CN117553337B - Multisource complementary scheduling method considering agricultural photovoltaic heating and integrated central heating pipe network - Google Patents
Multisource complementary scheduling method considering agricultural photovoltaic heating and integrated central heating pipe network Download PDFInfo
- Publication number
- CN117553337B CN117553337B CN202410039600.2A CN202410039600A CN117553337B CN 117553337 B CN117553337 B CN 117553337B CN 202410039600 A CN202410039600 A CN 202410039600A CN 117553337 B CN117553337 B CN 117553337B
- Authority
- CN
- China
- Prior art keywords
- heat
- storage tank
- photovoltaic
- heating unit
- agricultural
- 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
- 238000010438 heat treatment Methods 0.000 title claims abstract description 438
- 230000000295 complement effect Effects 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000005338 heat storage Methods 0.000 claims abstract description 144
- 230000033228 biological regulation Effects 0.000 claims abstract description 39
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 12
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 12
- 238000005265 energy consumption Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 56
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 45
- 238000009826 distribution Methods 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 30
- 230000008859 change Effects 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 16
- 238000004088 simulation Methods 0.000 claims description 16
- 239000000446 fuel Substances 0.000 claims description 15
- 230000007246 mechanism Effects 0.000 claims description 13
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000005286 illumination Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 10
- 238000004519 manufacturing process Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 6
- 230000020169 heat generation Effects 0.000 claims description 6
- 238000009825 accumulation Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000011084 recovery Methods 0.000 claims description 4
- 230000001629 suppression Effects 0.000 claims description 4
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 3
- 239000001569 carbon dioxide Substances 0.000 claims description 3
- 238000004146 energy storage Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 230000021715 photosynthesis, light harvesting Effects 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 230000008901 benefit Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 239000000047 product Substances 0.000 description 4
- 230000000087 stabilizing effect Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D3/00—Hot-water central heating systems
- F24D3/02—Hot-water central heating systems with forced circulation, e.g. by pumps
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D19/00—Details
- F24D19/10—Arrangement or mounting of control or safety devices
- F24D19/1006—Arrangement or mounting of control or safety devices for water heating systems
- F24D19/1009—Arrangement or mounting of control or safety devices for water heating systems for central heating
- F24D19/1045—Arrangement or mounting of control or safety devices for water heating systems for central heating the system uses a heat pump and solar energy
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D3/00—Hot-water central heating systems
- F24D3/10—Feed-line arrangements, e.g. providing for heat-accumulator tanks, expansion tanks ; Hydraulic components of a central heating system
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D3/00—Hot-water central heating systems
- F24D3/18—Hot-water central heating systems using heat pumps
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D2101/00—Electric generators of small-scale CHP systems
- F24D2101/50—Thermophotovoltaic [TPV] modules
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a multisource complementary scheduling method for combining agricultural photovoltaic heating into a central heating pipe network, which comprises the following steps: establishing a heating quantity prediction model of the agricultural photovoltaic heating unit; establishing an end heat user load prediction model; converting the heat energy generated by the agricultural photovoltaic heating unit into heat energy matched with the parameters of the central heating network through a heat pump, and then accessing the heat energy into the central heating network; the heat produced by the agricultural photovoltaic heating unit is stored and released through the heat storage tank, and the heat is balanced by cooperating with a central heating pipe network; setting a multi-objective function with minimum energy consumption rate, minimum carbon emission and minimum economic cost, and establishing a multi-heat source complementary joint scheduling model; setting target operation parameters of a central heating pipe network, and establishing a heat pump regulation and control identification model by combining heat parameters of an agricultural photovoltaic heating unit, heat parameters of a heat storage tank and heat pump operation characteristics to obtain heat pump regulation and control parameters matched with grid connection parameters for heat pump regulation and control.
Description
Technical Field
The invention belongs to the technical field of intelligent heat supply, and particularly relates to a multisource complementary scheduling method for combining agricultural photovoltaic heating into a central heat supply pipe network.
Background
With the improvement of life quality, the demands of residents on living environment comfort level are higher and the number of urban population and newly-increased heating communities is increased, and the heat production pressure of the traditional coal-fired heat source and boiler is increased dramatically, so that the pressure of a heating system is further increased. In addition, the heating requirement and the environmental protection requirement of towns cannot be met by adopting the traditional coal-fired heating, so that the search and research of an energy-saving, environmental-friendly and economic heating heat source become a necessary trend.
Agricultural photovoltaics are a way of realizing clean energy, efficient land utilization, agricultural modernization and rural development, and can combine photovoltaic heating with the existing agriculture, so that multiple benefits are generated by limited land resources. In the alpine region, farmland does not have agricultural product output when heating the period in winter, can set up movable dismantlement formula photovoltaic board in the farmland and carry out photovoltaic heating, dismantle the recovery with photovoltaic board and be convenient for agricultural product growth when the non-heating period in spring, be equivalent to the photovoltaic board and mainly use in the heating period in the alpine region, can satisfy the heat user demand of part resident. Therefore, the agricultural photovoltaic heating and the central heating pipe network are combined to meet the heat demand of heat users, the pressure of a central heating system can be relieved, the agricultural photovoltaic energy can be fully utilized, and the economic benefit maximization is realized. However, at present, the problems of fluctuation of photovoltaic heating, running fluctuation condition of a pipe network, parameter matching of the photovoltaic heating quantity in a large network, multi-heat source joint optimization scheduling and the like are urgently solved by integrating the agricultural photovoltaic heating quantity into a central heating pipe network in a heating season of a alpine region.
Based on the technical problems, a new multisource complementary scheduling method considering that agricultural photovoltaic heating is integrated into a central heating pipe network needs to be designed.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the defects of the prior art and providing a multisource complementary scheduling method which considers that agricultural photovoltaic heating is integrated into a central heating pipe network.
In order to solve the technical problems, the technical scheme of the invention is as follows:
the invention provides a multisource complementary scheduling method for combining agricultural photovoltaic heating into a central heating pipe network, which comprises the following steps:
acquiring historical operation data and meteorological data of an agricultural photovoltaic heating unit, establishing a heating quantity prediction model of the agricultural photovoltaic heating unit, and calculating to obtain heating quantity prediction values of the agricultural photovoltaic heating unit in future time periods;
acquiring historical operation data and gas image data of a central heating network, establishing a terminal heat user load prediction model, and calculating to obtain load demand predicted values of the terminal heat user in future time periods;
a heat pump and a matching strategy are arranged between the agricultural photovoltaic heating unit and the central heating pipe network, and after the heat energy generated by the agricultural photovoltaic heating unit is converted into heat energy matched with the parameters of the central heating pipe network through the heat pump, the heat energy is connected into the central heating pipe network;
A heat storage tank and a heat storage and release strategy are arranged between the agricultural photovoltaic heating unit and the central heating pipe network, and heat generated by the agricultural photovoltaic heating unit is stored and released through the heat storage tank, so that heat supply and heat demand balance is carried out in cooperation with the central heating pipe network;
building a multi-heat source complementary joint scheduling model of an agricultural photovoltaic heating unit, a central heating pipe network and a heat storage tank: based on the photovoltaic heating quantity predicted value, the heat user load demand predicted value, the running state of the heat storage tank and the time-sharing heat, setting a multi-objective function with minimum energy consumption rate, minimum carbon emission and minimum economic cost on the basis of supply-demand balance, setting related operation constraint conditions, and solving and obtaining an optimal load distribution strategy of the agricultural photovoltaic heating unit, the central heating pipe network and the heat storage tank to perform multi-heat source joint scheduling control;
establishing a heat pump regulation and control identification model: setting target operation parameters of the central heating network based on an optimal load distribution strategy of the central heating network, and acquiring heat pump regulation parameters matched with grid-connected parameters for heat pump regulation after on-line mechanism simulation and identification algorithm analysis by combining the heat parameters of the agricultural photovoltaic heating unit, the heat parameters of the heat storage tank and the heat pump operation characteristics.
Further, the step of obtaining historical operation data and meteorological data of the agricultural photovoltaic heating unit, establishing a heating quantity prediction model of the agricultural photovoltaic heating unit, and calculating to obtain a heating quantity prediction value of the agricultural photovoltaic heating unit in each future period comprises the following steps:
acquiring operation data of a solar heat collector, a photovoltaic panel, radiating pipe equipment and a water circulation system in an agricultural photovoltaic heating unit; the agricultural photovoltaic heating units are distributed in farmlands in alpine regions, and are deployed in a heating period in winter, so that movable detachable recovery is performed in a non-heating period in spring;
acquiring historical meteorological data comprising illumination intensity, temperature and humidity, and clustering the historical meteorological data into different time periods and weather scenes, wherein the weather scenes comprise strong sunshine in sunny days, weak sunshine in sunny days, no sunshine at night and weak sunshine in overcast and rainy days;
dividing the next day into different time periods according to the divided different time periods and weather scenes, acquiring historical operation data of the agricultural photovoltaic heating unit in the same scene, establishing a data sample by combining the weather data in the same historical scene, training and learning the data sample by adopting a machine learning algorithm, and establishing a heating quantity prediction model of the agricultural photovoltaic heating unit in different time periods of different weather scenes in the future, thereby obtaining a photovoltaic heating quantity prediction value in the future time-division scene.
Further, the step of obtaining historical operation data and meteorological data of the central heating network, establishing a terminal heat user load prediction model, and calculating to obtain load demand predicted values of terminal heat users in future time periods comprises the following steps:
acquiring historical operation data comprising historical water supply and return temperature, water supply and return flow and water supply and return pressure of a central heating pipe network; acquiring historical meteorological data comprising illumination intensity, temperature, humidity and wind power; constructing a data sample comprising historical operating data and historical meteorological data;
and training and learning data samples by adopting an XGBoost algorithm, establishing a central heating network terminal heat user load prediction model, and calculating to obtain load demand predicted values of terminal heat users in future time periods.
Further, the training and learning of the data samples are performed by adopting a machine learning algorithm, and a heating amount prediction model of the agricultural photovoltaic heating unit in different weather scenes in different time periods is established, which comprises the following steps:
training and learning data samples by adopting an improved LightGBM algorithm, and establishing an agricultural photovoltaic heating unit heating quantity prediction model based on the LightGBM algorithm;
analyzing the heat production quantity prediction model of the agricultural photovoltaic heating unit based on the LightGBM algorithm by adopting a SHAP algorithm, calculating the SHAP value of each input characteristic variable, determining the influence of each input characteristic variable on the photovoltaic heat production quantity, and obtaining the importance ranking of each input characteristic variable;
Selecting input characteristic variables with preset proportions from front to back according to importance sorting, combining the input characteristic variables as candidate characteristic variables, training a prediction model of the heating quantity of the agricultural photovoltaic heating unit through an improved LightGBM algorithm, calculating an average absolute error and a decisive coefficient, and evaluating a model prediction precision value of the combined characteristic;
selecting an input feature set corresponding to the minimum average absolute error and the maximum decisive coefficient as an optimal feature set, and training and establishing heating quantity prediction models of the agricultural photovoltaic heating unit in different weather scenes in the future in different time periods through the optimal feature set;
wherein, the improved LightGBM algorithm adopts ISSA algorithm to optimize the number of cotyledons, the maximum depth and the learning rate in the LightGBM algorithm model;
the SHAP value for each input feature variable is calculated as:
；
；
is a model predictive value; />The prediction result is that no characteristic value exists; />Is->SHAP values for the individual feature variables;to be at->The feature variables are equal to 1 when selected, otherwise equal to 0; />The number of the characteristic variables; />A set of all feature variables; />For a given subset of predicted features; />To include->Model prediction results of the individual feature variables; / >To not include->Model predictions for individual feature variables.
Further, set up heat pump and matching strategy between the unit is heated to agricultural photovoltaic and central heating pipe network, after converting the heat energy that the unit was heated to agricultural photovoltaic and is produced into with central heating pipe network parameter assorted heat energy through the heat pump, the access central heating pipe network specifically includes:
the heat pump is set up between the agricultural photovoltaic heating unit and the central heating pipe network, when the heat energy parameter between the two parties is unmatched, consider the heat quantity change of the agricultural photovoltaic heating unit, the temperature, the pressure and the flow parameter of the central heating pipe network to carry out the heat pump and adjust, include: when the temperature of the photovoltaic heat generation is too high or too low, the temperature of the photovoltaic heat generation is adjusted to a temperature range matched with a central heating pipe network by adjusting a heat pump; when the flow and the pressure of the photovoltaic heating system are too large or too small, the pipe network is broken or equipment is damaged, and the flow and the pressure of the photovoltaic heating system are adjusted to be in a flow range and a pressure range matched with the central heating pipe network by adjusting the heat pump;
according to the predicted value of the heating amount in each future period of the agricultural photovoltaic heating unit, the dynamic change period of the photovoltaic heating amount is obtained, and according to the predicted value of the load demand of each future period of the tail end heat user of the central heating pipe network, the dynamic change period of the load demand of the tail end heat user is obtained, and the network access parameter matching is satisfied through the adjustment of the heat pump related equipment in each dynamic change period of the photovoltaic heat supply and the heat demand of the heat user.
Further, set up heat storage tank and heat accumulation and release strategy between the unit is heated to agricultural photovoltaic and central heating pipe network, store and release the heat of unit output is heated to agricultural photovoltaic through the heat storage tank, supply and demand heat's balance with central heating pipe network is cooperated, include:
a heat storage tank is arranged between the agricultural photovoltaic heating unit and the central heating pipe network, when the deviation between the predicted value and the actual value of the heating quantity of the agricultural photovoltaic heating unit exceeds a threshold value, the heat storage tank is utilized to store redundant heat when the actual value of the photovoltaic heating quantity exceeds the predicted value, or release the stored heat when the actual value of the photovoltaic heating quantity is smaller than the predicted value to make up for the missing heat, and when the expected heat is still not reached, the output cooperation of the central heating pipe network is enhanced to balance the heat supply and demand;
when the heat supply and demand balance is carried out between the agricultural photovoltaic heating unit and the central heating pipe network, the photovoltaic heating amount is monitored and predicted in real time, and the heat storage tank is utilized for dispatching and adjusting the photovoltaic heating amount.
Further, the operation state and time-sharing heat of the heat storage tank includes: according to the heat accumulation and release state, the maximum energy-of-charge state and the minimum energy-of-charge state of the heat storage tank, a heat model of the heat storage tank is established, and the heat value and the corresponding running state of the heat storage tank in each period are obtained;
The thermal model of the heat storage tank is expressed as:
；
the heat stored by the heat storage tank at the time t is stored; />The coefficient of energy dissipation of the heat storage tank; />The heat storage power of the heat storage tank at the time t; />Is the heat storage efficiency; />The exothermic power of the heat storage tank at the time t;is exothermic efficiency;
when the stored heat of the heat storage tank at the moment t is equal to the maximum stored heat, the heat storage tank can not store heat; when the stored heat of the heat storage tank at the time t is smaller than the maximum stored heat, the heat storage tank can store heat;
when the stored heat of the heat storage tank at the time t is equal to the minimum stored heat, the heat storage tank cannot release heat; when the stored heat of the heat storage tank is larger than the minimum stored heat at the time t, the heat storage tank can release heat.
Further, in the multi-heat source complementary joint scheduling model for establishing the agricultural photovoltaic heating unit, the central heating pipe network and the heat storage tank, a multi-objective function comprising the minimum energy consumption rate, the minimum carbon emission and the minimum economic cost is set, and is expressed as:
；
；/>；
；
；
is the minimum energy consumption rate +.>Is energy input quantity->For energy output, < >>Output of traditional heat supply unit for central heat supply>For generating heat by photovoltaic, add>To output other heat sources; />In order to minimize the amount of carbon emissions, For the fuel usage at time t, < >>A coefficient for carbon dioxide generation when the fuel is in use; />In order to minimize the cost of the economy,for fuel cost->For the amount of fuel purchased at time t +.>Is fuel unit price->For the operating costs of the individual devices, < > for>Is->Operating maintenance cost factor of individual devices, +.>Is->Output power at time t of individual device, +.>For the number of devices>To install the agricultural photovoltaic heating apparatus, it is necessary to give the agricultural user economic compensation costs, +.>For the photovoltaic heating capacity at time t +.>Economic compensation unit price for photovoltaic heating, +.>To install agricultureInstallation costs of industrial photovoltaic heating devices, < >>For the photovoltaic capacity at time t +.>Installing a cost coefficient for the photovoltaic heating equipment;
the setting related operation constraint conditions comprises: thermal power balance constraint conditions, upper and lower limit constraint conditions for operation of central heating heat source equipment, energy storage constraint conditions of a heat storage tank and operation constraint conditions of an agricultural photovoltaic heating unit;
the solving to obtain the optimal load distribution strategy of the agricultural photovoltaic heating unit, the central heating network and the heat storage tank to perform the multi-heat source joint scheduling control comprises the following steps: and solving a multi-heat source complementary joint scheduling model by adopting an intelligent optimization algorithm to obtain an optimal load distribution strategy of the agricultural photovoltaic heating unit, the central heating pipe network and the heat storage tank.
Further, the building of a heat pump regulation and control identification model: setting target operation parameters of a central heating network based on an optimal load distribution strategy of the central heating network, and combining heat parameters of an agricultural photovoltaic heating unit, heat parameters of a heat storage tank and heat pump operation characteristics, and obtaining heat pump regulation parameters matched with grid-connected parameters for heat pump regulation after analysis through online mechanism simulation and identification algorithm, wherein the method comprises the following steps:
setting target water supply and return temperature, target water supply and return pressure and target water supply and return flow of the central heating pipe network in each period based on an optimal load distribution strategy of the central heating pipe network;
based on an optimal load distribution strategy of the agricultural photovoltaic heating unit and the heat storage tank, acquiring heat supply values of the agricultural photovoltaic heating unit in each period, the running state of the heat storage tank, and heat storage capacity and heat release capacity of each period, and acquiring temperature, flow and pressure parameters of photovoltaic heat supply of the agricultural photovoltaic heating unit and the heat storage tank in each period before the agricultural photovoltaic heating unit and the heat storage tank are integrated into a central heating pipe network;
acquiring heat pump characteristic parameters including inlet and outlet water temperature, condenser water flow, condenser side water pressure drop, evaporator water flow, evaporator side water pressure drop, compressor running frequency and pump valve parameters of a heat pump;
The heat of the agricultural photovoltaic heating unit and the heat storage tank is regulated by a heat pump and is integrated into a structure of a central heating pipe network, a heating mechanism simulation model is built by adopting a mechanism modeling and data driving method, a target water supply and return temperature, a target water supply and return pressure, a target water supply and return flow, a pipe network load distribution value, an agricultural photovoltaic heating unit load distribution value, a heat storage tank running state, heat storage and release quantity, a photovoltaic heat temperature, a photovoltaic heat flow, a photovoltaic heat pressure and heat pump characteristic parameters are taken as model inputs, a heat pump regulation parameter at the next moment is taken as model output, a heat parameter change curve with time under the condition of multiple working conditions is combined, a heat pump regulation and prediction model is built by adopting machine learning algorithm training, and heat pump regulation and control parameters at each time period are obtained.
Further, the machine learning algorithm is a GAN-MFO-BPNN algorithm model, the heat pump characteristic parameters are subjected to countertraining through GAN, simulation data similar to the characteristics of the original heat pump characteristic parameters are generated after training is completed, the original heat pump characteristic parameters and the simulation data are mixed to form an expanded heat pump characteristic parameter set, and the heat pump characteristic parameter set and other input data of the model are input into the MFO-BPNN model together for training, and a heat pump regulation and control prediction model is built; the MFO-BPNN model optimizes the weight and the threshold value of the back propagation neural network BPNN through a moth fire suppression optimization algorithm MFO.
The beneficial effects of the invention are as follows:
(1) According to the method, the historical operation data and the meteorological data of the agricultural photovoltaic heating unit are obtained, a heating quantity prediction model of the agricultural photovoltaic heating unit is established, and heating quantity prediction values of the agricultural photovoltaic heating unit in future time periods are obtained through calculation; acquiring historical operation data and gas image data of a central heating network, establishing a terminal heat user load prediction model, and calculating to obtain load demand predicted values of the terminal heat user in future time periods; the method can accurately predict the heating capacity of the agricultural photovoltaic heating unit and the heat load demand of the heat users at the tail end of the central heating network in a time-sharing manner, and establish a data base of supply-demand balance for the follow-up multi-source complementary scheduling;
(2) According to the invention, the heat pump and the matching strategy are arranged between the agricultural photovoltaic heating unit and the central heating pipe network, so that the heat energy generated by the agricultural photovoltaic heating unit is converted into the heat energy matched with the parameters of the central heating pipe network through the heat pump, and then the heat energy is connected into the central heating pipe network; the heat generated by photovoltaic heating can meet the requirement of network access heat through heat pump regulation, so that the stability and safety of the whole heating system are ensured;
(3) According to the invention, the heat storage tank and the heat storage and release strategy are arranged between the agricultural photovoltaic heating unit and the central heating pipe network, so that the heat generated by the agricultural photovoltaic heating unit is stored and released through the heat storage tank, and the heat supply and demand balance is carried out in cooperation with the central heating pipe network; the energy fluctuation can be stabilized through the heat storage tank, the heat load peak is relieved, the photovoltaic heating energy is improved to be integrated into the large-network capacity, the effects of peak clipping and valley filling are achieved, and the dynamic change of the photovoltaic heating quantity and the heat load requirement can be well adapted;
(4) The invention establishes a multi-heat source complementary joint scheduling model of an agricultural photovoltaic heating unit, a central heating pipe network and a heat storage tank: based on the photovoltaic heating quantity predicted value, the heat user load demand predicted value, the running state of the heat storage tank and the time-sharing heat, setting a multi-objective function with minimum energy consumption rate, minimum carbon emission and minimum economic cost on the basis of supply-demand balance, setting related operation constraint conditions, and solving and obtaining an optimal load distribution strategy of the agricultural photovoltaic heating unit, the central heating pipe network and the heat storage tank to perform multi-heat source joint scheduling control; when the combined dispatching of the agricultural photovoltaic heating and the central heating pipe network is ensured, the alignment optimization on time, space, quantity and quality is considered, so that the efficient utilization of energy and the energy-saving, environment-friendly, economical and stable operation of the system are realized;
(5) The invention establishes a heat pump regulation and control identification model: setting target operation parameters of a central heating network based on an optimal load distribution strategy of the central heating network, and acquiring heat pump regulation parameters matched with grid-connected parameters for heat pump regulation after on-line mechanism simulation and identification algorithm analysis by combining heat parameters of an agricultural photovoltaic heating unit, heat parameters of a heat storage tank and heat pump operation characteristics; the heat pump system can realize accurate regulation and control of heat pump parameters, ensures that the heat parameters of photovoltaic heating output and the heat operation parameters of the central heating pipe network are accurately matched through heat pump regulation and control, and ensures the stability and safety of system operation.
Additional features and advantages will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a multi-source complementary scheduling method for incorporating agricultural photovoltaic heating into a central heating pipe network according to the present invention;
fig. 2 is a schematic diagram of a multi-source complementary scheduling structure of the agricultural photovoltaic heating integrated central heating pipe network of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, but 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.
Example 1
Fig. 1 is a flow chart of a multi-source complementary scheduling method for integrating agricultural photovoltaic heating into a central heating pipe network according to the invention.
Fig. 2 is a schematic diagram of a multi-source complementary scheduling structure of an agricultural photovoltaic heating integrated central heating pipe network according to the invention.
As shown in fig. 1-2, embodiment 1 provides a multi-source complementary scheduling method for incorporating agricultural photovoltaic heating into a central heating network, which includes:
acquiring historical operation data and meteorological data of an agricultural photovoltaic heating unit, establishing a heating quantity prediction model of the agricultural photovoltaic heating unit, and calculating to obtain heating quantity prediction values of the agricultural photovoltaic heating unit in future time periods;
Acquiring historical operation data and gas image data of a central heating network, establishing a terminal heat user load prediction model, and calculating to obtain load demand predicted values of the terminal heat user in future time periods;
a heat pump and a matching strategy are arranged between the agricultural photovoltaic heating unit and the central heating pipe network, and after the heat energy generated by the agricultural photovoltaic heating unit is converted into heat energy matched with the parameters of the central heating pipe network through the heat pump, the heat energy is connected into the central heating pipe network;
a heat storage tank and a heat storage and release strategy are arranged between the agricultural photovoltaic heating unit and the central heating pipe network, and heat generated by the agricultural photovoltaic heating unit is stored and released through the heat storage tank, so that heat supply and heat demand balance is carried out in cooperation with the central heating pipe network;
building a multi-heat source complementary joint scheduling model of an agricultural photovoltaic heating unit, a central heating pipe network and a heat storage tank: based on the photovoltaic heating quantity predicted value, the heat user load demand predicted value, the running state of the heat storage tank and the time-sharing heat, setting a multi-objective function with minimum energy consumption rate, minimum carbon emission and minimum economic cost on the basis of supply-demand balance, setting related operation constraint conditions, and solving and obtaining an optimal load distribution strategy of the agricultural photovoltaic heating unit, the central heating pipe network and the heat storage tank to perform multi-heat source joint scheduling control;
Establishing a heat pump regulation and control identification model: setting target operation parameters of the central heating network based on an optimal load distribution strategy of the central heating network, and acquiring heat pump regulation parameters matched with grid-connected parameters for heat pump regulation after on-line mechanism simulation and identification algorithm analysis by combining the heat parameters of the agricultural photovoltaic heating unit, the heat parameters of the heat storage tank and the heat pump operation characteristics.
In this embodiment, the obtaining the historical operation data and the meteorological data of the agricultural photovoltaic heating unit, establishing a heating amount prediction model of the agricultural photovoltaic heating unit, and calculating to obtain the heating amount prediction value of the agricultural photovoltaic heating unit in each future period includes:
acquiring operation data of a solar heat collector, a photovoltaic panel, radiating pipe equipment and a water circulation system in an agricultural photovoltaic heating unit; the agricultural photovoltaic heating units are distributed in farmlands in alpine regions, and are deployed in a heating period in winter, so that movable detachable recovery is performed in a non-heating period in spring;
acquiring historical meteorological data comprising illumination intensity, temperature and humidity, and clustering the historical meteorological data into different time periods and weather scenes, wherein the weather scenes comprise strong sunshine in sunny days, weak sunshine in sunny days, no sunshine at night and weak sunshine in overcast and rainy days;
Dividing the next day into different time periods according to the divided different time periods and weather scenes, acquiring historical operation data of the agricultural photovoltaic heating unit in the same scene, establishing a data sample by combining the weather data in the same historical scene, training and learning the data sample by adopting a machine learning algorithm, and establishing a heating quantity prediction model of the agricultural photovoltaic heating unit in different time periods of different weather scenes in the future, thereby obtaining a photovoltaic heating quantity prediction value in the future time-division scene.
It should be noted that, this patent is applied to the winter heating period in alpine region, and the agricultural photovoltaic heating unit can be distributed and removed the dismantlement formula and set up and carry out unified dispatch control management in the farmland. The agricultural photovoltaic heating is an important presentation form of the existing agriculture, can drive the transformation and upgrading of the agricultural industry, promote the high-quality development of rural economy, can relieve rural land utilization pressure, improve land utilization rate, does not occupy land resources additionally, can realize the transformation of land resources, does not generally need to operate in the period of heating in winter, has no agricultural product explanation, is convenient to heat through a photovoltaic heating unit, and can give farmland users a certain economic compensation. The arrangement of the agricultural photovoltaic heating unit is required to follow the principle of local conditions, and proper installation positions and modes are selected according to local illumination conditions and topography. For example, in a region with better illumination conditions, a solar panel can be installed on a space of a farmland, and in a region with more complex terrain or worse illumination conditions, the solar panel needs to be designed according to specific situations.
In this embodiment, the obtaining historical operation data and meteorological data of the central heating network, establishing a load prediction model of the end heat user, and calculating to obtain load demand predicted values of the end heat user in future time periods includes:
acquiring historical operation data comprising historical water supply and return temperature, water supply and return flow and water supply and return pressure of a central heating pipe network; acquiring historical meteorological data comprising illumination intensity, temperature, humidity and wind power; constructing a data sample comprising historical operating data and historical meteorological data;
and training and learning data samples by adopting an XGBoost algorithm, establishing a central heating network terminal heat user load prediction model, and calculating to obtain load demand predicted values of terminal heat users in future time periods.
In this embodiment, training and learning of the data samples are performed by using a machine learning algorithm, and a heating amount prediction model of the agricultural photovoltaic heating unit in different periods of different weather scenes in the future is established, including:
training and learning data samples by adopting an improved LightGBM algorithm, and establishing an agricultural photovoltaic heating unit heating quantity prediction model based on the LightGBM algorithm;
analyzing the heat production quantity prediction model of the agricultural photovoltaic heating unit based on the LightGBM algorithm by adopting a SHAP algorithm, calculating the SHAP value of each input characteristic variable, determining the influence of each input characteristic variable on the photovoltaic heat production quantity, and obtaining the importance ranking of each input characteristic variable;
Selecting input characteristic variables with preset proportions from front to back according to importance sorting, combining the input characteristic variables as candidate characteristic variables, training a prediction model of the heating quantity of the agricultural photovoltaic heating unit through an improved LightGBM algorithm, calculating an average absolute error and a decisive coefficient, and evaluating a model prediction precision value of the combined characteristic;
selecting an input feature set corresponding to the minimum average absolute error and the maximum decisive coefficient as an optimal feature set, and training and establishing heating quantity prediction models of the agricultural photovoltaic heating unit in different weather scenes in the future in different time periods through the optimal feature set;
wherein, the improved LightGBM algorithm adopts ISSA algorithm to optimize the number of cotyledons, the maximum depth and the learning rate in the LightGBM algorithm model;
the SHAP value for each input feature variable is calculated as:
；
；
is a model predictive value; />The prediction result is that no characteristic value exists; />Is->SHAP values for the individual feature variables;to be at->The feature variables are equal to 1 when selected, otherwise equal to 0; />The number of the characteristic variables; />A set of all feature variables; />For a given subset of predicted features; />To include->Model prediction results of the individual feature variables; To not include->Model predictions for individual feature variables.
It should be noted that, the SHAP is an additive feature attribution model based on the cooperative game, which can be understood that the actual predicted value of the model is obtained by linearly adding the average predicted value of the model and the contribution of each input feature. The introduction of the SHAP model further enhances the interpretability of the improved LightGBM model, and in using SHAP for interpretable analysis, the feature profile interprets the predictions of the model from a global perspective, helping to understand the response trend of each feature within the model.
In this embodiment, set up heat pump and matching strategy between the unit is heated to the agricultural photovoltaic and central heating pipe network, after converting the heat energy that the unit was heated to the agricultural photovoltaic and central heating pipe network parameter assorted heat energy through the heat pump, and the access central heating pipe network specifically includes:
the heat pump is set up between the agricultural photovoltaic heating unit and the central heating pipe network, when the heat energy parameter between the two parties is unmatched, consider the heat quantity change of the agricultural photovoltaic heating unit, the temperature, the pressure and the flow parameter of the central heating pipe network to carry out the heat pump and adjust, include: when the temperature of the photovoltaic heat generation is too high or too low, the temperature of the photovoltaic heat generation is adjusted to a temperature range matched with a central heating pipe network by adjusting a heat pump; when the flow and the pressure of the photovoltaic heating system are too large or too small, the pipe network is broken or equipment is damaged, and the flow and the pressure of the photovoltaic heating system are adjusted to be in a flow range and a pressure range matched with the central heating pipe network by adjusting the heat pump;
According to the predicted value of the heating amount in each future period of the agricultural photovoltaic heating unit, the dynamic change period of the photovoltaic heating amount is obtained, and according to the predicted value of the load demand of each future period of the tail end heat user of the central heating pipe network, the dynamic change period of the load demand of the tail end heat user is obtained, and the network access parameter matching is satisfied through the adjustment of the heat pump related equipment in each dynamic change period of the photovoltaic heat supply and the heat demand of the heat user.
It should be noted that, network access parameter matching mainly includes temperature matching, flow matching and pressure matching, and satisfies network access heat requirement together, so as to ensure stability and safety of the whole heating system.
Temperature matching: the temperature of heat generated by the agricultural photovoltaic heating unit needs to be matched with parameters of a central heating network. If the temperature of the heat generated by the photovoltaic heating is too high or too low, the operation of the heating large network may be unstable and even the equipment is damaged, so that the temperature of the heat generated by the photovoltaic heating needs to be adjusted to be matched with the heating large network through the heat pump.
Flow matching: the heat generated by the agricultural photovoltaic heating unit needs to be transmitted to each user of the large network through the heat supply pipeline, so that the flow of the pipeline needs to be ensured to be matched with the flow of the heat generated by photovoltaic heating, and if the flow is too large or too small, uneven heat supply or equipment damage can be caused.
Pressure matching: the heat pressure generated by the agricultural photovoltaic heating unit needs to be matched with the pipeline pressure of the heat supply large network. If the pressure is too high or too low, the pipelines may be broken or the equipment may be damaged, so that parameters of the heat pump system need to be adjusted to ensure that the heat pressure of the photovoltaic heating system is matched with the pipeline pressure of the heating large network.
In this embodiment, set up heat storage tank and heat accumulation and release strategy between agricultural photovoltaic heating unit and concentrated heating pipe network, store and release the heat of agricultural photovoltaic heating unit output through the heat storage tank, supply and demand heat's balance in coordination with the concentrated heating pipe network, include:
a heat storage tank is arranged between the agricultural photovoltaic heating unit and the central heating pipe network, when the deviation between the predicted value and the actual value of the heating quantity of the agricultural photovoltaic heating unit exceeds a threshold value, the heat storage tank is utilized to store redundant heat when the actual value of the photovoltaic heating quantity exceeds the predicted value, or release the stored heat when the actual value of the photovoltaic heating quantity is smaller than the predicted value to make up for the missing heat, and when the expected heat is still not reached, the output cooperation of the central heating pipe network is enhanced to balance the heat supply and demand;
When the heat supply and demand balance is carried out between the agricultural photovoltaic heating unit and the central heating pipe network, the photovoltaic heating amount is monitored and predicted in real time, and the heat storage tank is utilized for dispatching and adjusting the photovoltaic heating amount.
The heat storage tank has the functions of stabilizing energy fluctuation, relieving heat load peak, improving the capacity of the photovoltaic heating energy source for being integrated into a large network, cutting peaks and filling valleys, and can better adapt to the dynamic change of the photovoltaic heating quantity and the heat load demand.
In this embodiment, the operation state and time-sharing heat of the heat storage tank includes: according to the heat accumulation and release state, the maximum energy-of-charge state and the minimum energy-of-charge state of the heat storage tank, a heat model of the heat storage tank is established, and the heat value and the corresponding running state of the heat storage tank in each period are obtained;
the thermal model of the heat storage tank is expressed as:
；
the heat stored by the heat storage tank at the time t is stored; />The coefficient of energy dissipation of the heat storage tank; />The heat storage power of the heat storage tank at the time t; />Is the heat storage efficiency; />The exothermic power of the heat storage tank at the time t;is exothermic efficiency;
when the stored heat of the heat storage tank at the moment t is equal to the maximum stored heat, the heat storage tank can not store heat; when the stored heat of the heat storage tank at the time t is smaller than the maximum stored heat, the heat storage tank can store heat;
When the stored heat of the heat storage tank at the time t is equal to the minimum stored heat, the heat storage tank cannot release heat; when the stored heat of the heat storage tank is larger than the minimum stored heat at the time t, the heat storage tank can release heat.
In this embodiment, in the building of the multi-heat source complementary joint scheduling model of the agricultural photovoltaic heating unit, the central heating pipe network and the heat storage tank, a multi-objective function including the minimum energy consumption rate, the minimum carbon emission and the minimum economic cost is set, and is expressed as:
；
；/>；
；
；
is the minimum energy consumption rate +.>Is energy input quantity->For energy output, < >>Output of traditional heat supply unit for central heat supply>For generating heat by photovoltaic, add>To output other heat sources; />Is minimum in carbon emission>For the fuel usage at time t, < >>A coefficient for carbon dioxide generation when the fuel is in use; />To minimize economic cost->For fuel cost->For the amount of fuel purchased at time t +.>Is fuel unit price->For the operating costs of the respective devices,is->Operating maintenance cost factor of individual devices, +.>Is->Output power at time t of individual device, +.>For the number of devices>To install the agricultural photovoltaic heating apparatus, it is necessary to give the agricultural user economic compensation costs, +. >For the photovoltaic heating capacity at time t +.>Economic compensation unit price for photovoltaic heating, +.>To install the installation cost of the agricultural photovoltaic heating apparatus,for the photovoltaic capacity at time t +.>Installing a cost coefficient for the photovoltaic heating equipment;
the setting related operation constraint conditions comprises: thermal power balance constraint conditions, upper and lower limit constraint conditions for operation of central heating heat source equipment, energy storage constraint conditions of a heat storage tank and operation constraint conditions of an agricultural photovoltaic heating unit;
the solving to obtain the optimal load distribution strategy of the agricultural photovoltaic heating unit, the central heating network and the heat storage tank to perform the multi-heat source joint scheduling control comprises the following steps: and solving a multi-heat source complementary joint scheduling model by adopting an intelligent optimization algorithm to obtain an optimal load distribution strategy of the agricultural photovoltaic heating unit, the central heating pipe network and the heat storage tank.
In the multi-source complementary scheduling, photovoltaic heating capacity is preferentially utilized, photovoltaic heating capacity can be guaranteed to be fully utilized, in order to avoid fluctuation of the photovoltaic heating capacity, problems of hydraulic fluctuation and the like caused by frequent central heating network regulation and control are avoided, the photovoltaic heating capacity can be stored and released, fluctuation is stabilized, and load peaks Gu Ping can be cooperatively processed in a day, so that load output is more stable. For example, during the daytime, when the output of the photovoltaic heat source is strong, the photovoltaic heat source can be preferentially used for supplying heat, and meanwhile, the redundant heat energy is stored; at night, when the output of the photovoltaic heat source is weak or not, the stored heat energy can be utilized to supplement heat, and the heat is supplemented into a central heat supply large network, so that the stable operation of the system is ensured. The heat storage tank is arranged between the photovoltaic heating and the central heating large network, and can play roles of stabilizing fluctuation, balancing heat, stabilizing output and the like, so that the photovoltaic heating is more reliably and stably connected into the large network system.
In practical application, the method further comprises the step of evaluating scheduling performance after the optimal load distribution strategy is executed, wherein the scheduling performance comprises energy consumption, carbon emission and heat supply stability, and the scheduling strategy is adjusted and optimized according to the performance evaluation result so as to further improve the scheduling effect.
When the agricultural photovoltaic heating and the central heating pipe network are jointly scheduled, the alignment optimization in terms of time, space, quantity and quality is important, and the aim of realizing the efficient utilization of energy and the stable operation of the system is achieved.
Time alignment: the output of photovoltaic heating is influenced by illumination conditions, and has the characteristics of daytime peaks and nighttime valleys. In order to ensure the balance of heat supply and heat demand in each time period, time alignment is needed, and a dispatching system performs heat cooperative supply in each time period of the day and the night so as to ensure continuous heat supply.
Spatial alignment: the agricultural photovoltaic heating units are distributed at different farmland geographic positions, a central heating large network covers a certain heat user area, and in order to achieve spatial alignment, a dispatching system needs to consider the geographic position of the agricultural photovoltaic heating and the coverage area of the large network so as to ensure that the agricultural photovoltaic heating can be efficiently conveyed to the heat user area needing heat supply.
Alignment of the number: the heat supply quantity of the agricultural photovoltaic heating and the load demand of the heat user at the tail end of the large network are balanced, and a scheduling system needs to formulate a reasonable scheduling strategy according to the load demand of the large network and the predicted output of the photovoltaic heating so as to ensure the stability of the supply quantity and meet the heat load demand.
Alignment of the materials: the heat production quality of agricultural photovoltaic heating is affected by factors such as illumination conditions and equipment performance, and the central heating large network has certain requirements on the heat quality, so that quality parameters of photovoltaic heating need to be monitored and controlled in order to achieve quality alignment, and the heat requirement of the load large network is guaranteed to be matched.
In this embodiment, the heat pump regulation and control identification model is established: setting target operation parameters of a central heating network based on an optimal load distribution strategy of the central heating network, and combining heat parameters of an agricultural photovoltaic heating unit, heat parameters of a heat storage tank and heat pump operation characteristics, and obtaining heat pump regulation parameters matched with grid-connected parameters for heat pump regulation after analysis through online mechanism simulation and identification algorithm, wherein the method comprises the following steps:
setting target water supply and return temperature, target water supply and return pressure and target water supply and return flow of the central heating pipe network in each period based on an optimal load distribution strategy of the central heating pipe network;
Based on an optimal load distribution strategy of the agricultural photovoltaic heating unit and the heat storage tank, acquiring heat supply values of the agricultural photovoltaic heating unit in each period, the running state of the heat storage tank, and heat storage capacity and heat release capacity of each period, and acquiring temperature, flow and pressure parameters of photovoltaic heat supply of the agricultural photovoltaic heating unit and the heat storage tank in each period before the agricultural photovoltaic heating unit and the heat storage tank are integrated into a central heating pipe network;
acquiring heat pump characteristic parameters including inlet and outlet water temperature, condenser water flow, condenser side water pressure drop, evaporator water flow, evaporator side water pressure drop, compressor running frequency and pump valve parameters of a heat pump;
the heat of the agricultural photovoltaic heating unit and the heat storage tank is regulated by a heat pump and is integrated into a structure of a central heating pipe network, a heating mechanism simulation model is built by adopting a mechanism modeling and data driving method, a target water supply and return temperature, a target water supply and return pressure, a target water supply and return flow, a pipe network load distribution value, an agricultural photovoltaic heating unit load distribution value, a heat storage tank running state, heat storage and release quantity, a photovoltaic heat temperature, a photovoltaic heat flow, a photovoltaic heat pressure and heat pump characteristic parameters are taken as model inputs, a heat pump regulation parameter at the next moment is taken as model output, a heat parameter change curve with time under the condition of multiple working conditions is combined, a heat pump regulation and prediction model is built by adopting machine learning algorithm training, and heat pump regulation and control parameters at each time period are obtained.
In this embodiment, the machine learning algorithm is a GAN-MFO-BPNN algorithm model, the heat pump characteristic parameters are subjected to countertraining by GAN, after training is completed, simulation data similar to the characteristics of the original heat pump characteristic parameters are generated, the original heat pump characteristic parameters and the simulation data are mixed to form an expanded heat pump characteristic parameter set, and the expanded heat pump characteristic parameter set and other input data of the model are input into the MFO-BPNN model together for training, so as to establish a heat pump regulation and control prediction model; the MFO-BPNN model optimizes the weight and the threshold value of the back propagation neural network BPNN through a moth fire suppression optimization algorithm MFO.
It should be noted that, the historical real data samples of the heat pump regulation are fewer, in order to solve the problem of insufficient heat pump data samples, the GAN network is introduced to generate the simulation data with similar characteristics to the historical characteristic parameters of the heat pump through the countermeasure training of the generator and the discriminator, so that the accuracy of the heat pump regulation prediction model under the data expansion is higher. The GAN generation countermeasure network consists of a generator and a discriminator, and the generator and the discriminator are both neural network models. The basic idea of generating the countermeasure network is to continuously improve the generating capacity of the generator and the discriminating capacity of the discriminator through the game of the generator and the discriminator, and finally, nash equilibrium is achieved, at the moment, the discriminator cannot judge the authenticity of the input sample, and the fact that the generator learns the data characteristics and the distribution of the real sample is indicated.
Distinguishing deviceThe loss function of (2) is expressed as: />；
A generatorThe loss function of (2) is expressed as: />；
Is a sample label; />Is a real sample; />The input to the generator is random Gaussian noise; />A pseudo sample generated by the generator; />And->The output of the corresponding pseudo sample and the real sample of the discriminator is 0 or 1 respectively.
Generating a countermeasure network, optimizing parameters of a generator and a discriminator through alternate training, wherein the final discriminator cannot discriminate the authenticity of a pseudo sample generated by the generator, and at the moment, the objective function is minimized and expressed as:
；
is->Entropy of (2); />Is->Probability distribution of (2); />Is->Entropy of (2); />Is->Is a probability distribution of (c).
A flame-based position updating mechanism is adopted in the moth fire suppression optimization algorithm MFO, a certain number of moths are initialized, and initial weights and thresholds are randomly distributed for the network; and then calculating fitness, namely calculating and recording output errors by using a given training set for each neural network, and updating the position of each moth according to the fitness. If the adaptability of a certain moth is high, the position of the moth is kept unchanged; otherwise, the position is moved to a position more suitable for solving the problem by a certain distance.
The location update is expressed as:
；
；
；
Is a moth; />Is a flame; />Is a spiral flight function of the moths; />Is the distance between the flame and the moth; />Is a spiral constant; />Is [ -1,1]Random numbers in between.
And sorting the updated moths and flame positions according to the fitness, and selecting the position with better fitness as the position of the next-generation flame for updating. As the iteration proceeds, the number of flames will adaptively decrease, expressed as:
；
is the number of flames; />Is the population number of the moths; />The current iteration number; />Is the maximum number of iterations.
When the number of the flame is reduced, the number of the moths is larger than that of the flame, and the position of the moths is updated according to the flame with the worst current fitness; and when the preset iteration times are reached or the fitness value meets the requirements, ending the algorithm, and outputting the weight and the threshold of the neural network with the best fitness.
In the several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways as well. The system embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present invention may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored on a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
With the above-described preferred embodiments according to the present invention as an illustration, the above-described descriptions can be used by persons skilled in the relevant art to make various changes and modifications without departing from the scope of the technical idea of the present invention. The technical scope of the present invention is not limited to the description, but must be determined according to the scope of claims.
Claims (8)
1. A multi-source complementary scheduling method for incorporating agricultural photovoltaic heating into a central heating network, comprising:
acquiring historical operation data and meteorological data of an agricultural photovoltaic heating unit, establishing a heating quantity prediction model of the agricultural photovoltaic heating unit, and calculating to obtain heating quantity prediction values of the agricultural photovoltaic heating unit in future time periods;
acquiring historical operation data and gas image data of a central heating network, establishing a terminal heat user load prediction model, and calculating to obtain load demand predicted values of the terminal heat user in future time periods;
a heat pump and a matching strategy are arranged between the agricultural photovoltaic heating unit and the central heating pipe network, and after the heat energy generated by the agricultural photovoltaic heating unit is converted into heat energy matched with the parameters of the central heating pipe network through the heat pump, the heat energy is connected into the central heating pipe network;
a heat storage tank and a heat storage and release strategy are arranged between the agricultural photovoltaic heating unit and the central heating pipe network, and heat generated by the agricultural photovoltaic heating unit is stored and released through the heat storage tank, so that heat supply and heat demand balance is carried out in cooperation with the central heating pipe network;
building a multi-heat source complementary joint scheduling model of an agricultural photovoltaic heating unit, a central heating pipe network and a heat storage tank: based on the photovoltaic heating quantity predicted value, the heat user load demand predicted value, the running state of the heat storage tank and the time-sharing heat, setting a multi-objective function with minimum energy consumption rate, minimum carbon emission and minimum economic cost on the basis of supply-demand balance, setting related operation constraint conditions, and solving and obtaining an optimal load distribution strategy of the agricultural photovoltaic heating unit, the central heating pipe network and the heat storage tank to perform multi-heat source joint scheduling control;
In the multi-heat source complementary joint scheduling model for establishing the agricultural photovoltaic heating unit, the central heating pipe network and the heat storage tank, a multi-objective function with minimum energy consumption rate, minimum carbon emission and minimum economic cost is set, and is expressed as:
；
；/>；
；
；
is the minimum energy consumption rate +.>Is energy input quantity->For energy output, < >>Output of traditional heat supply unit for central heat supply>For generating heat by photovoltaic, add>To output other heat sources; />Is minimum in carbon emission>For the fuel usage at time t, < >>A coefficient for carbon dioxide generation when the fuel is in use; />In order to minimize the cost of the economy,for fuel cost->For the amount of fuel purchased at time t +.>Is fuel unit price->For the operating costs of the individual devices, < > for>Is->Operating maintenance cost factor of individual devices, +.>Is->Output power at time t of individual device, +.>For the number of devices>To install the agricultural photovoltaic heating apparatus, it is necessary to give the agricultural user economic compensation costs, +.>For the photovoltaic heating capacity at time t +.>Economic compensation unit price for photovoltaic heating, +.>Installation cost for installing agricultural photovoltaic heating equipment, < >>For the photovoltaic capacity at time t +.>Installing a cost coefficient for the photovoltaic heating equipment;
The setting related operation constraint conditions comprises: thermal power balance constraint conditions, upper and lower limit constraint conditions for operation of central heating heat source equipment, energy storage constraint conditions of a heat storage tank and operation constraint conditions of an agricultural photovoltaic heating unit;
the solving to obtain the optimal load distribution strategy of the agricultural photovoltaic heating unit, the central heating network and the heat storage tank to perform the multi-heat source joint scheduling control comprises the following steps: solving a multi-heat source complementary joint scheduling model by adopting an intelligent optimization algorithm to obtain an optimal load distribution strategy of the agricultural photovoltaic heating unit, the central heating pipe network and the heat storage tank;
establishing a heat pump regulation and control identification model: setting target operation parameters of a central heating network based on an optimal load distribution strategy of the central heating network, and combining heat parameters of an agricultural photovoltaic heating unit, heat parameters of a heat storage tank and heat pump operation characteristics, and obtaining heat pump regulation parameters matched with grid-connected parameters for heat pump regulation after analysis through online mechanism simulation and identification algorithm, wherein the method comprises the following steps:
setting target water supply and return temperature, target water supply and return pressure and target water supply and return flow of the central heating pipe network in each period based on an optimal load distribution strategy of the central heating pipe network;
Based on an optimal load distribution strategy of the agricultural photovoltaic heating unit and the heat storage tank, acquiring heat supply values of the agricultural photovoltaic heating unit in each period, the running state of the heat storage tank, and heat storage capacity and heat release capacity of each period, and acquiring temperature, flow and pressure parameters of photovoltaic heat supply of the agricultural photovoltaic heating unit and the heat storage tank in each period before the agricultural photovoltaic heating unit and the heat storage tank are integrated into a central heating pipe network;
acquiring heat pump characteristic parameters including inlet and outlet water temperature, condenser water flow, condenser side water pressure drop, evaporator water flow, evaporator side water pressure drop, compressor running frequency and pump valve parameters of a heat pump;
the heat of the agricultural photovoltaic heating unit and the heat storage tank is regulated by a heat pump and is integrated into a structure of a central heating pipe network, a heating mechanism simulation model is built by adopting a mechanism modeling and data driving method, a target water supply and return temperature, a target water supply and return pressure, a target water supply and return flow, a pipe network load distribution value, an agricultural photovoltaic heating unit load distribution value, a heat storage tank running state, heat storage and release quantity, a photovoltaic heat temperature, a photovoltaic heat flow, a photovoltaic heat pressure and heat pump characteristic parameters are taken as model inputs, a heat pump regulation parameter at the next moment is taken as model output, a heat parameter change curve with time under the condition of multiple working conditions is combined, a heat pump regulation and prediction model is built by adopting machine learning algorithm training, and heat pump regulation and control parameters at each time period are obtained.
2. The multi-source complementary scheduling method according to claim 1, wherein the steps of obtaining historical operation data and meteorological data of the agricultural photovoltaic heating unit, establishing a heating amount prediction model of the agricultural photovoltaic heating unit, and calculating and obtaining heating amount prediction values of the agricultural photovoltaic heating unit in future time periods include:
acquiring operation data of a solar heat collector, a photovoltaic panel, radiating pipe equipment and a water circulation system in an agricultural photovoltaic heating unit; the agricultural photovoltaic heating units are distributed in farmlands in alpine regions, and are deployed in a heating period in winter, so that movable detachable recovery is performed in a non-heating period in spring;
acquiring historical meteorological data comprising illumination intensity, temperature and humidity, and clustering the historical meteorological data into different time periods and weather scenes, wherein the weather scenes comprise strong sunshine in sunny days, weak sunshine in sunny days, no sunshine at night and weak sunshine in overcast and rainy days;
dividing the next day into different time periods according to the divided different time periods and weather scenes, acquiring historical operation data of the agricultural photovoltaic heating unit in the same scene, establishing a data sample by combining the weather data in the same historical scene, training and learning the data sample by adopting a machine learning algorithm, and establishing a heating quantity prediction model of the agricultural photovoltaic heating unit in different time periods of different weather scenes in the future, thereby obtaining a photovoltaic heating quantity prediction value in the future time-division scene.
3. The multi-source complementary scheduling method according to claim 1, wherein the steps of obtaining historical operation data and air condition data of the central heating network, establishing an end heat user load prediction model, and calculating and obtaining load demand predicted values of the end heat user in future time periods include:
acquiring historical operation data comprising historical water supply and return temperature, water supply and return flow and water supply and return pressure of a central heating pipe network; acquiring historical meteorological data comprising illumination intensity, temperature, humidity and wind power; constructing a data sample comprising historical operating data and historical meteorological data;
and training and learning data samples by adopting an XGBoost algorithm, establishing a central heating network terminal heat user load prediction model, and calculating to obtain load demand predicted values of terminal heat users in future time periods.
4. The multi-source complementary scheduling method according to claim 2, wherein the training and learning of the data samples by using a machine learning algorithm, and the building of the prediction model of the heating amount of the agricultural photovoltaic heating unit in different periods of different weather scenes in the future, comprises:
training and learning data samples by adopting an improved LightGBM algorithm, and establishing an agricultural photovoltaic heating unit heating quantity prediction model based on the LightGBM algorithm;
Analyzing the heat production quantity prediction model of the agricultural photovoltaic heating unit based on the LightGBM algorithm by adopting a SHAP algorithm, calculating the SHAP value of each input characteristic variable, determining the influence of each input characteristic variable on the photovoltaic heat production quantity, and obtaining the importance ranking of each input characteristic variable;
selecting input characteristic variables with preset proportions from front to back according to importance sorting, combining the input characteristic variables as candidate characteristic variables, training a prediction model of the heating quantity of the agricultural photovoltaic heating unit through an improved LightGBM algorithm, calculating an average absolute error and a decisive coefficient, and evaluating a model prediction precision value of the combined characteristic;
selecting an input feature set corresponding to the minimum average absolute error and the maximum decisive coefficient as an optimal feature set, and training and establishing heating quantity prediction models of the agricultural photovoltaic heating unit in different weather scenes in the future in different time periods through the optimal feature set;
wherein, the improved LightGBM algorithm adopts ISSA algorithm to optimize the number of cotyledons, the maximum depth and the learning rate in the LightGBM algorithm model;
the SHAP value for each input feature variable is calculated as:
；
；
is a model predictive value; />The prediction result is that no characteristic value exists; / >Is->SHAP values for the individual feature variables; />To be at->The feature variables are equal to 1 when selected, otherwise equal to 0; />The number of the characteristic variables; />A set of all feature variables; />For a given subset of predicted features; />To include->Model prediction results of the individual feature variables;to not include->Model predictions for individual feature variables.
5. The multi-source complementary scheduling method according to claim 1, wherein a heat pump and a matching strategy are set between the agricultural photovoltaic heating unit and the central heating pipe network, and after the heat energy generated by the agricultural photovoltaic heating unit is converted into the heat energy matched with the parameters of the central heating pipe network by the heat pump, the heat energy is accessed into the central heating pipe network, and the method specifically comprises the following steps:
the heat pump is set up between the agricultural photovoltaic heating unit and the central heating pipe network, when the heat energy parameter between the two parties is unmatched, consider the heat quantity change of the agricultural photovoltaic heating unit, the temperature, the pressure and the flow parameter of the central heating pipe network to carry out the heat pump and adjust, include: when the temperature of the photovoltaic heat generation is too high or too low, the temperature of the photovoltaic heat generation is adjusted to a temperature range matched with a central heating pipe network by adjusting a heat pump; when the flow and the pressure of the photovoltaic heating system are too large or too small, the pipe network is broken or equipment is damaged, and the flow and the pressure of the photovoltaic heating system are adjusted to be in a flow range and a pressure range matched with the central heating pipe network by adjusting the heat pump;
According to the predicted value of the heating amount in each future period of the agricultural photovoltaic heating unit, the dynamic change period of the photovoltaic heating amount is obtained, and according to the predicted value of the load demand of each future period of the tail end heat user of the central heating pipe network, the dynamic change period of the load demand of the tail end heat user is obtained, and the network access parameter matching is satisfied through the adjustment of the heat pump related equipment in each dynamic change period of the photovoltaic heat supply and the heat demand of the heat user.
6. The multi-source complementary scheduling method according to claim 1, wherein a heat storage tank and a heat storage and release strategy are arranged between the agricultural photovoltaic heating unit and the central heating pipe network, heat generated by the agricultural photovoltaic heating unit is stored and released through the heat storage tank, and heat supply and heat demand balance is performed in cooperation with the central heating pipe network, and the method comprises the following steps:
a heat storage tank is arranged between the agricultural photovoltaic heating unit and the central heating pipe network, when the deviation between the predicted value and the actual value of the heating quantity of the agricultural photovoltaic heating unit exceeds a threshold value, the heat storage tank is utilized to store redundant heat when the actual value of the photovoltaic heating quantity exceeds the predicted value, or release the stored heat when the actual value of the photovoltaic heating quantity is smaller than the predicted value to make up for the missing heat, and when the expected heat is still not reached, the output cooperation of the central heating pipe network is enhanced to balance the heat supply and demand;
When the heat supply and demand balance is carried out between the agricultural photovoltaic heating unit and the central heating pipe network, the photovoltaic heating amount is monitored and predicted in real time, and the heat storage tank is utilized for dispatching and adjusting the photovoltaic heating amount.
7. The multi-source complementary scheduling method of claim 1, wherein the operating state and time-sharing heat of the heat storage tank comprises: according to the heat accumulation and release state, the maximum energy-of-charge state and the minimum energy-of-charge state of the heat storage tank, a heat model of the heat storage tank is established, and the heat value and the corresponding running state of the heat storage tank in each period are obtained;
the thermal model of the heat storage tank is expressed as:
；
the heat stored by the heat storage tank at the time t is stored; />The coefficient of energy dissipation of the heat storage tank; />The heat storage power of the heat storage tank at the time t; />Is the heat storage efficiency; />The exothermic power of the heat storage tank at the time t;is exothermic efficiency;
when the stored heat of the heat storage tank at the moment t is equal to the maximum stored heat, the heat storage tank can not store heat; when the stored heat of the heat storage tank at the time t is smaller than the maximum stored heat, the heat storage tank can store heat;
when the stored heat of the heat storage tank at the time t is equal to the minimum stored heat, the heat storage tank cannot release heat; when the stored heat of the heat storage tank is larger than the minimum stored heat at the time t, the heat storage tank can release heat.
8. The multi-source complementary scheduling method according to claim 1, wherein the machine learning algorithm is a GAN-MFO-BPNN algorithm model, the heat pump characteristic parameters are subjected to countertraining by GAN, simulation data similar to the characteristics of the original heat pump characteristic parameters are generated after the training is completed, the original heat pump characteristic parameters and the simulation data are mixed to form an expanded heat pump characteristic parameter set, and the heat pump characteristic parameter set and other input data of the model are input into the MFO-BPNN model for training, so that a heat pump regulation and control prediction model is established; the MFO-BPNN model optimizes the weight and the threshold value of the back propagation neural network BPNN through a moth fire suppression optimization algorithm MFO.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410039600.2A CN117553337B (en) | 2024-01-11 | 2024-01-11 | Multisource complementary scheduling method considering agricultural photovoltaic heating and integrated central heating pipe network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410039600.2A CN117553337B (en) | 2024-01-11 | 2024-01-11 | Multisource complementary scheduling method considering agricultural photovoltaic heating and integrated central heating pipe network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117553337A CN117553337A (en) | 2024-02-13 |
| CN117553337B true CN117553337B (en) | 2024-03-22 |
Family
ID=89818989
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410039600.2A Active CN117553337B (en) | 2024-01-11 | 2024-01-11 | Multisource complementary scheduling method considering agricultural photovoltaic heating and integrated central heating pipe network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117553337B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103115389A (en) * | 2012-12-27 | 2013-05-22 | 重庆大学 | Solar energy combined type phase-change heat storage heating system |
| CN111524028A (en) * | 2020-04-03 | 2020-08-11 | 中煤科工(天津)清洁能源研究院有限公司 | Configuration method of multi-energy complementary coupling system |
| CN114508784A (en) * | 2022-02-16 | 2022-05-17 | 重庆邮电大学 | Multi-source complementary heating system and optimization control method thereof |
| WO2022168049A1 (en) * | 2021-02-07 | 2022-08-11 | Octopus Energy Group Limited | Heating installations, methods and systems |
| CN115455835A (en) * | 2022-09-21 | 2022-12-09 | 浙江英集动力科技有限公司 | Optimized operation method of renewable energy-containing multi-heat-source networked heating system |
| CN115828726A (en) * | 2022-10-19 | 2023-03-21 | 浙江英集动力科技有限公司 | Machine learning-based solar cross-season heat storage and supply system optimization control method |
| CN116613828A (en) * | 2023-05-23 | 2023-08-18 | 中国南方电网有限责任公司 | Configuration method and configuration device of multi-energy system for promoting new energy consumption |
| CN116628972A (en) * | 2023-05-19 | 2023-08-22 | 英集动力科技(山东)有限公司 | Heat supply system control method for industrial waste heat integrated heat supply network based on predictive model |
| CN116989377A (en) * | 2023-09-28 | 2023-11-03 | 河北三环太阳能有限公司 | Solar heating system |
-
2024
- 2024-01-11 CN CN202410039600.2A patent/CN117553337B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103115389A (en) * | 2012-12-27 | 2013-05-22 | 重庆大学 | Solar energy combined type phase-change heat storage heating system |
| CN111524028A (en) * | 2020-04-03 | 2020-08-11 | 中煤科工(天津)清洁能源研究院有限公司 | Configuration method of multi-energy complementary coupling system |
| WO2022168049A1 (en) * | 2021-02-07 | 2022-08-11 | Octopus Energy Group Limited | Heating installations, methods and systems |
| CN114508784A (en) * | 2022-02-16 | 2022-05-17 | 重庆邮电大学 | Multi-source complementary heating system and optimization control method thereof |
| CN115455835A (en) * | 2022-09-21 | 2022-12-09 | 浙江英集动力科技有限公司 | Optimized operation method of renewable energy-containing multi-heat-source networked heating system |
| CN115828726A (en) * | 2022-10-19 | 2023-03-21 | 浙江英集动力科技有限公司 | Machine learning-based solar cross-season heat storage and supply system optimization control method |
| CN116628972A (en) * | 2023-05-19 | 2023-08-22 | 英集动力科技(山东)有限公司 | Heat supply system control method for industrial waste heat integrated heat supply network based on predictive model |
| CN116613828A (en) * | 2023-05-23 | 2023-08-18 | 中国南方电网有限责任公司 | Configuration method and configuration device of multi-energy system for promoting new energy consumption |
| CN116989377A (en) * | 2023-09-28 | 2023-11-03 | 河北三环太阳能有限公司 | Solar heating system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117553337A (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shirazi et al. | A comprehensive, multi-objective optimization of solar-powered absorption chiller systems for air-conditioning applications | |
| CN102184337B (en) | Dynamic combination analysis method of new energy generating capacity influenced by meteorological information | |
| CN109858173B (en) | Multi-target tangent method for joint scheduling of wind, light and water complementary power generation system | |
| CN109886473A (en) | A kind of basin scene water system Multiobjective Optimal Operation method considering downstream ecology | |
| US20160018125A1 (en) | Energy management systems and methods of use | |
| CN111735178A (en) | Air conditioner energy-saving system based on elite meaning and SVR regression algorithm and optimization method | |
| CN112415924A (en) | Energy-saving optimization method and system for air conditioning system | |
| Lu et al. | Study on the optimal hydropower generation of Zhelin reservoir | |
| CN110909911A (en) | Method for aggregating multidimensional time series data considering space-time correlation | |
| CN110796279A (en) | Multi-energy complementary optimization operation method and system | |
| Hirvonen et al. | Neural network metamodelling in multi-objective optimization of a high latitude solar community | |
| CN116628972A (en) | Heat supply system control method for industrial waste heat integrated heat supply network based on predictive model | |
| Quaiyum et al. | Application of artificial neural network in forecasting solar irradiance and sizing of photovoltaic cell for standalone systems in Bangladesh | |
| CN117553337B (en) | Multisource complementary scheduling method considering agricultural photovoltaic heating and integrated central heating pipe network | |
| CN110188912B (en) | Improved pollen algorithm-based surface water and underground water combined scheduling optimization method | |
| CN115983492A (en) | Hydrogen-containing multi-energy system operation carbon emission optimization decision method, system and medium | |
| CN116499023A (en) | Intelligent control method and system for geothermal coupling solar heating station | |
| CN112734451B (en) | Green house multi-energy system based on non-cooperative game and optimization method | |
| CN115828726A (en) | Machine learning-based solar cross-season heat storage and supply system optimization control method | |
| Ran et al. | A bi-level optimization method for regional integrated energy system considering uncertainty and load prediction under climate change | |
| CN115271244A (en) | Two-stage distribution robust optimization-based short-term peak regulation model of cascade hydropower station | |
| Zhang et al. | A day-ahead operation regulation method for solar water heating based on model predictive control | |
| CN115660187B (en) | Low-carbon town ground source heat pump capacity optimization configuration method | |
| Ćirić et al. | Intelligent Heat Demand prediction for Advanced District Heat Plant Control | |
| CN117744894B (en) | Active learning agent optimization method of comprehensive energy system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |