CN108736515A - Wind electricity digestion phase-change thermal storage station load prediction system and method based on neural network - Google Patents
Wind electricity digestion phase-change thermal storage station load prediction system and method based on neural network Download PDFInfo
- Publication number
- CN108736515A CN108736515A CN201810537740.7A CN201810537740A CN108736515A CN 108736515 A CN108736515 A CN 108736515A CN 201810537740 A CN201810537740 A CN 201810537740A CN 108736515 A CN108736515 A CN 108736515A
- Authority
- CN
- China
- Prior art keywords
- thermal storage
- phase
- change thermal
- storage station
- neural network
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 124
- 230000005611 electricity Effects 0.000 title claims abstract description 88
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 74
- 230000029087 digestion Effects 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title description 9
- 238000009825 accumulation Methods 0.000 claims abstract description 23
- 238000005338 heat storage Methods 0.000 claims abstract description 16
- 238000010348 incorporation Methods 0.000 claims abstract description 10
- 230000004044 response Effects 0.000 claims abstract description 10
- 238000010835 comparative analysis Methods 0.000 claims abstract description 8
- 239000010410 layer Substances 0.000 claims description 42
- 238000012549 training Methods 0.000 claims description 42
- 230000004913 activation Effects 0.000 claims description 12
- 230000005284 excitation Effects 0.000 claims description 12
- 238000005485 electric heating Methods 0.000 claims description 7
- 238000004134 energy conservation Methods 0.000 claims description 6
- 239000011229 interlayer Substances 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000005855 radiation Effects 0.000 claims description 6
- 238000013277 forecasting method Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- 238000009472 formulation Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 210000005036 nerve Anatomy 0.000 claims description 2
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000001172 regenerating effect Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004146 energy storage Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- CPLXHLVBOLITMK-UHFFFAOYSA-N Magnesium oxide Chemical compound [Mg]=O CPLXHLVBOLITMK-UHFFFAOYSA-N 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000013486 operation strategy Methods 0.000 description 2
- 230000005622 photoelectricity Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 206010068052 Mosaicism Diseases 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 239000000395 magnesium oxide Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000012782 phase change material Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 210000003765 sex chromosome Anatomy 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- H02J3/382—
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/24—Arrangements for preventing or reducing oscillations of power in networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
- H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
-
- H02J3/386—
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/76—Power conversion electric or electronic aspects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E70/00—Other energy conversion or management systems reducing GHG emissions
- Y02E70/30—Systems combining energy storage with energy generation of non-fossil origin
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a kind of wind electricity digestion phase-change thermal storage station based on neural network load prediction, load prediction module is according to the meteorological data of weather bureau first, historical load information, the quantity of heat storage at phase-change thermal storage station, and heat accumulation temperature carries out load prediction, obtain phase-change thermal storage station dissolves electricity, then energy management predicts load centrally through wind power and phase-change thermal storage station, and the comparative analysis of wind-powered electricity generation rate for incorporation into the power network and alternating current price, according to analysis result, and controlled based on demand response, propose operation reserve.The present invention solves the problems, such as wind electricity digestion, reduces the fluctuation that wind-powered electricity generation is brought to power grid, considers time-of-use tariffs, provides the most economical operation reserve of user.In addition, the present invention is even more to the perfect of wind energy utilization technology, a wide range of use to wind energy may advantageously facilitate.
Description
Technical field
The present invention relates to a kind of technical field of electric power more particularly to a kind of wind electricity digestion phase-change thermal storages based on neural network
It stands load prediction system and method.
Background technology
As traditional fossil energy is reduced increasingly, environmental pollution increasingly sharpens, and the development and utilization of regenerative resource is alive
It is more and more important in various countries of boundary energy strategy.Large-scale development with regenerative resource and utilization, regenerative resource is in power grid
The effect of middle performance is more and more obvious, wherein most representative with wind-powered electricity generation and photoelectricity.However, the infiltration of regenerative resource is to electricity
Net brings many new problems.After large-scale distributed regenerative resource access, power grid needs while balancing random fluctuation
Workload demand and using wind-powered electricity generation, photoelectricity as representative uncontrollable distributed generation resource contribute.In the northern area of China, abandoning wind, to abandon light existing
As serious, power generation exacerbates energy resource supply with mismatch of the electricity consumption on space-time and consumes unbalance contradiction.Therefore, how to drop
Low wind of abandoning abandons light rate, solves clean energy resource consumption as the key point of energy sustainable development is realized.
Energy storage technology as a kind of effective measures, ask by the intermittence and stochastic volatility that can solve renewable energy power generation
Topic improves electric system peak modulation capacity, meets requirement of the socio-economic development to high-quality and safety, reliable power supply.In big rule at present
Under the background that mould electricity storage technology is immature, economic cost remains high, the heat-storage technology of relative maturity can clean energy in the north
Source is for hankering playing an important role.Currently, carrying out, for hankering, mostly using the material uses such as magnesia brick both at home and abroad using heat-storage technology
Material sensible heat is warm to carry out storage.When storing heat using sensible heat, temperature can occur continuously to change, and cannot maintain certain
At a temperature of discharge all energy, be unable to reach the purpose of control temperature, and the heat accumulation mode energy storage density is low, to make
Related device is bulky.And phase-change thermal storage is then to carry out storage heat using the latent heat of substance, which not only can be with
Storage heat is carried out under conditions of approximately constant temperature, and energy storage density is high, device volume is relatively small, has broad prospects.
The research contents of phase-change thermal storage technology includes the good phase-change material research of storage hot property, and phase-change thermal storage problem is modeled and asked
The problems such as solution research and phase-change thermal storage engineer application.
Since the intermittence of wind energy influences, the generated output of Wind turbines is with meteorologic parameter dynamic change, phase-change thermal storage station
The electric load of access changes also with the variation of quantity of heat storage, therefore wind-powered electricity generation and the power match at phase-change thermal storage station are poor.
For off-grid operation system, the storage of electric power is realized by using accumulator, but that there is efficiency for charge-discharges is low, makes for accumulator
With the high drawback of short life, cost of investment, and the system that is incorporated into the power networks will produce fluctuation due to the variation of wind power to power grid,
Influence the normal operation of power grid.
Invention content
In view of the above problems, the present invention proposes a kind of wind electricity digestion phase-change thermal storage station load prediction system based on neural network
System and method, the present invention provides a kind of technical solution is as follows:
A kind of wind electricity digestion phase-change thermal storage station load prediction system based on neural network, for being stored up to wind electricity digestion phase transformation
The load of heat stations is predicted that wind electricity digestion phase-change thermal storage station includes electric heating converting system, hot storage system, control system
System and heat accumulation room, Wind turbines are connect by control circuit with inverter circuit with phase-change thermal storage station, utility grid and control circuit
Connection, the system include:
Load prediction module, for according to current weather data, historical load information, the quantity of heat storage at phase-change thermal storage station and
Heat accumulation temperature is based on neural network phase-change thermal storage station load forecasting model, and can dissolve electricity to phase-change thermal storage station and carry out
Prediction;Energy conservation module, phase-change thermal storage station load and wind-powered electricity generation for being obtained with prediction by wind power are surfed the Internet electric
Demand response is made in the comparative analysis of valence and alternating current price, formulates operation reserve and is controlled.
Wherein, the load prediction module of the system includes:
Data acquisition unit, for acquiring the input quantity for determining the phase-change thermal storage station load forecasting model based on neural network
And output quantity:
Wherein, the input quantity include at least outdoor temperature, humidity, wind speed, historical load information, intensity of solar radiation,
The quantity of heat storage and heat accumulation temperature at phase-change thermal storage station;The output quantity is to predict that the load of the prediction model of day is output quantity;
Predict preparatory unit, the excitation function of structure and each interlayer for determining BP neural network;
Wherein, the structure of the BP neural network is three layers of BP neural network, and input layer corresponds to described pre-
The input quantity of model is surveyed, the number of output node layer corresponds to the output quantity of the prediction model, and hidden layer node is several
It is determined according to following formula (1):
M=2n+1 (1)
In formula, m is hidden layer node number, and n is input layer number;
Training unit determines training parameter, starts to train, after training, obtain prediction for establishing BP neural network
As a result;
Wherein, the training parameter includes training function, frequency of training and training objective.
Wherein, the BP neural network excitation function that the prediction preparatory unit is formulated uses tanh S type activation primitives,
BP neural network output layers use linear activation primitive.
Wherein, when the training unit establishes BP neural network, established using MATLAB Neural Network Toolbox.
Wherein, the load prediction module further includes prediction optimization unit, for phase-change thermal storage station load forecasting model
The sample data of input quantity be normalized by following formula (2):
In formula, XIFor the target after normalization, XiFor input data, XmaxWith XminRespectively XiIn maximum value and minimum
Value.
Wherein, the operation reserve that the energy conservation module of the system is formulated is as follows:
The present invention provides another technical solutions, specific as follows:
A kind of wind electricity digestion phase-change thermal storage station load forecasting method based on neural network, for being stored up to wind electricity digestion phase transformation
The load of heat stations is predicted that wind electricity digestion phase-change thermal storage station includes electric heating converting system, hot storage system, control system
System and heat accumulation room, Wind turbines are connect by control circuit with inverter circuit with phase-change thermal storage station, utility grid and control circuit
Connection, including:
According to current weather data, historical load information, the quantity of heat storage at phase-change thermal storage station and heat accumulation temperature, based on nerve
Network establishes phase-change thermal storage station load forecasting model, and can dissolve electricity to phase-change thermal storage station and predict;
Pass through pair of phase-change thermal storage station load and wind-powered electricity generation rate for incorporation into the power network and alternating current price that wind power is obtained with prediction
Than analysis, demand response is made, formulate operation reserve and is controlled.
Wherein, in it can dissolve the step of electricity is predicted to phase-change thermal storage station, including step:
Acquisition determines the input quantity and output quantity of the phase-change thermal storage station load forecasting model based on neural network:
Wherein, the input quantity include at least outdoor temperature, humidity, wind speed, historical load information, intensity of solar radiation,
The quantity of heat storage and heat accumulation temperature at phase-change thermal storage station;The output quantity is to predict that the load of the prediction model of day is output quantity;
Determine the structure of BP neural network and the excitation function of each interlayer;
Wherein, the structure of the BP neural network is three layers of BP neural network, and input layer corresponds to described pre-
The input quantity of model is surveyed, the number of output node layer corresponds to the output quantity of the prediction model, and hidden layer node is several
It is determined according to following formula (1):
M=2n+1 (1)
In formula, m is hidden layer node number, and n is input layer number;
Excitation function uses tanh S type activation primitives, BP neural network output layer to use linear activation primitive;
Place is normalized by following formula (2) to the sample data of the input quantity of phase-change thermal storage station load forecasting model
Reason:
In formula, XIFor the target after normalization, XiFor input data, XmaxWith XminRespectively XiIn maximum value and minimum
Value;
Using MATLAB Neural Network Toolbox BP neural networks, training parameter is determined, start to train, after training,
Obtain prediction result;
Wherein, the training parameter includes training function, frequency of training and training objective.
Wherein, in the phase-change thermal storage station load and wind-powered electricity generation rate for incorporation into the power network and alternating current obtained with prediction by wind power
The comparative analysis of price, makes demand response, and in the step of formulating operation reserve and being controlled, the operation reserve of formulation is such as
Under:
The advantageous effect of technical solution provided by the invention is:Effective knot of wind-powered electricity generation and phase-change thermal storage station can be achieved in the present invention
It closes, by load prediction, obtains the power demand at phase-change thermal storage station, consider time-of-use tariffs, and formulate economical optimal operation
Strategy solves the problems, such as the consumption of wind-powered electricity generation, reduces the fluctuation that wind-powered electricity generation is brought to power grid, can meet the needs of users but also
Realize energy-saving and emission-reduction;It solves the problems, such as the consumption of wind-powered electricity generation, reduces system accumulator configuration capacity, reduce system cost, to the greatest extent
It is likely to reduced the fluctuation that wind-powered electricity generation generates power grid, and gives most economical operation reserve.
Description of the drawings
Fig. 1 is by a kind of wind electricity digestion phase-change thermal storage station load prediction system company based on neural network provided by the invention
The phase-change thermal storage station structure schematic diagram connect.
Fig. 2 is a kind of knot of the wind electricity digestion phase-change thermal storage station load prediction system based on neural network provided by the invention
Structure schematic diagram.
Fig. 3 is a kind of work of the wind electricity digestion phase-change thermal storage station load prediction system based on neural network provided by the invention
Make principle schematic.
Fig. 4 is a kind of stream of the wind electricity digestion phase-change thermal storage station load forecasting method based on neural network provided by the invention
Journey schematic diagram.
In attached drawing, the component representated by each label is as follows:
1:Utility grid; 2:Wind turbines; 3:Control circuit; 4:Accumulator group;
5:Inverter circuit; 6:Electric heating converting system; 7:Hot storage system;
8:Control system; 9:Heat accumulation room 10:Phase-change thermal storage station
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
His embodiment, shall fall within the protection scope of the present invention.
Referring to Fig.2, Fig. 2 is a kind of wind electricity digestion phase-change thermal storage station load prediction based on neural network provided by the invention
The structural schematic diagram of system.The system is for predicting the load at wind electricity digestion phase-change thermal storage station 10, the wind electricity digestion
Phase-change thermal storage station (10) includes electric heating converting system (6), hot storage system (7), control system (8) and heat accumulation room (9), wind-powered electricity generation
Unit (2) is connect by control circuit (3) with inverter circuit (5) with phase-change thermal storage station (10), utility grid (1) and control electricity
Road (3) connects.The structure at wind electricity digestion phase-change thermal storage station 10 is as shown in Figure 1.
Wind electricity digestion phase-change thermal storage station load prediction system provided by the invention based on neural network includes:
Load prediction module, for according to current weather data, historical load information, the quantity of heat storage of phase-change thermal storage station (10)
And heat accumulation temperature, it is based on neural network phase-change thermal storage station (10) load forecasting model, and can dissolve to phase-change thermal storage station
Electricity is predicted;
Energy conservation module, phase-change thermal storage station (10) load and wind-powered electricity generation for being obtained with prediction by wind power
Demand response is made in the comparative analysis of rate for incorporation into the power network and alternating current price, formulates operation reserve and is controlled.
Preferably, load prediction module includes:
Data acquisition unit determines the defeated of phase-change thermal storage station (10) load forecasting model based on neural network for acquiring
Enter amount and output quantity:
Wherein, the input quantity include at least outdoor temperature, humidity, wind speed, historical load information, intensity of solar radiation,
The quantity of heat storage and heat accumulation temperature at phase-change thermal storage station;The output quantity is to predict that the load of the prediction model of day is output quantity;
Predict preparatory unit, the excitation function of structure and each interlayer for determining BP neural network;
Wherein, the structure of the BP neural network is three layers of BP neural network, and input layer corresponds to described pre-
The input quantity of model is surveyed, the number of output node layer corresponds to the output quantity of the prediction model, and hidden layer node is several
It is determined according to following formula (1):
M=2n+1 (1)
In formula, m is hidden layer node number, and n is input layer number;
Training unit determines training parameter, starts to train, after training, obtain prediction for establishing BP neural network
As a result;
Wherein, the training parameter includes training function, frequency of training and training objective.
Preferably, the BP neural network excitation function that prediction preparatory unit is formulated uses tanh S type activation primitives, BP
Neural network output layer uses linear activation primitive.
Preferably, when training unit establishes BP neural network, established using MATLAB Neural Network Toolbox.
Preferably, load prediction module further includes prediction optimization unit, for phase-change thermal storage station (10) load prediction mould
The sample data of the input quantity of type is normalized by following formula (2):
In formula, XIFor the target after normalization, XiFor input data, XmaxWith XminRespectively XiIn maximum value and minimum
Value.
Preferably, the operation reserve that the energy conservation module of system is formulated is as follows:
The operation principle schematic diagram of the system is as shown in Figure 3.When wind-powered electricity generation rate for incorporation into the power network be more than alternating current price when, no matter wind-powered electricity generation
How power predicts load relationship with phase-change thermal storage station, and using pattern 1, i.e. wind-powered electricity generation is all grid-connected, phase-change thermal storage station alternating current, warp
Ji property is best;When wind-powered electricity generation rate for incorporation into the power network is less than alternating current price, if wind power is more than phase-change thermal storage station and predicts load,
Using pattern 2, i.e. wind-powered electricity generation supply phase-change thermal storage station, extra electric energy charges a battery;If wind power is less than phase-change thermal storage
It stands and predicts load, then pattern 3, i.e. phase-change thermal storage station is used preferentially to use the electric energy of wind-powered electricity generation and accumulator, alternating current is connect when insufficient.
Refering to Fig. 4, the present invention also provides a kind of wind electricity digestion phase-change thermal storage station load prediction side based on neural network
Method, this method is for predicting the load at wind electricity digestion phase-change thermal storage station, wind electricity digestion phase-change thermal storage station (10) packet
It includes electric heating converting system (6), hot storage system (7), control system (8) and heat accumulation room (9), Wind turbines (2) and passes through control
Circuit (3) is connect with inverter circuit (5) with phase-change thermal storage station (10), and utility grid (1) is connect with control circuit (3), this method
The step of include:
According to current weather data, historical load information, the quantity of heat storage of phase-change thermal storage station (10) and heat accumulation temperature, it is based on
Neural network phase-change thermal storage station (10) load forecasting model, and electricity can be dissolved to phase-change thermal storage station and predicted;
Phase-change thermal storage station (10) load and wind-powered electricity generation rate for incorporation into the power network and alternating current price obtained with prediction by wind power
Comparative analysis, make demand response, formulate operation reserve and simultaneously controlled.
Preferably, in it can dissolve the step of electricity is predicted to phase-change thermal storage station, including step:
Acquisition determines the input quantity and output quantity of phase-change thermal storage station (10) load forecasting model based on neural network:
Wherein, the input quantity include at least outdoor temperature, humidity, wind speed, historical load information, intensity of solar radiation,
The quantity of heat storage and heat accumulation temperature at phase-change thermal storage station;The output quantity is to predict that the load of the prediction model of day is output quantity;
Determine the structure of BP neural network and the excitation function of each interlayer;
Wherein, the structure of the BP neural network is three layers of BP neural network, and input layer corresponds to described pre-
The input quantity of model is surveyed, the number of output node layer corresponds to the output quantity of the prediction model, and hidden layer node is several
It is determined according to following formula (1):
M=2n+1 (1)
In formula, m is hidden layer node number, and n is input layer number;
Excitation function uses tanh S type activation primitives, BP neural network output layer to use linear activation primitive;
The sample data of the input quantity of phase-change thermal storage station (10) load forecasting model is normalized by following formula (2)
Processing:
In formula, XIFor the target after normalization, XiFor input data, XmaxWith XminRespectively XiIn maximum value and minimum
Value;
Using MATLAB Neural Network Toolbox BP neural networks, training parameter is determined, start to train, after training,
Obtain prediction result;
Wherein, the training parameter includes training function, frequency of training and training objective.
Preferably, in phase-change thermal storage station (10) load and wind-powered electricity generation rate for incorporation into the power network obtained with prediction by wind power
In the step of with the comparative analysis of alternating current price, making demand response, formulate operation reserve and being controlled, the operation of formulation
Strategy is as follows:
In conclusion wind electricity digestion phase-change thermal storage proposed by the present invention station, it can be achieved that wind-powered electricity generation and phase-change thermal storage station it is effective
In conjunction with by load prediction, obtaining the electricity that dissolves at phase-change thermal storage station, consider time-of-use tariffs, and it is optimal to formulate economy
Operation reserve solves the matching sex chromosome mosaicism of wind-powered electricity generation and phase-change thermal storage station, reduces the fluctuation that wind-powered electricity generation is brought to power grid, can
It meets the needs of users and can realize energy-saving and emission-reduction.
The advantageous effect of technical solution provided by the invention is:Effective knot of wind-powered electricity generation and phase-change thermal storage station can be achieved in the present invention
It closes, by load prediction, obtains the power demand at phase-change thermal storage station, consider time-of-use tariffs, and formulate economical optimal operation
Strategy solves the problems, such as the consumption of wind-powered electricity generation, reduces the fluctuation that wind-powered electricity generation is brought to power grid, can meet the needs of users but also
Realize energy-saving and emission-reduction;It solves the problems, such as the consumption of wind-powered electricity generation, reduces system accumulator configuration capacity, reduce system cost, to the greatest extent
It is likely to reduced the fluctuation that wind-powered electricity generation generates power grid, and gives most economical operation reserve.
Although the invention has been described by way of example and in terms of the preferred embodiments, but it is not for limiting the present invention, any this field
Technical staff without departing from the spirit and scope of the present invention, may be by the methods and technical content of the announcement to this
Inventive technique scheme makes possible variation and modification, therefore, every content without departing from technical solution of the present invention, according to this
The technical spirit of invention belongs to the technology of the present invention to any simple modifications, equivalents, and modifications made by above example
The protection domain of scheme.
Claims (9)
1. a kind of wind electricity digestion phase-change thermal storage station load prediction system based on neural network, for wind electricity digestion phase-change thermal storage
The load of (10) of standing is predicted that wind electricity digestion phase-change thermal storage station (10) includes electric heating converting system (6), hot storage system
(7), control system (8) and heat accumulation room (9), Wind turbines (2) pass through control circuit (3) and inverter circuit (5) and phase-change thermal storage
It stands (10) connection, utility grid (1) connect with control circuit (3), which is characterized in that the system includes:
Load prediction module, for according to current weather data, historical load information, the quantity of heat storage of phase-change thermal storage station (10) and
Heat accumulation temperature is based on neural network phase-change thermal storage station (10) load forecasting model, and can dissolve electricity to phase-change thermal storage station
It is predicted;
Energy conservation module, phase-change thermal storage station (10) load and wind-powered electricity generation for being obtained with prediction by wind power are surfed the Internet
Demand response is made in the comparative analysis of electricity price and alternating current price, formulates operation reserve and is controlled.
2. a kind of wind electricity digestion phase-change thermal storage station load prediction system based on neural network according to claim 1,
It is characterized in that, the load prediction module of the system includes:
Data acquisition unit, for acquiring the input quantity for determining phase-change thermal storage station (10) load forecasting model based on neural network
And output quantity:
Wherein, the input quantity includes at least outdoor temperature, humidity, wind speed, historical load information, intensity of solar radiation, phase transformation
The quantity of heat storage and heat accumulation temperature at heat accumulation station;The output quantity is to predict that the load of the prediction model of day is output quantity;
Predict preparatory unit, the excitation function of structure and each interlayer for determining BP neural network;
Wherein, the structure of the BP neural network is three layers of BP neural network, and input layer corresponds to the prediction mould
The number of the input quantity of type, output node layer corresponds to the output quantity of the prediction model, and node in hidden layer is under
Formula (1) is stated to determine:
M=2n+1 (1)
In formula, m is hidden layer node number, and n is input layer number;
Training unit determines training parameter, starts to train, after training, obtain prediction knot for establishing BP neural network
Fruit;
Wherein, the training parameter includes training function, frequency of training and training objective.
3. a kind of wind electricity digestion phase-change thermal storage station load prediction system based on neural network according to claim 2,
It is characterized in that, the BP neural network excitation function that the prediction preparatory unit is formulated uses tanh S type activation primitives, BP god
Linear activation primitive is used through network output layer.
4. a kind of wind electricity digestion phase-change thermal storage station load prediction system based on neural network according to claim 2,
It is characterized in that, when the training unit establishes BP neural network, is established using MATLAB Neural Network Toolbox.
5. a kind of wind electricity digestion phase-change thermal storage station load prediction system based on neural network according to claim 2,
It is characterized in that, the load prediction module further includes prediction optimization unit, for phase-change thermal storage station (10) load forecasting model
The sample data of input quantity be normalized by following formula (2):
In formula, XIFor the target after normalization, XiFor input data, XmaxWith XminRespectively XiIn maximum value and minimum value.
6. a kind of wind electricity digestion phase-change thermal storage station load prediction system based on neural network according to claim 1,
It is characterized in that, the operation reserve that the energy conservation module of the system is formulated is as follows:
7. a kind of wind electricity digestion phase-change thermal storage station load forecasting method based on neural network, for wind electricity digestion phase-change thermal storage
The load stood predicted, wind electricity digestion phase-change thermal storage station (10) include electric heating converting system (6), hot storage system (7),
Control system (8) and heat accumulation room (9), Wind turbines (2) pass through control circuit (3) and inverter circuit (5) and phase-change thermal storage station
(10) it connects, utility grid (1) is connect with control circuit (3), which is characterized in that including:
According to current weather data, historical load information, the quantity of heat storage of phase-change thermal storage station (10) and heat accumulation temperature, based on nerve
Network establishes phase-change thermal storage station (10) load forecasting model, and can dissolve electricity to phase-change thermal storage station and predict;
Pass through pair of phase-change thermal storage station (10) load and wind-powered electricity generation rate for incorporation into the power network and alternating current price that wind power is obtained with prediction
Than analysis, demand response is made, formulate operation reserve and is controlled.
8. a kind of wind electricity digestion phase-change thermal storage station load forecasting method based on neural network according to claim 7,
It is characterized in that, in it can dissolve the step of electricity is predicted to phase-change thermal storage station, including step:
Acquisition determines the input quantity and output quantity of phase-change thermal storage station (10) load forecasting model based on neural network:
Wherein, the input quantity includes at least outdoor temperature, humidity, wind speed, historical load information, intensity of solar radiation, phase transformation
The quantity of heat storage and heat accumulation temperature at heat accumulation station;The output quantity is to predict that the load of the prediction model of day is output quantity;
Determine the structure of BP neural network and the excitation function of each interlayer;
Wherein, the structure of the BP neural network is three layers of BP neural network, and input layer corresponds to the prediction mould
The number of the input quantity of type, output node layer corresponds to the output quantity of the prediction model, and node in hidden layer is under
Formula (1) is stated to determine:
M=2n+1 (1)
In formula, m is hidden layer node number, and n is input layer number;
Excitation function uses tanh S type activation primitives, BP neural network output layer to use linear activation primitive;
Place is normalized by following formula (2) to the sample data of the input quantity of phase-change thermal storage station (10) load forecasting model
Reason:
In formula, XIFor the target after normalization, XiFor input data, XmaxWith XminRespectively XiIn maximum value and minimum value;
Using MATLAB Neural Network Toolbox BP neural networks, training parameter is determined, start to train, after training, obtain
Prediction result;
Wherein, the training parameter includes training function, frequency of training and training objective.
9. a kind of wind electricity digestion phase-change thermal storage station load forecasting method based on neural network according to claim 7,
It is characterized in that, in phase-change thermal storage station (10) load and wind-powered electricity generation rate for incorporation into the power network and alternating current obtained with prediction by wind power
The comparative analysis of price, makes demand response, and in the step of formulating operation reserve and being controlled, the operation reserve of formulation is such as
Under:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810537740.7A CN108736515A (en) | 2018-05-30 | 2018-05-30 | Wind electricity digestion phase-change thermal storage station load prediction system and method based on neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810537740.7A CN108736515A (en) | 2018-05-30 | 2018-05-30 | Wind electricity digestion phase-change thermal storage station load prediction system and method based on neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108736515A true CN108736515A (en) | 2018-11-02 |
Family
ID=63936774
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810537740.7A Pending CN108736515A (en) | 2018-05-30 | 2018-05-30 | Wind electricity digestion phase-change thermal storage station load prediction system and method based on neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108736515A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110007613A (en) * | 2019-04-10 | 2019-07-12 | 北方工业大学 | Warming prediction method and system for heat storage type electric heater and storage medium |
CN111160653A (en) * | 2019-12-31 | 2020-05-15 | 国网内蒙古东部电力有限公司经济技术研究院 | Distributed energy storage system wind power consumption capacity monitoring method based on cloud computing |
CN111207433A (en) * | 2020-01-15 | 2020-05-29 | 浙江大学 | Long-distance regional heating system based on thermoelectric cooperation and thermoelectric cooperation method |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102062052A (en) * | 2009-11-18 | 2011-05-18 | 中国科学院工程热物理研究所 | Wind and solar hybrid energy storage and power generation integration system and process |
CN202204031U (en) * | 2011-07-26 | 2012-04-25 | 芜湖市科华新型材料应用有限责任公司 | Wind power, photoelectricity and electrical network complementation variable power energy storage and heat supply system |
CN103953966A (en) * | 2014-05-16 | 2014-07-30 | 中国科学院工程热物理研究所 | High-capacity heat storage system and high-capacity heat storage method for increasing wind energy absorption |
CN105928292A (en) * | 2016-04-20 | 2016-09-07 | 山东三九制冷设备有限公司 | Photovoltaic refrigerator system controlled based on load prediction and demand response of neural network |
CN106712086A (en) * | 2017-01-17 | 2017-05-24 | 无锡协鑫分布式能源开发有限公司 | Microgrid optimization control mode |
CN106786753A (en) * | 2016-12-29 | 2017-05-31 | 上海博翎能源科技有限公司 | The system and its adjusting method of the Regional Energy internet of multi-user |
CN106961104A (en) * | 2017-04-06 | 2017-07-18 | 新疆大学 | Wind power forecasting method based on data analysis and combination basis function neural network |
-
2018
- 2018-05-30 CN CN201810537740.7A patent/CN108736515A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102062052A (en) * | 2009-11-18 | 2011-05-18 | 中国科学院工程热物理研究所 | Wind and solar hybrid energy storage and power generation integration system and process |
CN202204031U (en) * | 2011-07-26 | 2012-04-25 | 芜湖市科华新型材料应用有限责任公司 | Wind power, photoelectricity and electrical network complementation variable power energy storage and heat supply system |
CN103953966A (en) * | 2014-05-16 | 2014-07-30 | 中国科学院工程热物理研究所 | High-capacity heat storage system and high-capacity heat storage method for increasing wind energy absorption |
CN105928292A (en) * | 2016-04-20 | 2016-09-07 | 山东三九制冷设备有限公司 | Photovoltaic refrigerator system controlled based on load prediction and demand response of neural network |
CN106786753A (en) * | 2016-12-29 | 2017-05-31 | 上海博翎能源科技有限公司 | The system and its adjusting method of the Regional Energy internet of multi-user |
CN106712086A (en) * | 2017-01-17 | 2017-05-24 | 无锡协鑫分布式能源开发有限公司 | Microgrid optimization control mode |
CN106961104A (en) * | 2017-04-06 | 2017-07-18 | 新疆大学 | Wind power forecasting method based on data analysis and combination basis function neural network |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110007613A (en) * | 2019-04-10 | 2019-07-12 | 北方工业大学 | Warming prediction method and system for heat storage type electric heater and storage medium |
CN110007613B (en) * | 2019-04-10 | 2022-04-29 | 北方工业大学 | Warming prediction method and system for heat storage type electric heater and storage medium |
CN111160653A (en) * | 2019-12-31 | 2020-05-15 | 国网内蒙古东部电力有限公司经济技术研究院 | Distributed energy storage system wind power consumption capacity monitoring method based on cloud computing |
CN111160653B (en) * | 2019-12-31 | 2023-06-27 | 国网内蒙古东部电力有限公司经济技术研究院 | Distributed energy storage system wind power consumption capability monitoring method based on cloud computing |
CN111207433A (en) * | 2020-01-15 | 2020-05-29 | 浙江大学 | Long-distance regional heating system based on thermoelectric cooperation and thermoelectric cooperation method |
CN111207433B (en) * | 2020-01-15 | 2020-12-08 | 浙江大学 | Long-distance regional heating system based on thermoelectric cooperation and thermoelectric cooperation method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Cheng et al. | Energy Internet: Concept and practice exploration | |
Lund | Large-scale urban renewable electricity schemes–Integration and interfacing aspects | |
CN111969603B (en) | Micro-energy network system and cooperative optimization operation control method thereof | |
CN110661246B (en) | Capacity optimization configuration method for urban rail transit photovoltaic energy storage system | |
CN103151797A (en) | Multi-objective dispatching model-based microgrid energy control method under grid-connected operation mode | |
Li et al. | A review of renewable energy applications in buildings in the hot-summer and warm-winter region of China | |
CN105205552B (en) | A kind of independent new energy hybrid power system Method for optimized planning | |
CN106329522A (en) | Multi-energy flexible control system and method for urban and rural residents based on demand side response | |
KR101298500B1 (en) | Micro-Grid Simulation Apparatus and Power Management System | |
CN107910863A (en) | Consider the power distribution network dispatching method that photovoltaic is contributed with workload demand forecast interval | |
CN202841012U (en) | Domestic micro-grid power supply system | |
CN105676824A (en) | Optimized energy dispatching system and method for renewable-energy-source-based combined supply of cooling, heating and power | |
CN108494018A (en) | A kind of wisdom energy demonstration area planing method considering Demand Side Response | |
CN105305472B (en) | A kind of substation capacity optimization method based on multiple-energy-source collaboration energy supply | |
CN108736515A (en) | Wind electricity digestion phase-change thermal storage station load prediction system and method based on neural network | |
CN112710021A (en) | Source-grid-load heat storage pump heating system | |
CN107968428A (en) | A kind of smart home energy distribution system and its implementation | |
CN114139816A (en) | Regional energy optimization method and system based on comprehensive demand response | |
CN109993345A (en) | A kind of isolated operation towards garden is provided multiple forms of energy to complement each other system dynamic economic dispatch method | |
CN108493986A (en) | Distributed power generation coordination optimization dispatching method based on upper and lower dual-layer optimization theory | |
CN107681701A (en) | The hierarchy optimization dispatching method of alternating current-direct current power distribution network | |
CN203014421U (en) | Solar green operating room power supply system | |
CN105576702A (en) | Community energy network system and household energy route | |
CN102208834A (en) | Scheduling system and method of intelligent power grid | |
CN107827256A (en) | A kind of wind-light storage complementation container-type intelligent micro-grid seawater desalination 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181102 |