CN116826726A - Micro-grid power generation amount prediction method, device and storage medium - Google Patents
Micro-grid power generation amount prediction method, device and storage medium Download PDFInfo
- Publication number
- CN116826726A CN116826726A CN202310773265.4A CN202310773265A CN116826726A CN 116826726 A CN116826726 A CN 116826726A CN 202310773265 A CN202310773265 A CN 202310773265A CN 116826726 A CN116826726 A CN 116826726A
- Authority
- CN
- China
- Prior art keywords
- power generation
- weather
- output
- power
- generator
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000003062 neural network model Methods 0.000 claims abstract description 21
- 230000008569 process Effects 0.000 claims abstract description 7
- 239000000446 fuel Substances 0.000 claims description 40
- 239000007789 gas Substances 0.000 claims description 35
- 238000013528 artificial neural network Methods 0.000 claims description 24
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 21
- 230000005855 radiation Effects 0.000 claims description 14
- 238000005286 illumination Methods 0.000 claims description 13
- 239000002028 Biomass Substances 0.000 claims description 12
- ZZUFCTLCJUWOSV-UHFFFAOYSA-N furosemide Chemical compound C1=C(Cl)C(S(=O)(=O)N)=CC(C(O)=O)=C1NCC1=CC=CO1 ZZUFCTLCJUWOSV-UHFFFAOYSA-N 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 8
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000002485 combustion reaction Methods 0.000 claims description 4
- 238000010438 heat treatment Methods 0.000 claims description 4
- 239000003345 natural gas Substances 0.000 claims description 4
- 239000008239 natural water Substances 0.000 claims description 4
- 238000003306 harvesting Methods 0.000 description 2
- 102000003712 Complement factor B Human genes 0.000 description 1
- 108090000056 Complement factor B Proteins 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application discloses a method, a device and a storage medium for predicting the power generation capacity of a micro-grid, wherein the method comprises the following steps: collecting distributed energy distribution data in the running process of the micro-grid, and constructing a corresponding power generation characteristic model; acquiring historical power generation data and historical weather data of remote rural micro-grids, and calculating the proportion of the generated energy of various generators according to a generator characteristic model; taking the proportion of historical weather data and the generated energy of various generators as input, and taking weather influence factors influencing the output power of various generators as output to obtain neural network models corresponding to various generator sets; acquiring weather forecast information of a certain day in the future, and analyzing to obtain a weather factor value; and inputting the weather factor values into the neural network model to obtain the predicted power generation amount of various power generators. According to the application, the influence of different weather factors on the output power of the generator sets is comprehensively considered, and the prediction accuracy of the generated energy of each generator set in the micro-grid can be effectively improved.
Description
Technical Field
The application relates to the technical field of power systems, in particular to a method and a device for predicting the power generation capacity of a micro-grid and a storage medium.
Background
For the network side, the remote rural areas have the characteristics of remote geographic positions, scattered residence of residents and the like, the construction of the main network extension power supply engineering has certain difficulty, and the construction cost is high. Secondly, most of distribution network structures are single radiation networks, and direct access of wind-light-based distributed renewable energy sources and the like affects the operation safety of the distribution network, so that the level of the renewable energy sources is affected. For the load side, the load of a remote rural area is mostly household electric load such as illumination power consumption, televisions, electric rice cookers, washing machines and other household electric equipment, and in the crop planting and harvesting seasons, the power consumption requirements of equipment such as water pumping irrigation, paddy husking and the like exist, so that the load power consumption of the area has a certain seasonal relevance. Secondly, because the residents are more scattered and the population density is relatively smaller, the power load in the remote rural areas has the characteristics of wide distribution and small density. Finally, according to residential electricity habits, the load is mainly concentrated at night, and the daytime electricity consumption may also increase during crop harvesting or planting. How to reasonably plan the power resources of remote rural areas in a coordinated manner is a problem which needs to be solved at present.
The micro-grid power generation amount prediction is an important component of the micro-grid energy management system, is a basis for optimally scheduling controllable micro-sources such as wind power, photovoltaic, micro-gas turbines, diesel engines and energy storage, and the like, and the prediction result directly influences the micro-grid operation strategy and the electric energy transaction. Compared with a large power grid environment, the micro-grid has the advantages that the difficulty of short-term power generation capacity prediction is higher, the randomness of the load is strong, the similarity of historical load curves is low, the capacity of users is limited, the load characteristics among the users have smaller interaction smoothness, and the overall fluctuation of the load is larger.
The existing micro-grid power generation amount prediction method is usually used for prediction by adopting a BP-NN prediction method, but the existing micro-grid power generation amount prediction method does not comprehensively consider influence factors on power generation amount, so that the power generation amount prediction accuracy is low.
Disclosure of Invention
The application provides a method, a device and a storage medium for predicting the generating capacity of a micro-grid, and aims to solve the technical problem that the existing method for predicting the generating capacity of the micro-grid does not comprehensively consider influencing factors on the generating capacity, so that the predicting precision of the generating capacity is low.
One embodiment of the application provides a method for predicting the power generation capacity of a micro-grid, which comprises the following steps:
collecting distributed energy distribution data in the running process of the micro-grid, and constructing a corresponding power generation characteristic model according to the distributed energy distribution data;
acquiring historical power generation data and historical weather data of remote rural micro-grids, and calculating the proportion of the generated energy of various generators according to the generator characteristic model;
taking the proportion of the historical weather data and the generated energy of each generator as input, taking weather influence factors influencing the output power of each generator as output, and performing model training to obtain neural network models corresponding to each generator set;
acquiring weather forecast information of a certain day in the future, and analyzing the weather forecast information to obtain a weather factor value;
and inputting the weather factor values into the neural network model to obtain the predicted power generation amount of various power generators.
Further, the power generation characteristic model comprises a gas turbine power generation output model, a fuel cell power generation output model, a wind turbine generator power generation output model, a photovoltaic turbine generator power generation output model and a small hydropower generator power generation output model.
Further, the gas turbine power generation output model is as follows:
wherein P is MT (t) is the t period gas turbine output power; alpha c The power conversion efficiency of the gas turbine is; m is m b (t) is the biomass burned in period t; η (eta) b Biomass energy combustion conversion; f (f) NCVb A net biomass energy heating value;
the fuel cell power generation output model is as follows:
P FC (t)＝η FC ·X ng ·V FC (t)
wherein eta FC The electricity-producing efficiency for the fuel cell; alpha 1 、β 1 、γ 1 Is the efficiency coefficient of the fuel cell; p (P) FC (t) outputting electric power for the fuel cell for a period t; v (V) FC (t) consuming natural gas for a fuel cell t-period;
the power generation output model of the wind turbine generator is as follows:
wherein P is r Rated power of the wind turbine generator; v wr (t) is the wind speed of the wind turbine generator blade at the moment t; v max 、v min The wind speed is the upper limit and the lower limit of the wind speed in the working state of the wind turbine generator; v r The wind turbine generator system is a minimum wind speed corresponding to rated power of the wind turbine generator system;
the power generation output model of the photovoltaic unit is as follows:
wherein P is PV (t) is the output of the photovoltaic unit at the moment t; η (eta) PV Efficiency is solar panel; s is the area of the battery plate;the unit area illumination radiation intensity of the photovoltaic unit is set;
the output model of the small hydroelectric generating set is as follows:
wherein P is hydro (t) is the output of the unit at the moment t; q (t) is the water flow at the moment t;the upper and lower limits of the output of the small hydroelectric generating set are set; k is the output coefficient of the unit; h is the working water head of the unit, and the rated water head is taken here; q (Q) max 、Q min Introducing upper and lower flow limits for the small hydroelectric generating set; q (Q) water (t) natural water inflow at the moment of the basin t where the unit is positioned; p (P) abandon And (t) the water discarding electric quantity at the moment t.
Furthermore, various types of generators comprise a gas turbine, a fuel cell, a wind turbine generator set, a photovoltaic generator set and a small hydropower generator set.
Further, the weather factors comprise data such as haze indexes, temperatures, wind speeds, illumination radiation intensities, rainfall and the like.
Further, the obtaining weather forecast information of a future day, analyzing the weather forecast information to obtain a weather factor value includes:
and acquiring weather forecast information with the granularity of hours in a future day, and analyzing the weather forecast information to obtain a weather factor value.
Further, the outputting of the weather influence factors influencing the output power of various generators includes:
setting the maximum weight of the haze index when training the neural network corresponding to the gas turbine, and determining a first atmospheric influence factor influencing the output power of the gas turbine;
when training the neural network corresponding to the fuel cell, setting the maximum weight of the temperature, and determining a second weather influence factor influencing the output power of the fuel cell;
when training a neural network corresponding to a wind turbine generator, setting the maximum weight of wind speed, and determining a third weather influence factor influencing the output power of the wind turbine generator;
setting the maximum weight of illumination radiation intensity when training the neural network corresponding to the photovoltaic unit, and determining a fourth weather influence factor influencing the output power of the photovoltaic unit;
and when training the neural network corresponding to the small hydropower station, setting the maximum weight of the rainfall and determining a fifth weather influence factor influencing the output power of the small hydropower station.
An embodiment of the present application provides a microgrid power generation amount prediction apparatus, including:
the power generation characteristic model construction module is used for acquiring distributed energy distribution data in the running process of the micro-grid and constructing a corresponding power generation characteristic model according to the distributed energy distribution data;
the model training data acquisition module is used for acquiring historical power generation data and historical weather data of the remote rural micro-grid, and calculating the proportion of the generated energy of various generators according to the generator characteristic model;
the model training module is used for taking the proportion of the historical weather data and the generated energy of each generator as input, taking weather influence factors influencing the output power of each generator as output, and carrying out model training to obtain neural network models corresponding to each generator set;
the weather factor numerical analysis module is used for acquiring weather forecast information of a certain day in the future and analyzing the weather forecast information to obtain a weather factor numerical value;
and the power generation amount prediction module is used for inputting the weather factor value into the neural network model to obtain the predicted power generation amount of various power generators.
An embodiment of the present application provides a computer readable storage medium, where the computer readable storage medium includes a stored computer program, and when the computer program runs, controls a device where the computer readable storage medium is located to execute a method for predicting a power generation amount of a micro grid as described above.
According to the embodiment of the application, the weather factors and the generating capacity duty ratio are associated with the corresponding weather influence factors, the model training is carried out to obtain the neural network model, then the weather factor numerical value of a certain day in the future is obtained through analysis, and the weather factor numerical value is input into the neural network model, so that the respective generating capacity of different generating sets can be predicted, the influence of different weather factors on the output power of the generating sets is comprehensively considered, and the generating capacity prediction accuracy of each generating set in the micro-grid can be effectively improved.
Furthermore, the embodiment of the application inputs the weather factor value obtained by analyzing the weather forecast information with the hour as granularity into the neural network, so that the power generation amount of various power generating sets can be predicted by taking the hour as a unit, and the power generation amount prediction accuracy of each power generating set in the micro-grid is further improved.
Drawings
Fig. 1 is a schematic flow chart of a method for predicting the power generation capacity of a micro-grid according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a micro-grid power generation amount prediction device provided by an embodiment of the application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the description of the present application, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more.
In the description of the present application, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
Referring to fig. 1, an embodiment of the present application provides a method for predicting a power generation amount of a micro grid, including:
s1, collecting distributed energy distribution data in the running process of a micro-grid, and constructing a corresponding power generation characteristic model according to the distributed energy distribution data;
s2, acquiring historical power generation data and historical weather data of remote rural micro-grids, and calculating the proportion of the generated energy of each generator according to a generator characteristic model;
in the embodiment of the application, various generators comprise a gas turbine, a fuel cell, a wind turbine, a photovoltaic generator and a small hydropower generator. The proportion of the generated energy of the gas turbine can be represented by v, the proportion of the generated energy of the fuel cell can be represented by w, the proportion of the generated energy of the wind turbine can be represented by x, the proportion of the generated energy of the photovoltaic turbine can be represented by y, and the generated energy of the small hydroelectric turbine can be represented by z.
In the embodiment of the application, the proportion of the generated energy of various generators can be calculated according to the historical generated data and the generator characteristic model.
S3, taking the proportion of historical weather data and the generated energy of each generator as input, taking weather influence factors influencing the output power of each generator as output, and performing model training to obtain neural network models corresponding to each generator set;
s4, weather forecast information of a future day is obtained, and the weather forecast information is analyzed to obtain a weather factor value;
in the embodiment of the application, as the weather conditions in remote mountainous areas change rapidly, the granularity of the weather conditions can be liked to each hour every day, so that the predicted power generation capacity of various power generators can be effectively improved.
S5, inputting the weather factor values into the neural network model to obtain the predicted power generation amount of various power generators.
According to the embodiment of the application, the pre-trained neural network model can output the predicted generated energy of various generators according to the relation between the weather factor data and the generated energy and the input weather factor value, wherein the predicted generated energy comprises the generated energy of a gas turbine, the generated energy of a fuel cell, the generated energy of a wind turbine unit, the generated energy of a photovoltaic unit and the generated energy of a small hydropower unit.
According to the embodiment of the application, the weather factors and the generating capacity duty ratio are associated with the corresponding weather influence factors, the model training is carried out to obtain the neural network model, then the weather factor numerical value of a certain day in the future is obtained through analysis, and the weather factor numerical value is input into the neural network model, so that the respective generating capacity of different generating sets can be predicted, the influence of different weather factors on the output power of the generating sets is comprehensively considered, and the generating capacity prediction accuracy of each generating set in the micro-grid can be effectively improved.
In one embodiment, the power generation characteristic model includes a gas turbine power generation output model, a fuel cell power generation output model, a wind turbine power generation output model, a photovoltaic turbine power generation output model, and a small hydropower turbine power generation output model.
In one embodiment, the gas turbine power generation output model is:
wherein P is MT (t) is the t period gas turbine output power; alpha c The power conversion efficiency of the gas turbine is; m is m b (t) is the biomass burned in period t; η (eta) b Biomass energy combustion conversion; f (f) NCVb A net biomass energy heating value;
the fuel cell power generation output model is as follows:
P FC (t)＝η FC ·X ng ·V FC (t)
wherein eta FC The electricity-producing efficiency for the fuel cell; alpha 1 、β 1 、γ 1 Is the efficiency coefficient of the fuel cell; p (P) FC (t) outputting electric power for the fuel cell for a period t; v (V) FC (t) consuming natural gas for a fuel cell t-period;
the power generation output model of the wind turbine generator is as follows:
wherein P is r Rated power of the wind turbine generator; v wr (t) is the wind speed of the wind turbine generator blade at the moment t; v max 、v min The wind speed is the upper limit and the lower limit of the wind speed in the working state of the wind turbine generator; v r The wind turbine generator system is a minimum wind speed corresponding to rated power of the wind turbine generator system;
the power generation output model of the photovoltaic unit is as follows:
wherein P is PV (t) is the output of the photovoltaic unit at the moment t; η (eta) PV Efficiency is solar panel; s is the area of the battery plate;the unit area illumination radiation intensity of the photovoltaic unit is set;
the output model of the small hydroelectric generating set is as follows:
wherein P is hydro (t) is the output of the unit at the moment t; q (t) is the water flow at the moment t;the upper and lower limits of the output of the small hydroelectric generating set are set; k is the output coefficient of the unit; h is the working water head of the unit, and the rated water head is taken here; q (Q) max 、Q min Introducing upper and lower flow limits for the small hydroelectric generating set; q (Q) water (t) natural water inflow at the moment of the basin t where the unit is positioned; p (P) abandon And (t) the water discarding electric quantity at the moment t.
In one embodiment, the weather factors include data such as haze index, temperature, wind speed, illumination radiation intensity, and rainfall.
In one embodiment, step S4, obtaining weather forecast information of a future day, analyzing the weather forecast information to obtain a weather factor value, includes:
and acquiring weather forecast information with the granularity of hours in a future day, and analyzing the weather forecast information to obtain weather factor values, wherein the weather factor values comprise specific values corresponding to the weather factors.
In one embodiment, step S3, taking as output weather influencing factors influencing output power of various types of generators, includes:
setting the maximum weight of the haze index when training the neural network corresponding to the gas turbine, and determining a first atmospheric influence factor influencing the output power of the gas turbine;
in the embodiment of the application, different weather factors have different degrees of influence on the output power of various generator sets. For example, due to the influence of haze weather, the difference of the air inlet filter screen of the press machine is obviously increased, so that the gas turbine cannot output full power, and therefore the size of the haze index is the largest in weight when training the neural network corresponding to the gas turbine, and the first air influence factor A of the output power of the gas turbine can be accurately determined.
When training the neural network corresponding to the fuel cell, setting the maximum weight of the temperature, and determining a second weather influence factor B which influences the output power of the fuel cell;
in the embodiment of the application, the temperature is a main factor affecting the average output power of the fuel cell.
When training a neural network corresponding to a wind turbine generator, setting the maximum weight of wind speed, and determining a third weather influence factor C for influencing the output power of the wind turbine generator;
in the embodiment of the application, the wind speed is a main factor influencing the output power of the wind turbine.
Setting the maximum weight of illumination radiation intensity when training a neural network corresponding to the photovoltaic unit, and determining a fourth weather influence factor D which influences the output power of the photovoltaic unit;
in the embodiment of the application, the illumination radiation intensity is a main factor influencing the output power of the photovoltaic unit.
And when training the neural network corresponding to the small hydropower station, setting the maximum weight of the rainfall and determining a fifth weather influence factor E for influencing the output power of the small hydropower station.
In the embodiment of the application, the rainfall is a main factor affecting the output power of the small hydroelectric generating set.
In one embodiment, weather factor values obtained by analyzing weather forecast information with the granularity of hours are input into a neural network to obtain the predicted power generation amount of each generator set in units of each hour, wherein the predicted power generation amount of the gas turbine is P MT (t) A, the predicted power generation amount of the fuel cell is P FC (t) B, the predicted power generation amount of the wind turbine generator is P r * C, the predicted generating capacity of the photovoltaic unit is P PV (t) D, the predicted power generation amount of the small hydroelectric generating set is P hydro (t)*E。
The embodiment of the application has the following beneficial effects:
according to the embodiment of the application, the weather factors and the generating capacity duty ratio are associated with the corresponding weather influence factors, the model training is carried out to obtain the neural network model, then the weather factor numerical value of a certain day in the future is obtained through analysis, and the weather factor numerical value is input into the neural network model, so that the respective generating capacity of different generating sets can be predicted, the influence of different weather factors on the output power of the generating sets is comprehensively considered, and the generating capacity prediction accuracy of each generating set in the micro-grid can be effectively improved.
Furthermore, the embodiment of the application inputs the weather factor value obtained by analyzing the weather forecast information with the hour as granularity into the neural network, so that the power generation amount of various power generating sets can be predicted by taking the hour as a unit, and the power generation amount prediction accuracy of each power generating set in the micro-grid is further improved.
Referring to fig. 2, based on the same inventive concept as the above embodiment, an embodiment of the present application provides a micro grid power generation amount prediction apparatus, including:
the power generation characteristic model construction module 10 is used for acquiring distributed energy distribution data in the running process of the micro-grid and constructing a corresponding power generation characteristic model according to the distributed energy distribution data;
the model training data acquisition module 20 is used for acquiring historical power generation data and historical weather data of the remote rural micro-grid and calculating the proportion of the generated energy of each generator according to the generator characteristic model;
the model training module 30 is configured to perform model training by taking the historical weather data and the proportion of the generated energy of each generator as input, and taking weather influence factors affecting the output power of each generator as output, so as to obtain neural network models corresponding to each generator set;
the weather factor value analysis module 40 is configured to obtain weather forecast information of a future day, and analyze the weather forecast information to obtain a weather factor value;
the power generation amount prediction module 50 is used for inputting the weather factor values into the neural network model to obtain predicted power generation amounts of various power generators.
In one embodiment, the power generation characteristic model includes a gas turbine power generation output model, a fuel cell power generation output model, a wind turbine power generation output model, a photovoltaic turbine power generation output model, and a small hydropower turbine power generation output model.
In one embodiment, the gas turbine power generation output model is:
wherein P is MT (t) is the t period gas turbine output power; alpha c The power conversion efficiency of the gas turbine is; m is m b (t) is the biomass burned in period t; η (eta) b Biomass energy combustion conversion; f (f) NCVb A net biomass energy heating value;
the fuel cell power generation output model is as follows:
P FC (t)＝η FC ·X ng ·V FC (t)
wherein eta FC The electricity-producing efficiency for the fuel cell; alpha 1 、β 1 、γ 1 Is a fuel cellEfficiency coefficient; p (P) FC (t) outputting electric power for the fuel cell for a period t; v (V) FC (t) consuming natural gas for a fuel cell t-period;
the power generation output model of the wind turbine generator is as follows:
wherein P is r Rated power of the wind turbine generator; v wr (t) is the wind speed of the wind turbine generator blade at the moment t; v max 、v min The wind speed is the upper limit and the lower limit of the wind speed in the working state of the wind turbine generator; v r The wind turbine generator system is a minimum wind speed corresponding to rated power of the wind turbine generator system;
the power generation output model of the photovoltaic unit is as follows:
wherein P is PV (t) is the output of the photovoltaic unit at the moment t; η (eta) PV Efficiency is solar panel; s is the area of the battery plate;the unit area illumination radiation intensity of the photovoltaic unit is set;
the output model of the small hydroelectric generating set is as follows:
wherein P is hydro (t) is the output of the unit at the moment t; q (t) is the water flow at the moment t;the upper and lower limits of the output of the small hydroelectric generating set are set; k is the output coefficient of the unit; h is the working water head of the unit, and the rated water head is taken here; q (Q) max 、Q min Introducing upper and lower flow limits for the small hydroelectric generating set; q (Q) water (t) is the natural water flow rate of the unit in the basin t moment；P abandon And (t) the water discarding electric quantity at the moment t.
In one embodiment, the various types of generators include gas turbines, fuel cells, wind turbines, photovoltaic turbines, and small hydroelectric turbines.
In one embodiment, the weather factors include data such as haze index, temperature, wind speed, illumination radiation intensity, and rainfall.
In one embodiment, model training module 30 is further to:
and acquiring weather forecast information with the granularity of hours in a future day, and analyzing the weather forecast information to obtain a weather factor value.
In one embodiment, taking as output weather effect factors that affect the output power of various types of generators, includes:
setting the maximum weight of the haze index when training the neural network corresponding to the gas turbine, and determining a first atmospheric influence factor influencing the output power of the gas turbine;
when training the neural network corresponding to the fuel cell, setting the maximum weight of the temperature, and determining a second weather influence factor influencing the output power of the fuel cell;
when training a neural network corresponding to a wind turbine generator, setting the maximum weight of wind speed, and determining a third weather influence factor influencing the output power of the wind turbine generator;
setting the maximum weight of illumination radiation intensity when training the neural network corresponding to the photovoltaic unit, and determining a fourth weather influence factor influencing the output power of the photovoltaic unit;
and when training the neural network corresponding to the small hydropower station, setting the maximum weight of the rainfall and determining a fifth weather influence factor influencing the output power of the small hydropower station.
An embodiment of the present application provides a computer readable storage medium, where the computer readable storage medium includes a stored computer program, and when the computer program is executed, controls a device where the computer readable storage medium is located to execute the method for predicting the power generation amount of a micro grid as described above.
The foregoing is a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.
Claims (9)
1. A microgrid power generation capacity prediction method, characterized by comprising:
collecting distributed energy distribution data in the running process of the micro-grid, and constructing a corresponding power generation characteristic model according to the distributed energy distribution data;
acquiring historical power generation data and historical weather data of remote rural micro-grids, and calculating the proportion of the generated energy of various generators according to the generator characteristic model;
taking the proportion of the historical weather data and the generated energy of each generator as input, taking weather influence factors influencing the output power of each generator as output, and performing model training to obtain neural network models corresponding to each generator set;
acquiring weather forecast information of a certain day in the future, and analyzing the weather forecast information to obtain a weather factor value;
and inputting the weather factor values into the neural network model to obtain the predicted power generation amount of various power generators.
2. The method of claim 1, wherein the power generation characteristic model comprises a gas turbine power generation output model, a fuel cell power generation output model, a wind turbine generator power generation output model, a photovoltaic turbine generator power generation output model, and a small hydropower generator power generation output model.
3. The method for predicting power generation capacity of a micro-grid according to claim 2, wherein the power generation output model of the gas turbine is:
wherein P is MT (t) is the t period gas turbine output power; alpha c The power conversion efficiency of the gas turbine is; m is m b (t) is the biomass burned in period t; η (eta) b Biomass energy combustion conversion; f (f) NCVb A net biomass energy heating value;
the fuel cell power generation output model is as follows:
P FC (t)＝η FC ·X ng ·V FC (t)
wherein eta FC The electricity-producing efficiency for the fuel cell; alpha 1 、β 1 、γ 1 Is the efficiency coefficient of the fuel cell; p (P) FC (t) outputting electric power for the fuel cell for a period t; v (V) FC (t) consuming natural gas for a fuel cell t-period;
the power generation output model of the wind turbine generator is as follows:
wherein P is r Rated power of the wind turbine generator; v wr (t) is the wind speed of the wind turbine generator blade at the moment t; v max 、v min The wind speed is the upper limit and the lower limit of the wind speed in the working state of the wind turbine generator; v r The wind turbine generator system is a minimum wind speed corresponding to rated power of the wind turbine generator system;
the power generation output model of the photovoltaic unit is as follows:
wherein P is PV (t) is the output of the photovoltaic unit at the moment t; η (eta) PV Efficiency is solar panel; s is the area of the battery plate;the unit area illumination radiation intensity of the photovoltaic unit is set;
the output model of the small hydroelectric generating set is as follows:
wherein P is hydro (t) is the output of the unit at the moment t; q (t) is the water flow at the moment t;the upper and lower limits of the output of the small hydroelectric generating set are set; k is the output coefficient of the unit; h is the working water head of the unit, and the rated water head is taken here; q (Q) max 、Q min Introducing upper and lower flow limits for the small hydroelectric generating set; q (Q) water (t) natural water inflow at the moment of the basin t where the unit is positioned; p (P) abandon And (t) the water discarding electric quantity at the moment t.
4. The method of claim 1, wherein each of the power generators includes a gas turbine, a fuel cell, a wind turbine, a photovoltaic generator, and a small hydroelectric generator.
5. The method of claim 1, wherein the weather factors include haze index, temperature, wind speed, light radiation intensity, and rainfall data.
6. The method for predicting the power generation capacity of a micro-grid according to claim 1, wherein the step of obtaining weather forecast information of a future day and analyzing the weather forecast information to obtain a weather factor value comprises the steps of:
and acquiring weather forecast information with the granularity of hours in a future day, and analyzing the weather forecast information to obtain a weather factor value.
7. The method for predicting power generation of a micro-grid according to claim 6, wherein the outputting of the weather-influencing factors influencing the output power of the various generators comprises:
setting the maximum weight of the haze index when training the neural network corresponding to the gas turbine, and determining a first atmospheric influence factor influencing the output power of the gas turbine;
when training the neural network corresponding to the fuel cell, setting the maximum weight of the temperature, and determining a second weather influence factor influencing the output power of the fuel cell;
when training a neural network corresponding to a wind turbine generator, setting the maximum weight of wind speed, and determining a third weather influence factor influencing the output power of the wind turbine generator;
setting the maximum weight of illumination radiation intensity when training the neural network corresponding to the photovoltaic unit, and determining a fourth weather influence factor influencing the output power of the photovoltaic unit;
and when training the neural network corresponding to the small hydropower station, setting the maximum weight of the rainfall and determining a fifth weather influence factor influencing the output power of the small hydropower station.
8. A micro-grid power generation amount prediction device, characterized by comprising:
the power generation characteristic model construction module is used for acquiring distributed energy distribution data in the running process of the micro-grid and constructing a corresponding power generation characteristic model according to the distributed energy distribution data;
the model training data acquisition module is used for acquiring historical power generation data and historical weather data of the remote rural micro-grid, and calculating the proportion of the generated energy of various generators according to the generator characteristic model;
the model training module is used for taking the proportion of the historical weather data and the generated energy of each generator as input, taking weather influence factors influencing the output power of each generator as output, and carrying out model training to obtain neural network models corresponding to each generator set;
the weather factor numerical analysis module is used for acquiring weather forecast information of a certain day in the future and analyzing the weather forecast information to obtain a weather factor numerical value;
and the power generation amount prediction module is used for inputting the weather factor value into the neural network model to obtain the predicted power generation amount of various power generators.
9. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the microgrid generation capacity prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310773265.4A CN116826726A (en) | 2023-06-27 | 2023-06-27 | Micro-grid power generation amount prediction method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310773265.4A CN116826726A (en) | 2023-06-27 | 2023-06-27 | Micro-grid power generation amount prediction method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116826726A true CN116826726A (en) | 2023-09-29 |
Family
ID=88117948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310773265.4A Pending CN116826726A (en) | 2023-06-27 | 2023-06-27 | Micro-grid power generation amount prediction method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116826726A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117639113A (en) * | 2024-01-25 | 2024-03-01 | 湖北世纪森源电力工程有限公司 | Intelligent micro-grid intelligent power distribution method, device and storage medium |
-
2023
- 2023-06-27 CN CN202310773265.4A patent/CN116826726A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117639113A (en) * | 2024-01-25 | 2024-03-01 | 湖北世纪森源电力工程有限公司 | Intelligent micro-grid intelligent power distribution method, device and storage medium |
| CN117639113B (en) * | 2024-01-25 | 2024-04-05 | 湖北世纪森源电力工程有限公司 | Intelligent micro-grid intelligent power distribution method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dawoud et al. | Hybrid renewable microgrid optimization techniques: A review | |
| CN106099993B (en) | A kind of power source planning method for adapting to new energy and accessing on a large scale | |
| Feng et al. | Cost advantage of adjustable-speed pumped storage unit for daily operation in distributed hybrid system | |
| CN109103929A (en) | Based on the power distribution network economic optimization dispatching method for improving dynamic gram Li Sijin model | |
| Li et al. | Multi-objective capacity optimization of a hybrid energy system in two-stage stochastic programming framework | |
| Askarzadeh | Optimisation of solar and wind energy systems: A survey | |
| CN116826726A (en) | Micro-grid power generation amount prediction method, device and storage medium | |
| Wang et al. | Hybrid time-scale optimal scheduling considering multi-energy complementary characteristic | |
| CN105678415A (en) | Method for predicting net load of distributed power supply power distribution network | |
| CN114301089A (en) | Energy storage capacity configuration optimization method for wind-solar combined power generation system | |
| CN116911695B (en) | Flexible resource adequacy evaluation method and device | |
| CN104135037B (en) | A kind of wind-light storage optimizing operation method | |
| CN110165699B (en) | Photo-thermal power station optimal configuration method based on individual optimization and system multi-energy complementation | |
| Mostofi et al. | Application of ABC algorithm for grid-independent hybrid hydro/photovoltaic/wind/fuel cell power generation system considering cost and reliability | |
| Ochoa-Malhaber et al. | Technical-economic comparison of microgrids for rural communities in the island region of Galapagos, Ecuador: Isabela Island case | |
| CN109546647B (en) | Safety and stability evaluation method for power system containing wind, light and water storage | |
| CN111262270A (en) | Light, diesel and storage hybrid power generation system | |
| Han et al. | Analysis of economic operation model for virtual power plants considering the uncertainties of renewable energy power generation | |
| CN114819362A (en) | Power grid power load balancing method for wind-solar power system | |
| Wang et al. | Capacity Optimization of Island Integrated Energy System Considering Hydrogen Energy Access | |
| Delice | Selection of on-site energy generation technology with a new MCDM approach using MABAC & AHP | |
| CN107292768B (en) | Photovoltaic power generation system daily generated energy fuzzy probability calculation method and device | |
| Luo et al. | The Research on High Proportion Wind Power Integration in China’s Power System | |
| Zhu et al. | Regulation capability of small cascade hydropower stations for photovoltaic generation | |
| CN110768306A (en) | Power supply capacity configuration method for improving emergency capacity of micro-grid in bottom-protected power grid |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |