γi t·～ct，
wherein
～ct＝tanh(ht-1，xt))，
The text description is: input gate calculation result dot product ht-1And xtAfter the result of the tanh layer calculation, the connecting vector is added with the information retained after the previous neuron unit is calculated, and the result is C to be finally outputt。
The output gate is used for determining the implicit vector h output by the current neuron unitt，htAnd CtDifferent, htTo be slightly more complex, it is CtAfter the tanh calculation, the result of the dot product operation is performed with the calculation result of the output gate, and the result is described by a formula:
ht＝tanh(ct)·Γo t。
σ in fig. 3 and 4 represents a sigmoid layer (a value of 0 to 1 at the output of the layer, 0 represents no passage, and 1 represents passage).
The working principle of the long-time memory neural network model is as follows:
(1) and inputting the hidden layer vector output by the previous neuron unit and the input of the current neuron unit, and connecting the hidden layer vector and the input of the current neuron unit. The computational process inside the neuron unit includes: firstly, the output h of the last neuron unitt-1With input x of the neuron element in the current statetAnd performing tanh calculation after splicing.
(2) And (3) transmitting the result in the step (1) into a forgetting gate, and deleting irrelevant information by the layer.
(3) And (3) transmitting the result in the step (1) to an input gate, wherein the layer determines which information in the alternative layer in the step (4) should be added to the cell state.
(4) An alternative layer will be created with the results from step (1), this layer will hold possible values or information that will be added to the cell state.
(5) And (3) updating the unit state of the current neuron unit by using the vector calculated in the steps (2), (3) and (4) and the unit state vector transmitted by the last neuron unit.
(6) And performing dot multiplication on the result obtained by the calculation in the steps (2), (3) and (4) and the new unit state to obtain a hidden vector of the current unit state.
And S104, dividing the preprocessed historical price data into training set data and testing set data.
For example, 80% of the historical price data is randomly used as training set data, and the remaining 20% of the historical price data is used as test set data, or 75% of the historical price data is randomly used as training set data, and the remaining 25% of the historical price data is used as test set data. The specific data distribution proportion can be adjusted according to actual needs.
And S105, training the neural network model by using the training set data, testing the trained neural network model by using the test set data until the trained neural network model meets the preset requirement, and obtaining the price prediction model of each energy source.
The preset requirement can adopt an accuracy threshold, namely the training can be stopped when the output accuracy of the trained neural network model reaches the preset accuracy threshold.
And S20, respectively predicting the prices of the energy sources after a period of time in the future by using the price prediction models of the energy sources.
For example, for three energy sources of natural gas, electric energy and hydrogen energy, the daily maximum price, minimum price, opening price, closing price, technical indexes MACD (Moving Average conversion and variation, different Moving Average), DMI (trend Index), KDJ (random Index) and ROC (variation rate Index) in the current stock futures transaction are respectively collected, the collected data are input into the corresponding price prediction model, and the output data are the price after a period of time in the future. In the step of collecting the historical price data of the various energy sources, the price of the raw material after the selected period of time is the same as the future period of time in the step S20. For example, if the selected period of time is 100 days in the step of collecting the historical price data of various energy sources, the price after 100 days in the future is predicted in step S20.
And S30, constructing a usage prediction model of various energy sources.
As shown in fig. 5, in some embodiments, step S30 includes:
s301, collecting historical consumption data of various energy sources.
Specifically, the historical usage data for a certain energy source may include energy usage data for all users per day over several days and energy usage data after a corresponding period of time. The corresponding period of time here is the same as the corresponding period of time in the historical price data in step S101, and for example, values of 90 days, 100 days, 120 days, etc. may be selected accordingly. One energy center is responsible for providing energy to all users in a certain area.
And collecting the consumption data of various energy sources, wherein the consumption data come from transaction platforms of different energy sources, and the consumption information can be acquired by an energy source operation system through energy consumption metering equipment. Historical usage data may be obtained by interfacing with third party material trading systems.
S302, preprocessing historical usage data of various energy sources.
The method comprises the steps of preprocessing historical usage data of various energy sources, cleaning the data and storing the data. The step of data cleaning comprises the steps of arranging the acquired data into a data format which is easy to process, removing abnormal data with large noise, supplementing missing data and deleting repeated data. The data storage comprises the step of storing the data subjected to data cleaning into a relational database. Missing data can be supplemented by methods such as K-value padding. In some embodiments, the sorting of the obtained data into a more manageable data format may include performing dimensionality reduction on historical price data through principal component analysis, and the like.
S303, respectively establishing a neural network model aiming at various energy sources.
Specifically, a long-term and short-term memory neural network model or other neural network models may be adopted, and the long-term and short-term memory neural network model is preferably adopted in this embodiment.
And S304, dividing the preprocessed historical usage data into training set data and testing set data.
For example, 80% of the historical usage data may be randomized as training set data and the remaining 20% of the historical usage data may be randomized as test set data, or 75% of the historical usage data may be randomized as training set data and the remaining 25% of the historical usage data may be randomized as test set data. The specific data distribution proportion can be adjusted according to actual needs.
S305, training the neural network model by using the training set data, testing the trained neural network model by using the test set data until the trained neural network model meets the preset requirement, and obtaining the usage prediction model of each energy source.
The preset requirement can adopt an accuracy threshold, namely the training can be stopped when the output accuracy of the trained neural network model reaches the preset accuracy threshold.
And S40, predicting the usage of each energy source after a period of time in the future by using the usage prediction models of each energy source.
For example, for three energy sources of natural gas, electric energy and hydrogen energy, energy consumption data of all current users per day are collected respectively, the collected data are input into corresponding consumption prediction models, and the output data are predicted consumption after a period of time in the future. In the step of collecting the historical usage data of the various energy sources, the predicted usage after the selected future period of time is the same as the future period of time in step S20. For example, if the selected period of time is 100 days in the step of collecting the historical price data of various energy sources, the price after 100 days in the future is predicted in the step S20, and the amount after 100 days in the future is also predicted in the step S40.
And S50, determining the energy supply amount ratio according to the predicted price and the predicted usage amount of each energy source after a period of time in the future and the conversion relation of the energy price ratio among the energy sources so as to minimize the total energy consumption cost.
The objective function is the minimum value of P ═ ax + by + cz + D, where P is the total cost, a represents the predicted price per unit of natural gas, b represents the predicted price per unit of hydrogen energy, and c represents the predicted price per unit of electrical energy; the cost ratio of the natural gas, the hydrogen energy source and the electric energy required by releasing the same energy is m: n: k, wherein m, n and k are known numbers, m is more than 0, n is more than 0, k is more than 0, A represents the predicted consumption of the natural gas, B represents the predicted consumption of the hydrogen energy source, C represents the predicted consumption of the electric energy, x is more than or equal to 0, y is more than or equal to 0, z is more than or equal to 0, and D is a constant value and represents the cost consumed by the irreplaceable energy source. The predicted amount of energy needed after a future period of time is Q ═ aA + bB + cC + E, where E is the amount of energy corresponding to D, a constant.
According to the method provided by the embodiment of the application, the price and the usage of each energy source after a period of time in the future are predicted through the constructed prediction model, and the energy supply amount is distributed according to the predicted price and the predicted usage of each energy source and the energy price ratio conversion relation among the energy sources, so that the total energy consumption cost is the lowest, the optimal distribution of various energy sources is realized, the energy consumption requirements are met, and the energy consumption cost of users is minimized.
As shown in fig. 6, another embodiment of the present application provides an energy supply amount ratio presetting apparatus, including:
the construction module 10 is used for constructing price prediction models of various energy sources;
the prediction module 20 is used for respectively predicting the prices of various energy sources after a period of time in the future by utilizing the price prediction models of various energy sources;
the construction module 10 is further used for constructing a usage prediction model of various energy sources;
the prediction module 20 is further configured to predict the usage amount of each energy source after a period of time in the future by using the usage amount prediction model of each energy source;
and the optimization solving module 30 is used for determining the energy supply ratio according to the predicted price and the predicted consumption of each energy source after a period of time in the future and the conversion relation of the energy price ratio among the energy sources, so that the total energy consumption cost is the lowest.
In certain embodiments, the building block 10 comprises:
the acquisition unit is used for acquiring historical price data of various energy sources;
the preprocessing unit is used for preprocessing the historical price data;
the modeling unit is used for respectively establishing a first neural network model aiming at various energy sources;
the data dividing unit is used for dividing the preprocessed historical price data into training set data and test set data;
the training unit is used for training the first neural network model by using the training set data, testing the trained first neural network model by using the test set data until the trained first neural network model meets the preset requirement, and obtaining price prediction models of various energy sources;
the acquisition unit is also used for acquiring historical consumption data of various energy sources;
the preprocessing unit is also used for preprocessing the historical usage data;
the modeling unit is also used for respectively establishing a second neural network model aiming at various energy sources;
the data dividing unit is also used for dividing the preprocessed historical usage data into training set data and test set data;
the training unit is also used for training a second neural network model by using the training set data, testing the trained second neural network model by using the test set data until the trained second neural network model meets the preset requirement, and obtaining the consumption prediction model of each energy source.
It should be noted that the terms "first", "second", and the like used in the present embodiment may be used to describe various components in the present embodiment, but the components are not limited by these terms. These terms are only used to distinguish one element from another. For example, the first neural network model may be referred to as a second neural network model, and the second neural network model may be referred to as the first neural network model, without departing from the scope of the present application.
Another embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the energy supply ratio presetting method according to any one of the above embodiments. As shown in fig. 7, the electronic device 20 may include: the system comprises a processor 200, a memory 201, a bus 202 and a communication interface 203, wherein the processor 200, the communication interface 203 and the memory 201 are connected through the bus 202; the memory 201 stores a computer program that can be executed on the processor 200, and the processor 200 executes the energy supply ratio presetting method provided by any one of the foregoing embodiments when executing the computer program.
The Memory 201 may include a high-speed Random Access Memory (RAM), and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 203 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used.
The processor 200 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 200. The Processor 200 may be a general-purpose Processor, and may include a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and completes the steps of the method in combination with the hardware thereof.
Another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, the program being executed by a processor to implement the energy supply amount ratio presetting method of any one of the above embodiments.
It should be noted that:
the term "module" is not intended to be limited to a particular physical form. Depending on the particular application, a module may be implemented as hardware, firmware, software, and/or combinations thereof. Furthermore, different modules may share common components or even be implemented by the same component. There may or may not be clear boundaries between the various modules.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may be used with the teachings herein. The required structure for constructing such a device will be apparent from the description above. In addition, this application is not directed to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the present application as described herein, and any descriptions of specific languages are provided above to disclose the best modes of the present application.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the application, various features of the application are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: this application is intended to cover such departures from the present disclosure as come within known or customary practice in the art to which this invention pertains. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The above-mentioned embodiments only express the embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (9)
1. An energy supply amount ratio presetting method is characterized by comprising the following steps:
constructing price prediction models of various energy sources;
respectively predicting the prices of various energy sources after a period of time in the future by using the price prediction models of various energy sources;
constructing a consumption prediction model of various energy sources;
predicting the consumption of various energy sources after a period of time in the future by using the consumption prediction model of various energy sources;
and determining the energy supply ratio according to the predicted price and the predicted consumption of each energy source after a period of time in the future and the conversion relation of the energy price ratio among the energy sources so as to minimize the total energy consumption cost.
2. The method of claim 1, wherein constructing a price prediction model for the various energy sources comprises:
collecting historical price data of various energy sources;
preprocessing the historical price data;
respectively establishing a neural network model aiming at various energy sources;
dividing the preprocessed historical price data into training set data and testing set data;
and training the neural network model by using the training set data, testing the trained neural network model by using the test set data until the trained neural network model meets the preset requirement, and obtaining price prediction models of various energy sources.
3. The method of claim 2, wherein the historical price data comprises: the maximum price, the minimum price, the opening price, the closing price, the technical index dissimilarity moving average line, the trend index, the random index, the variation rate index and the raw material price after a corresponding period of time in the raw material futures trading of several days.
4. The method of claim 2, wherein the pre-processing the historical price data comprises: and performing dimension reduction processing on the historical price data, then removing abnormal data with large noise, supplementing missing data and deleting repeated data.
5. The method of claim 1, wherein the constructing the model for predicting the usage of the various energy sources comprises:
collecting historical consumption data of various energy sources;
preprocessing the historical usage data;
respectively establishing a neural network model aiming at various energy sources;
dividing the preprocessed historical usage data into training set data and testing set data;
and training the neural network model by using the training set data, testing the trained neural network model by using the test set data until the trained neural network model meets the preset requirement, and obtaining the consumption prediction model of each energy source.
6. The method of claim 5, wherein the pre-processing the historical usage data comprises: and performing dimension reduction processing on the historical usage data, then removing abnormal data with large noise, supplementing missing data and deleting repeated data.
7. An energy supply amount ratio presetting device is characterized by comprising:
the construction module is used for constructing price prediction models of various energy sources;
the forecasting module is used for respectively forecasting the prices of various energy sources after a period of time in the future by utilizing the price forecasting models of various energy sources;
the construction module is also used for constructing a consumption prediction model of various energy sources;
the prediction module is also used for predicting the consumption of various energy sources after a period of time in the future by utilizing the consumption prediction model of various energy sources;
and the optimization solving module is used for determining the energy supply amount ratio according to the predicted price and the predicted consumption of each energy source after a period of time in the future and the energy price ratio conversion relation among the energy sources so as to minimize the total energy consumption cost.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of any one of claims 1-6.
9. A computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor to implement the method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011438939.8A CN112613899A (en) | 2020-12-10 | 2020-12-10 | Energy supply amount ratio presetting method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011438939.8A CN112613899A (en) | 2020-12-10 | 2020-12-10 | Energy supply amount ratio presetting method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112613899A true CN112613899A (en) | 2021-04-06 |
Family
ID=75232610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011438939.8A Pending CN112613899A (en) | 2020-12-10 | 2020-12-10 | Energy supply amount ratio presetting method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112613899A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106707778A (en) * | 2016-12-06 | 2017-05-24 | 长沙理工大学 | Model predictive control-based home integrated energy intelligent optimization and management system |
| CN109713718A (en) * | 2019-01-17 | 2019-05-03 | 上海大学 | A kind of microgrid energy Optimal Management System based on electric energy router |
| CN112036646A (en) * | 2020-09-02 | 2020-12-04 | 南方电网科学研究院有限责任公司 | Comprehensive energy system planning method and device considering multi-type energy storage configuration |
-
2020
- 2020-12-10 CN CN202011438939.8A patent/CN112613899A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106707778A (en) * | 2016-12-06 | 2017-05-24 | 长沙理工大学 | Model predictive control-based home integrated energy intelligent optimization and management system |
| CN109713718A (en) * | 2019-01-17 | 2019-05-03 | 上海大学 | A kind of microgrid energy Optimal Management System based on electric energy router |
| CN112036646A (en) * | 2020-09-02 | 2020-12-04 | 南方电网科学研究院有限责任公司 | Comprehensive energy system planning method and device considering multi-type energy storage configuration |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Dynamic pricing for decentralized energy trading in micro-grids | |
| CN108711077B (en) | Photovoltaic type microgrid transaction method based on block chain technology | |
| Kong et al. | Optimal operation strategy for interconnected microgrids in market environment considering uncertainty | |
| CN112651770B (en) | Load declaration optimization method and system for power selling merchants in power spot market | |
| CN105164883A (en) | Demand shaping in an electrical power grid using day ahead market and real time market prices | |
| CN110543697B (en) | Electric power market simulation running system | |
| Lu et al. | A hybrid deep learning-based online energy management scheme for industrial microgrid | |
| CN110135761A (en) | For power demand side response Load Regulation method of commerce, system and terminal device | |
| CN109118012B (en) | Industrial dynamic multi-dimensional energy consumption cost prediction method, system, storage medium and terminal | |
| CN110852519A (en) | Optimal profit method considering various types of loads for electricity selling companies | |
| Nguyen et al. | Bi-objective-based cost allocation for cooperative demand-side resource aggregators | |
| CN114493049A (en) | Production line optimization method and device based on digital twin, electronic equipment and medium | |
| CN111176635A (en) | Modularized quantization system, execution method thereof and electronic equipment | |
| CN112200489B (en) | Integrated optimization system, method and device for nonferrous metal smelting production and supply marketing | |
| Nguyen et al. | Sharing profit from joint offering of a group of wind power producers in day ahead markets | |
| CN107230004A (en) | A kind of regenerative resource portfolio optimization optimization method, device and computing device | |
| Han et al. | Optimal scheduling of distribution system with edge computing and data-driven modeling of demand response | |
| US11669060B2 (en) | Hybrid machine learning and simulation based system for forecasting in electricity systems | |
| CN107944640A (en) | A kind of regenerative resource portfolio optimization optimisation technique method and device | |
| CN110717779A (en) | Electric power transaction system, method and application thereof | |
| CN112613899A (en) | Energy supply amount ratio presetting method and device, electronic equipment and storage medium | |
| Umarov et al. | The cognitive model and its implementation of the enterprise Uzmobile | |
| CN114358756A (en) | Electric power point-to-point transaction method and system based on double-layer block chain | |
| Fernandes et al. | Elspot: nord pool spot integration in MASCEM electricity market simulator | |
| Bublitz et al. | Agent-based simulation of interrelated wholesale electricity markets |
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 |