Intelligent heat supply control method based on load prediction and related equipment thereof

Abstract

The invention provides an intelligent heat supply control method based on load prediction and related equipment thereof, and the method comprises the steps: obtaining environment data and real-time operation data of heat supply equipment, and the environment data comprises indoor environment data of the heat supply equipment and outdoor meteorological data; processing the indoor environment data, the outdoor meteorological data and the operation data through a preset prediction model, and determining target load prediction data; based on the target load prediction data and the current time-of-use electricity price data, constructing an optimization control target function; through the optimization control objective function, performing optimization processing on initial output parameters of the heat supply equipment, and determining target adjustment parameters of the heat supply equipment; and the output of the heat supply equipment is regulated and controlled through the target adjustment parameters. Through the steps of the method, cooperative adjustment of the multi-heat-source equipment can be achieved, and the operation cost is remarkably reduced while stable and comfortable heat supply is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent detection, and in particular to an intelligent heating control method and device based on load prediction, an electronic device and a storage medium thereof. BACKGROUND

[0002] With the acceleration of urbanization and the promotion of energy-saving and emission-reduction policies, central heating and district heating systems are widely used in building heating. In recent years, air source heat pumps and gas boilers, as the main heating equipment, have been gradually introduced into multi-energy coupling systems to achieve a balance between clean energy utilization and operation cost control. At the same time, the operation environment and user demand of the heating system have obvious dynamics and uncertainty, such as the fluctuation of outdoor meteorological conditions with seasonal and time period changes, and the continuous change of indoor thermal load demand due to user behavior differences, which puts higher requirements on the intelligence and economy of the heating system.

[0003] The operation control of the existing heating system still mainly relies on fixed logic strategy or local optimization of a single device. This kind of way usually sets the operation parameters based on empirical formula in the design stage, and it is difficult to dynamically adjust in combination with real-time environmental conditions and energy prices, resulting in problems of high energy consumption, high cost and insufficient flexibility in the operation process. Especially in the air source heat pump and gas boiler collaborative heating scene, how to reasonably predict the thermal load and determine the equipment output allocation.

[0004] Therefore, the existing intelligent heating control method based on load prediction has the problem of being unable to dynamically predict and optimize control in combination with environmental data, operation data and energy prices. SUMMARY

[0005] The present application provides an intelligent heating control method based on load prediction to solve the problem that the existing intelligent heating control method based on load prediction cannot dynamically predict and optimize control in combination with environmental data, operation data and energy prices.

[0006] In a first aspect, the present application provides an intelligent heating control method based on load prediction, which comprises the following steps: Obtain environmental data and real-time operation data of the heating equipment, wherein the environmental data includes indoor environmental data and outdoor meteorological data of the heating equipment; Determine target load prediction data by processing the indoor environmental data, outdoor meteorological data and operation data through a preset prediction model; Based on the target load prediction data and current time-of-use electricity price data, an optimization control objective function is constructed; The initial output parameter of the heating equipment is optimized by the optimization control objective function, and a target adjustment parameter of the heating equipment is determined. The output of the heating equipment is regulated and controlled by the target adjustment parameter.

[0007] Optionally, the outdoor meteorological data includes temperature, humidity, and wind speed, the operation data includes water supply and return temperature data, flow data, and energy consumption parameters, and the indoor environment data includes environment temperature data. The environment data and real-time operation data of the heating equipment are obtained by: Real-time collection of outdoor meteorological data, indoor environment temperature data, and operation data of the heating equipment based on a preset sensor array to obtain an initial sensor data set, the initial sensor data set including temperature, humidity, wind speed, water supply and return temperature data, flow data, energy consumption parameters, and environment temperature data, the preset sensor array including a temperature sensor, a meteorological monitor, a flow meter, a pressure sensor, and an energy metering sensor; The sensor data in the initial sensor data set is preprocessed to determine target environment data and real-time operation data of the heating equipment.

[0008] Optionally, the indoor environment data, outdoor meteorological data, and operation data are processed by a preset prediction model to determine target load prediction data, including: The indoor environment data, outdoor meteorological data, and operation data are feature extracted and normalized to construct a prediction input feature set data; The prediction input feature set data is input into a preset neural network model, and the target load prediction data in a future preset period is output according to a preset weight and heating demand constraint.

[0009] Optionally, the optimization control objective function is constructed based on the target load prediction data and current time-of-use electricity price data, including: The heating demand amount in a future preset period is determined based on the target load prediction data; The energy consumption cost parameter set is determined according to the current time-of-use electricity price data and the heating demand amount; An optimization control objective function framework is established with the minimization of the operation cost of the heating equipment in the future preset period as the target; The energy consumption cost parameter set is introduced as a constraint condition into the optimization control objective function framework to generate an optimization control objective function framework.

[0010] Optionally, after the optimization control objective function is constructed based on the target load prediction data and the current time-of-use electricity price data, the method further includes: based on a preset time window, the target load prediction data is updated in a rolling manner; when the fluctuation range of the target load prediction data or the current time-of-use electricity price data exceeds a preset threshold, the target load prediction data is updated; based on the updated target load prediction data, a new optimization control objective function is constructed.

[0011] Optionally, the optimization processing of the initial output parameter of the heat supply equipment based on the optimization control objective function to determine the target adjustment parameter of the heat supply equipment comprises: based on the optimization control objective function, optimal output combination data of the air source heat pump and the gas boiler corresponding to the heat supply equipment is determined; a first target outlet water temperature set value and a first target load rate of the air source heat pump are determined; a second target outlet water temperature set value and a second load rate of the gas boiler are determined; based on the optimal output combination data, the first target outlet water temperature set value, the first target load rate, the second target outlet water temperature set value and the second load rate are optimized and calculated to determine the target adjustment parameter of the heat supply equipment.

[0012] Optionally, the optimization calculation of the first target outlet water temperature set value, the first target load rate, the second target outlet water temperature set value and the second load rate based on the optimal output combination data to determine the target adjustment parameter of the heat supply equipment comprises: based on the optimization control objective function, a temperature relay point between the air source heat pump and the gas boiler is determined; based on the temperature relay point, outlet water temperature optimization values and load rate optimization values of the air source heat pump and the gas boiler when performing heat supply division switching are determined; based on the outlet water temperature optimization values and the load rate optimization values, the target adjustment parameter of the heat supply equipment is generated.

[0013] In a second aspect, the present application further provides an intelligent heat supply control device based on load prediction, which comprises: a first acquisition module for acquiring environmental data and real-time operation data of a heat supply equipment, wherein the environmental data comprises indoor environmental data and outdoor meteorological data of the heat supply equipment; a first processing module for processing the indoor environmental data, the outdoor meteorological data and the operation data by a preset prediction model to determine target load prediction data; a first construction module for constructing an optimization control objective function based on the target load prediction data and current time-of-use electricity price data; The first determining module is configured to determine the target adjustment parameter of the heating device by optimizing the initial output parameter of the heating device according to the optimization control target function. The first regulating module is configured to regulate the output of the heating device according to the target adjustment parameter.

[0014] In a third aspect, the present application provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the intelligent heating control method based on load prediction provided by the present application when executing the computer program.

[0015] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the intelligent heating control method based on load prediction provided by the present application when executed by a processor.

[0016] The present application acquires environmental data and real-time operation data of a heating device, wherein the environmental data comprises indoor environmental data and outdoor meteorological data of the heating device; a preset prediction model is used to process the indoor environmental data, the outdoor meteorological data, and the operation data to determine target load prediction data; an optimization control target function is constructed based on the target load prediction data and current time-of-use electricity price data; the initial output parameter of the heating device is optimized according to the optimization control target function to determine the target adjustment parameter of the heating device; and the output of the heating device is regulated according to the target adjustment parameter. The above method steps can realize the collaborative regulation of multiple heating source devices, which can significantly reduce the operation cost while ensuring the stability and comfort of heating. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0018] Figure 1 is a flowchart of an intelligent heating control method based on load prediction provided by an embodiment of the present application; Figure 2 is a structural schematic diagram of another intelligent heating control device based on load prediction provided by an embodiment of the present application; Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0020] As shown in Figure 1 , Figure 1 is a flowchart of an intelligent heating control method based on load prediction provided by an embodiment of the present application. The intelligent heating control method based on load prediction comprises the following steps: 101, obtaining environmental data and real-time operation data of a heating device.

[0021] In the embodiments of the present application, the intelligent heating control method based on load prediction can be applied to an intelligent heating control platform based on load prediction. The intelligent heating control platform based on load prediction has functions of heating data processing, heating data transceiving, and heating data memory storage, and can be constructed based on a server or a server cluster. The server or the server cluster can be an electronic device with a heating data processing capability.

[0022] The environmental data can include, but is not limited to, indoor environmental data of the heating device and outdoor meteorological data for reflecting external and internal conditions in which the heating device operates. Specifically, the heating device can include an air source heat pump, a gas boiler, or a multi-energy coupling heating system formed by combination of the air source heat pump and the gas boiler. The heating device can be connected to the intelligent heating control platform based on load prediction through a built-in data acquisition module and upload real-time operation data, including but not limited to, supply and return water temperature, flow, compressor power, combustion power, and energy consumption parameters.

[0023] The indoor environmental data can be used to reflect the comfort level of the heating device, including but not limited to, indoor air temperature and humidity. In the present embodiment, the indoor environmental data can be collected by devices such as temperature sensors and humidity sensors arranged in the room, and uploaded to the intelligent heating control platform based on load prediction through wired or wireless communication.

[0024] The outdoor meteorological data can be used to reflect external climate conditions of the area where the heating device is located, including but not limited to, outdoor temperature, relative humidity, wind speed, and solar radiation intensity. In the present embodiment, the outdoor meteorological data can be collected by a meteorological monitor outside the energy station in real time, or predicted data can be obtained by establishing an interface with a third-party meteorological platform.

[0025] 102. The indoor environment data, outdoor meteorological data, and operation data are processed by a preset prediction model to determine target load prediction data.

[0026] In the embodiment of the present application, the preset prediction model can be trained based on historical operation data and environment data of the heating equipment before deployment and stored in the algorithm model of the intelligent heating control platform based on load prediction. It can be understood that the model can use any algorithm structure suitable for time series prediction, such as neural network, long short-term memory network, or convolutional neural network. Generally, the preset prediction model can be used to predict the heating demand in a future preset period under the input of limited real-time data.

[0027] In the embodiment, the collected indoor environment data, outdoor meteorological data, and heating equipment operation data can be subjected to feature extraction and normalization operation, and input as input feature set data into the preset prediction model. Specifically, the data can be subjected to processing means including but not limited to selection and combination of air temperature, humidity, wind speed, indoor temperature, supply and return water temperature, flow, energy consumption parameters, and mapping of different dimensional data to a unified interval, so as to improve the efficiency of model training and reasoning, and finally obtain target load prediction data.

[0028] The target load prediction data can be a prediction result output by the preset prediction model for representing the heating load demand in a future period. Generally, the target load prediction data contains time series distribution, so it can not only reflect the future heating demand, but also provide trend information combined with the time dimension, thereby providing input basis for subsequent optimization control target function construction.

[0029] In one possible embodiment, the intelligent heating control platform based on load prediction calls the preset prediction model to process and normalize the collected indoor environment data, outdoor meteorological data, and heating equipment operation data, and outputs target load prediction data for a future preset period, so as to perceive the change of heating demand in advance and realize forward-looking regulation and control of the multi-heat-source system.

[0030] Through the above method steps, the prediction accuracy can be improved, the energy waste can be reduced, and the basis for subsequent optimization control can be provided, thereby ensuring the stability and economy of the heating system.

[0031] 103. An optimization control target function is constructed based on the target load prediction data and current time-of-use electricity price data.

[0032] In the embodiments of the present application, the current time-of-use electricity price data can be a data set that divides the power supply period of a day into different periods such as peak, flat, valley, and formulates differentiated electricity price strategies according to the load characteristics of the power grid, including but not limited to the electricity price values of each period, the specific start and end times of peak and valley periods, the differentiated electricity price strategies of holidays and weekdays, and other data reflecting the electricity price change level at different times. It can be understood that the intelligent heating control platform based on load prediction can synchronize these data in real time through the interface with the power company, so as to include them in the cost constraint condition when optimizing energy consumption.

[0033] In the embodiments, the intelligent heating control platform based on load prediction can comprehensively calculate the target load prediction data, the current time-of-use electricity price data, and the corresponding constraint conditions during the heating control process, construct a mathematical optimization model, and specifically can include but is not limited to the mathematical expression derivation of the objective function and the establishment of the constraint conditions, such as the maximum output limit of the heat pump and the boiler, the minimum start-stop time limit, the comfort temperature interval constraint, and the like. According to such constraint conditions, an optimization solving framework that can be called by the intelligent heating control platform based on load prediction is constructed, i.e., an optimization control objective function.

[0034] The optimization control objective function can be a mathematical model that takes the minimization of operating cost as the optimization objective while considering multiple constraint conditions. Generally, the optimization control objective function can be defined as the weighted sum of the total operating cost within a predetermined period, such as "total cost = electricity fee x heat pump output + gas fee x boiler output". By introducing time-of-use electricity price, gas price, and other cost parameters, the optimization control objective function can dynamically reflect the changes in the energy market price, and the intelligent heating control platform based on load prediction can solve the optimization control objective function through linear programming, nonlinear programming, or intelligent algorithms (such as genetic algorithm, particle swarm optimization, etc.), and output the optimal device output combination.

[0035] In one possible embodiment, after obtaining the target load prediction data for a future predetermined period, the intelligent heating control platform based on load prediction further calls the power company interface to obtain the current time-of-use electricity price data, determines the heat load distribution of each period according to the predicted heating demand, and establishes an optimization control objective function by taking the real-time obtained peak, flat, and valley electricity price data and gas cost parameters as cost inputs, taking "minimization of operating cost" as the optimization objective, and taking the device output upper limit, heating demand balance, and indoor comfort interval as constraint conditions. By solving this function, the optimal output distribution scheme of the air source heat pump and the gas boiler in different time periods is obtained, which provides a basis for subsequent parameter generation and device control.

[0036] By incorporating time-of-use electricity price data into the optimization model through the above methods and steps, the system can automatically select to prioritize the use of heat pumps during off-peak electricity price periods and rationally switch to boiler operation during peak electricity price periods, thereby effectively reducing operating costs while meeting heat demand.

[0037] 104. By optimizing the control objective function, the initial output parameters of the heating equipment are optimized to determine the target adjustment parameters of the heating equipment.

[0038] In this embodiment of the invention, the aforementioned initial output parameters may refer to the default operating settings of the heating equipment before optimization, such as the basic outlet water temperature and compressor power of an air source heat pump, and the default outlet water temperature, combustion power, and basic load rate of a gas boiler. Generally, these parameters are set at the factory and lack responsiveness to real-time environmental data and energy prices.

[0039] In this embodiment, the initial output parameters can be corrected and adjusted through the aforementioned intelligent heating control platform based on load forecasting, thereby optimizing the heating equipment. Specifically, the aforementioned intelligent heating control platform based on load forecasting solves a mathematical model, comprehensively considering constraints such as target load forecast data, time-of-use electricity prices, gas prices, equipment performance boundaries, and user comfort, to obtain the optimal power allocation scheme, thereby minimizing operating costs and rationalizing equipment start-up and shutdown frequencies.

[0040] The aforementioned target adjustment parameters can be the final output of the optimization process, used to guide the actual operation of the aforementioned heating equipment. These parameters may include, but are not limited to, the target outlet water temperature setpoint and target load rate for air source heat pumps, and the target outlet water temperature setpoint and target load rate for gas-fired boilers. It should be noted that these target adjustment parameters can be directly sent to the control unit of the corresponding heating equipment and act on the corresponding compressor power, combustion power, and other execution components, thereby achieving coordinated operation of multiple heat sources.

[0041] In one possible embodiment, after constructing the optimized control objective function, the aforementioned intelligent heating control platform based on load forecasting inputs the basic operating parameters (including default outlet water temperature, load rate, etc.) of the air source heat pump and gas boiler as initial output parameters into the model. Subsequently, it combines the target load forecast data and the current time-of-use electricity price data to optimize and solve the initial parameters. Through the above method steps, the aforementioned intelligent heating control platform based on load forecasting can determine the target outlet water temperature and load rate of the air source heat pump during low electricity price periods, and correct the outlet water temperature and load rate of the gas boiler during high demand periods, forming a complete set of target adjustment parameters. These parameters are then sent to the equipment control unit to dynamically adjust the compressor power and combustion power, thereby achieving optimal operation of the equipment at different times.

[0042] 105. Adjust parameters according to targets to regulate the output of heating equipment.

[0043] In this embodiment of the invention, after generating the target adjustment parameters, the above-mentioned intelligent heating control platform based on load prediction sends the parameters to the control unit of the heating equipment to adjust the output of the equipment in real time.

[0044] Specifically, the target outlet water temperature setpoint and target load rate of an air source heat pump are converted into control commands for compressor operating power and outlet water temperature, which are executed by the heat pump controller, enabling the heat pump to undertake the main heating task under low electricity prices or suitable climatic conditions. The target outlet water temperature setpoint and target load rate of a gas-fired boiler are converted into control commands for combustion power and secondary heating temperature, which are executed by the boiler controller, thus providing compensation during peak load periods or when the heat pump efficiency is insufficient.

[0045] The aforementioned intelligent heating control platform based on load forecasting also coordinates the operational status of the two types of equipment. When the heat pump outlet water temperature reaches the temperature relay point, the boiler automatically connects to the secondary heating stage to ensure that the main pipeline water supply temperature remains stable within the target range; when the outside temperature rises and the electricity price falls, the boiler output gradually decreases, and the heat pump gradually assumes the main load.

[0046] Through the above methods and steps, the target adjustment parameters can be directly applied to the execution stage of the heating equipment to achieve the regulation of compression power and combustion power. This not only ensures that the heating can operate stably according to the predicted demand, but also dynamically adjusts the division of labor of the equipment according to electricity prices and environmental conditions, thereby reducing energy waste, lowering operating costs, and avoiding losses caused by frequent start-ups and shutdowns of the heating equipment, thus improving economy and stability.

[0047] In this embodiment of the invention, environmental data and real-time operating data of the heating equipment are acquired. The environmental data includes indoor environmental data and outdoor meteorological data. A preset prediction model is used to process the indoor environmental data, outdoor meteorological data, and operating data to determine the target load prediction data. Based on the target load prediction data and current time-of-use electricity price data, an optimized control objective function is constructed. The initial output parameters of the heating equipment are optimized using the optimized control objective function to determine the target adjustment parameters of the heating equipment. The output of the heating equipment is then regulated using the target adjustment parameters. These methods enable coordinated regulation of multiple heat source devices, significantly reducing operating costs while ensuring stable and comfortable heating.

[0048] Optionally, in the step of acquiring environmental data and real-time operation data of the heating equipment, the outdoor meteorological data, the indoor environmental temperature data and the operation data of the heating equipment can also be collected in real time based on a preset sensor array to obtain an initial sensor data set; and each sensor data in the initial sensor data set is preprocessed to determine the target environmental data and the real-time operation data of the heating equipment.

[0049] In the embodiment of the present application, the above-mentioned preset sensor array can be a set of hardware collection devices deployed in the above-mentioned operating environment of the heating equipment, for multi-dimensional perception of operating conditions, including but not limited to temperature sensors, meteorological monitors, flow meters, pressure sensors and energy metering sensors.

[0050] The above-mentioned initial sensor data set can be a raw data set collected by the preset sensor array, including but not limited to air temperature, humidity, wind speed, supply and return water temperature data, flow data, energy consumption parameters and environmental temperature data, etc. It can be understood that the data in the above-mentioned initial sensor data set is not filtered and processed, and there can be noise and missing data.

[0051] The above-mentioned outdoor meteorological data includes air temperature, humidity and wind speed; The above-mentioned operation data includes supply and return water temperature data, flow data and energy consumption parameters; The above-mentioned indoor environmental data includes environmental temperature data.

[0052] In the embodiment, the above-mentioned initial sensor data set can be cleaned, corrected and standardized to achieve the purpose of preprocessing the above-mentioned initial sensor data set. Through the above-mentioned preprocessing operation, the accuracy and availability of the data can be improved. Specifically, the missing data can be interpolated and completed; the abnormal points can be filtered and corrected; the data of different dimensions (such as temperature, flow and energy consumption) can be normalized and mapped to a unified range; and the feature parameters related to load prediction can be extracted to finally generate the target environmental data and real-time operation data.

[0053] In a possible embodiment, when the above-mentioned intelligent heating control platform based on load prediction executes the data acquisition step, the preset sensor array can also be called to collect the outdoor meteorological data, the indoor environmental temperature data and the operation data of the heating equipment in real time to form an initial sensor data set, and the initial sensor data set is preprocessed to obtain standardized target environmental data and heating equipment operation data, providing input for subsequent load prediction and optimization control.

[0054] Optionally, in the step of determining the target load prediction data by processing the indoor environment data, outdoor meteorological data and operation data through a preset prediction model, the step further comprises: performing feature extraction and normalization processing on the indoor environment data, outdoor meteorological data and operation data to construct prediction input feature set data; inputting the prediction input feature set data into a preset neural network model, and performing calculation according to a preset weight and a heating demand constraint to output the target load prediction data in a future preset time period.

[0055] In the embodiment of the present application, the parameters most representative and relevant to load prediction can be selected from the original data, such as indoor temperature, humidity, outdoor temperature, wind speed, supply and return water temperature, flow, energy consumption, etc., and the trend, fluctuation amplitude and other characteristic information can be extracted through an algorithm to reduce the interference of redundant data on the prediction model.

[0056] After the extraction is completed, the process of formatting, normalizing and combining various data into a structured data set can be performed so that the data set can be used as an effective input of the model to obtain the prediction input feature set data.

[0057] The prediction input feature set data described above can be a complete data set formed after feature extraction and normalization processing, which contains a multi-dimensional parameter set required for prediction and can be used to represent the correlation between the operation state of the heating system and the environmental conditions.

[0058] The preset neural network model described above can be a feedforward neural network, a long short-term memory network (LSTM), a convolutional neural network (CNN), etc., which is a neural network model capable of processing time series data and outputting prediction results.

[0059] The preset weight described above can be a constraint parameter during the training of the preset neural network model, which is used to describe the influence strength of the input features on the prediction results. It can be understood that different features have different contributions to the output results through weight adjustment, thereby improving the prediction accuracy.

[0060] The heating demand constraint described above can be a boundary condition introduced in the prediction calculation process, such as keeping the indoor temperature within a comfortable range and not exceeding the maximum power of the equipment, etc., which is used to ensure the rationality and executability of the prediction results. It should be noted that the heating demand constraint described above can be a representation of the relationship between demand and supply in the future preset time period, which is used to pursue the dynamic balance between the heat of the target demand and the supply of the heating equipment.

[0061] The future preset time period described above can refer to the time range covered by the prediction, which can be 15 minutes, 1 hour or 24 hours in the future, which is used to guide the heating scheduling and equipment operation.

[0062] The target load prediction data can be a prediction result output by a preset neural network model after inputting a feature set, and is used to represent a heating demand in a future preset period.

[0063] In a possible embodiment, after collecting indoor environment data, outdoor weather data and operation data, the intelligent heating control platform based on load prediction performs feature extraction, filters key parameters such as temperature, humidity, wind speed, supply and return water temperature, flow and energy consumption, forms a feature set highly related to load prediction, normalizes the selected features, maps data of different dimensions to a unified interval, and combines them to build a prediction input feature set data. The feature set data is input into a preset neural network model, and the preset weight in the model is calculated according to the preset weight, while the heating demand constraint is introduced as a limiting condition, and the target load prediction data in the future preset period is output, which is used to reflect the upcoming heating demand change trend and as the core input of the optimization control.

[0064] Through the above method steps, the neural network model can be used to fuse and calculate multi-source environment data and operation data to obtain accurate future load prediction results.

[0065] Optionally, in the step of building an optimization control objective function based on the target load prediction data and the current time-of-use electricity price data, the step further includes determining a heating demand in the future preset period based on the target load prediction data; determining an energy consumption cost parameter set according to the current time-of-use electricity price data and the heating demand; establishing an optimization control objective function framework with the minimum operation cost of the heating equipment in the future preset period as the target; and introducing the energy consumption cost parameter set as a constraint condition into the optimization control objective function framework to generate the optimization control objective function framework.

[0066] In the embodiment of the present application, the heating demand can refer to the total heat load that needs to be met by the heating equipment in the future preset period, which can generally be calculated from the target load prediction data. For example, in the winter peak period, the prediction model outputs a heating demand of 300 kW in the next hour.

[0067] The energy consumption cost parameter set can refer to a price parameter set used to calculate the operation cost, including current time-of-use electricity price information (peak, flat and valley periods) and gas price parameters. The energy consumption cost of using different energy sources in different periods can be determined by combining the heating demand.

[0068] In the embodiment, the energy consumption cost parameter set can be added to the model as a constraint condition when building the optimization control objective function. For example, in the optimization calculation, the heat pump output is not allowed to exceed a certain proportion in the peak period of electricity price, or the boiler output is limited when the gas price is high.

[0069] The above optimization control objective function framework refers to a mathematical optimization model prototype established with "minimum operation cost" as the target, containing multi-dimensional conditions such as predicted heating demand, equipment output limit, comfort constraint, etc., but before the cost parameter is added, it is only a structure of control optimization, and when the corresponding optimization control objective function is generated, the cost parameter set is added for constraint, thereby forming a complete optimization control objective function that can be solved, which can output the optimal output combination of multiple heat sources for generating target adjustment parameters subsequently.

[0070] In a possible embodiment, after the intelligent heating control platform based on load prediction obtains the target load prediction data of a future preset period, the heating demand of the period is calculated as a basic constraint condition, and the data interface of the power department and the gas supplier is called to obtain the current time-of-use electricity price and gas price information, the cost parameter set of energy consumption is formed in combination with the predicted demand, the optimization control objective function framework is established with "minimum operation cost of the heating system in the future preset period" as the target, the cost parameter set of energy consumption is introduced into the optimization framework, a complete optimization control objective function is generated, and the optimization control objective function is solved through a mathematical optimization algorithm to obtain the optimal output proportion scheme of the air source heat pump and the gas boiler in each period.

[0071] Through the above method steps, the heating demand is considered, and the time-of-use electricity price and gas price factors are also taken into the model, the comprehensive optimization of cost and heating demand is realized, the operation cost of the heating equipment can be reduced, the user comfort is ensured, and stable output basis is provided for the collaborative operation of multiple heat sources.

[0072] Optionally, after the optimization control objective function is constructed based on the target load prediction data and the current time-of-use electricity price data, the steps further include rolling updating the target load prediction data based on a preset time window; when the fluctuation amplitude of the target load prediction data or the current time-of-use electricity price data exceeds a preset threshold, the target load prediction data is updated; and a new optimization control objective function is constructed according to the updated target load prediction data.

[0073] In the embodiment of the application, the above preset time window can be a fixed time period for determining a suitable time for updating the prediction data, for example, in the heating season, 30 minutes can be set as the window, and every 30 minutes, the environmental data (outdoor temperature, humidity, wind speed), indoor environmental temperature, and real-time operation data (supply and return water temperature, flow, energy consumption, etc.) of the heating equipment are re-collected, and the prediction model is iteratively updated in combination with the latest time-of-use electricity price. In this way, the prediction data can be prevented from gradually becoming distorted over time.

[0074] The rolling update can refer to continuously advancing the prediction period forward on the time axis, and re-predicting the load demand for a future period (e.g., 2 hours in the future) every time a preset time window elapses. For example, when the prediction is made at 10:00, the heating demand from 10:00 to 12:00 is obtained; when the prediction is made again at 10:30, the heating demand from 10:30 to 12:30 is obtained. In this way, a prediction data of "the latest two hours" can be maintained at all times, ensuring that the prediction is real-time and continuous.

[0075] The preset threshold can be a critical value for determining whether the data fluctuation is significant. For example, a 5% fluctuation in the heating load prediction can be set as the threshold, i.e., when the prediction deviates from the previous result by more than 5%, it is considered that the heating demand has changed significantly and needs to be recalculated. Similarly, for the electricity price, a 10% price fluctuation threshold can be set, e.g., when the electricity price increases from 0.5 yuan / kWh to 0.6 yuan / kWh (+20%), the threshold is triggered.

[0076] The fluctuation amplitude can be the difference between the current data and the historical data. For example, if the heating demand predicted in the previous period is 500 kW and the latest prediction is 550 kW, the fluctuation amplitude is +10%. For example, if the time-of-use electricity price increases from 0.5 yuan / kWh to 0.55 yuan / kWh, the fluctuation amplitude is +10%. This value is directly compared with the threshold to determine whether the update is triggered.

[0077] In one possible embodiment, the intelligent heating control platform based on load prediction immediately re-executes the prediction and optimization process to generate a new control objective function when the data exceeds the threshold. For example, when the temperature suddenly drops by 5°C, causing the heating load prediction to increase by 20%, the heating demand and energy cost parameter set are immediately updated, and the optimization control objective function is re-generated, thereby ensuring that the control strategy closely follows changes in environmental and market conditions.

[0078] In another possible embodiment, the intelligent heating control platform based on load prediction sets a 30-minute time window as the prediction update period after completing the construction of the initial optimization control objective function. At the end of each window, the intelligent heating control platform based on load prediction re-collects indoor and outdoor environmental data and equipment operation data, iterates the prediction model, and updates the target load prediction data for the next 2 hours.

[0079] During operation, the change of data is also monitored in real time. When it is detected that the fluctuation amplitude of the heating load prediction value relative to the previous window result exceeds ±5%, or the time-of-use electricity price changes by more than ±10%, the threshold update mechanism is triggered. At this time, the intelligent heating control platform based on load prediction immediately regenerates the heating demand and energy consumption cost parameter set, and constructs a new optimization control objective function. For example, when a cold wave arrives and the temperature drops sharply, the heating load prediction value increases from 500 kW to 600 kW (+20%), the intelligent heating control platform based on load prediction will immediately update the prediction and re-optimize the output distribution scheme of the heat pump and the boiler to ensure sufficient heating capacity.

[0080] Through the above method steps, not only can the regular update be performed in the time window, but also the quick response can be realized in the sudden situation, the real-time and robustness of the prediction result are improved, the control logic can be quickly adjusted when the environment or electricity price changes suddenly, the heating shortage or high energy consumption caused by prediction lag is avoided, and therefore the economy and stability of the heating equipment operation are ensured.

[0081] Optionally, in the step of optimizing the initial output parameters of the heating equipment by the optimization control objective function to determine the target adjustment parameters of the heating equipment, the step further includes: determining the optimal output combination data of the air source heat pump and the gas boiler corresponding to the heating equipment based on the optimization control objective function; determining a first target outlet water temperature set value and a first target load rate of the air source heat pump; determining a second target outlet water temperature set value and a second load rate of the gas boiler; and performing optimization calculation on the first target outlet water temperature set value, the first target load rate, the second target outlet water temperature set value and the second load rate based on the optimal output combination data to determine the target adjustment parameters of the heating equipment.

[0082] In the embodiment of the present application, the optimal output combination data can be the heat pump and boiler heating output distribution scheme calculated by the optimization control objective function. For example, the heat pump bears 60% of the output and the boiler bears 40% of the output in a certain period, which is the optimal output combination data. It comprehensively considers the load prediction, electricity price, gas cost and equipment efficiency.

[0083] The first target outlet water temperature set value can be the air source heat pump outlet water temperature target set to meet the heating demand under the optimal output combination. For example, the heat pump needs to maintain an outlet water temperature of 42°C to meet the main pipe network water supply demand.

[0084] The first target load rate can be the running load percentage of the air source heat pump under the optimal output combination. For example, when the maximum output of the heat pump is 300 kW and the current distribution result is 180 kW, the first target load rate is 60%.

[0085] The second target outlet water temperature set value can refer to the target outlet water temperature of the gas boiler set for achieving coordinated operation under the optimal output combination. For example, the outlet water temperature of the heat pump is 42℃, and the boiler needs to heat it twice to 45℃, so 45℃ is the second target outlet water temperature set value.

[0086] The second target load rate can refer to the operating load percentage of the gas boiler under the optimal output combination. For example, when the maximum output of the boiler is 500 kW, and the current allocation result is 200 kW, the second target load rate is 40%.

[0087] In this embodiment, the temperature set value and the load rate can be numerically adjusted and calculated based on the optimal output combination data. For example, a mathematical optimization algorithm is used to obtain the parameters corresponding to the minimum operating cost under equipment constraints, thereby obtaining accurate target adjustment parameters.

[0088] In one possible embodiment, after the intelligent heating control platform based on load prediction constructs the optimal control target function, the optimal output combination data for a certain period is calculated: the air source heat pump needs to bear 60% of the load, and the gas boiler needs to bear 40% of the load. According to the result, the first target outlet water temperature set value of the air source heat pump is determined to be 42℃, and the first target load rate is 60%; the second target outlet water temperature set value of the gas boiler is 45℃, and the second target load rate is 40%. Based on the optimal output combination data, an optimization calculation is performed, considering the performance curve of the heat pump, the time-of-use electricity price, and the boiler gas efficiency, and the temperature set value and the load rate are finely adjusted. For example, when the external air temperature drops, causing the heat pump efficiency to decrease, the platform automatically reduces the heat pump load rate to 55%, and increases the boiler load rate to 45% to ensure that the water supply temperature is stable at 45℃. Finally, the platform generates a set of target adjustment parameters and issues them to the heating equipment control unit, realizing dynamic regulation and control of the heat pump compressor power and the boiler combustion power.

[0089] Through the above method steps, the optimization calculation result can be refined to specific temperature set value and load rate parameters, ensuring that the heat pump and the boiler play their respective advantages in coordinated operation, and also enabling dynamic adjustment when external conditions change, significantly improving the intelligence and adaptive ability of the heating equipment.

[0090] Optionally, in the step of performing optimization calculation on the first target outlet water temperature set value, the first target load rate, the second target outlet water temperature set value and the second load rate based on the optimal output combination data to determine the target adjustment parameter of the heating equipment, the step further comprises: determining a temperature relay point between the air source heat pump and the gas-fired boiler based on an optimization control objective function; determining an outlet water temperature optimization value and a load rate optimization value of the air source heat pump and the gas-fired boiler when performing the heating division switching based on the temperature relay point; and generating the target adjustment parameter of the heating equipment based on the outlet water temperature optimization value and the load rate optimization value.

[0091] In the embodiment of the present application, the temperature relay point can be a switching temperature threshold of the air source heat pump and the gas-fired boiler when performing the cooperative heating. For example, the heat pump can heat water to 42℃, and then the boiler can heat the water to 45℃. The 42℃ is the temperature relay point, which determines the division boundary of the two types of equipment. It should be noted that the temperature relay point can also be used as a reference threshold for rolling optimization. When the external air temperature, load prediction result or time-of-use electricity price fluctuates significantly, the division of the heat pump and the boiler can be re-divided based on the new relay point, so that the energy consumption is not uneven or the operation cost is increased due to the change of the environment. The temperature relay point can also be used as a monitoring index of operation abnormality. When the actual outlet water temperature of the heat pump is lower than the set relay point for a long time, or the boiler still cannot reach the target outlet water temperature after secondary heating, the system can determine that the equipment has a fault or energy efficiency decay, and automatically trigger an alarm or enter a protection mode.

[0092] The heating division switching can be a switching strategy between the heat pump and the boiler under different load conditions and economic conditions. When the environment temperature is high and the electricity price is low, the heat pump undertakes the main heating task; when the environment temperature is low or the electricity price is at the peak, the boiler undertakes more output. The switching point usually depends on the temperature relay point.

[0093] The outlet water temperature optimization value can be an optimal outlet water temperature set value obtained by optimization calculation. For example, the optimal outlet water temperature of the heat pump is 42℃, and the optimal outlet water temperature of the boiler after secondary heating is 45℃. Unlike the fixed set value, the outlet water temperature optimization value is dynamically generated based on the prediction and optimization algorithm.

[0094] The load rate optimization value can be a device load rate distribution value obtained by optimization calculation under the condition of the temperature relay point. For example, the load rate optimization of the heat pump is 55% and the load rate optimization of the boiler is 45% in a certain period of time, so as to realize the lowest operation cost.

[0095] In a possible embodiment, after the optimal output combination data is calculated, the intelligent heating control platform based on load prediction determines the temperature relay point between the air source heat pump and the gas boiler. Taking the winter night as an example, the platform obtains, through prediction and optimization calculation, that the heat pump runs optimally at the low valley of electricity price, and the outlet water temperature is set to 42 DEG C, which is the temperature relay point between the heat pump and the boiler.

[0096] When the water temperature reaches 42 DEG C, the boiler takes over the secondary heating to increase the outlet water temperature to 45 DEG C to meet the water supply demand of the main pipe network. In this process, the platform optimizes the load rate of the two types of equipment to obtain the heat pump load rate optimization value of 55% and the boiler load rate optimization value of 45%. Subsequently, the optimization values are integrated as target adjustment parameters and issued to the equipment controller to be converted into the compressor power control instruction of the air source heat pump and the boiler combustion power control instruction, respectively, to realize dynamic regulation and control.

[0097] Through the above method steps, the temperature relay point can be reasonably determined, and smooth switching between the heat pump and the boiler can be realized to avoid energy waste and equipment wear caused by frequent switching. Dynamic distribution is performed by using the outlet water temperature optimization value and the load rate optimization value, which not only ensures the stability of the main pipe network water supply temperature, but also realizes the minimization of operation cost, thereby improving the economy, stability and intelligent level of the heating equipment.

[0098] As shown in Figure 2 The embodiment of the present application also provides an intelligent heating control device 200 based on load prediction, which comprises: A first acquisition module 201 is configured to acquire environmental data and real-time operation data of a heating equipment, wherein the environmental data comprises indoor environmental data and outdoor meteorological data of the heating equipment; A first processing module 202 is configured to process the indoor environmental data, the outdoor meteorological data and the operation data by using a preset prediction model to determine target load prediction data; A first construction module 203 is configured to construct an optimization control target function based on the target load prediction data and current time-of-use electricity price data; A first determination module 204 is configured to optimize the initial output parameter of the heating equipment by using the optimization control target function to determine target adjustment parameters of the heating equipment; A first regulation and control module 205 is configured to regulate and control the output of the heating equipment by using the target adjustment parameters.

[0099] Optionally, the first acquisition module 201 comprises: The first obtaining sub-module is configured to collect outdoor meteorological data, indoor environmental temperature data and operation data of the heating equipment in real time based on a preset sensor array to obtain an initial sensor data set, wherein the initial sensor data set includes temperature, humidity, wind speed, supply and return water temperature data, flow data, energy consumption parameters and environmental temperature data, and the preset sensor array includes a temperature sensor, a meteorological monitor, a flow meter, a pressure sensor and an energy metering sensor. The first processing sub-module is configured to pre-process each sensor data in the initial sensor data set, and determine target environmental data and real-time operation data of the heating equipment.

[0100] Optionally, the first processing module 202 includes: The second processing sub-module is configured to extract and normalize features of the indoor environmental data, outdoor meteorological data and operation data to construct a prediction input feature set data. The first calculation sub-module is configured to input the prediction input feature set data into a preset neural network model, and perform calculation according to a preset weight and a heating demand constraint to output target load prediction data in a future preset period.

[0101] Optionally, the first construction module 203 includes: The first determination sub-module is configured to determine a heating demand amount in the future preset period based on the target load prediction data. The second determination sub-module is configured to determine an energy consumption cost parameter set according to current time-of-use electricity price data and the heating demand amount. The construction sub-module is configured to establish an optimization control objective function framework with the objective of minimizing operation cost of the heating equipment in the future preset period. The generation sub-module is configured to introduce the energy consumption cost parameter set as a constraint condition into the optimization control objective function framework to generate an optimization control objective function framework.

[0102] Optionally, the apparatus further includes: The second update module is configured to perform rolling update on the target load prediction data based on a preset time window. The first update module is configured to update the target load prediction data when a fluctuation amplitude of the target load prediction data or the current time-of-use electricity price data exceeds a preset threshold. The new construction module is configured to construct a new optimization control objective function according to the updated target load prediction data.

[0103] Optionally, the first determination module 204 includes: a third determining sub-module, configured to determine optimal output combination data of the air source heat pump and the gas boiler of the heating device based on the optimization control objective function; a fourth determining sub-module, configured to determine a first target outlet water temperature setting value and a first target load rate of the air source heat pump; a fifth determining sub-module, configured to determine a second target outlet water temperature setting value and a second load rate of the gas boiler; a sixth determining sub-module, configured to perform optimization calculation on the first target outlet water temperature setting value, the first target load rate, the second target outlet water temperature setting value and the second load rate based on the optimal output combination data, and determine a target adjustment parameter of the heating device.

[0104] Optionally, the first regulating module 205 includes: a seventh determining sub-module, configured to determine a temperature relay point between the air source heat pump and the gas boiler based on the optimization control objective function; an eighth determining sub-module, configured to determine an outlet water temperature optimization value and a load rate optimization value of the air source heat pump and the gas boiler when the air source heat pump and the gas boiler switch the heating division based on the temperature relay point; a ninth determining sub-module, configured to generate a target adjustment parameter of the heating device based on the outlet water temperature optimization value and the load rate optimization value.

[0105] As shown in Figure 3 the embodiment of the present application also provides an electronic device 300, which includes a processor, and the processor can execute any one of the intelligent heating control methods based on load prediction.

[0106] Specifically, the electronic device 300 includes a processor 301, a memory 302, and a computer program stored in the memory 302 and capable of running on the processor 301 to execute the intelligent heating control method based on load prediction, wherein: the processor 301 runs the computer program of the intelligent heating control method based on load prediction stored in the memory 302 to execute the following steps: obtain environment data and real-time operation data of the heating device, wherein the environment data includes indoor environment data and outdoor meteorological data of the heating device; determine target load prediction data by processing the indoor environment data, the outdoor meteorological data and the operation data through a preset prediction model; construct an optimization control objective function based on the target load prediction data and current time-of-use electricity price data; perform optimization processing on initial output parameters of the heating device through the optimization control objective function to determine a target adjustment parameter of the heating device; The output of the heat supply equipment is regulated by the target adjustment parameter.

[0107] Optionally, the processor 301 executes the outdoor meteorological data including air temperature, humidity and wind speed, the operation data including supply and return water temperature data, flow data and energy consumption parameters, and the indoor environment data including environment temperature data, and the environment data and real-time operation data of the heat supply equipment are obtained, including: Based on a preset sensor array, the outdoor meteorological data, indoor environment temperature data and operation data of the heat supply equipment are collected in real time to obtain an initial sensor data set, the initial sensor data set including air temperature, humidity, wind speed, supply and return water temperature data, flow data, energy consumption parameters and environment temperature data, and the preset sensor array including temperature sensors, meteorological monitors, flow meters, pressure sensors and energy metering sensors. The sensor data in the initial sensor data set is preprocessed to determine the target environment data and real-time operation data of the heat supply equipment.

[0108] Optionally, the processor 301 executes the processing of the indoor environment data, outdoor meteorological data and operation data by the preset prediction model to determine the target load prediction data, including: The indoor environment data, outdoor meteorological data and operation data are feature extracted and normalized to construct a prediction input feature set data; The prediction input feature set data is input into a preset neural network model, and the target load prediction data in a future preset period is output according to a preset weight and heat demand constraint.

[0109] Optionally, the processor 301 executes the construction of the optimization control objective function based on the target load prediction data and the current time-of-use electricity price data, including: Based on the target load prediction data, the heat demand amount in a future preset period is determined; According to the current time-of-use electricity price data and the heat demand amount, an energy consumption cost parameter set is determined; The optimization control objective function framework is established with the minimization of the operation cost of the heat supply equipment in the future preset period as the target; The energy consumption cost parameter set is introduced as a constraint condition into the optimization control objective function framework to generate an optimization control objective function framework.

[0110] Optionally, after the processor 301 executes the construction of the optimization control objective function based on the target load prediction data and the current time-of-use electricity price data, the method further includes: Based on a preset time window, the target load prediction data is updated rolling. when a fluctuation range of the target load prediction data or the current time-of-use electricity price data exceeds a preset threshold, updating the target load prediction data; constructing a new optimization control target function according to the updated target load prediction data.

[0111] Optionally, the processor 301 performs the optimization processing on the initial output parameter of the heat supply equipment by the optimization control target function to determine the target adjustment parameter of the heat supply equipment, including: determining optimal output combination data of the air source heat pump and the gas boiler corresponding to the heat supply equipment based on the optimization control target function; determining a first target outlet water temperature set value and a first target load rate of the air source heat pump; determining a second target outlet water temperature set value and a second load rate of the gas boiler; performing optimization calculation on the first target outlet water temperature set value, the first target load rate, the second target outlet water temperature set value and the second load rate based on the optimal output combination data to determine the target adjustment parameter of the heat supply equipment.

[0112] Optionally, the processor 301 performs the optimization calculation on the first target outlet water temperature set value, the first target load rate, the second target outlet water temperature set value and the second load rate based on the optimal output combination data to determine the target adjustment parameter of the heat supply equipment, including: determining a temperature relay point between the air source heat pump and the gas boiler based on the optimization control target function; determining outlet water temperature optimization values and load rate optimization values of the air source heat pump and the gas boiler when performing heat supply division switching based on the temperature relay point; generating the target adjustment parameter of the heat supply equipment based on the outlet water temperature optimization values and the load rate optimization values.

[0113] The embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, the computer program is executed by a processor to realize each process of the intelligent heat supply control method based on load prediction or the application end intelligent heat supply control method based on load prediction provided by the embodiment of the present application, and the same technical effects can be achieved, and details are not repeated here.

[0114] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing relevant hardware, and can be stored in a computer readable storage medium. The program can include the processes of the above-mentioned embodiment methods when executed. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM).

[0115] The above disclosure is only the preferred embodiments of the present application, and of course cannot limit the scope of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope of the present application.

Claims

1. A smart heating control method based on load forecasting, characterized in that, include: Acquire environmental data and real-time operating data of the heating equipment, wherein the environmental data includes indoor environmental data and outdoor meteorological data of the heating equipment; By using a preset prediction model, the indoor environmental data, outdoor meteorological data, and operational data are processed to determine the target load prediction data; Based on the target load forecast data and the current time-of-use electricity price data, an optimization control objective function is constructed; The initial output parameters of the heating equipment are optimized using the optimized control objective function to determine the target adjustment parameters of the heating equipment. The output of the heating equipment is regulated by adjusting the target parameters.

2. The intelligent heating control method based on load forecasting as described in claim 1, characterized in that, The outdoor meteorological data includes air temperature, humidity, and wind speed; the operational data includes supply and return water temperature data, flow rate data, and energy consumption parameters; the indoor environmental data includes ambient temperature data; and the acquisition of environmental data and real-time operational data of the heating equipment includes: Based on a preset sensor array, outdoor meteorological data, indoor ambient temperature data, and operational data of the heating equipment are collected in real time to obtain an initial sensor dataset. The initial sensor dataset includes air temperature, humidity, wind speed, supply and return water temperature data, flow rate data, energy consumption parameters, and ambient temperature data. The preset sensor array includes a temperature sensor, a meteorological monitor, a flow meter, a pressure sensor, and an energy metering sensor. The sensor data in the initial sensor dataset are preprocessed to determine the target environmental data and the real-time operating data of the heating equipment.

3. The intelligent heating control method based on load forecasting as described in claim 1, characterized in that, The process of processing the indoor environmental data, outdoor meteorological data, and operational data using a preset prediction model to determine the target load prediction data includes: The indoor environmental data, outdoor meteorological data, and operational data are subjected to feature extraction and normalization to construct a predictive input feature set data. The predicted input feature set data is input into a preset neural network model, and calculations are performed according to preset weights and heating demand constraints to output the target load prediction data for a preset future time period.

4. The intelligent heating control method based on load forecasting as described in claim 1, characterized in that, The step of constructing an optimization control objective function based on the target load forecast data and the current time-of-use electricity price data includes: Based on the target load forecast data, the heating demand in the future preset period is determined; Determine the set of energy consumption cost parameters based on current time-of-use electricity price data and heating demand; An optimization control objective function framework is established with the goal of minimizing the operating cost of the heating equipment over a future preset period. The energy consumption cost parameter set is introduced as a constraint into the optimization control objective function framework to generate the optimization control objective function framework.

5. The intelligent heating control method based on load forecasting as described in any one of claims 3 or 4, characterized in that, After constructing the optimized control objective function based on the target load forecast data and the current time-of-use electricity price data, the method further includes: The target load forecast data is updated on a rolling basis based on a preset time window; When the fluctuation range of the target load forecast data or the current time-of-use electricity price data exceeds a preset threshold, the target load forecast data is updated; Based on the updated target load forecast data, a new optimal control objective function is constructed.

6. The intelligent heating control method based on load forecasting as described in claim 1, characterized in that, The step of optimizing the initial output parameters of the heating equipment through the optimized control objective function to determine the target adjustment parameters of the heating equipment includes: Based on the optimized control objective function, the optimal output combination data of the air source heat pump and gas boiler corresponding to the heating equipment is determined; Determine the first target outlet water temperature setpoint and the first target load rate of the air source heat pump; Determine the second target outlet water temperature setpoint and the second load rate of the gas-fired boiler; Based on the optimal output combination data, the first target outlet water temperature setpoint, the first target load rate, the second target outlet water temperature setpoint, and the second load rate are optimized and calculated to determine the target adjustment parameters of the heating equipment.

7. The intelligent heating control method based on load forecasting as described in claim 6, characterized in that, Based on the optimal output combination data, the first target outlet water temperature setpoint, the first target load rate, the second target outlet water temperature setpoint, and the second load rate are optimized and calculated to determine the target adjustment parameters of the heating equipment, including: Based on the optimized control objective function, the temperature relay point between the air source heat pump and the gas boiler is determined. Based on the temperature relay point, the optimized values ​​of outlet water temperature and load rate are determined when the air source heat pump and gas boiler switch heating functions. Based on the optimized outlet water temperature and the optimized load rate, target adjustment parameters for the heating equipment are generated.

8. A smart heating control device based on load forecasting, characterized in that, include: The first acquisition module is used to acquire environmental data and real-time operating data of the heating equipment. The environmental data includes indoor environmental data and outdoor meteorological data of the heating equipment. The first processing module is used to process the indoor environmental data, outdoor meteorological data and operational data through a preset prediction model to determine the target load prediction data. The first construction module is used to construct an optimized control objective function based on the target load forecast data and the current time-of-use electricity price data; The first determining module is used to optimize the initial output parameters of the heating equipment through the optimized control objective function, and determine the target adjustment parameters of the heating equipment. The first control module is used to control the output of the heating equipment by adjusting the target parameters.

9. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the intelligent heating control method based on load forecasting as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the intelligent heating control method based on load forecasting as described in any one of claims 1 to 7.

Images