Dynamic simulation time sequence driven heat pump system agent training strategy generation method

Abstract

The invention belongs to the technical field of building energy management and control, and relates to a dynamic simulation time sequence driven heat pump system agent training strategy generation method. A set of complete and hourly heat pump system intelligent agent training samples are established by obtaining the annual hourly fan coil heat load supply amount, the fan coil water supply temperature, the number of started heat pumps, the number of started hot water pumps, the water flow of the hot water pumps and the operation frequency of the hot water pumps, and the heat pump system intelligent agent is trained by utilizing the training samples. And efficient and stable operation of the building heat pump system is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of building energy management and control, and specifically relates to a method for generating a heat pump system intelligent agent training strategy driven by dynamic simulation timing. Background Art

[0002] Currently, intelligent agent training primarily relies on offline datasets constructed from historical operating data, with policy optimization guided by a reward function in reinforcement learning. However, this approach has significant drawbacks: actual data rarely covers complex operating conditions such as extreme weather and equipment failures, and the reward function's setting relies heavily on human experience. This makes the trained policy prone to falling into local optimality and unable to meet the global control requirements in complex dynamic environments.

[0003] To improve learning efficiency, existing technologies often incorporate pre-trained models based on expert knowledge, such as setting device start / stop thresholds and temperature fluctuation ranges. However, existing technologies also suffer from two major issues: First, rule bases are often based on independent device control logic, failing to consider the trade-off between energy consumption and comfort when multiple devices are coupled. Second, the dynamic correlation between environmental parameters (such as outdoor temperature and humidity) and temporal dimensions (such as hourly load fluctuations) is not effectively decoupled, making it difficult for pre-set rules to adapt to the real-time thermal inertia characteristics of buildings and user behavior patterns. For example, in the training of intelligent agents under winter heating conditions, the traditional heat pump system's crude operational control methods lead to energy waste and low equipment efficiency. Specifically, this manifests itself in an inability to precisely adjust heat pump and hot water pump operating parameters based on actual heat load, resulting in high energy consumption during low-load conditions. Furthermore, frequent switching of equipment units not only shortens unit lifespan but also increases maintenance costs. These issues fundamentally reflect the shortcomings of existing policy generation methods in addressing dynamic and complex scenarios. Summary of the Invention

[0004] The purpose of this invention is to provide a method for generating training strategies for intelligent agents in heat pump systems, driven by dynamic simulation timing. This method is used to achieve refined control of building heating systems and provide precise decision-making strategies for intelligent agent training. By constructing a fine-grained knowledge model through hourly simulation and deduction, this method deeply explores the dynamic relationship between environmental parameters and the time dimension, fully considering the coupling characteristics of multiple devices, and providing a decision-making benchmark for intelligent agent training that combines physical realism with temporal continuity. This method optimizes intelligent agent training strategies and improves system operational efficiency and stability.

[0005] The present invention is achieved through the following technical solutions: A dynamic simulation time-series driven heat pump system agent training strategy generation method is proposed, which includes the following steps: obtaining the heat load data of the entire building hourly throughout the year; obtaining the hourly water flow of each fan coil unit throughout the year based on the supply and return water temperature difference and the heat load data of the entire building hourly throughout the year; obtaining the actual hourly heating supply of each fan coil unit at each water supply temperature based on the supply and return water temperature difference, the hourly water flow of each fan coil unit throughout the year and multiple preset water supply temperatures; summarizing the actual heating supply of multiple fan coil units at the same water supply temperature and the same time period; determining the actual hourly heating supply of the entire year based on the heat load data of the entire building hourly throughout the year and the summarized multiple actual heating supplies. Water supply temperature; according to the hourly heat load data of the entire building throughout the year and the actual heating capacity of a single heat pump, obtain the hourly number of heat pumps turned on throughout the year; according to the hourly number of heat pumps turned on throughout the year and the engineering ratio of heat pumps to hot water pumps, obtain the hourly number of hot water pumps throughout the year; according to the supply and return water temperature difference, the hourly heat load data of the entire building throughout the year and the hourly number of hot water pumps throughout the year, obtain the hourly water flow of each hot water pump throughout the year; according to the hourly water flow of each hot water pump throughout the year, obtain the hourly operating frequency of each hot water pump throughout the year; comprehensively consider the actual hourly water supply temperature throughout the year, the number of heat pumps turned on, the number of hot water pumps and the hourly operating frequency of each hot water pump throughout the year to generate an intelligent agent training strategy.

[0006] Compared with existing technologies, this invention offers the following advantages and benefits: By refining the agent control strategy, a complete set of refined hourly control strategies for heat pump feedwater temperature, number of heat pumps, number of hot water pumps, and hot water pump frequency is formed. The hourly data sequences generated by these strategies provide a large number of authentic and effective data samples and clear target strategies for agent training, effectively optimizing the agent training process, improving system operating efficiency, reducing energy consumption, and ensuring stable equipment operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings: Figure 1 This is a flow chart of the method for generating a heat pump system agent training strategy driven by dynamic simulation timing provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0008] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below in conjunction with the examples. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention. The embodiments described below are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0009] In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that these specific details are not necessarily required to practice the present invention. In other examples, well-known structures, materials, or methods are not specifically described to avoid obscuring the present invention. The materials, instruments, and reagents used in the following examples, unless otherwise specified, are commercially available. The techniques used in the examples, unless otherwise specified, are conventional techniques well known to those skilled in the art.

[0010] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0011] Example 1: The provided dynamic simulation timing driven heat pump system intelligent agent training strategy generation method includes: Figure 1 The following steps are shown: Step 1: Create a dynamic mapping between actual demand heat load and coil water flow.

[0012] The purpose of this step is to provide the agent with training data samples that reflect the actual heat load demand of the entire building, enabling it to learn the changing patterns of coil water flow. This step is achieved by obtaining hourly heat load data for the entire building throughout the year. Based on the supply and return water temperature difference and the hourly heat load data for the entire building throughout the year, the agent obtains the hourly water flow rate for each fan coil unit throughout the year.

[0013] Hourly heat load data for the entire building throughout the year can be obtained by collecting the building's structural parameters, internal air conditioning system parameters, and local meteorological data for the entire year. Based on the structural parameters, create a 3D model of the entire building, assign parameters to the building's envelope, and set the building's internal heat source and heat dissipation pattern. Build an air conditioning system model for the entire building based on the air conditioning system parameters. Set the boundary conditions for the building energy simulation based on local meteorological data. Set the time step, iteration accuracy, and output format for the building energy simulation. Input the building's 3D structural model, envelope parameters, internal heat source and heat dissipation pattern, and air conditioning system model, along with the local climate data for the entire year, as well as the boundary conditions, time step, iteration accuracy, and output format for the building energy simulation into the building energy simulation software. Run the building energy simulation software to obtain and output hourly heat load data for the entire building throughout the year.

[0014] Furthermore, obtaining the hourly water flow of each fan coil unit throughout the year includes the following steps: 1. Set the supply and return water temperature difference of the fan coil unit.

[0015] In this embodiment, the supply and return water temperature difference of the fan coil unit is fixedly set to 5°C.

[0016] 2. Execute steps A1 to A2 for the hourly heat load data of the entire building for each period throughout the year.

[0017] Step A1: Allocate the heat load data of the entire building to each fan coil unit to obtain the heat load data of each fan coil unit.

[0018] Step A2: Calculate the water flow rate of each fan coil unit based on the supply and return water temperature difference and heat load data.

[0019] According to the heat transfer formula Q=CRΔT Calculate the water flow of the fan coil unit, where Q represents the heat load. C represents the specific heat capacity of water, R Indicates water flow, ΔT Indicates the supply and return water temperature difference. For example, according to step A1, if the calculated heat load is 3560 W The specific heat capacity of water is 4.1868 (kJ / kg·°C). Based on the determined supply and return water temperature difference of 5°C, the water flow rate of the fan coil unit is R=3560 W ÷4.1868(kJ / kg·°C)÷5℃≈170m 3 / h.

[0020] Step 2: Calculate the actual heat supply value of the fan coil unit at different water supply temperatures and at different times.

[0021] The corresponding relationship between these actual heating data and different water supply temperatures constitutes the knowledge system for heating performance during agent training, helping the agent understand the impact of water supply temperature on coil heating, thereby optimizing its decision-making strategy during training. This step is implemented by obtaining the actual hourly heating value of each fan coil at each water supply temperature based on the supply and return water temperature difference, the hourly water flow rate of each fan coil throughout the year, and multiple preset water supply temperatures.

[0022] Specifically, the software provided by the fan coil manufacturer is used to calculate the actual heat supply value of the fan coil unit of the heating equipment. The specific method is: First, set the input parameters in the software: (1) Supply and return water temperature difference. This is the same as the supply and return water temperature difference of the fan coil unit set in step 1, fixed at 5°C.

[0023] (2) The hourly water flow rate of the fan coil unit throughout the year. This is the hourly water flow rate of the fan coil unit throughout the year obtained in step 1 above.

[0024] (3) Water supply temperature value sequence. The water supply temperature value sequence contains multiple water supply temperature values (such as 40°C, 41°C and 42°C) that are lower than the factory design water supply temperature of the fan coil unit (45°C).

[0025] The input parameters are then imported into the fan coil unit manufacturer's software, which automatically calculates the actual hourly heat load supplied by each fan coil unit at each water supply temperature throughout the year. This heat supply data, along with the corresponding water supply temperature and time information, is then fed into an intelligent agent training model, allowing the agent to learn the relationship between water supply temperature and heat supply, enabling it to make better decisions in real-world operations.

[0026] Step 3: Check the water supply temperature.

[0027] First, the actual heating capacity of multiple fan coil units is summarized at the same water supply temperature and the same time period.

[0028] For example, when the water supply temperature is 41°C, the period from 0:00 to 1:00 on January 1st corresponds to the actual heat load supply of each fan coil unit. This step is to add up the actual heat load supply of all fan coil units corresponding to the period from 0:00 to 1:00 on January 1st when the water supply temperature is 41°C.

[0029] Then, based on the heat load data of the entire building at each hour throughout the year and the summarized multiple actual heating amounts, the actual water supply temperature at each hour throughout the year is determined.

[0030] The purpose of this step is to enable the agent to learn how to select the appropriate water supply temperature according to the heat load demand to achieve rational use of energy.

[0031] Among them, the method for determining the actual hourly water supply temperature throughout the year is: 1. Subtract the actual heat supply of each item from the heat load data of the entire building during the corresponding period.

[0032] For example, for a temperature of 41°C and the first hour, the actual heat supply corresponding to the first hour is subtracted from the heat load data for the entire building at the first hour to obtain the difference value corresponding to the first hour at 41°C. The calculation method for each hour at the remaining temperatures is the same, ultimately obtaining the difference value for each hour at each water supply temperature.

[0033] 2. Filter out the differences greater than zero from the differences corresponding to each time period.

[0034] If the fan coil unit's actual heat supply at a given water supply temperature can meet the building's heat load requirements at all times, then that water supply temperature is determined to be the actual water supply temperature the system should provide at that time. Therefore, from the multiple heat load differences corresponding to each time period, select the difference greater than zero. For example, if the first hour corresponds to the differences at 40°C, 41°C, and 42°C, select the difference greater than zero from the three heat load differences at 40°C, 41°C, and 42°C.

[0035] 3. For each time period, the water supply temperature corresponding to the screened difference is determined as the actual water supply temperature.

[0036] Step 4: Determine the number of heat pumps to be turned on.

[0037] The purpose of this step is to provide the agent with learning samples of heat pump control strategies, allowing it to master how to rationally control the number of heat pumps under varying heat loads and operating conditions. This step is implemented by obtaining the hourly number of heat pumps active throughout the year based on the building's hourly heat load data and the actual heating capacity of each heat pump.

[0038] Prior to this, it is necessary to first obtain the actual heating capacity of a single heat pump. The specific method is: use the defrost correction model, the regional humidity correction model and the ambient temperature correction model corresponding to the water supply temperature in each period to correct the rated heating capacity of a single heat pump.

[0039] 1. Use the defrost correction model to correct First, collect the defrost data of the heat pump under different operating conditions, including defrost frequency, defrost time, heat loss during defrost, etc. This data can be obtained through experimental testing or monitoring during actual operation.

[0040] Then, we analyze the main factors that affect the defrost process, such as outdoor temperature, humidity, wind speed, and heat pump operating time. Generally speaking, the lower the outdoor temperature and the higher the humidity, the more frequent the defrost and the greater the heat loss.

[0041] Next, a defrost correction model is established based on the collected data and analyzed influencing factors. The functional relationship between a defrost correction coefficient and each influencing factor can be obtained by numerical fitting. For example, the correction coefficient K d It can be expressed as K d =f ( T 0 ,H 0 ,t ),in, T 0 is the outdoor temperature, H 0 is the outdoor humidity, t The continuous operation time of the heat pump.

[0042] Finally, the outdoor temperature, humidity and heat pump operation time and other parameters are monitored in real time, and these parameters are substituted into the defrost correction model to calculate the defrost correction coefficient. K d Use the defrost correction factor to multiply the rated heating capacity of the heat pump. Q e , get the heating capacity after defrost correction Q d = K d Q e .

[0043] 2. Correction using the regional humidity correction model First, collect humidity data from different regions. You can obtain long-term average humidity data from the meteorological department or use a professional meteorological database. At the same time, clarify the specific geographical location of the heat pump.

[0044] Then, we obtained the variation patterns of the heat pump's heating performance under different humidity conditions. Generally speaking, when the humidity is high, the heat pump's evaporator surface is more likely to frost, which affects the heat transfer effect and reduces the heating capacity.

[0045] Next, based on the analysis of the impact of humidity on heat pump performance, a regional humidity correction model is established. For example, the region can be divided into several humidity zones based on the average humidity of different regions, and each zone corresponds to a correction coefficient. K h . Or establish a continuous correction function, such as K h = a + ikB a ,in, H a is the local annual average humidity,a and b is a constant determined through data analysis.

[0046] Finally, the humidity data of the area where the heat pump is located is substituted into the regional humidity correction model to calculate the regional humidity correction coefficient. K h Then, multiply the defrost-corrected heating capacity by this factor. Q d , get the heating capacity after regional humidity correction Q h = K h Q d .

[0047] 3. Use ambient temperature to correct the model Perform the following steps for each time period of the water supply temperature determined in step 3: First, during the operation of the heat pump, the outdoor ambient temperature is monitored in real time. T 0 A high-precision temperature sensor can be installed near the heat pump outdoor unit to obtain accurate ambient temperature data.

[0048] Then, based on the performance characteristics of the heat pump and experimental data, determine the correction function of the ambient temperature on the heating capacity. Generally, the heating capacity of the heat pump decreases as the ambient temperature decreases. Common correction function forms include linear function, quadratic function or exponential function. For example, the correction function can be expressed as K t = c + dT o + e ( T o ) 2 ,in c 、 d and e are the polynomial coefficients determined experimentally.

[0049] Finally, the real-time monitored ambient temperature T o Substitute into the ambient temperature correction function to calculate the ambient temperature correction coefficient K t . Use the ambient temperature correction factor K t Multiply the heating capacity by the regional humidity correction Q h , and obtain the final corrected heating value Q f = K tQ h .

[0050] Furthermore, to prevent frequent switching of the number of active heat pumps and protect the heat pump unit's service life, this embodiment implements a protection mechanism for the hourly calculated number of active heat pumps after obtaining it. This mechanism limits the frequency of changes in the number of active heat pumps. For example, the number of active heat pumps can be limited to only once every three hours. By inputting this hourly data into the agent training model, the agent learns strategies for properly controlling the number of heat pumps under different operating conditions, preventing damage to the equipment caused by frequent switching.

[0051] Step 5: Determine the number and frequency of variable frequency hot water pumps.

[0052] The purpose of this step is to provide the agent with learning content about the hot water pump control strategy, enabling it to learn how to adjust the hot water pump's operating status according to system requirements and achieve efficient collaboration with the heat pump. This step is implemented by: obtaining the hourly number of hot water pumps per year based on the hourly number of heat pumps running throughout the year and the engineering ratio of heat pumps to hot water pumps; obtaining the hourly water flow rate of each hot water pump per year based on the supply and return water temperature difference, the hourly heat load data of the entire building per year, and the hourly number of hot water pumps per year; obtaining the hourly operating frequency of each hot water pump per year based on the hourly water flow rate of each hot water pump; and limiting the hourly operating frequency of each hot water pump per year.

[0053] Specifically, according to the actual engineering ratio of heat pumps and hot water pumps in the building, and based on the number of heat pumps turned on hourly throughout the year determined in step 4, calculate the corresponding number of hot water pumps turned on hourly throughout the year to ensure the coordinated operation of the hot water pumps and heat pumps.

[0054] The specific method for obtaining the hourly water flow of each hot water pump throughout the year is as follows: 1. Set the supply and return water temperature difference of the hot water pump.

[0055] The supply and return water temperature difference in this step is the same as that set in step 1, both of which are fixed at 5°C.

[0056] 2. Execute steps B1 and B2 for the heat load data of the entire building corresponding to each time period.

[0057] Step B1: Distribute the heat load data of the entire building to each hot water pump to obtain the heat load data of each hot water pump.

[0058] For the specific implementation of this step, refer to step A1.

[0059] Step B2: Calculate the water flow rate of each hot water pump based on the supply and return water temperature difference and the heat load data of each hot water pump.

[0060] For the specific implementation of this step, please refer to step A2.

[0061] Furthermore, the operating frequency of the hot water pump is calculated based on the water flow of the hot water pump calculated above and the correspondence between the water flow and the operating frequency recorded on the rated nameplate of the hot water pump, combined with the calculation formula "operating frequency = actual water flow of the hot water pump ÷ rated water flow of the hot water pump × rated operating frequency of the hot water pump".

[0062] Furthermore, since the hot water pump's efficiency decreases significantly when its operating frequency falls below 30 Hz, to improve efficiency, the hourly operating frequency of the heat pump water is limited to a minimum of 30 Hz. The final hot water pump operating frequency is determined within the range from 30 Hz to the rated maximum operating frequency. This step aims to guide the agent in prioritizing decisions that keep the hot water pump operating in the high-efficiency range when learning the hot water pump's control strategy, ensuring that the hot water pump operates within this range.

[0063] Step 6: Generate agent training strategy.

[0064] The agent training strategy is generated by comprehensively considering the actual hourly water supply temperature throughout the year, the number of heat pumps turned on, the number of hot water pumps, and the hourly operating frequency of each hot water pump throughout the year.

[0065] It should be understood that the terms "system," "device," "unit," and / or "module" used in this specification are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0066] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0067] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0068] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for understanding and reading by those familiar with this technology, and are not used to limit the conditions for implementation of the present invention. Therefore, they have no substantial technical significance. Any modification of the structure, change in the proportional relationship, or adjustment of the size should still fall within the scope of the technical content disclosed by the present invention without affecting the efficacy and purpose of the present invention. At the same time, the terms such as "upper", "lower", "left", "right", "middle", etc. quoted in this specification are only for the convenience of description and are not used to limit the scope of implementation of the present invention. Changes or adjustments in their relative relationships should also be regarded as the scope of implementation of the present invention without substantially changing the technical content.

Claims

1. A method for generating a heat pump system agent training strategy driven by dynamic simulation timing, characterized in that: The following steps are involved: Obtain the heat load data of the entire building hourly throughout the year; obtain the hourly water flow of each fan coil unit throughout the year based on the supply and return water temperature difference and the heat load data of the entire building hourly throughout the year; According to the supply and return water temperature difference, the hourly water flow of each fan coil unit throughout the year and multiple preset water supply temperatures, the actual hourly heating capacity of each fan coil unit at each water supply temperature throughout the year is obtained; Under the same water supply temperature and in the same time period, the actual heat supply of multiple fan coil units is aggregated; based on the hourly heat load data of the entire building and the aggregated actual heat supply, the actual water supply temperature for each hour of the year is determined; Based on the hourly heat load data of the entire building and the actual heating capacity of a single heat pump, the number of heat pumps that are turned on at each hour throughout the year is obtained; Based on the hourly number of heat pumps turned on throughout the year and the engineering ratio of heat pumps to hot water pumps, the hourly number of hot water pumps throughout the year is obtained; based on the supply and return water temperature difference, the hourly heat load data of the entire building throughout the year, and the hourly number of hot water pumps throughout the year, the hourly water flow rate of each hot water pump throughout the year is obtained; based on the hourly water flow rate of each hot water pump throughout the year, the hourly operating frequency of each hot water pump throughout the year is obtained; The agent training strategy is generated by comprehensively considering the actual hourly water supply temperature throughout the year, the number of heat pumps turned on, the number of hot water pumps, and the hourly operating frequency of each hot water pump throughout the year.

2. The method for generating a heat pump system agent training strategy driven by dynamic simulation timing according to claim 1 is characterized in that: Obtaining the hourly water flow of each fan coil unit throughout the year includes the following steps: Based on the hourly heat load data for the entire building throughout the year corresponding to each time period, execute steps A1 to A2. Step A1 distributes the heat load data for the entire building to each fan coil unit to obtain the heat load data for each fan coil unit. Step A2 calculates the water flow rate for each fan coil unit based on the supply and return water temperature difference and the heat load data.

3. The method for generating a heat pump system agent training strategy driven by dynamic simulation timing according to claim 1 is characterized in that: Determining the actual hourly water supply temperature throughout the year involves the following steps: Subtract the summed actual heat supply from the heat load data of the entire building during the corresponding period; Filter the differences that are greater than zero from the differences corresponding to each period; For each time period: the water supply temperature corresponding to the screened difference is determined as the actual water supply temperature.

4. The method for generating a heat pump system agent training strategy driven by dynamic simulation timing according to claim 1 is characterized in that: After determining the actual hourly water supply temperature throughout the year, the following steps are also included: The rated heating capacity of a single heat pump is corrected by using the defrost correction model, the regional humidity correction model and the ambient temperature correction model corresponding to the actual water supply temperature in each period to obtain the actual heating capacity of the single heat pump.

5. The method for generating a heat pump system agent training strategy driven by dynamic simulation timing according to claim 1 is characterized in that: After obtaining the hourly number of heat pumps turned on throughout the year, the following steps are also included: limiting the frequency of changes in the number of heat pumps turned on.

6. The method for generating a heat pump system agent training strategy driven by dynamic simulation timing according to claim 1 is characterized in that: Obtaining the hourly water flow of each hot water pump throughout the year includes the following steps: For the heat load data of the entire building corresponding to each time period, execute steps B1 to B2; wherein, step B1: distributes the heat load data of the entire building to each hot water pump to obtain the heat load data of each hot water pump; step B2: calculates the water flow rate of each hot water pump based on the supply and return water temperature difference and the heat load data of each hot water pump.

7. The method for generating a heat pump system agent training strategy driven by dynamic simulation timing according to claim 1, characterized in that: After obtaining the hourly operating frequency of each hot water pump throughout the year, the following steps are also included: Limit the hourly operating frequency of each hot water pump throughout the year; Add the limited running frequency to the agent training strategy.

8. The method for generating a heat pump system agent training strategy driven by dynamic simulation timing according to claim 7 is characterized in that: The operating frequency range is [30Hz, rated maximum frequency].

Images