CN116613792B - Near zero energy consumption building community energy storage system and method based on energy consumption data - Google Patents
Near zero energy consumption building community energy storage system and method based on energy consumption data Download PDFInfo
- Publication number
- CN116613792B CN116613792B CN202310572118.0A CN202310572118A CN116613792B CN 116613792 B CN116613792 B CN 116613792B CN 202310572118 A CN202310572118 A CN 202310572118A CN 116613792 B CN116613792 B CN 116613792B
- Authority
- CN
- China
- Prior art keywords
- energy
- time period
- data
- energy consumption
- energy storage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 98
- 238000004146 energy storage Methods 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 62
- 238000010801 machine learning Methods 0.000 claims abstract description 40
- 238000012360 testing method Methods 0.000 claims abstract description 28
- 238000010248 power generation Methods 0.000 claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 230000007613 environmental effect Effects 0.000 claims description 50
- 238000005286 illumination Methods 0.000 claims description 25
- 239000013598 vector Substances 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000005611 electricity Effects 0.000 claims description 12
- 238000001228 spectrum Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 229910021417 amorphous silicon Inorganic materials 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 7
- 229910021421 monocrystalline silicon Inorganic materials 0.000 claims description 7
- 229910021420 polycrystalline silicon Inorganic materials 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 5
- 239000002699 waste material Substances 0.000 abstract description 6
- 210000004027 cell Anatomy 0.000 description 6
- 238000010276 construction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Abstract
The invention discloses a near-zero energy consumption building community energy storage system and method based on energy consumption data, and relates to the technical field of near-zero energy consumption building community energy storage, wherein a photovoltaic collection module is arranged to collect model training data of each test area, a photovoltaic power generation model training module is arranged to train a machine learning model for predicting the power value of a photovoltaic unit area by using the model training data, a community energy information collection module is arranged to collect energy consumption data and application environment characteristic data of the near-zero energy consumption building community, a community energy storage analysis module is arranged to calculate the area of a photovoltaic panel required to be set in the near-zero energy consumption building community and the maximum energy storage value of an energy storage system based on the energy consumption data, the application environment characteristic data and the machine learning model; the waste of generated energy and the shortage of community power supply are avoided, and the power utilization efficiency of the building community with near zero energy consumption is improved.
Description
Technical Field
The invention belongs to the energy storage technology of near-zero energy consumption building communities, and particularly relates to a near-zero energy consumption building community energy storage system and method based on energy consumption data.
Background
The near zero energy consumption building community is a building concept focusing on energy efficiency and environmental sustainability, and aims to reduce energy consumption to the maximum extent and improve energy utilization efficiency. Photovoltaic systems, one of the important energy supply modes, meet the power demand of communities by converting solar energy into electric energy. However, how to determine the proper photovoltaic panel area and the maximum energy storage value of the energy storage system is a critical issue in the construction and planning process of the photovoltaic system.
Currently, photovoltaic system construction and planning is generally based on general design criteria and empirical values, lacking in accurate analysis and optimization of specific community energy usage data. This results in the following disadvantages:
waste of generated energy: the lack of photovoltaic panel area planning based on energy consumption data may cause the generated energy of the photovoltaic system to exceed the actual demands of communities, thereby causing energy waste.
The power supply of the community is insufficient: if the photovoltaic system is insufficient in scale, the power requirements of communities cannot be met, and energy shortage and unstable power supply conditions can be caused.
The energy utilization efficiency is low: current photovoltaic system construction and planning lacks optimization for energy storage systems, and energy storage technologies are not fully utilized to balance supply and demand differences, so that energy utilization efficiency is low.
Therefore, the invention provides a near zero energy consumption building community energy storage system and method based on energy consumption data.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides the energy storage system and the method for the near-zero energy consumption building community based on the energy consumption data, so that the waste of generated energy and the shortage of community power supply are avoided, and the electricity utilization efficiency of the near-zero energy consumption building community is improved.
In order to achieve the above objective, an embodiment 1 of the present invention proposes a near zero energy consumption building community energy storage system based on energy consumption data, which includes a photovoltaic collection module, a photovoltaic power generation model training module, a community energy information collection module, and a community energy storage analysis module; wherein, each module is connected by a wired and/or wireless network mode;
The photovoltaic sign collection module is mainly used for collecting model training data of each test area;
the model training data comprise environmental characteristic data and photovoltaic power generation power data;
The environmental characteristic data comprise average illumination intensity, average solar spectrum distribution, average temperature, photovoltaic module conversion efficiency and photovoltaic cell materials of a plurality of test areas in each preset energy utilization time period; the test areas are pre-selected test places with different environmental characteristic data so as to acquire training data;
The energy utilization time period is divided into a plurality of time periods in advance, and each time period is used as an energy utilization time period;
Wherein the average illumination intensity is an average value of illumination intensity in each energy utilization time period; the illumination intensity is obtained in real time by using an illumination intensity sensor, and the average illumination intensity is obtained by dividing the sum of the illumination intensities at all the moments in the energy utilization time period by the duration of the energy utilization time period;
Wherein, the average distribution of solar spectrum refers to the average energy density value of sunlight under different sampled wavelength values; for different wavelength values, dividing the average energy density value of the energy utilization time period by the duration of the energy utilization time period according to the sum of the energy density values corresponding to the wavelength values;
Wherein the average temperature is an average value of the temperatures in each energy utilization time period; the temperature is obtained in real time by using a temperature sensor, and the average temperature is obtained by dividing the sum of the temperatures at all times in the energy utilization time period by the duration of the energy utilization time period;
The photovoltaic module conversion efficiency is an inherent attribute value of the photovoltaic module, and is determined when the type of the photovoltaic module is selected;
The photovoltaic cell comprises monocrystalline silicon, polycrystalline silicon and amorphous silicon, wherein the monocrystalline silicon, the polycrystalline silicon and the amorphous silicon are respectively represented by discrete values;
The photovoltaic power generation power data are power values of unit areas generated by corresponding environmental characteristic data in each preset energy utilization time period in each test area; the power is obtained in real time through a power sensor, and the sum of the power at all times in the energy utilization time period is divided by the area of the photovoltaic panel to be used to obtain a power value of a unit area;
The photovoltaic sign collection module sends the collected model training data of each test area to the photovoltaic power generation model training module;
The photovoltaic power generation model training module is mainly used for training a machine learning model for predicting the power value of the photovoltaic unit area by using model training data;
the mode of training a machine learning model for predicting the power value of the photovoltaic unit area is as follows:
The number of the usable time period is marked as j, the environmental characteristic data sets of all the test areas of the jth usable time period are marked as Cj, and the number of each group of environmental characteristic data sets in the environmental characteristic data sets Cj is marked as Cj; the power value set of the unit area corresponding to the environment characteristic data set Cj of the jth energy utilization time period is marked as Bj;
For the j energy utilization time period, combining each group of environmental characteristic data into a characteristic vector form, wherein elements in the characteristic vector comprise average illumination intensity, average energy density value at each wavelength value of the sun, average temperature, photovoltaic module conversion efficiency and photovoltaic cell materials; the set of all feature vectors is used as an input of a machine learning model, the machine learning model takes a predicted power value of a unit area for each group of environmental feature data as an output, the power value of the unit area for the cj-th group of environmental feature data is used as a prediction target, and the sum of prediction error degrees of the power values of the unit areas for the cj-th group of environmental feature data is used as a training target; the calculation formula of the prediction error degree is as follows; zcj= (acj-wcj) 2, wherein zcj is a prediction error degree, acj is a predicted power value of unit area corresponding to the environmental characteristic data of the cj group, wcj is a power value of unit area of the cj in a power value set Bj of unit area corresponding to the environmental characteristic data of the cj group; training the machine learning model until the sum of prediction accuracy reaches convergence, and stopping training;
The photovoltaic power generation model training module sends the machine learning model corresponding to each energy utilization time period after the training is completed to the community energy storage analysis module;
The community energy information collection module is mainly used for collecting energy consumption data of a near-zero energy consumption building community and application environment characteristic data;
The energy consumption data comprise the electricity consumption of a near-zero energy consumption building community in each energy consumption time period; the electricity consumption of the near-zero energy consumption building community refers to the total amount of power used in each energy consumption time period acquired by using a power sensor;
The application environment characteristic data comprise environment characteristic data of the near-zero energy consumption building community in each energy utilization time period;
The community energy information collection module sends energy consumption data of the near zero energy consumption building community and application environment characteristic data to the community energy storage analysis module;
The community energy storage analysis module is mainly used for calculating the area of a photovoltaic panel required to be set in a near-zero energy consumption building community and the maximum energy storage value of an energy storage system based on energy consumption data, application environment characteristic data and a machine learning model;
the mode of calculating the area of the photovoltaic panel that needs to be set up at near zero energy consumption building community is:
Combining the environment characteristic data of each energy utilization time period in the application environment characteristic data into a characteristic vector form, and inputting the characteristic vector form into a corresponding machine learning model to obtain a predicted power value of a unit area generated in each energy utilization time period;
marking the predicted power value of the unit area in the jth energy utilization time period as Sj, and marking the power consumption of the building community with near zero energy consumption in the jth energy utilization time period as Yj;
setting an area variable x for the required photovoltaic panel area, wherein the calculation formula of the area variable x is as follows
Calculating energy storage power Zj in the jth energy utilization time period; wherein, the calculation formula of the energy storage power Zj is Zj=Sj x-Yj;
The mode for calculating the maximum energy storage value of the energy storage system is as follows:
the number of usable time periods is denoted J;
for a J-th energy use time period, calculating J remaining energy storage values from the energy use time period, and marking the k-th remaining energy storage value as Wjk, wherein k=0, 1, … J-1; the calculation formula of the residual energy storage value Wjk is Wherein% is a remainder function;
And finding out the maximum residual energy storage value Wjk from all the residual energy storage values Wjk of all the energy utilization time periods, wherein the maximum residual energy storage value is the maximum energy storage value of the energy storage system.
According to embodiment 2 of the invention, a near zero energy consumption building community energy storage method based on energy consumption data is provided, which comprises the following steps:
step one: collecting model training data of each test area;
step two: training a machine learning model for predicting the power value of the photovoltaic unit area by using model training data;
step three: collecting energy consumption data and application environment characteristic data of a near-zero energy consumption building community;
Step four: based on the energy consumption data, the application environment characteristic data and the machine learning model, calculating the area of the photovoltaic panel required to be set in the near-zero energy consumption building community, and obtaining the maximum energy storage value of the energy storage system based on the area of the photovoltaic panel.
Compared with the prior art, the invention has the beneficial effects that:
According to the method, model training data of each test area are collected in advance, a machine learning model for predicting the power value of the photovoltaic unit area is trained by using the model training data, energy consumption data and application environment characteristic data of a near-zero energy consumption building community are collected, the area of a photovoltaic panel required to be arranged in the near-zero energy consumption building community is calculated based on the energy consumption data, the application environment characteristic data and the machine learning model, and the maximum energy storage value of an energy storage system is obtained based on the area of the photovoltaic panel; before the photovoltaic system of the near-zero energy consumption building community is built, a proper photovoltaic panel area and the maximum energy storage value of the energy storage system are planned for the photovoltaic system, waste of generated energy and the shortage of community power supply are avoided, and the electricity utilization efficiency of the near-zero energy consumption building community is improved.
Drawings
FIG. 1 is a block diagram of a near zero energy consumption building community energy storage system of example 1 of the present invention;
Fig. 2 is a flow chart of a near zero energy consumption building community energy storage method in embodiment 2 of the invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, a near zero energy consumption building community energy storage system based on energy consumption data comprises a photovoltaic collection module, a photovoltaic power generation model training module, a community energy information collection module and a community energy storage analysis module; wherein, each module is connected by a wired and/or wireless network mode;
The photovoltaic sign collection module is mainly used for collecting model training data of each test area;
the model training data comprise environmental characteristic data and photovoltaic power generation power data;
In a preferred embodiment, the environmental characteristic data comprises average illumination intensity, solar spectrum average distribution, average temperature, photovoltaic module conversion efficiency and photovoltaic cell material of a plurality of test areas in each preset energy utilization time period; the test areas are pre-selected test places with different environmental characteristic data so as to acquire training data;
The energy utilization time period is divided into a plurality of time periods in advance, and each time period is used as an energy utilization time period; the annual division mode can be specifically divided according to actual requirements or a photovoltaic module power generation rule and community energy utilization habits, such as monthly division or quarterly division;
Wherein the average illumination intensity is an average value of illumination intensity in each energy utilization time period; the illumination intensity is obtained in real time by using an illumination intensity sensor, and the average illumination intensity is obtained by dividing the sum of the illumination intensities at all the moments in the energy utilization time period by the duration of the energy utilization time period;
The energy density distribution of the solar spectrum refers to the distribution of solar radiation energy in different wavelength ranges; the solar spectrum can be divided into different wavelength ranges of visible light, ultraviolet light, infrared light and the like, and the energy density corresponding to each wavelength range is different; the energy density distribution can be represented by a solar spectrum curve showing the energy density of solar radiation at different wavelengths; solar spectrum curves generally have a wavelength on the horizontal axis and an energy density on the vertical axis; therefore, the energy density values under different wavelength values can be obtained by performing wavelength sampling on the energy density distribution of the solar spectrum to discretize;
Wherein, the average distribution of solar spectrum refers to the average energy density value of sunlight under different sampled wavelength values; for different wavelength values, dividing the average energy density value of the energy utilization time period by the duration of the energy utilization time period according to the sum of the energy density values corresponding to the wavelength values;
Wherein the average temperature is an average value of the temperatures in each energy utilization time period; the temperature is obtained in real time by using a temperature sensor, and the average temperature is obtained by dividing the sum of the temperatures at all times in the energy utilization time period by the duration of the energy utilization time period;
The photovoltaic module conversion efficiency is an inherent attribute value of the photovoltaic module, and is determined when the type of the photovoltaic module is selected;
The photovoltaic cell comprises monocrystalline silicon, polycrystalline silicon and amorphous silicon, wherein the monocrystalline silicon, the polycrystalline silicon and the amorphous silicon are respectively represented by discrete values; for example, single crystal silicon is 0, polycrystalline silicon is 1, amorphous silicon is 2;
The photovoltaic power generation power data are power values of unit areas generated by corresponding environmental characteristic data in each preset energy utilization time period in each test area; the power is obtained in real time through a power sensor, and the sum of the power at all times in the energy utilization time period is divided by the area of the photovoltaic panel to be used to obtain a power value of a unit area;
The photovoltaic sign collection module sends the collected model training data of each test area to the photovoltaic power generation model training module;
The photovoltaic power generation model training module is mainly used for training a machine learning model for predicting the power value of the photovoltaic unit area by using model training data;
in a preferred embodiment, the machine learning model that predicts the power value per unit area of the photovoltaic is trained in the following manner:
The number of the usable time period is marked as j, the environmental characteristic data sets of all the test areas of the jth usable time period are marked as Cj, and the number of each group of environmental characteristic data sets in the environmental characteristic data sets Cj is marked as Cj; the power value set of the unit area corresponding to the environment characteristic data set Cj of the jth energy utilization time period is marked as Bj; it can be understood that the power value of the cj unit area in the power value set Bj of the unit area corresponds to the environmental characteristic data of the cj group;
For the j energy utilization time period, combining each group of environmental characteristic data into a characteristic vector form, wherein elements in the characteristic vector comprise average illumination intensity, average energy density value at each wavelength value of the sun, average temperature, photovoltaic module conversion efficiency and photovoltaic cell materials; the set of all feature vectors is used as an input of a machine learning model, the machine learning model takes a predicted power value of a unit area for each group of environmental feature data as an output, the power value of the unit area for the cj-th group of environmental feature data is used as a prediction target, and the sum of prediction error degrees of the power values of the unit areas for the cj-th group of environmental feature data is used as a training target; the calculation formula of the prediction error degree is as follows; zcj= (acj-wcj) 2, wherein zcj is a prediction error degree, acj is a predicted power value of unit area corresponding to the environmental characteristic data of the cj group, wcj is a power value of unit area of the cj in a power value set Bj of unit area corresponding to the environmental characteristic data of the cj group; training the machine learning model until the sum of prediction accuracy reaches convergence, and stopping training; preferably, the machine learning model is any one of a deep neural network model or a deep belief network model;
it should be noted that, other model parameters of the machine learning model, such as the depth of the network model, the number of neurons in each layer, the activation function used by the network model, the convergence condition, the verification set proportion of the training set test set, the loss function and the like are all realized through actual engineering, and are obtained after experimental tuning is continuously performed;
The photovoltaic power generation model training module sends the machine learning model corresponding to each energy utilization time period after the training is completed to the community energy storage analysis module;
The community energy information collection module is mainly used for collecting energy consumption data of a near-zero energy consumption building community and application environment characteristic data;
in a preferred embodiment, the energy usage data includes an amount of energy used by the near zero energy consumption building community for each energy usage time period; the electricity consumption of the near-zero energy consumption building community refers to the total amount of power used in each energy consumption time period acquired by using a power sensor;
The application environment characteristic data comprise environment characteristic data of the near-zero energy consumption building community in each energy utilization time period;
The community energy information collection module sends energy consumption data of the near zero energy consumption building community and application environment characteristic data to the community energy storage analysis module;
The community energy storage analysis module is mainly used for calculating the area of a photovoltaic panel required to be set in a near-zero energy consumption building community and the maximum energy storage value of an energy storage system based on energy consumption data, application environment characteristic data and a machine learning model;
In a preferred embodiment, the area of photovoltaic panels that need to be located in a near zero energy consumption building community is calculated by:
Combining the environment characteristic data of each energy utilization time period in the application environment characteristic data into a characteristic vector form, and inputting the characteristic vector form into a corresponding machine learning model to obtain a predicted power value of a unit area generated in each energy utilization time period;
marking the predicted power value of the unit area in the jth energy utilization time period as Sj, and marking the power consumption of the building community with near zero energy consumption in the jth energy utilization time period as Yj;
setting an area variable x for the required photovoltaic panel area, wherein in the jth energy utilization time period, the generated total power value is Sj x; the total power value generated by the building community with near zero energy consumption in one year is sigma j x Sj, and the total power consumption is sigma j Yj; therefore, the calculation formula of the area variable x is
It should be understood that whenThe energy storage system can not waste generated electric power when the electricity consumption requirement is met, but in the j energy consumption time period, if the electricity consumption is smaller than the generated electricity consumption, the redundant electric power is required to be stored by the energy storage system, and if the electricity consumption is larger than the generated electricity consumption, the stored electric power is required to be extracted from the energy storage system, so that the maximum energy storage value of the energy storage device is required to be large enough, and the electric power is prevented from being wasted due to full storage of the energy storage device;
calculating energy storage power Zj in the jth energy utilization time period; wherein, the calculation formula of the energy storage power Zj is Zj=Sj x-Yj; if Zj is less than 0, the electric power value needing to be released is shown as |zj|;
calculating the maximum energy storage value of the energy storage system;
The mode of calculating the maximum energy storage value is as follows:
the number of usable time periods is denoted J;
for a J-th energy use time period, calculating J remaining energy storage values from the energy use time period, and marking the k-th remaining energy storage value as Wjk, wherein k=0, 1, … J-1; the calculation formula of the residual energy storage value Wjk is Wherein% is a remainder function; it is understood that Wjk refers to the value of the stored power from the jth energy use time period to the kth energy use time period that follows;
And finding out the maximum residual energy storage value Wjk from all the residual energy storage values Wjk of all the energy utilization time periods, wherein the maximum residual energy storage value is the maximum energy storage value of the energy storage system.
As shown in fig. 2, a near zero energy consumption building community energy storage method based on energy consumption data comprises the following steps:
step one: collecting model training data of each test area;
step two: training a machine learning model for predicting the power value of the photovoltaic unit area by using model training data;
step three: collecting energy consumption data and application environment characteristic data of a near-zero energy consumption building community;
Step four: based on the energy consumption data, the application environment characteristic data and the machine learning model, calculating the area of the photovoltaic panel required to be set in the near-zero energy consumption building community, and obtaining the maximum energy storage value of the energy storage system based on the area of the photovoltaic panel.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas which are obtained by acquiring a large amount of data and performing software simulation to obtain the closest actual situation, and preset parameters and preset thresholds in the formulas are set by a person skilled in the art according to the actual situation or are obtained by simulating a large amount of data.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (5)
1. The near zero energy consumption building community energy storage system based on energy consumption data is characterized by comprising a photovoltaic collection module, a photovoltaic power generation model training module, a community energy information collection module and a community energy storage analysis module; wherein, each module is connected by a wired and/or wireless network mode;
the photovoltaic sign collection module is used for collecting model training data of each test area and sending the collected model training data of each test area to the photovoltaic power generation model training module;
the photovoltaic power generation model training module is used for training a machine learning model for predicting the power value of the photovoltaic unit area by using model training data, and transmitting the machine learning model corresponding to each energy utilization time period after the training is completed to the community energy storage analysis module;
The community energy information collection module is used for collecting energy data and application environment characteristic data of the near-zero energy consumption building community and sending the energy data and the application environment characteristic data of the near-zero energy consumption building community to the community energy storage analysis module;
the community energy storage analysis module is used for calculating the area of the photovoltaic panel required to be set in the near-zero energy consumption building community and the maximum energy storage value of the energy storage system based on the energy consumption data, the application environment characteristic data and the machine learning model;
the mode of training a machine learning model for predicting the power value of the photovoltaic unit area is as follows:
The number of the usable time period is marked as j, the environmental characteristic data sets of all the test areas of the jth usable time period are marked as Cj, and the number of each group of environmental characteristic data sets in the environmental characteristic data sets Cj is marked as Cj; the power value set of the unit area corresponding to the environment characteristic data set Cj of the jth energy utilization time period is marked as Bj;
For the j energy utilization time period, combining each group of environmental characteristic data into a characteristic vector form, wherein elements in the characteristic vector comprise average illumination intensity, average energy density value at each wavelength value of the sun, average temperature, photovoltaic module conversion efficiency and photovoltaic cell materials; the set of all feature vectors is used as an input of a machine learning model, the machine learning model takes a predicted power value of a unit area for each group of environmental feature data as an output, the power value of the unit area for the cj-th group of environmental feature data is used as a prediction target, and the sum of prediction error degrees of the power values of the unit areas for the cj-th group of environmental feature data is used as a training target; the calculation formula of the prediction error degree is as follows; zcj= (acj-wcj) 2, wherein zcj is a prediction error degree, acj is a predicted power value of unit area corresponding to the environmental characteristic data of the cj group, wcj is a power value of unit area of the cj in a power value set Bj of unit area corresponding to the environmental characteristic data of the cj group; training the machine learning model until the sum of prediction accuracy reaches convergence, and stopping training;
the mode of calculating the area of the photovoltaic panel that needs to be set up at near zero energy consumption building community is:
Combining the environment characteristic data of each energy utilization time period in the application environment characteristic data into a characteristic vector form, and inputting the characteristic vector form into a corresponding machine learning model to obtain a predicted power value of a unit area generated in each energy utilization time period;
marking the predicted power value of the unit area in the jth energy utilization time period as Sj, and marking the power consumption of the building community with near zero energy consumption in the jth energy utilization time period as Yj;
setting an area variable x for the required photovoltaic panel area, wherein the calculation formula of the area variable x is as follows
Calculating energy storage power Zj in the jth energy utilization time period; wherein, the calculation formula of the energy storage power Zj is Zj=Sj x-Yj;
The mode for calculating the maximum energy storage value of the energy storage system is as follows:
the number of energy use time periods is marked as J;
for a J-th energy use time period, calculating J remaining energy storage values from the energy use time period, and marking the k-th remaining energy storage value as Wjk, wherein k=0, 1, … J-1; the calculation formula of the residual energy storage value Wjk is Wherein% is a remainder function;
And finding out the maximum residual energy storage value Wjk from all the residual energy storage values Wjk of all the energy utilization time periods, wherein the maximum residual energy storage value is the maximum energy storage value of the energy storage system.
2. The near zero energy consumption building community energy storage system based on energy usage data of claim 1, wherein the model training data comprises environmental characteristic data and photovoltaic power generation power data;
The environmental characteristic data comprise average illumination intensity, average solar spectrum distribution, average temperature, photovoltaic module conversion efficiency and photovoltaic cell materials of a plurality of test areas in each preset energy utilization time period; the test areas are pre-selected test places with different environmental characteristic data so as to acquire training data;
The energy utilization time period refers to dividing one year into a plurality of time periods in advance, and each time period is taken as an energy utilization time period.
3. A near zero energy consumption building community energy storage system based on energy usage data according to claim 2, wherein the average illumination intensity is an average of illumination intensities during each energy usage time period; the illumination intensity is obtained in real time by using an illumination intensity sensor, and the average illumination intensity is obtained by dividing the sum of the illumination intensities at all the moments in the energy utilization time period by the duration of the energy utilization time period;
The average distribution of solar spectrum refers to average energy density value of sunlight under different sampled wavelength values; for different wavelength values, dividing the average energy density value of the energy utilization time period by the duration of the energy utilization time period according to the sum of the energy density values corresponding to the wavelength values;
the average temperature is the average value of the temperature in each energy utilization time period; the temperature is obtained in real time by using a temperature sensor, and the average temperature is obtained by dividing the sum of the temperatures at all times in the energy utilization time period by the duration of the energy utilization time period;
The conversion efficiency of the photovoltaic module is an inherent attribute value of the photovoltaic module;
the photovoltaic cell comprises monocrystalline silicon, polycrystalline silicon and amorphous silicon, wherein the monocrystalline silicon, the polycrystalline silicon and the amorphous silicon are respectively represented by discrete values;
The photovoltaic power generation power data are power values of unit areas generated by corresponding environmental characteristic data in each preset energy utilization time period in each test area; the power is obtained in real time by a power sensor, and the sum of the power at all times in the energy utilization time period is divided by the area of the photovoltaic panel to be used to obtain the power value of a unit area.
4. A near zero energy consumption building community energy storage system based on energy usage data as claimed in claim 3, wherein the energy usage data comprises the amount of electricity used by the near zero energy consumption building community in each energy usage time period; the electricity consumption of the near-zero energy consumption building community refers to the total amount of power used in each energy consumption time period acquired by using a power sensor;
The application environment characteristic data comprise environment characteristic data of the near-zero energy consumption building community in each energy utilization time period.
5. A near zero energy consumption building community energy storage method based on energy consumption data, which is realized based on the near zero energy consumption building community energy storage system based on energy consumption data according to any one of claims 1 to 4, and is characterized by comprising the following steps:
step one: collecting model training data of each test area;
step two: training a machine learning model for predicting the power value of the photovoltaic unit area by using model training data;
step three: collecting energy consumption data and application environment characteristic data of a near-zero energy consumption building community;
Step four: calculating the area of a photovoltaic panel which needs to be set in a near-zero energy consumption building community based on energy consumption data, application environment characteristic data and a machine learning model, and obtaining the maximum energy storage value of an energy storage system based on the area of the photovoltaic panel;
the mode of training a machine learning model for predicting the power value of the photovoltaic unit area is as follows:
The number of the usable time period is marked as j, the environmental characteristic data sets of all the test areas of the jth usable time period are marked as Cj, and the number of each group of environmental characteristic data sets in the environmental characteristic data sets Cj is marked as Cj; the power value set of the unit area corresponding to the environment characteristic data set Cj of the jth energy utilization time period is marked as Bj;
For the j energy utilization time period, combining each group of environmental characteristic data into a characteristic vector form, wherein elements in the characteristic vector comprise average illumination intensity, average energy density value at each wavelength value of the sun, average temperature, photovoltaic module conversion efficiency and photovoltaic cell materials; the set of all feature vectors is used as an input of a machine learning model, the machine learning model takes a predicted power value of a unit area for each group of environmental feature data as an output, the power value of the unit area for the cj-th group of environmental feature data is used as a prediction target, and the sum of prediction error degrees of the power values of the unit areas for the cj-th group of environmental feature data is used as a training target; the calculation formula of the prediction error degree is as follows; zcj= (acj-wcj) 2, wherein zcj is a prediction error degree, acj is a predicted power value of unit area corresponding to the environmental characteristic data of the cj group, wcj is a power value of unit area of the cj in a power value set Bj of unit area corresponding to the environmental characteristic data of the cj group; training the machine learning model until the sum of the prediction accuracy reaches convergence, and stopping training.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310572118.0A CN116613792B (en) | 2023-05-22 | Near zero energy consumption building community energy storage system and method based on energy consumption data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310572118.0A CN116613792B (en) | 2023-05-22 | Near zero energy consumption building community energy storage system and method based on energy consumption data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116613792A CN116613792A (en) | 2023-08-18 |
CN116613792B true CN116613792B (en) | 2024-06-07 |
Family
ID=
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012018167A1 (en) * | 2010-08-06 | 2012-02-09 | 지솔라(주) | Device for generating grid-connected photovoltaic power and method for operating same |
CN103944175A (en) * | 2014-03-28 | 2014-07-23 | 上海电力设计院有限公司 | Wind-solar-storage combined power generation system output characteristic optimization method |
KR102064918B1 (en) * | 2019-06-20 | 2020-01-10 | (주) 씨이랩 | Energy diagnosis system and method with high accuracy for realization of zero energy building |
WO2020249125A1 (en) * | 2019-06-14 | 2020-12-17 | 第四范式(北京)技术有限公司 | Method and system for automatically training machine learning model |
CN112803567A (en) * | 2021-01-29 | 2021-05-14 | 西安交通大学 | Parameter optimization design method and system based on intelligent building optical storage power supply equipment |
CN113224756A (en) * | 2021-05-11 | 2021-08-06 | 湖南中大设计院有限公司 | Method applied to photovoltaic building integrated optimal installed capacity measurement and calculation |
CN114970959A (en) * | 2022-04-24 | 2022-08-30 | 中国能源建设集团浙江省电力设计院有限公司 | Low-energy-consumption building power distribution system planning method considering source network load storage characteristics |
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012018167A1 (en) * | 2010-08-06 | 2012-02-09 | 지솔라(주) | Device for generating grid-connected photovoltaic power and method for operating same |
CN103944175A (en) * | 2014-03-28 | 2014-07-23 | 上海电力设计院有限公司 | Wind-solar-storage combined power generation system output characteristic optimization method |
WO2020249125A1 (en) * | 2019-06-14 | 2020-12-17 | 第四范式(北京)技术有限公司 | Method and system for automatically training machine learning model |
KR102064918B1 (en) * | 2019-06-20 | 2020-01-10 | (주) 씨이랩 | Energy diagnosis system and method with high accuracy for realization of zero energy building |
CN112803567A (en) * | 2021-01-29 | 2021-05-14 | 西安交通大学 | Parameter optimization design method and system based on intelligent building optical storage power supply equipment |
CN113224756A (en) * | 2021-05-11 | 2021-08-06 | 湖南中大设计院有限公司 | Method applied to photovoltaic building integrated optimal installed capacity measurement and calculation |
CN114970959A (en) * | 2022-04-24 | 2022-08-30 | 中国能源建设集团浙江省电力设计院有限公司 | Low-energy-consumption building power distribution system planning method considering source network load storage characteristics |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102930358B (en) | A kind of neural net prediction method of photovoltaic power station power generation power | |
CN110474339B (en) | Power grid reactive power control method based on deep power generation load prediction | |
CN103106544B (en) | A kind of photovoltaic generation prognoses system based on T-S Fuzzy neutral net | |
CN103390116B (en) | Use the photovoltaic power station power generation power forecasting method of stepping mode | |
CN109858673A (en) | A kind of photovoltaic generating system power forecasting method | |
Guo et al. | Study on short-term photovoltaic power prediction model based on the Stacking ensemble learning | |
CN109902874A (en) | A kind of micro-capacitance sensor photovoltaic power generation short term prediction method based on deep learning | |
CN109103926A (en) | Photovoltaic power generation based on more Radiation Characteristics year meteorology scenes receives capacity calculation method | |
CN105184678A (en) | Method for constructing photovoltaic power station generation capacity short-term prediction model based on multiple neural network combinational algorithms | |
CN108280545A (en) | A kind of photovoltaic power prediction technique based on K mean cluster neural network | |
CN114021420A (en) | Distributed photovoltaic ultra-short-term power generation prediction method and system | |
CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
Ganguly et al. | Solar–wind hybrid renewable energy system: current status of research on configurations, control, and sizing methodologies | |
CN112215428B (en) | Photovoltaic power generation power prediction method and system based on error correction and fuzzy logic | |
CN104463356A (en) | Photovoltaic power generation power prediction method based on multi-dimension information artificial neural network algorithm | |
CN105207573A (en) | Quantitative optimal configuration method of wind-solar hybrid power system based on discrete probability model | |
CN110309972A (en) | A kind of renewable energy system and its load forecasting method based on indoor occupant behavior | |
CN109636054A (en) | Solar energy power generating amount prediction technique based on classification and error combination prediction | |
CN107453396A (en) | A kind of Multiobjective Optimal Operation method that distributed photovoltaic power is contributed | |
CN109272134A (en) | A kind of region photovoltaic electric station grid connection power forecasting method considering system loss | |
CN116167531A (en) | Photovoltaic power generation prediction method based on digital twin | |
CN114707767A (en) | Method for predicting peak-adjustable power of new energy power system in off-peak period | |
CN113516271A (en) | Wind power cluster power day-ahead prediction method based on space-time neural network | |
CN112101626A (en) | Distributed photovoltaic power generation power prediction method and system | |
CN115423153A (en) | Photovoltaic energy storage system energy management method based on probability prediction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |