A method for optimizing heating cost of gas-fired air-source heat pump based on climate compensation

Abstract

The present invention discloses a method for optimizing heating cost of a gas-fired air-source heat pump based on climate compensation, and relates to the technical field of heating cost optimization. The method comprises the following steps: S1, collecting the outdoor temperature of a heating area and the indoor temperature of a building in the heating area; S2, analyzing the heat load of a building to maintain a specified indoor temperature under different outdoor temperature conditions; S3, obtaining the unit parameters of a gas-fired air-source heat pump, and establishing a unit efficiency model; S4, formulating climate compensation rules to match the target temperature required to be maintained by various types of buildings under future outdoor temperature conditions; S5, optimizing the supply task based on the unit efficiency model and the amount of heat supplied, and analyzing the future amount of gas supplied in the heating area. The present invention dynamically adjusts the heating system parameters, optimizes the heating strategy, and maximizes the utilization of the unit efficiency, thereby improving the flexibility and response speed of the heating system, reducing the heating cost, and improving the user's comfort.

Description

Technical Field

[0001] The invention relates to the technical field of heating cost optimization, and in particular to a method for optimizing heating costs of a gas-fired air-source heat pump based on climate compensation. Background Art

[0002] In order to meet the heating needs in residential, commercial and industrial fields, especially in cold seasons or cold areas, heating is an important means to ensure people's quality of life and the normal production activities. Gas-fired air-source heat pumps have become an important choice for modern heating systems due to their high efficiency, energy saving and environmental protection. Gas-fired air-source heat pump heating is a common regional heating method. Its principle is to use gas boilers to burn natural gas to generate heat, and extract heat from the ambient air through air-source heat pumps, combining the two for heat exchange to provide efficient heating and hot water services. This heating method takes advantage of the efficient combustion characteristics of gas and the energy-saving advantages of air-source heat pumps to maximize the use of thermal energy.

[0003] Compared with traditional heating equipment, such as electric furnaces or coal-fired boilers, the gas-fired air-source heat pump system includes multiple parts such as gas boilers, air-source heat pumps, heat exchangers and intelligent control systems. Gas and electricity costs are the main expenses, resulting in a corresponding increase in heating costs. At the same time, the operation of the compressor and fan of the air-source heat pump requires electricity, and the increase in electricity costs will also affect the overall operating costs. Especially in areas with higher electricity prices or during peak electricity consumption periods, the impact of electricity costs on heating costs is more significant.

[0004] In the current heating system, in the heat exchange station or small heat source station, the core function of the commonly used automatic control system is the climate compensation function. The climate compensation function automatically adjusts the water supply temperature according to the change of outdoor temperature, that is, when the temperature is low, the water supply temperature is increased to ensure that the indoor temperature meets the standard, and when the temperature is high, the water supply temperature is reduced to avoid waste caused by overheating of the room temperature. However, the traditional climate compensation function is only applicable to simple single energy or regional unified heating such as a single gas boiler, coal-fired boiler or power plant waste heat. It cannot take into account the type or performance of the target building, that is, under different outdoor temperature conditions, it cannot effectively maintain the comfort of the indoor temperature of all buildings in the area; and it cannot detect the outdoor temperature changes in time, and quickly adjust the response of the heating equipment, making it difficult to effectively control and reduce the heating cost. Summary of the invention

[0005] Based on this, it is necessary to provide a method for optimizing the heating cost of a gas-fired air source heat pump based on climate compensation to address the above technical issues.

[0006] The present invention provides a method for optimizing heating cost of a gas-fired air-source heat pump based on climate compensation, the method comprising the following steps:

[0007] S1, collecting the outdoor temperature of the heating area and the indoor temperature of the buildings in the heating area;

[0008] S2. Analyze the heat load of the building to maintain a specified indoor temperature under different outdoor temperature conditions, and establish a heat supply correlation chart for the building by combining the heating network and building information;

[0009] S3. Obtain the unit parameters of the gas-fired air source heat pump, establish a unit efficiency model, and predict the future outdoor temperature through a climate prediction model, and perform simulation in combination with the unit efficiency model;

[0010] S4. Formulate climate compensation rules to match the target temperature that each type of building needs to maintain under future outdoor temperature conditions, and calculate the heat supply required for the building to maintain the target temperature;

[0011] S5. Based on the unit efficiency model and heating supply, optimize the supply task, analyze the future gas supply in the heating area, and manage the heating supply of the building in a differentiated manner through secondary side regulation.

[0012] Furthermore, the analysis of the heat load of the building to maintain a specified indoor temperature under different outdoor temperature conditions and the establishment of a heat load correlation chart of the building in combination with the heating network and building information includes the following steps:

[0013] S21, setting the individual number of the building in the heating area and obtaining the building information;

[0014] S22, based on the individual number and building information of the building, using a heat load formula to calculate the heat load of each building to maintain a specified indoor temperature at different outdoor temperatures;

[0015] S23, obtaining the layout and operation parameters of the heating network, as well as the pipeline distance between the secondary network and each building, and calculating the heat loss amount transferred to the building by setting the heat loss coefficient of the network;

[0016] S24. Integrate the heat load of each building in the heating area, draw the heat load curve under different outdoor temperature conditions, and establish a correlation chart containing the individual building number, building information and heat loss, and then use visualization tools for intuitive display.

[0017] Furthermore, the building information includes building type, floor height, insulation material, building surface area and building heat transfer coefficient.

[0018] Furthermore, the acquisition of the unit parameters of the gas air source heat pump, the establishment of the unit efficiency model, and the prediction of the future outdoor temperature by the climate prediction model, and the simulation combined with the unit efficiency model include the following steps:

[0019] S31, obtaining unit parameters of the gas air source heat pump; wherein the unit parameters include rated power, heating capacity, operating temperature range, input power, output heat and performance coefficient;

[0020] S32, collecting the operating data of the gas-fired air source heat pump, and using the regression analysis method to establish a mathematical relationship model between input power, output power and outdoor temperature as a unit efficiency model;

[0021] S33, obtaining environmental parameters, building a climate prediction model based on the long short-term memory network model and the distributed gradient boosting model, and predicting the future outdoor temperature during the future control cycle;

[0022] S34. The predicted future outdoor temperature, unit parameters and unit efficiency model are input into the simulation platform to simulate the unit efficiency of the gas air source heat pump in the future control cycle.

[0023] Furthermore, the environmental parameters are obtained, and a climate prediction model is constructed based on a long short-term memory network model and a distributed gradient boosting model to predict the future outdoor temperature during the future control cycle, including the following steps:

[0024] S331, setting a control cycle, obtaining environmental parameters in the heating area, cleaning and normalizing the environmental parameters to form time series data, and then constructing a three-dimensional data set;

[0025] S332, dividing the data set into a training set and a test set, defining the time series data as the input variable, the predicted outdoor temperature as the output variable, constructing a long short-term memory network model and performing model training;

[0026] S333, using the prediction result of the long short-term memory network as an input feature, and defining the core parameters of the distributed gradient boosting model to optimize the prediction result of the long short-term memory network model;

[0027] S334. Integrate the long short-term memory network model and the distributed gradient boosting model as a climate prediction model, and predict the future outdoor temperature of the next regulation cycle by inputting the environmental parameters of the current regulation cycle.

[0028] Furthermore, the environmental parameters include meteorological data, temperature and humidity data, carbon dioxide concentration, PM2.5 and PM10; the core parameters include task type, number of leaf nodes, maximum tree depth, minimum number of samples of leaf nodes, training model learning rate and number of iterations.

[0029] Furthermore, the formulation of climate compensation rules to match the target temperature that each type of building needs to maintain under future outdoor temperature conditions and the calculation of the heat supply required for the building to maintain the target temperature includes the following steps:

[0030] S41, dividing the outdoor temperature into multiple intervals from low to high, each interval is set as a level, and when at any level, the corresponding temperature control range and target temperature inside different types of buildings are set, and climate compensation rules for various types of buildings in the heating area are formulated;

[0031] S42, based on the climate compensation rules and the predicted future outdoor temperature, matching the target temperature that each type of building needs to maintain in the future control cycle;

[0032] S43, calculating the heat load required for each type of building to maintain the target temperature under future outdoor temperature conditions, and combining the heat loss of the building to calculate the actual heating demand of each building in the future control cycle.

[0033] Furthermore, the method of optimizing supply tasks based on unit efficiency model and heating amount, analyzing future gas supply in the heating area, and differentially managing heating amount of buildings through secondary side regulation includes the following steps:

[0034] S51, integrating the heat supply required by all buildings in the heating area and calculating the total heat supply;

[0035] S52, setting the gas air source pump to complete the supply task of the total heat supply, and establishing a supply objective function based on a linear programming algorithm with minimizing the gas supply cost as the optimization goal;

[0036] S53, obtaining the optimization result of the supply task, obtaining the gas supply required by the gas-fired air-source heat pump in the future control cycle, and then using the simulation platform to perform simulation and optimization;

[0037] S54. Based on the gas supply after simulation optimization, the hot water flow of different buildings is adjusted by configuring the secondary side equipment, and the heat supply reaching the buildings is managed in a differentiated manner.

[0038] Furthermore, the supply objective function is expressed as:

[0039]

[0040] Where P gas (t) represents the gas supply in the tth time period in the future control cycle; Q heat_i (t) represents the heat supply of the i-th building in the t-th time period; Q total(t) represents the total heating supply in the tth time period; n represents the total number of buildings in the heating area; T represents the duration of the future control cycle; COP(t) represents the unit efficiency in the tth time period.

[0041] Furthermore, the gas supply amount after simulation optimization is adjusted by configuring secondary side equipment to adjust the hot water flow of different buildings and differentially manage the heat supply reaching the buildings, including the following steps:

[0042] S541. Mark the required heating amount of each building according to the association chart established based on the individual building number, and mark the secondary side equipment controlling each building in the heating network;

[0043] S542, calculating the hot water flow rate of the secondary pipe network in a unit time period based on the heating amount of the building in the future control cycle and the supply and return water temperature difference;

[0044] S543. According to the calculated hot water flow rate required by each building, the adjustment parameters of the secondary side equipment are controlled to differentially adjust the hot water flow rate of each building.

[0045] The beneficial effects of the present invention are:

[0046] 1. By utilizing environmental parameters and climate prediction models, the heating system parameters are dynamically adjusted, the heating strategy is optimized, and the efficiency of the units is maximized and utilized. At the same time, the intelligent level of the heating system is improved by optimizing and adjusting the operation of heating equipment in real time. The heating amount can be accurately adjusted according to the heat load requirements of different buildings, differentiated management can be achieved, and energy waste can be avoided. This improves the flexibility and response speed of the heating system, minimizes the heating cost, and improves the comfort of users.

[0047] 2. By collecting and analyzing outdoor and indoor temperature data, establishing heat load and unit efficiency models, formulating climate compensation rules in combination with climate forecasts, optimizing heat supply and gas supply, and achieving differentiated management of heating through secondary side regulation, the overall efficiency of the heating system can be significantly improved, gas consumption and heating costs can be reduced, and stable and comfortable indoor temperatures can be provided for various types of buildings under different climatic conditions, achieving a win-win situation in economic and environmental benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0049] Figure 1 The present invention is a flowchart of a method for optimizing heating costs of a gas-fired air source heat pump based on climate compensation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0051] See also Figure 1 , provides a method for optimizing heating cost of a gas-fired air source heat pump based on climate compensation, the method comprising the following steps:

[0052] S1. Collect the outdoor temperature of the heating area and the indoor temperature of the buildings in the heating area.

[0053] Specifically, since the heating area is large and there are many buildings in the area, only representative buildings are selected for testing, mainly distinguishing different building types. For example, by building type classification, the buildings in the heating area are classified by use and structural type, such as residential, office, shopping mall, school, etc. Or by representative building selection, representative buildings are selected from each type of building for temperature testing.

[0054] For outdoor temperature, select multiple representative locations in the heating area to install outdoor temperature sensors to ensure that the temperature data can reflect the average situation of the entire area. For indoor temperature, install temperature sensors inside representative buildings of each type. At the same time, in order to simplify the workload, select typical rooms of buildings (such as living rooms and bedrooms in residential buildings, offices and conference rooms in office buildings) for installation. Finally, use relational databases (such as MySQL, PostgreSQL) or time series databases (such as InfluxDB, TimescaleDB) to store temperature data. And back up data regularly to ensure data security and recoverability.

[0055] S2. Analyze the heat load of the building to maintain a specified indoor temperature under different outdoor temperature conditions, and establish a heat supply correlation chart for the building by combining the heating network and building information.

[0056] In the description of the present invention, the analysis of the heat load of a building to maintain a specified indoor temperature under different outdoor temperature conditions, and combining the heating network and building information to establish a heat load association chart of the building includes the following steps:

[0057] S21. Set the individual number of the building in the heating area and obtain the building information.

[0058] The building information includes building type, floor height, insulation material, building surface area and building heat transfer coefficient.

[0059] Building types: such as residential buildings, office buildings, shopping malls, schools, etc.

[0060] Floor Height: The number of floors in a building and the height of each floor.

[0061] Insulation materials: types of insulation materials used in buildings and their insulation performance parameters.

[0062] Building surface area: the sum of the surface areas of a building’s exterior walls, roof, floor, etc.

[0063] Building heat transfer coefficient: includes the heat transfer coefficient of walls, windows, roofs, etc.

[0064] S22. Based on the individual numbers and building information of the buildings, a heat load formula is used to calculate the heat load of each building to maintain a specified indoor temperature at different outdoor temperatures.

[0065] The heat load formula is: Q = U × A × (T in -T out ), where Q represents the heat load; U represents the building heat transfer coefficient; A represents the building surface area; T in Indicates indoor temperature; T out Indicates the outdoor temperature.

[0066] S23. Obtain the layout and operation parameters of the heating network, as well as the pipeline distance between the secondary network and each building, and calculate the heat loss amount transferred to the building by setting the heat loss coefficient of the network.

[0067] Specifically, obtain the specific layout diagram of the heating trunk network and branch network, including the direction of the pipeline, node location, connection method, etc. Use GIS (Geographic Information System) or CAD software to build a detailed network layout model to ensure the accuracy of the layout information.

[0068] Obtain operating parameters, such as the temperature range and changes of the heating medium (such as hot water or steam); heating medium pressure, the working pressure of the medium in the pipe network; flow rate, the flow rate of the heating medium in the pipe network; pipe material and diameter, the material (such as steel pipe, PPR pipe) and diameter of the pipe and other basic information. Then measure the pipeline distance between the secondary pipe network and each building, and record the pipeline distance between each building and the secondary pipe network to ensure the accuracy of the data. Establish a pipeline distance database and enter the measured pipeline distance data into the database to facilitate subsequent calculations and management.

[0069] In addition, multiple heat loss coefficients are set based on factors such as pipeline material, insulation material, and surface temperature. The heat loss coefficient reflects the heat loss per meter of pipeline under unit temperature difference. According to the change of outdoor temperature, the heat loss coefficient is dynamically adjusted to reflect the heat loss under different environmental conditions. For example, in a colder environment, the heat loss coefficient may increase because the temperature difference is greater and the heat loss is more obvious.

[0070] S24. Integrate the heat load of each building in the heating area, draw the heat load curve under different outdoor temperature conditions, and establish a correlation chart containing the individual building number, building information and heat loss, and then use visualization tools for intuitive display.

[0071] S3. Obtain the unit parameters of the gas air source heat pump, establish a unit efficiency model, and predict the future outdoor temperature through the climate prediction model, and perform simulation in combination with the unit efficiency model.

[0072] In the description of the present invention, the acquisition of the unit parameters of the gas air source heat pump, the establishment of the unit efficiency model, and the prediction of the future outdoor temperature by the climate prediction model, and the simulation combined with the unit efficiency model include the following steps:

[0073] S31. Obtaining unit parameters of the gas-fired air-source heat pump, wherein the unit parameters include rated power, heating capacity, operating temperature range, input power, output heat, and performance coefficient.

[0074] Specifically, you can obtain the equipment manual of the gas-fired air-source heat pump from the manufacturer or supplier to understand the detailed technical parameters. And check the product specification to obtain the equipment's rated power, heating capacity, COP (coefficient of performance), operating temperature range and other key parameters.

[0075] Conduct tests in the actual operating environment to collect real-time operating data of the equipment, including input power, output heat, gas consumption, etc. Use data loggers or monitoring systems to monitor the operation of the equipment over a long period of time and collect performance data under different working conditions.

[0076] S32. Collect the operating data of the gas-fired air source heat pump, and use the regression analysis method to establish a mathematical relationship model between input power, output power and outdoor temperature as the unit efficiency model.

[0077] Specifically, the unit efficiency model is used to simulate the performance of the gas air source heat pump under different working conditions, mainly considering the following factors:

[0078] Input power (P in ): Input power of the gas air source heat pump.

[0079] Output heat (Q out): Output heat of the gas air source heat pump.

[0080] Unit efficiency / coefficient of performance (COP): Under different operating conditions, COP = Q out / Pi n .

[0081] Using regression analysis method, a relationship model between input power, output heat and outdoor temperature is established, that is, a unit efficiency model (COP model) is established to predict the unit's performance coefficient according to different outdoor temperatures and operating conditions. The COP model can be expressed as: COP = a + b·T out +c·T in +d·log(P in ), where a, b, c, and d are regression coefficients.

[0082] S33. Obtain environmental parameters, build a climate prediction model based on the long short-term memory network model and the distributed gradient boosting model, and predict the future outdoor temperature during the future control cycle.

[0083] Specifically, the LSTM-LightGBM model adopted in the present invention combines the advantages of the LSTM (Long Short-Term Memory Network) and LightGBM (Light Gradient Boosting Machine, distributed gradient boosting model) models to process time series prediction tasks.

[0084] In the description of the present invention, the environmental parameters are obtained, and a climate prediction model is constructed based on a long short-term memory network model and a distributed gradient boosting model to predict the future outdoor temperature during the future regulation cycle, including the following steps:

[0085] S331. Set a control cycle, obtain environmental parameters in the heating area, clean and normalize the environmental parameters to form time series data, and then construct a three-dimensional data set.

[0086] Among them, the three-dimensional data structure:

[0087] Number of samples (N): The total number of samples in the time series.

[0088] Timestep (T): The number of timesteps (window size) in each sample.

[0089] Number of features (F): The number of features (environment parameters) at each time step.

[0090] The shape of the dataset is (N, T, F), where N is the number of samples, T is the number of time steps per sample, and F is the number of features.

[0091] For example, for an environmental parameter data set containing 10 days of data with 24 hours of recording every day, assuming there are three environmental parameters (temperature, humidity, wind speed), the shape of the data set is (N, 10, 3), where each sample contains the environmental data of the past 10 days and predicts future heating demand.

[0092] In the description of the present invention, the environmental parameters include meteorological data, temperature and humidity data, carbon dioxide concentration, PM2.5 and PM10. The core parameters include task type, number of leaf nodes, maximum tree depth, minimum number of samples of leaf nodes, training model learning rate and number of iterations.

[0093] S332. Divide the data set into a training set and a test set, define the time series data as the input variable, predict the outdoor temperature as the output variable, build a long short-term memory network model and perform model training.

[0094] Specifically, the structure of the LSTM model is as follows:

[0095] Input layer: Input three-dimensional time series data.

[0096] LSTM layer: Use LSTM units to process time series data and extract time-dependent features.

[0097] Fully connected layer: maps the output of the LSTM layer to the target prediction space.

[0098] S333. Use the prediction results of the long short-term memory network as input features, define the core parameters of the distributed gradient boosting model, and optimize the prediction results of the long short-term memory network model.

[0099] Specifically, the structure of the LightGBM model is as follows:

[0100] Input layer: The features extracted by LSTM are used as the input of LightGBM.

[0101] Feature selection: Select important features for model training.

[0102] Training: Use LightGBM for training and optimize the prediction results.

[0103] S334. Integrate the long short-term memory network model and the distributed gradient boosting model as a climate prediction model, and predict the future outdoor temperature of the next regulation cycle by inputting the environmental parameters of the current regulation cycle.

[0104] Specifically, in the climate prediction model, LSTM is combined with LightGBM. LSTM is responsible for time series feature extraction, and LightGBM is used for feature processing and final prediction.

[0105] S34. The predicted future outdoor temperature, unit parameters and unit efficiency model are input into the simulation platform to simulate the unit efficiency of the gas air source heat pump in the future control cycle.

[0106] S4. Develop climate compensation rules to match the target temperature that each type of building needs to maintain under future outdoor temperature conditions, and calculate the heat supply required for the building to maintain the target temperature.

[0107] In the description of the present invention, the formulation of climate compensation rules, matching the target temperature required to be maintained by various types of buildings under future outdoor temperature conditions, and calculating the heat supply required for the buildings to maintain the target temperature includes the following steps:

[0108] S41. Divide the outdoor temperature into multiple intervals from low to high, and set each interval as a level. When at any level, set the corresponding temperature control range and target temperature inside different types of buildings, and formulate climate compensation rules for various types of buildings in the heating area.

[0109] Specifically, the outdoor temperature is divided into multiple intervals (for example, -10℃ to 0℃, 0℃ to 10℃, 10℃ to 20℃, etc.), each interval represents a level. Buildings are then divided into different types (such as residential, commercial, industrial, etc.), and each type of building has different heating needs and target temperatures. The internal target temperature of different types of buildings is set for each temperature interval.

[0110] Based on the above settings, create a climate compensation rule document. For example:

[0111] Residential: When the outdoor temperature is between -5℃ and 5℃, the indoor target temperature is 21℃ and the control range is 20℃ to 22℃.

[0112] Commercial buildings: When the outdoor temperature is between -5℃ and 5℃, the indoor target temperature is 19℃ and the control range is 18℃ to 20℃.

[0113] S42. Based on the climate compensation rules and the predicted future outdoor temperature, the target temperature that each type of building needs to maintain in the future control cycle is matched.

[0114] S43, calculating the heat load required for each type of building to maintain the target temperature under future outdoor temperature conditions, and combining the heat loss of the building to calculate the actual heating demand of each building in the future control cycle.

[0115] S5. Based on the unit efficiency model and heating supply, optimize the supply task, analyze the future gas supply in the heating area, and manage the heating supply of the building in a differentiated manner through secondary side regulation.

[0116] In the description of the present invention, the optimization of supply tasks based on unit efficiency model and heating amount, analysis of future gas supply in the heating area, and differentiated management of heating amount of buildings through secondary side regulation include the following steps:

[0117] S51. Integrate the heat supply required by all buildings in the heating area and calculate the total heat supply.

[0118] S52. Set the gas-air source pump to complete the task of supplying total heating amount, and establish a supply objective function based on a linear programming algorithm with minimizing the gas supply cost as the optimization goal.

[0119] In the description of the present invention, the expression of the supply objective function is:

[0120]

[0121] Where P gas (t) represents the gas supply in the tth time period in the future control cycle; Q heat_i (t) represents the heat supply of the i-th building in the t-th time period; Q total (t) represents the total heating supply in the tth time period; n represents the total number of buildings in the heating area; T represents the duration of the future control cycle; COP(t) represents the unit efficiency in the tth time period.

[0122] Specifically, for the above objective function and constraints, existing linear programming algorithms and tools are used to solve the optimization problem, for example, commercial optimization software such as IBM CPLEX, Gurobi, etc. are used.

[0123] S53. Obtain the optimization result of the supply task, obtain the gas supply required by the gas air source heat pump in the future control cycle, and then use the simulation platform to perform simulation and optimization.

[0124] S54. Based on the gas supply after simulation optimization, the hot water flow of different buildings is adjusted by configuring the secondary side equipment, and the heat supply reaching the buildings is managed in a differentiated manner.

[0125] In the description of the present invention, the gas supply amount after simulation optimization is adjusted by configuring the secondary side equipment to adjust the hot water flow of different buildings and to manage the heat supply reaching the buildings in a differentiated manner, including the following steps:

[0126] S541. According to the association chart established based on the individual building numbers, the required heating amount of each building is marked, and the secondary side equipment controlling each building is marked in the heating network.

[0127] S542. Calculate the hot water flow rate of the secondary pipe network in a unit time period based on the heating amount of the building in the future control cycle and the supply and return water temperature difference.

[0128] S543. According to the calculated hot water flow rate required by each building, the adjustment parameters of the secondary side equipment are controlled to differentially adjust the hot water flow rate of each building.

[0129] In summary, with the help of the above technical scheme of the present invention, by utilizing environmental parameters and climate prediction models, the parameters of the heating system are dynamically adjusted, the heating strategy is optimized, and the efficiency of the unit is maximized and utilized; at the same time, the intelligent level of the heating system is improved by optimizing and adjusting the operation of the heating equipment in real time; the heating amount can be accurately adjusted according to the heat load requirements of different buildings, and differentiated management can be achieved to avoid energy waste; thereby improving the flexibility and response speed of the heating system, minimizing the heating cost, and improving the user's comfort. By collecting and analyzing outdoor and indoor temperature data, establishing a heat load and unit efficiency model, formulating climate compensation rules in combination with climate prediction, optimizing the heat supply and gas supply, and realizing differentiated management of heating through secondary side regulation, the overall efficiency of the heating system can be significantly improved, gas consumption and heating costs can be reduced, and stable and comfortable indoor temperatures can be provided for various buildings under different climatic conditions, achieving a win-win situation of economic and environmental benefits.

[0130] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

Claims

1. A method for optimizing heating costs of a gas-fired air source heat pump based on climate compensation, characterized in that: The method comprises the following steps: S1, collecting the outdoor temperature of the heating area and the indoor temperature of the buildings in the heating area; S2. Analyze the heat load of the building to maintain a specified indoor temperature under different outdoor temperature conditions, and establish a heat supply correlation chart for the building by combining the heating network and building information; S3. Obtain the unit parameters of the gas-fired air source heat pump, establish a unit efficiency model, and predict the future outdoor temperature through a climate prediction model, and perform simulation in combination with the unit efficiency model; S4. Formulate climate compensation rules to match the target temperature that each type of building needs to maintain under future outdoor temperature conditions, and calculate the heat supply required for the building to maintain the target temperature; S5. Based on the unit efficiency model and heating supply, optimize the supply task, analyze the future gas supply in the heating area, and manage the heating supply of the building through secondary side regulation; The method of obtaining the unit parameters of the gas-fired air source heat pump, establishing a unit efficiency model, predicting the future outdoor temperature through a climate prediction model, and performing simulation in combination with the unit efficiency model includes the following steps: S31, obtaining unit parameters of the gas air source heat pump; wherein the unit parameters include rated power, heating capacity, operating temperature range, input power, output heat and performance coefficient; S32, collecting the operating data of the gas-fired air source heat pump, and using the regression analysis method to establish a mathematical relationship model between input power, output power and outdoor temperature as a unit efficiency model; S33, obtaining environmental parameters, building a climate prediction model based on the long short-term memory network model and the distributed gradient boosting model, and predicting the future outdoor temperature during the future control cycle; S34, input the predicted future outdoor temperature, unit parameters and unit efficiency model into the simulation platform to simulate the unit efficiency of the gas air source heat pump in the future control cycle; The environmental parameters are obtained, and a climate prediction model is constructed based on a long short-term memory network model and a distributed gradient boosting model to predict the future outdoor temperature during the future control cycle, including the following steps: S331, setting a control cycle, obtaining environmental parameters in the heating area, cleaning and normalizing the environmental parameters to form time series data, and then constructing a three-dimensional data set; S332, dividing the data set into a training set and a test set, defining the time series data as the input variable, the predicted outdoor temperature as the output variable, constructing a long short-term memory network model and performing model training; S333, using the prediction result of the long short-term memory network as an input feature, and defining the core parameters of the distributed gradient boosting model to optimize the prediction result of the long short-term memory network model; S334. Integrate the long short-term memory network model and the distributed gradient boosting model as a climate prediction model, and predict the future outdoor temperature of the next regulation cycle by inputting the environmental parameters of the current regulation cycle.

2. A method for optimizing heating costs of a gas-fired air source heat pump based on climate compensation according to claim 1, characterized in that: The analysis of the heat load of the building to maintain a specified indoor temperature under different outdoor temperature conditions and the establishment of a heat load correlation chart of the building in combination with the heating network and building information include the following steps: S21, setting the individual number of the building in the heating area and obtaining the building information; S22, based on the individual number and building information of the building, using a heat load formula to calculate the heat load of each building to maintain a specified indoor temperature at different outdoor temperatures; S23, obtaining the layout and operation parameters of the heating network, as well as the pipeline distance between the secondary network and each building, and calculating the heat loss amount transferred to the building by setting the heat loss coefficient of the network; S24. Integrate the heat load of each building in the heating area, draw the heat load curve under different outdoor temperature conditions, and establish a correlation chart containing the individual building number, building information and heat loss, and then use visualization tools for intuitive display.

3. A method for optimizing heating costs of a gas-fired air source heat pump based on climate compensation according to claim 2, characterized in that: The building information includes building type, floor height, insulation material, building surface area and building heat transfer coefficient.

4. A method for optimizing heating costs of a gas-fired air source heat pump based on climate compensation according to claim 3, characterized in that: The environmental parameters include meteorological data, temperature and humidity data, carbon dioxide concentration, PM2.5 and PM10; the core parameters include task type, number of leaf nodes, maximum tree depth, minimum number of samples of leaf nodes, training model learning rate and number of iterations.

5. The method for optimizing heating cost of a gas-fired air source heat pump based on climate compensation according to claim 2, characterized in that: The formulation of climate compensation rules to match the target temperature that each type of building needs to maintain under future outdoor temperature conditions and calculate the heat supply required for the building to maintain the target temperature includes the following steps: S41, dividing the outdoor temperature into multiple intervals from low to high, each interval is set as a level, and when at any level, the corresponding temperature control range and target temperature inside different types of buildings are set, and climate compensation rules for various types of buildings in the heating area are formulated; S42, based on the climate compensation rules and the predicted future outdoor temperature, matching the target temperature that each type of building needs to maintain in the future control cycle; S43, calculating the heat load required for each type of building to maintain the target temperature under future outdoor temperature conditions, and combining the heat loss of the building to calculate the actual heating demand of each building in the future control cycle.

6. The method for optimizing heating cost of a gas-fired air source heat pump based on climate compensation according to claim 2, characterized in that: The method of optimizing supply tasks based on unit efficiency models and heat supply, analyzing future gas supply in the heating area, and differentially managing the heat supply of buildings through secondary side regulation includes the following steps: S51, integrating the heat supply required by all buildings in the heating area and calculating the total heat supply; S52, setting the gas air source pump to complete the supply task of the total heat supply, and establishing a supply objective function based on a linear programming algorithm with minimizing the gas supply cost as the optimization goal; S53, obtaining the optimization result of the supply task, obtaining the gas supply required by the gas-fired air-source heat pump in the future control cycle, and then using the simulation platform to perform simulation and optimization; S54. Based on the gas supply after simulation optimization, the hot water flow of different buildings is adjusted by configuring the secondary side equipment, and the heat supply reaching the buildings is managed in a differentiated manner.

7. A method for optimizing heating costs of a gas-fired air source heat pump based on climate compensation according to claim 6, characterized in that: The expression of the supply objective function is: Where P gas (t) represents the gas supply in the tth time period in the future control cycle; Q heat_i (t) represents the heat supply of the i-th building in the t-th time period; Q total (t) represents the total heat supply in the tth time period; n represents the total number of buildings within the heating area; T represents the duration of the future regulation cycle; COP(t) represents the unit efficiency in the tth time period.

8. The method for optimizing heating cost of a gas-fired air source heat pump based on climate compensation according to claim 6, characterized in that: The method of adjusting the hot water flow of different buildings based on the gas supply after simulation optimization by configuring the secondary side equipment and differentially managing the heat supply reaching the buildings includes the following steps: S541. Mark the required heating amount of each building according to the association chart established based on the individual building number, and mark the secondary side equipment controlling each building in the heating network; S542, calculating the hot water flow rate of the secondary pipe network in a unit time period based on the heating amount of the building in the future control cycle and the supply and return water temperature difference; S543. According to the calculated hot water flow rate required by each building, the adjustment parameters of the secondary side equipment are controlled to differentially adjust the hot water flow rate of each building.

Images