CN106897796A - Distributed light stores up generated output to operation of air conditioner stability influence index forecasting method - Google Patents

Distributed light stores up generated output to operation of air conditioner stability influence index forecasting method Download PDF

Info

Publication number
CN106897796A
CN106897796A CN201710098970.3A CN201710098970A CN106897796A CN 106897796 A CN106897796 A CN 106897796A CN 201710098970 A CN201710098970 A CN 201710098970A CN 106897796 A CN106897796 A CN 106897796A
Authority
CN
China
Prior art keywords
vgl
air conditioner
generated output
distributed light
stability influence
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
Application number
CN201710098970.3A
Other languages
Chinese (zh)
Inventor
滕云
李新
王泽镝
姚生鹏
赵东升
任佳钰
回茜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenyang University of Technology
Original Assignee
Shenyang University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenyang University of Technology filed Critical Shenyang University of Technology
Priority to CN201710098970.3A priority Critical patent/CN106897796A/en
Publication of CN106897796A publication Critical patent/CN106897796A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/004Artificial life, i.e. computing arrangements simulating life
    • G06N3/006Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06Energy or water supply

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Air Conditioning Control Device (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Operations Research (AREA)

Abstract

The present invention provides a kind of distributed light and stores up generated output to operation of air conditioner stability influence index forecasting method, is related to distributed light storage technical field of power generation.After the method carries out phase space reconfiguration to distributed light storage generated output with the Nonlinear Time Series of operation of air conditioner systematic parameter, set up the distributed light containing application factor and store up generated output to operation of air conditioner stability influence index Mathematical Modeling, the Mathematical Modeling is solved using fuzzy neural network, the stability influence index of subsequent time is predicted for the phase point in the phase space of reconstruct, obtains stability influence exponential forecasting value.The present invention carries out real-time monitoring for light storage with air conditioner load system, the geographical environment parament of measuring system operational factor and system, distributed light storage generated output is predicted to operation of air conditioner stability influence index, the system is controlled in real time according to result of calculation, solar energy can be effectively utilized, the reliability and economy of system operation is significantly improved.

Description

Distributed light stores up generated output to operation of air conditioner stability influence index forecasting method
Technical field
Generated output is stored up to air-conditioning the present invention relates to distributed light storage technical field of power generation, more particularly to a kind of distributed light Operation stability Intrusion Index Forecasting Methodology.
Background technology
Efficiently to utilize the energy, the growing growth of co-generation unit, distributed light storage equipment in co-generation unit A system for complexity is constituted with air conditioner load.Because photovoltaic has fluctuation and uncertainty, photovoltaic generation can give system Substantial amounts of harmonic wave is introduced, so as to influence the quality of power supply, existing research is related to distributed light and stores up generated output to operation of air conditioner The method of stability influence is less, it is impossible to effectively assess light according to operation of power networks status data and geographical meteorology integrated data resource Can storage generates electricity meet the need for electricity of air conditioner load.
The content of the invention
For the defect of prior art, the present invention provides a kind of distributed light and stores up generated output to operation of air conditioner stability shadow Index forecasting method is rung, carrying out distributed light according to distributed light-preserved system and air conditioner load operation characteristic stores up generated output to sky Allocation and transportation row stability influence exponential forecasting assessment, enables each photo-thermal combined generating system and its air conditioner load that is accessed to pacify Entirely, stably, Effec-tive Function.
A kind of distributed light stores up generated output to operation of air conditioner stability influence index forecasting method, comprises the following steps:
Step 1:Set up distributed light storage generated output and operation of air conditioner systematic parameter Nonlinear Time Series, specific method For:
Step 1.1:The systematic parameter of identical time interval measurement wind-powered electricity generation cold supply system, the system are pressed according to time sequencing System parameter includes:Wind speed v, temperature T, air pressure P, humidity W, the intensity of illumination S, air-conditioning of environment where distributed light storage electricity generation system Load total load electric current I and system busbar average voltage V;
Step 1.2:Systematic parameter according to measurement builds following Nonlinear Time Series:
Wherein, vgl1, vgl2..., vglnRepresent wind speed time series, Tgl1, Tgl2..., TglnWhen representing temperature Between sequence, Pgl1, Pgl2..., PglnRepresent air pressure time series, Wgl1, Wgl2..., WglnHumidity time series is represented, Sgl1, Sgl2..., SglnRepresent intensity of illumination time series, Igl1, Igl2..., IglnRepresent total load current time sequence Row, Vgl1, Vgl2..., VglnRepresent system busbar average voltage time series;
Step 2:Phase space reconfiguration is carried out to the Nonlinear Time Series for building using coordinate delay method, method is as follows:
Gustiness vector v gl is reconstructed in n dimension state spacesi', state of temperature vector T gli', atmospheric pressure state vector Pgli', moisture condition vector Wgli', intensity of illumination state vector Sgli', total load current status vector Igli', busbar voltage State vector Vgli' be expressed as:
vgli'={ vgli, vgli+τ..., vgli+(m-1)τ};
Tgli'={ Tgli, Tgli+τ..., Tgli+(m-1)τ};
Pgli'={ Pgli, Pgli+τ..., Pgli+(m-1)τ};
Wgli'={ Wgli, Wgli+τ..., Wgli+(m-1)τ};
Sgli'={ Sgli, Sgli+τ..., Sgli+(m-1)τ};
Igli'={ Igli, Igli+τ..., Igli+(m-1)τ};
Vgli'={ Vgli, Vgli+τ..., Vgli+(m-1)τ};
Wherein, i=1,2 ..., n, τ be time delay, m is Embedded dimensions;
Step 3:Using the phase point in the phase space that step 2 is reconstructed as sample set, the distribution containing application factor is set up Light stores up generated output to operation of air conditioner stability influence index Mathematical Modeling, is shown below:
Wherein, ygli' it is that distributed light stores up generated output to operation of air conditioner stability influence index, kjRepresent operating mode j conditions Application factor corresponding to lower Mathematical Modeling, j is integer, 1≤j≤mgl, mglIt is optimal classification number, max () is phase space reconfiguration Maximum in data afterwards, min () is the minimum value in data after phase space reconfiguration;
Step 4:Distributed light containing application factor is solved using fuzzy neural network and stores up generated output to operation of air conditioner Stability influence index Mathematical Modeling, for the phase point in the phase space of reconstruct to the stability of a system Intrusion Index of subsequent time It is predicted, obtains distributed light and store up generated output to operation of air conditioner stability influence exponential forecasting value, specific method is:
Step 4.1:The system conditions representated by the phase space phase point after reconstruct are entered using population clustering algorithm Row classification, obtains optimal classification number mgl, and to obtain system difference operating condition numbering be 1~mgl;Population clustering algorithm The sample set that is constituted for data after phase space reconfiguration of input, sample set data amount check is Ngl, maximum iteration is τmax
Step 4.2:Phase point in phase space after reconstruct corresponding to operating mode numbering j is extracted, using fuzzy neural Network stores up generated output to the application factor in operation of air conditioner stability influence index Mathematical Modeling to the distributed light set up kjSolved, that is, distributed light stores up what generated output determined to operation of air conditioner stability influence index under the conditions of obtaining operating mode j Mathematical Modeling;
Step 4.3:The corresponding application factor k that will be tried to achievejWith the data input distribution light storage hair after phase space reconfiguration Electricity is exerted oneself to operation of air conditioner stability influence index Mathematical Modeling, is obtained moment distribution light and is stored up generated output to operation of air conditioner Stability influence exponential forecasting value ygli′。
Further, the specific method of the step 4.1 is:
Step 4.1.1:Classification number initialization, mgl=1;
Step 4.1.2:Particle swarm parameter is initialized;M is randomly choosed in phase space phase pointglIndividual value is used as in cluster Center value, and by this mglIndividual cluster centre value is used as population initial value;
Step 4.1.3:Population iterative search is carried out, method of operation classification number m is obtainedglUnder Optimal cluster centers, most Big iterations is τmax, population iteration renewal equation is shown below;
Wherein,For under kth time iteration, i-th speed of particle;I-th particle untill representing kth time iteration Optimum position;Optimum position untill representing kth time iteration in particle populations in all particle positions,Represent i-th Particle kth time iteration position, c1、c2Study constant is represented, rand () is the random number between 0~1, and w is inertia weight, For weighing local optimum ability and global optimum's ability;
Population fitness is calculated with such as minor function;
Wherein, ffitIt is population fitness function, JmIt is the Euclidean distance sum of each particle to cluster centre;
Step 4.1.4:Calculate the Euclidean distance sum JP between cluster centre valuephm, wherein phm=1,2 ..., Ngl
Step 4.1.5:By mglPlus 1, if mgl< Ngl, then repeat step 4.1.2 to 4.1.5, otherwise, performs step 4.1.6;
Step 4.1.6:Match stop number mglFrom 1 to NglCorresponding Euclidean distance sumBy JPphmMost M corresponding to small valueglAs the optimal classification number of operating mode.
Further, the step 4.2 is to application factor kjThe specific method for being solved one by one is:
Step 4.2.1:Duty parameter is initialized, j=1 is made;
Step 4.2.2:The operating mode institute is asked in phase point after reconstruct corresponding to extraction operating mode numbering j in phase space, foundation The neural network model of corresponding application factor, defines neutral net object function and is shown below;
Wherein,It is the desired output of nerve network system after the m times training under jth kind operating mode, kjM () is jth kind Under operating mode the m times training after nerve network system reality output;
Step 4.2.3:Network weight training is carried out, output layer weights ω ' is calculated, right value update formula is shown below;
ω ' (m)=ω ' (m-1)+Δ ω ' (m)+a (ω ' (m-1)-ω ' (m-2))
Wherein, ω ' (m) is the output layer weights after the m times training,η is learning rate, and a is Factor of momentum, η, a ∈ [0,1];Given thresholdWhenWhen, network weight training terminates;The k of network reality outputjI.e. It is the application factor under operating mode j;
Step 4.2.4:J plus 1, if j < mgl, then repeat step 4.2.2 to 4.2.4, otherwise, calculating terminates, obtain 1~ mglThe corresponding application factor of operating mode drag, performs step 4.3.
As shown from the above technical solution, the beneficial effects of the present invention are:The distributed light storage that the present invention is provided generates electricity out Power carries out real-time monitoring to operation of air conditioner stability influence index forecasting method for light storage and air conditioner load system, chooses system System operational factor --- air conditioner load total load electric current, system busbar average voltage, and environmental geography is meteorological where system Ambient parameter --- wind speed, temperature, air pressure, humidity, intensity of illumination, and generated output pair is stored up to distributed light according to monitoring parameter Operation of air conditioner stability influence index is predicted, and the system is controlled in real time according to result of calculation, can be effectively sharp With solar energy, the reliability and economy of system operation are significantly improved.
Brief description of the drawings
Fig. 1 stores up generated output to operation of air conditioner stability influence exponential forecasting for distributed light provided in an embodiment of the present invention Method flow diagram.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiment of the invention is described in further detail.Hereinafter implement Example is not limited to the scope of the present invention for illustrating the present invention.
A kind of distributed wind-power generator is exerted oneself and heat load sync index Forecasting Methodology, as shown in figure 1, specific method is such as It is lower described.
Step 1:Set up distributed light storage generated output and operation of air conditioner systematic parameter Nonlinear Time Series, specific method For:
Step 1.1:The systematic parameter of identical time interval measurement wind-powered electricity generation cold supply system, the system are pressed according to time sequencing System parameter includes:Wind speed v, temperature T, air pressure P, humidity W, the intensity of illumination S, air-conditioning of environment where distributed light storage electricity generation system Load total load electric current I and system busbar average voltage V;
Step 1.2:Systematic parameter according to measurement builds following Nonlinear Time Series:
Wherein, vgl1, vgl2..., vglnRepresent wind speed time series, Tgl1, Tgl2..., TglnWhen representing temperature Between sequence, Pgl1, Pgl2..., PglnRepresent air pressure time series, Wgl1, Wgl2..., WglnHumidity time series is represented, Sgl1, Sgl2..., SglnRepresent intensity of illumination time series, Igl1, Igl2..., IglnRepresent total load current time sequence Row, Vgl1, Vgl2..., VglnRepresent system busbar average voltage time series.
Step 2:Phase space reconfiguration is carried out to the Nonlinear Time Series for building using coordinate delay method, method is as follows:
Gustiness vector v gl is reconstructed in n dimension state spacesi', state of temperature vector T gli', atmospheric pressure state vector Pgli', moisture condition vector Wgli', intensity of illumination state vector Sgli', total load current status vector Igli', busbar voltage State vector Vgli' be expressed as:
vgli'={ vgli, vgli+τ..., vgli+(m-1)τ};
Tgli'={ Tgli, Tgli+τ..., Tgli+(m-1)τ};
Pgli'={ Pgli, Pgli+τ..., Pgli+(m-1)τ};
Wgli'={ Wgli, Wgli+τ..., Wgli+(m-1)τ};
Sgli'={ Sgli, Sgli+τ..., Sgli+(m-1)τ};
Igli'={ Igli, Igli+τ..., Igli+(m-1)τ};
Vgli'={ Vgli, Vgli+τ..., Vgli+(m-1)τ};
Wherein, i=1,2 ..., n, τ be time delay, m is Embedded dimensions.In the present embodiment, select m=12, τ= 80ms。
Then predicted value of the distributed light storage generated output to operation of air conditioner stability influence index is calculated:To phase space weight Data after structure carry out clustering processing, divide data into the classification under different operating modes;Set up the distribution containing application factor Light stores up generated output to operation of air conditioner stability influence index Mathematical Modeling, according to the data after clustering, using nerve net Network calculates the application factor under every kind of operating mode.Generated output is stored up to operation of air conditioner stability influence index mathematics using distributed light Model, is predicted for the data after phase space reconfiguration to the system synchronicity of subsequent time;The distributed light storage generates electricity It is data after phase space reconfiguration to exert oneself to the input of operation of air conditioner stability influence index Mathematical Modeling, is output as distributed light storage Generated output is specific as described in step 3 and step 4 to operation of air conditioner stability influence index.
Step 3:Using the phase point in the phase space that step 2 is reconstructed as sample set, the distribution containing application factor is set up Light stores up generated output to operation of air conditioner stability influence index Mathematical Modeling, is shown below;
Wherein, ygli' it is that distributed light stores up generated output to operation of air conditioner stability influence index, kjRepresent operating mode j conditions Application factor corresponding to lower Mathematical Modeling, j is integer, 1≤j≤mgl, mglIt is optimal classification number, max () is phase space reconfiguration Maximum in data afterwards, min () is the minimum value in data after phase space reconfiguration.
Step 4:Distributed light containing application factor is solved using fuzzy neural network and stores up generated output to operation of air conditioner Stability influence index Mathematical Modeling, for the phase point in the phase space of reconstruct to the stability of a system Intrusion Index of subsequent time It is predicted, obtains distributed light and store up generated output to operation of air conditioner stability influence exponential forecasting value, specific method is:
Step 4.1:The system conditions representated by the phase space phase point after reconstruct are entered using population clustering algorithm Row classification, obtains optimal classification number mgl, and to obtain system difference operating condition numbering be 1~mgl;Population clustering algorithm The sample set that is constituted for data after phase space reconfiguration of input, sample set data amount check is Ngl=700, maximum iteration τmax =50, specific method is as follows:
Step 4.1.1:Classification number initialization, mgl=1;
Step 4.1.2:Particle swarm parameter is initialized;M is randomly choosed in phase space phase pointglIndividual value is used as in cluster Center value, and by this mglIndividual cluster centre value is used as population initial value;
Step 4.1.3:Population iterative search is carried out, method of operation classification number m is obtainedglUnder Optimal cluster centers, most Big iterations is τmax, population iteration renewal equation is shown below;
Wherein,For under kth time iteration, i-th speed of particle;I-th particle untill representing kth time iteration Optimum position;Optimum position untill representing kth time iteration in particle populations in all particle positions,Represent i-th Particle kth time iteration position, c1、c2Study constant is represented, rand () is the random number between 0~1, and w is inertia weight, For weighing local optimum ability and global optimum's ability.In the present embodiment, c1=1.8, c2=1.3, w=0.8, work as random number When rand () is respectively 0.4 or 0.3, particle cluster algorithm optimizing effect is best.
Population fitness is calculated with such as minor function;
Wherein, ffitIt is population fitness function, JmIt is the Euclidean distance sum of each particle to cluster centre;
Step 4.1.4:Calculate the Euclidean distance sum JP between cluster centre valuephm, wherein phm=1,2 ..., Ngl
Step 4.1.5:By mglPlus 1, if mgl< Ngl, then repeat step 4.1.2 to 4.1.5, otherwise, performs step 4.1.6;
Step 4.1.6:Match stop number mglFrom 1 to NglCorresponding Euclidean distance sumBy JPphmMost M corresponding to small valueglAs the optimal classification number of operating mode.In the present embodiment, optimal classification number mgl=3.
Step 4.2:Phase point in phase space after reconstruct corresponding to operating mode numbering j is extracted, using fuzzy neural Network stores up generated output to the application factor in operation of air conditioner stability influence index Mathematical Modeling to the distributed light set up kjSolved, that is, distributed light stores up what generated output determined to operation of air conditioner stability influence index under the conditions of obtaining operating mode j Mathematical Modeling, specific method is as follows.
Step 4.2.1:Duty parameter is initialized, j=1 is made;
Step 4.2.2:The operating mode institute is asked in phase point after reconstruct corresponding to extraction operating mode numbering j in phase space, foundation The neural network model of corresponding application factor, defines neutral net object function and is shown below;
Wherein,It is the desired output of nerve network system after the m times training under jth kind operating mode, kjM () is jth kind Under operating mode the m times training after nerve network system reality output;
Step 4.2.3:Network weight training is carried out, output layer weights ω ' is calculated, right value update formula is shown below;
ω ' (m)=ω ' (m-1)+Δ ω ' (m+a (ω ' (m-1)-ω ' (m-2))
Wherein, ω ' (m) is the output layer weights after the m times training,η is learning rate, and a is Factor of momentum, η, a ∈ [0,1];Given thresholdWhenWhen, network weight training terminates;The k of network reality outputjI.e. It is the application factor under operating mode j;In the present embodiment, setNeutral net node in hidden layer is 14;Training terminates Afterwards, ε (m)=0.0095 is obtained.
Step 4.2.4:J plus 1, if j < mgl, then repeat step 4.2.2 to 4.2.4, otherwise, calculating terminates, obtain 1~ mglThe corresponding application factor of operating mode drag, performs step 4.3;
The application factor asked for successively in this way under three kinds of operating modes is respectively:k1=1.1, k2=0.8, k3=1.35.
Step 4.3:The corresponding application factor k that will be tried to achievejWith the data input distribution light storage hair after phase space reconfiguration Electricity is exerted oneself to operation of air conditioner stability influence index Mathematical Modeling, is obtained moment distribution light and is stored up generated output to operation of air conditioner Stability influence exponential forecasting value ygli′。
In the present embodiment, when wind speed is 3km/h, temperature is 25 DEG C, and intensity of illumination is 1000W/m2, 45%RH, bus electricity It is 35kV to press, and when total load electric current is 15A, obtains this operating mode and belongs to the first kind, according to k1=1.1, obtain now distributed light Storage generated output is 2.1 to operation of air conditioner stability influence index.When stability influence index is 1~1.5, light storage generates electricity out Power influences smaller to operation of air conditioner, and system maintains current state, and when Intrusion Index exceeds the scope, light-preserved system can not remain empty Allocation and transportation row, operation of air conditioner is changed to conventional power source and powers.
The distributed light storage generated output that the present embodiment is provided to operation of air conditioner stability influence index forecasting method, for Light is stored up carries out real-time monitoring, selecting system operational factor with air conditioner load system --- and air conditioner load total load electric current, system are female Environmental geography environment parament --- wind speed, temperature, air pressure, humidity, illumination are strong where line voltage average value, and system Degree, and distributed light storage generated output is predicted to operation of air conditioner stability influence index according to monitoring parameter, according to meter Calculate result to be in real time controlled the system, can effectively utilize solar energy, significantly improve the reliability and warp of system operation Ji property.
Finally it should be noted that:The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although The present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those within the art that:It still may be used Modified with to the technical scheme described in previous embodiment, or which part or all technical characteristic are equal to Replace;And these modifications or replacement, the essence of appropriate technical solution is departed from the model that the claims in the present invention are limited Enclose.

Claims (3)

1. a kind of distributed light stores up generated output to operation of air conditioner stability influence index forecasting method, it is characterised in that:The party Method is comprised the following steps:
Step 1:Distributed light storage generated output and operation of air conditioner systematic parameter Nonlinear Time Series are set up, specific method is:
Step 1.1:The systematic parameter of identical time interval measurement wind-powered electricity generation cold supply system, the system ginseng are pressed according to time sequencing Number includes:Wind speed v, temperature T, air pressure P, humidity W, the intensity of illumination S, air conditioner load of environment where distributed light storage electricity generation system Total load electric current I and system busbar average voltage V;
Step 1.2:Systematic parameter according to measurement builds following Nonlinear Time Series:
vgl 1 , vgl 2 , .... , vgl n Tgl 1 , Tgl 2 , .... , Tgl n Pgl 1 , Pgl 2 , .... , Pgl n Wgl 1 , Wgl 2 , .... , Wgl n Sgl 1 , Sgl 2 , .... , Sgl n Igl 1 , Igl 2 , .... , Igl n Vgl 1 , Vgl 2 , .... , Vgl n ;
Wherein, vgl1, vgl2..., vglnRepresent wind speed time series, Tgl1, Tgl2..., TglnRepresent temperature-time sequence Row, Pgl1, Pgl2..., PglnRepresent air pressure time series, Wgl1, Wgl2..., WglnHumidity time series is represented, Sgl1, Sgl2..., SglnRepresent intensity of illumination time series, Igl1, Igl2..., IglnRepresent total load current time sequence Row, Vgl1, Vgl2..., VglnRepresent system busbar average voltage time series;
Step 2:Phase space reconfiguration is carried out to the Nonlinear Time Series for building using coordinate delay method, method is as follows:
Gustiness vector v gl is reconstructed in n dimension state spacesi', state of temperature vector T gli', atmospheric pressure state vector Pgli′、 Moisture condition vector Wgli', intensity of illumination state vector Sgli', total load current status vector Igli', busbar voltage state to Amount Vgli' be expressed as:
vgli'={ vgli, vgli+τ..., vgli+(m-1)τ};
Tgli'={ Tgli, Tgli+τ..., Tgli+(m-1)τ};
Pgli'={ Pgli, Pgli+τ..., Pgli+(m-1)τ};
Wgli'={ Wgli, Wgli+τ..., Wgli+(m-1)τ};
Sgli'={ Sgli, Sgli+τ..., Sgli+(m-1)τ};
Igli'={ Igli, Igli+τ..., Igli+(m-1)τ};
Vgli'={ Vgli, Vgli+τ..., Vgli+(m-1)τ};
Wherein, i=1,2 ..., n, τ be time delay, m is Embedded dimensions;
Step 3:Using the phase point in the phase space that step 2 is reconstructed as sample set, the distributed light storage containing application factor is set up Generated output is shown below to operation of air conditioner stability influence index Mathematical Modeling;
ygl i ′ = k j · Sgl ′ i 3 · Tgl ′ i 2 · vgl ′ i ( Wgl ′ i · Pgl ′ i ) 1 / k j - Vgl i ′ - m i n ( Vgl i ′ ) m a x ( Igl i ′ ) - Igl i ′
Wherein, ygli' it is that distributed light stores up generated output to operation of air conditioner stability influence index, kjRepresent number under the conditions of operating mode j The corresponding application factor of model is learned, j is integer, 1≤j≤mgl, mglIt is optimal classification number;
Step 4:Distributed light storage generated output containing application factor is solved to operation of air conditioner stabilization using fuzzy neural network Property Intrusion Index Mathematical Modeling, for reconstruct phase space in phase point the stability of a system Intrusion Index of subsequent time is carried out Prediction, obtains distributed light and stores up generated output to operation of air conditioner stability influence exponential forecasting value, and specific method is:
Step 4.1:The system conditions representated by the phase space phase point after reconstruct are divided using population clustering algorithm Class, obtains optimal classification number mgl, and to obtain system difference operating condition numbering be 1~mgl;Population clustering algorithm it is defeated Enter the sample set constituted for data after phase space reconfiguration, sample set data amount check is Ngl, maximum iteration is τmax
Step 4.2:Phase point in phase space after reconstruct corresponding to operating mode numbering j is extracted, using fuzzy neural network Distributed light to being set up stores up generated output to the application factor k in operation of air conditioner stability influence index Mathematical ModelingjEnter Row is solved, that is, distributed light stores up the mathematics that generated output determines to operation of air conditioner stability influence index under the conditions of obtaining operating mode j Model;
Step 4.3:The corresponding application factor k that will be tried to achievefWith the data input distribution light storage generated output after phase space reconfiguration To operation of air conditioner stability influence index Mathematical Modeling, obtain moment distribution light and store up generated output to operation of air conditioner stability Intrusion Index predicted value ygli′。
2. distributed light according to claim 1 stores up generated output to operation of air conditioner stability influence index forecasting method, It is characterized in that:The specific method of the step 4.1 is:
Step 4.1.1:Classification number initialization, mgl=1;
Step 4.1.2:Particle swarm parameter is initialized;M is randomly choosed in phase space phase pointglIndividual value is used as cluster centre Value, and by this mglIndividual cluster centre value is used as population initial value;
Step 4.1.3:Population iterative search is carried out, method of operation classification number m is obtainedglUnder Optimal cluster centers, maximum changes Generation number is τmax, population iteration renewal equation is shown below;
v i D k + 1 = wv i D k + c 1 r a n d ( ) ( pb i D k - x i D k ) + c 2 r a n d ( ) ( gb i D k - x i D k ) x i D k + 1 = x i D k + v i D k + 1
Wherein,For under kth time iteration, i-th speed of particle;I-th particle is optimal untill representing kth time iteration Position;Optimum position untill representing kth time iteration in particle populations in all particle positions,Represent i-th particle Kth time iteration position, c1、c2Study constant is represented, rand () is the random number between 0~1, and w is inertia weight, is used for Balance local optimum ability and global optimum's ability;
Population fitness is calculated with such as minor function;
f f i t = 1 1 + J m
Wherein, ffitIt is population fitness function, JmIt is the Euclidean distance sum of each particle to cluster centre;
Step 4.1.4:Calculate the Euclidean distance sum JP between cluster centre valuephm, wherein phm=1,2 ..., Ngl
Step 4.1.5:By mglPlus 1, if mgl< Ngl, then repeat step 4.1.2 to 4.1.5, otherwise, performs step 4.1.6;
Step 4.1.6:Match stop number mglFrom 1 to NglCorresponding Euclidean distance sumBy JPphmMinimum value Corresponding mglAs the optimal classification number of operating mode.
3. distributed light according to claim 2 stores up generated output to operation of air conditioner stability influence index forecasting method, It is characterized in that:The step 4.2 is to application factor kjThe specific method for being solved one by one is:
Step 4.2.1:Duty parameter is initialized, j=1 is made;
Step 4.2.2:Phase point after reconstruct corresponding to extraction operating mode numbering j in phase space, foundation is asked for corresponding to the operating mode Application factor neural network model, define neutral net object function be shown below:
ϵ ( m ) = 1 2 ( k ^ j ( m ) - k j ( m ) ) 2
Wherein,It is the desired output of nerve network system after the m times training under jth kind operating mode, kjM () is jth kind operating mode The reality output of nerve network system after lower the m times training;
Step 4.2.3:Network weight training is carried out, output layer weights ω ' is calculated, right value update formula is shown below;
ω ' (m)=ω ' (m-1)+△ ω ' (m)+a (ω ' (m-1)-ω ' (m-2))
Wherein, ω ' (m) is the output layer weights after the m times training,η is learning rate, and a is momentum The factor, η, a ∈ [0,1];Given thresholdWhenWhen, network weight training terminates;The k of network reality outputjAs work Application factor under condition j;
Step 4.2.4:J plus 1, if j < mgl, then repeat step 4.2.2 to 4.2.4, otherwise, calculating terminates, and obtains 1~mglWork The corresponding application factor of condition drag, performs step 4.3.
CN201710098970.3A 2017-02-23 2017-02-23 Distributed light stores up generated output to operation of air conditioner stability influence index forecasting method Pending CN106897796A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710098970.3A CN106897796A (en) 2017-02-23 2017-02-23 Distributed light stores up generated output to operation of air conditioner stability influence index forecasting method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710098970.3A CN106897796A (en) 2017-02-23 2017-02-23 Distributed light stores up generated output to operation of air conditioner stability influence index forecasting method

Publications (1)

Publication Number Publication Date
CN106897796A true CN106897796A (en) 2017-06-27

Family

ID=59185840

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710098970.3A Pending CN106897796A (en) 2017-02-23 2017-02-23 Distributed light stores up generated output to operation of air conditioner stability influence index forecasting method

Country Status (1)

Country Link
CN (1) CN106897796A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102915511A (en) * 2012-09-21 2013-02-06 四川大学 Safety monitoring method for neural network model of power-loaded chaotic phase space
CN103301926A (en) * 2013-05-22 2013-09-18 西安交通大学 Operation condition division method for milling system of ball mill in thermal power plant
CN104728974A (en) * 2015-03-20 2015-06-24 云南师范大学 Cold and heat double-effect energy storage air-conditioning system driven by distributed wind energy/photovoltaic independent energy
CN105719028A (en) * 2016-03-08 2016-06-29 北京工业大学 Method for dynamic prediction of air-conditioning loads based on multi-factor chaos support vector machine
CN106374831A (en) * 2016-09-26 2017-02-01 国电南瑞科技股份有限公司 Distributed photovoltaic monitoring system with power generation forecasting and monitoring method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102915511A (en) * 2012-09-21 2013-02-06 四川大学 Safety monitoring method for neural network model of power-loaded chaotic phase space
CN103301926A (en) * 2013-05-22 2013-09-18 西安交通大学 Operation condition division method for milling system of ball mill in thermal power plant
CN104728974A (en) * 2015-03-20 2015-06-24 云南师范大学 Cold and heat double-effect energy storage air-conditioning system driven by distributed wind energy/photovoltaic independent energy
CN105719028A (en) * 2016-03-08 2016-06-29 北京工业大学 Method for dynamic prediction of air-conditioning loads based on multi-factor chaos support vector machine
CN106374831A (en) * 2016-09-26 2017-02-01 国电南瑞科技股份有限公司 Distributed photovoltaic monitoring system with power generation forecasting and monitoring method

Similar Documents

Publication Publication Date Title
Xu et al. Data-driven configuration optimization of an off-grid wind/PV/hydrogen system based on modified NSGA-II and CRITIC-TOPSIS
Zhou et al. Prediction of photovoltaic power output based on similar day analysis, genetic algorithm and extreme learning machine
Behera et al. Solar photovoltaic power forecasting using optimized modified extreme learning machine technique
Ahmadi et al. Application of the Hybrid Big Bang–Big Crunch algorithm for optimal sizing of a stand-alone hybrid PV/wind/battery system
Saeed et al. An optimal approach of wind power assessment using Chebyshev metric for determining the Weibull distribution parameters
Guo et al. Study on short-term photovoltaic power prediction model based on the Stacking ensemble learning
CN107591844A (en) Consider the probabilistic active distribution network robust reconstructing method of node injecting power
CN106845863A (en) A kind of distributed wind-power generator is exerted oneself and heat load sync index Forecasting Methodology
CN107437824A (en) A kind of computational methods of the Area distribution formula power supply allowed capacity based on genetic algorithm
CN104269867B (en) A kind of node power of disturbance transfer distributing equilibrium degree analytical method
Yan et al. Solar radiation forecasting using artificial neural network for local power reserve
CN103208037B (en) A kind of power forecasting method based on on-line correction being applied to new energy power station
CN103106544A (en) Photovoltaic power generation prediction system based on T-S-type fuzzy neural network
Li et al. Day-ahead hourly photovoltaic generation forecasting using extreme learning machine
CN105703396A (en) Multi-turbine characterization equivalent modeling method of double-fed wind power plant
CN109034464A (en) A kind of method that short-term photovoltaic generating system power prediction and result are checked
CN106712065A (en) Prediction method of indexes of influence of electric card charging on power distribution network active loss
CN109272134A (en) A kind of region photovoltaic electric station grid connection power forecasting method considering system loss
CN107947228A (en) The Stochastic Stability Analysis method of electric system containing wind-powered electricity generation based on Markov theories
Khanahmadi et al. A novel economic method of battery modeling in stand-alone renewable energy systems to reduce life cycle costs
CN105281371A (en) Telescopic active static safety domain taking wind power generation into account
Ren et al. Analysis of the performance of the multi-objective hybrid hydropower-photovoltaic-wind system to reduce variance and maximum power generation by developed owl search algorithm
CN109978277A (en) Region online load prediction technique and device in photovoltaic power generation
Vohra et al. End-to-end learning with multiple modalities for system-optimised renewables nowcasting
Yadav et al. Short-term pv power forecasting using adaptive neuro-fuzzy inference system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
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: 20170627