Control method and device of building cold and heat source system adaptive to load demand

Abstract

The application discloses a kind of self-adapting load demand's building cold and heat source system control method and device.The control method comprises: obtaining the historical operation data of building, physical characteristics and equipment system data, establishes the building load prediction model;Generation the hourly load curve, and according to the curve, the cooling or heating demand of each period in the future is predicted;Dynamic adjustment refrigeration or heating load demand, generate corresponding cooling or heating curve;Machine learning algorithm based on equipment mechanism model is constructed, and the control strategy of cold and heat source system is optimized based on the historical operation data of the equipment, and the control parameter of equipment is output.The technical scheme of the present application intelligently predicts and adjusts the load of building cold and heat source system, improves system energy efficiency, reduces invalid energy consumption, optimizes energy utilization, realizes control parameter optimization through machine learning algorithm, ensures efficient operation, maintains indoor comfort, and achieves energy-saving purpose.

Description

Technical Field

[0001] This invention relates to the technical field of air conditioning, and more particularly to a control method and apparatus for a building cooling and heating source system that adapts to load demand. Background Technology

[0002] Central air conditioning systems with centralized cooling and heating sources are typically equipped with multiple chiller units or heat pump units to adapt to load demands under different operating conditions. In existing technologies, system regulation mainly relies on feedback control, which is relatively effective in controlling terminal equipment, but its control effect is not ideal for large-capacity, lagging systems such as chilled water systems. In the initial stage of chiller unit startup, there is a lack of an optimal combination of units to meet the actual load demands of the building, leading to increased system adjustment time and frequency, and higher operating energy consumption required to provide the same amount of cooling and heating.

[0003] In actual operation, load demand is dynamic and difficult to adjust in real time to keep up with changes in load, leading to a mismatch between heating and cooling supply and actual demand. To ensure that the building's internal temperature reaches the preset requirements, excess supply is often provided, increasing the building's energy consumption and operating costs.

[0004] How to properly solve the above problems has become an urgent issue for the industry. Summary of the Invention

[0005] This invention provides a control method, apparatus, equipment, and storage medium for a building heating and cooling source system that adapts to load demand. By intelligently predicting and adjusting the load of the building heating and cooling source system, the system's energy efficiency is improved, ineffective energy consumption is reduced, and energy utilization is optimized. Through machine learning algorithms, control parameters are optimized to ensure efficient operation, maintain indoor comfort, and achieve energy-saving goals.

[0006] According to a first aspect of the present invention, a control method for a building heating and cooling source system that adapts to load demand is provided, the control method comprising:

[0007] Acquire historical operational data, physical characteristics, and equipment system data of the building, and establish the building load prediction model;

[0008] Based on the historical operating data and building load prediction model, the hourly load demand of the building is calculated, the hourly load curve is generated, and the cooling or heating demand for each future period is predicted based on the curve.

[0009] Acquire real-time meteorological data and personnel flow data, and dynamically adjust the cooling or heating load demand based on the hourly load forecast results to generate corresponding cooling or heating curves;

[0010] A machine learning algorithm based on the device mechanism model is constructed to optimize the control strategy of the cold and heat source system based on the historical operating data of the device, and outputs the control parameters of the device, including any one or more of the following: start and stop time, number of operating units, outlet water temperature setpoint, and water pump frequency.

[0011] In one embodiment, establishing the building load forecasting model includes:

[0012] Based on the building's historical operational data and physical characteristics, data collected through at least one sensor is cleaned and repaired to eliminate outliers and missing data.

[0013] The data cleaning and repair process involves removing outlier data points, filling in missing data, and smoothing the data.

[0014] In one embodiment, the generation of the hourly load curve includes:

[0015] By combining the physical characteristics of the building, real-time meteorological data, and personnel flow data, the hourly cooling or heating load demand is calculated through the building load prediction model, and the hourly load curve is generated.

[0016] The hourly load curves are generated based on the heat transfer performance of the building envelope, the fresh air load, and the impact of indoor occupant activities on the thermal environment.

[0017] In one embodiment, the dynamic adjustment of cooling or heating load demand includes:

[0018] By acquiring real-time meteorological data and building occupancy data, the hourly load forecast results are dynamically corrected.

[0019] Adjust the cooling or heating curves of the cold and heat source system based on the revised load forecast results.

[0020] During the correction process, the immediate impact of meteorological data and population movement on heating and cooling loads is taken into account.

[0021] In one embodiment, the construction of the machine learning algorithm includes:

[0022] Based on the equipment mechanism model and historical operating data, the cooling capacity curve and energy efficiency curve of the cold and heat source system are established. The machine learning model is trained through historical data to optimize the equipment control strategy and select the optimal operating parameters.

[0023] Based on historical operating data, analyze the equipment's operating conditions and extract characteristic parameters.

[0024] In one embodiment, the output device control parameters include:

[0025] Based on the optimized control strategy, determine one or more of the following: equipment start-up and shutdown time, number of operating units, outlet water temperature setpoint, and water pump frequency.

[0026] Based on the preset energy efficiency ratio, operational stability, and indoor environmental comfort, control parameters are determined using a multi-objective optimization strategy.

[0027] Device right 1.

[0028] According to a third aspect of the present invention, an electronic device is provided, comprising: a communication interface, a processor, and a memory;

[0029] The feature is that the memory is used to store program instructions, which, when executed by the processor that is communicatively connected to the memory via the communication interface, implement any of the above-described control methods for building heating and cooling systems that adapt to load demand.

[0030] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a computer (e.g., a processor in a computer), implement a control method for any of the above-described adaptive load demand building heating and cooling source systems.

[0031] In summary, this invention provides a control method and apparatus for an adaptive load demand building cooling and heating source system. The method includes: acquiring historical operating data, physical characteristics, and equipment system data of the building, and establishing a building load prediction model; calculating the hourly load demand of the building based on the historical operating data and the building load prediction model, generating the hourly load curve, and predicting the cooling or heating demand for future periods based on the curve; acquiring real-time meteorological data and personnel flow data, dynamically adjusting the cooling or heating load demand based on the hourly load prediction results, and generating corresponding cooling or heating curves; constructing a machine learning algorithm based on an equipment mechanism model, optimizing the control strategy of the cooling and heating source system based on the historical operating data of the equipment, and outputting the control parameters of the equipment, including one or more of the following: start-up and shutdown time, number of operating units, outlet water temperature setpoint, and pump frequency. The technical solution of this application achieves a significant improvement in system energy efficiency by intelligently predicting and dynamically adjusting the load demand of the building cooling and heating source system. By utilizing the combination of historical and real-time data, cooling and heating load demand can be predicted more accurately, thereby optimizing energy allocation and reducing ineffective energy consumption. Meanwhile, machine learning algorithms based on equipment mechanism models optimize equipment control parameters, enabling the system to adapt and improve its automation and intelligence levels, reduce operating costs, and ensure indoor comfort under various environmental conditions, thus achieving energy conservation and emission reduction.

[0032] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0033] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0034] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0035] Figure 1 A flowchart of a control method for a building heating and cooling source system that adapts to load demand, provided as an embodiment of the present invention;

[0036] Figure 2 A flowchart for establishing a building load prediction model is provided for embodiments of the present invention;

[0037] Figure 3 A flowchart of a machine learning algorithm based on a device mechanism model provided for an embodiment of the present invention;

[0038] Figure 4 A flowchart illustrating the control strategy output adapted to operating conditions, provided for embodiments of the present invention;

[0039] Figure 5 A flowchart of an iterative optimization method for a system after implementing an optimization strategy, provided as an embodiment of the present invention;

[0040] Figure 6 A structural diagram of a control device for a building cooling and heating source system that adapts to load demand, provided as an embodiment of the present invention;

[0041] Figure 7 This is a structural diagram of an electronic device provided as an embodiment of the present invention. Detailed Implementation

[0042] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0043] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0044] like Figure 1 As shown, the present invention provides a control method for a building heating and cooling source system that adapts to load demand. The control method for this building heating and cooling source system includes:

[0045] In step S11, historical operating data, physical characteristics, and equipment system data of the building are acquired, and the building load prediction model is established.

[0046] In step S12, based on the historical operating data and the building load prediction model, the hourly load demand of the building is calculated, the hourly load curve is generated, and the cooling or heating demand for each future period is predicted based on the curve.

[0047] In step S13, real-time meteorological data and personnel flow data are acquired, and the cooling or heating load demand is dynamically adjusted according to the hourly load forecast results to generate corresponding cooling or heating curves.

[0048] In step S14, a machine learning algorithm based on the device mechanism model is constructed to optimize the control strategy of the cold and heat source system based on the historical operating data of the device, and output the control parameters of the device, including any one or more of the following: start-up and stop time, number of operating units, outlet water temperature setpoint, and water pump frequency.

[0049] In one embodiment, it is necessary to acquire the building's historical operating data, physical characteristics, and equipment system data. Historical operating data includes temperature, humidity, and energy consumption records inside and outside the building; physical characteristics involve the building's size, zoning, and envelope characteristics; and equipment system data includes the type, specifications, and efficiency of the equipment. A building load forecasting model built upon this data provides a foundation for predicting the building's heating and cooling demands under different conditions. This model can combine historical data with a comprehensive consideration of the building's structure and usage patterns to accurately predict the building's demand trends in future time periods. After establishing the load forecasting model, hourly load demand is calculated based on this model and the building's historical operating data, thereby generating an hourly load curve. The hourly load curve can reflect the fluctuations in the building's heating and cooling load demand in detail each hour. Through this hourly load curve, the cooling or heating demand in future time periods can be predicted, allowing for advance preparation of energy supply. Transforming historical data into actual hourly demand enables more precise energy supply planning.

[0050] Because actual conditions may deviate from historical data, real-time meteorological and population movement data are necessary. By integrating real-time meteorological data (such as current temperature and humidity, weather forecasts) and population density changes, combined with hourly load forecasts, the system can dynamically adjust cooling or heating load demands. This dynamic load regulation ensures that cooling or heating curves consistently meet actual needs.

[0051] Based on the hourly load curves, real-time load adjustment results, and historical operating data of the equipment, a machine learning algorithm based on the equipment mechanism model was constructed. This algorithm optimizes the control strategy of the heating and cooling source system to improve system efficiency and stability. Here, the machine learning algorithm iteratively optimizes the control strategy based on historical equipment data and outputs control parameters for the equipment. These parameters include equipment start-up and shutdown times, number of operating units, outlet water temperature setpoint, and pump frequency. These control parameters represent the final specific response to the building's heating and cooling demands; they directly affect the system equipment, thereby achieving intelligent and efficient heating and cooling source control.

[0052] The technical solution in this embodiment achieves a significant improvement in system energy efficiency by intelligently predicting and dynamically adjusting the load demand of the building's heating and cooling system. By combining historical and real-time data, heating and cooling load demands can be predicted more accurately, thereby optimizing energy allocation and reducing ineffective energy consumption. Simultaneously, machine learning algorithms based on equipment mechanism models optimize equipment control parameters, enabling the system to adaptively adjust, improving system automation and intelligence, reducing operating costs, and ensuring indoor environmental comfort under various conditions, thus achieving energy conservation and emission reduction goals.

[0053] In one embodiment, such as Figure 2 As shown, it also includes the following steps S21-S24:

[0054] In step S21, multi-dimensional historical data is collected and cleaned;

[0055] In step S22, detailed modeling of the building's physical characteristics is performed;

[0056] In step S23, the load curve is generated and corrected over multiple time periods;

[0057] In step S24, dynamic feedback and real-time load forecasting adjustments are performed.

[0058] In one embodiment, a large amount of historical data was collected to ensure the accuracy of load forecasting. Data sources included power consumption records of the heating and cooling systems, operating records of the heating and cooling equipment, indoor and outdoor temperature and humidity data, and average daily pedestrian traffic data in the building. The collection frequency and data granularity met the training requirements of the forecasting model.

[0059] A flow meter and temperature sensor were installed on the chilled water system main pipe to record a two-dimensional curve of cooling capacity supply hourly. During data processing, outlier data points were removed and missing values ​​were filled to generate a continuous historical dataset. This cleaning process provides accurate and reliable input data for load forecasting.

[0060] In order to accurately predict load demands in different regions and of different types, this embodiment has performed detailed modeling of the building's physical characteristics, including building area, division of each region, and the materials and characteristics of the building envelope.

[0061] Load types are further subdivided into: fresh air load, radiation load, heat transfer load, heat dissipation load from people and equipment, building heat storage load, and water capacity load. Fresh air load is determined based on the building's purpose and air exchange rate, while radiation load is estimated based on the solar radiation heat gain coefficient under different seasons and weather conditions.

[0062] The system corrects load forecasts by calculating the difference between the historical cooling supply curve Q and the load demand curve L. The generated hourly load curve is dynamically adjusted based on meteorological data, pedestrian traffic, and usage demand.

[0063] In the initial stage, the system automatically adjusts the load forecast based on the deviation between the cooling capacity supply curve and the actual load. For example, when the deviation between the load curve and the cooling capacity supply curve exceeds 10%, the system will calculate the correction value Qi for the load in the area by comparing the return air temperature with the set value, according to the following formula:

[0064] Q'i=(Q×ΔT) / A

[0065] The final cooling supply curve Qt is generated as the building's time-period cooling demand, taking into account the influence of factors such as weather, pedestrian traffic, and the building's work calendar.

[0066] When load demand fluctuates significantly (e.g., due to weather changes, fluctuations in population density), the system will dynamically adjust load forecasts based on real-time weather data and building usage. Real-time weather information obtained through the weather data interface can update load forecast results at any time, making the forecast model more consistent with actual operating conditions.

[0067] By modeling load forecasts using historical data and physical characteristics, and improving forecast accuracy through dynamic feedback, the system ensures the stability of heating and cooling supply and energy-saving effects, providing a reliable basis for regulating the building environment.

[0068] In one embodiment, such as Figure 3 As shown, it also includes the following steps S31-S34:

[0069] In step S31, the system collects equipment performance data and generates curves;

[0070] In step S32, the multi-condition equipment operation rule base is established;

[0071] In step S33, the equipment operating parameters are dynamically set;

[0072] In step S34, dynamic intelligent adjustment and operating condition switching are performed.

[0073] In one embodiment, a knowledge graph is constructed through equipment performance analysis and data learning to support equipment combinations and operating strategies under different working conditions, thereby ensuring efficient system operation and intelligent adjustment.

[0074] The system collects historical operating data from cold and heat source equipment (such as chillers, heat pumps, chilled water pumps, cooling water systems, etc.). This data includes the cooling capacity and load rate data of the equipment at different outlet water temperatures, cooling water system data, equipment COP energy efficiency curves, and pump power and flow rate curves, etc.

[0075] Based on the characteristics of different seasons, the performance parameters of each device are correlated with ambient temperature and humidity data to generate cooling capacity curves under different outlet water temperatures, cooling loads, and cooling water temperatures. For example, when the total load demand of the system is Qt i, the system will select the combination of devices with the highest energy efficiency based on the COP curve.

[0076] The knowledge graph of the equipment system is based on physical associations and operating rules. It performs multi-dimensional rule configuration for equipment such as water pumps, cooling towers, and chillers to ensure the optimal equipment combination under different loads.

[0077] The system establishes three main operating modes: standard mode, comfort mode, and energy-saving mode. Under each mode, the system will match an appropriate combination of equipment and operating parameters. For example, under comfort mode, the system will prioritize combinations with sufficient cooling capacity, while under energy-saving mode, it will prioritize combinations of equipment with higher energy efficiency.

[0078] Taking water pumps as an example, the system calculates the flow rate based on the load demand and the supply and return water temperature difference set under operating conditions, thus satisfying the selection of water pump combinations under different cooling capacity requirements. The calculation formula is as follows:

[0079]

[0080] Where Qti represents the target cooling capacity requirement, and the supply and return water temperature difference is set to 5°C. The system analyzes historical pump flow curves to determine the optimal pump combination and its operating frequency.

[0081] The cooling tower is selected based on the wet-bulb temperature plus 3°C as the outlet water temperature, and is adjusted according to changes in the wet-bulb temperature to ensure that the cooling tower meets the cooling requirements with the lowest energy consumption.

[0082] The system selects the most suitable operating combination based on the building's current load demand and environmental conditions. When the environment changes or the load demand changes, the system will prioritize selecting equipment combinations that meet the conditions from the equipment knowledge graph to achieve energy saving and high efficiency.

[0083] This embodiment generates a rule base by combining multiple modes and operating conditions of equipment, realizing intelligent adjustment of building heating and cooling source systems and providing optimal solutions for different environments and load requirements.

[0084] In one embodiment, such as Figure 4 As shown, it also includes the following steps S41-S44:

[0085] In step S41, the load forecast is matched with the equipment rule base;

[0086] In step S42, strategy generation and parameter setting are performed;

[0087] In step S43, real-time strategy adjustment and optimization are performed;

[0088] In step S44, dynamic intelligent adjustment and operating condition switching are performed.

[0089] In one embodiment, the system scores multiple indicators of equipment operation based on load forecasting results and the actual needs of the building, and generates a control strategy. The scoring indicators include main unit energy efficiency, system power consumption, switching frequency, and cooling capacity margin.

[0090] The control strategy is generated and scored based on the following formula:

[0091] S=ξ1·A+ξ2·B+ξ3·C+ξ4·D

[0092] Where A is the main unit's energy efficiency value, B is the system power consumption (kWh), C is the number of switching operations, and D is the cooling supply margin (kWh). Each weighting coefficient is set according to the operating mode.

[0093] The system outputs operating parameters according to scoring weights, including the start and stop times of the main unit, outlet water temperature, and chilled water pump frequency, and updates its strategy when load forecasts change. For example, in comfort mode, the system may increase the weight of cooling capacity margin to ensure sufficient cooling supply.

[0094] During strategy application, the system monitors the difference between actual and predicted loads. When the actual load deviation exceeds 10%, the system recalculates and adjusts the strategy to ensure that the control strategy matches the building's real-time needs.

[0095] The system records and stores strategies from each operational cycle in a database, which gradually expands over time. In the future, when generating new strategies, the system can refer to historical data and prioritize strategy combinations that best meet current needs and have historically proven effectiveness.

[0096] Through this embodiment, the control strategy can achieve self-optimization and efficient operation under dynamic demand, ensuring the stability of building heating and cooling supply and the rational use of energy.

[0097] In one embodiment, such as Figure 5 As shown, it also includes the following steps S51-S54:

[0098] In step S51, the multi-dimensional performance evaluation is conducted.

[0099] In step S52, the feedback mechanism and rule base are updated;

[0100] In step S53, dynamic self-learning and optimization adjustments are performed.

[0101] In step S54, the feedback strategy is updated cyclically.

[0102] In one embodiment, the system evaluates the strategy execution effect after the end of the running cycle. The evaluation dimensions include: load accuracy, environmental comfort, energy saving improvement rate, and ease of operation. Load accuracy requires a deviation of ≤5%, environmental comfort is scored within ±1℃ of temperature and humidity, energy saving rate is scored as the actual percentage of energy saved, and ease of operation is based on the number of host switching operations. Strategies with excellent evaluation results are added to the historical rule base, forming reference targets for subsequent runs. If the strategy effect does not meet expectations in actual operation, the system will refer to historical strategies with higher scores and prioritize their selection in the next round of optimization. As the running time increases, the system adds high-quality solutions from historical strategies to the target set and achieves self-adjustment of the rule base by learning new control parameters. For example, when the system identifies a strategy that is significantly effective under current conditions, this strategy will be recorded and prioritized for application in subsequent cycles under similar conditions. The evaluation and feedback of each running cycle form an update cycle for the strategy base, ultimately achieving self-learning and optimization of the strategy base. Regardless of whether the original strategy or the updated strategy is used, the system will achieve continuous strategy optimization through feedback. This embodiment, through feedback mechanisms and historical data accumulation, enables the control strategy to have the ability to learn and continuously optimize itself, thus ensuring the intelligent operation of building heating and cooling source systems.

[0103] In one embodiment, Figure 6 This is a block diagram illustrating a control device for a building heating and cooling source system that adapts to load demand, according to an exemplary embodiment. Figure 6 As shown, the control device for the building heating and cooling source system that adapts to load demand includes a setup module 61, a calculation module 62, a generation module 63, and an output module 64.

[0104] The module 61 is used to acquire historical operating data, physical characteristics and equipment system data of the building, and to establish the building load prediction model to provide an accurate estimate of future load demand.

[0105] The calculation module 62 is used to calculate the hourly load demand of the building based on the historical operating data and the building load prediction model, generate the hourly load curve, and predict the cooling or heating demand for each future period based on the curve.

[0106] The generation module 63 is used to acquire real-time meteorological data and personnel flow data, and dynamically adjust the cooling or heating load demand according to the hourly load forecast results to generate corresponding cooling or heating curves.

[0107] The output module 64 is used to construct a machine learning algorithm based on the device mechanism model, optimize the control strategy of the cold and heat source system based on the historical operating data of the device, and output the control parameters of the device, including any one or more of the following: start and stop time, number of operating units, outlet water temperature setpoint, and water pump frequency.

[0108] The block diagram of the control device for an adaptive load demand building heating and cooling source system includes a setup module 61, a calculation module 62, a generation module 63, and an output module 64, which are controlled to execute the control method for the adaptive load demand building heating and cooling source system described in any of the above embodiments.

[0109] like Figure 7 As shown, the present invention provides an electronic device 700, which includes: a communication interface, a processor 701, and a memory 702;

[0110] The memory 702 stores program instructions. When executed by the processor 701, which is connected to the memory 702 via the communication interface, the program instructions acquire historical operating data, physical characteristics, and equipment system data of the building, and establish the building load prediction model. Based on the historical operating data and the building load prediction model, the hourly load demand of the building is calculated, the hourly load curve is generated, and the cooling or heating demand for future periods is predicted based on the curve. Real-time meteorological data and personnel flow data are acquired, and the cooling or heating load demand is dynamically adjusted based on the hourly load prediction results to generate corresponding cooling or heating curves. A machine learning algorithm based on the equipment mechanism model is constructed to optimize the control strategy of the cold and heat source system based on the historical operating data of the equipment, and output the control parameters of the equipment, including any one or more of the following: start-up and shutdown time, number of operating units, outlet water temperature setpoint, and pump frequency.

[0111] This invention provides a computer-readable storage medium storing computer program instructions. When executed by a processor, the computer program instructions acquire historical operating data, physical characteristics, and equipment system data of a building, and establish a building load prediction model. Based on the historical operating data and the building load prediction model, the hourly load demand of the building is calculated, generating the hourly load curve, and the cooling or heating demand for future periods is predicted based on the curve. Real-time meteorological data and personnel flow data are acquired, and the cooling or heating load demand is dynamically adjusted based on the hourly load prediction results to generate corresponding cooling or heating curves. A machine learning algorithm based on an equipment mechanism model is constructed to optimize the control strategy of the cold and heat source system based on the historical operating data of the equipment, and outputs the control parameters of the equipment, including one or more of the following: start-up and shutdown time, number of operating units, outlet water temperature setpoint, and pump frequency.

[0112] It should be understood that the specific features, operations, and details described above regarding the method of the present invention can also be similarly applied to the apparatus and system of the present invention, or vice versa. Furthermore, each step of the method of the present invention described above can be performed by a corresponding component or unit of the apparatus or system of the present invention.

[0113] It should be understood that the various modules / units of the device of the present invention can be implemented wholly or partially through software, hardware, firmware, or a combination thereof. Each module / unit can be embedded in the processor of a computer device in hardware or firmware form or independent of the processor, or it can be stored in the memory of a computer device in software form for the processor to call to execute the operation of each module / unit. Each module / unit can be implemented as an independent component or module, or two or more modules / units can be implemented as a single component or module.

[0114] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores computer instructions executable by the processor, which, when executed by the processor, instruct the processor to perform steps of the methods of embodiments of the present invention. The computer device can be broadly categorized as a server, terminal, or any other electronic device with the necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, memory, network interface, communication interface, etc., connected via a system bus. The processor of the computer device can be used to provide the necessary computing, processing, and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system, computer programs, etc. The internal memory can provide an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface and communication interface of the computer device can be used to connect and communicate with external devices via a network. When the computer program is executed by the processor, it performs the methods of the present invention.

[0115] This invention can be implemented as a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, causes the methods of embodiments of the invention to be performed. In one embodiment, the computer program is distributed across multiple network-coupled computer devices or processors, such that the computer program is stored, accessed, and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, may be executed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations may be executed by one or more computer devices or processors, and one or more other method steps / operations may be executed by one or more other computer devices or processors. One or more computer devices or processors may execute a single method step / operation, or execute two or more method steps / operations.

[0116] It will be understood by those skilled in the art that the method steps of this invention can be performed by a computer program instructing related hardware, such as a computer device or processor. The computer program may be stored in a non-transitory computer-readable storage medium, and its execution causes the invention to be performed. Depending on the context, any references to memory, storage, database, or other media herein may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (PROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0117] The technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification, provided that such combination does not contain contradictions.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method for a building heating and cooling source system that adapts to load demand, characterized in that, The method includes: Acquire historical operational data, physical characteristics, and equipment system data of the building, and establish the building load prediction model; Based on the historical operating data and building load prediction model, the hourly load demand of the building is calculated, the hourly load curve is generated, and the cooling or heating demand for each future period is predicted based on the curve. Acquire real-time meteorological data and personnel flow data, and dynamically adjust the cooling or heating load demand based on the hourly load forecast results to generate corresponding cooling or heating curves; A machine learning algorithm based on the device mechanism model is constructed to optimize the control strategy of the cold and heat source system based on the historical operating data of the device, and outputs the control parameters of the device, including one or more of the following: start and stop time, number of operating units, outlet water temperature setpoint and water pump frequency. The construction of the machine learning algorithm includes: Based on the equipment mechanism model and historical operating data, the cooling capacity curve and energy efficiency curve of the cold and heat source system are established. The machine learning model is trained through historical data to optimize the equipment control strategy and select the optimal operating parameters. Analyze equipment operating conditions based on historical operating data and extract characteristic parameters; Historical operating data of the equipment is collected from the cold and heat source equipment. The historical operating data includes the cooling capacity, load rate data, cooling water system data, equipment COP energy efficiency curve, and water pump power and flow curve at different outlet water temperatures. Based on the characteristics of different seasons, the performance parameters of each device are correlated with the ambient temperature and humidity data. Based on the device mechanism model and the historical operating data of the device, cooling capacity curves and energy efficiency curves are generated at different outlet water temperatures, cooling loads and cooling water temperatures. The machine learning model is trained through the historical operating data of the device, and the operating conditions of the device are analyzed and feature parameters are extracted based on the historical operating data of the device. Equipment knowledge graphs are constructed through equipment performance analysis and data learning. These knowledge graphs are based on the physical relationships and operating rules between equipment, and rule configurations are applied to water pumps, cooling towers, and chillers. Standard operating conditions, comfort operating conditions, and energy-saving operating conditions are also set. Based on the building's current load demand and environmental conditions, the system matches equipment combinations and operating parameters corresponding to the current operating conditions from the equipment knowledge graph. Under comfort conditions, equipment combinations with sufficient cooling capacity are prioritized, while under energy-saving conditions, equipment combinations with higher energy efficiency are prioritized. The system determines the equipment combination based on the equipment's COP energy efficiency curve and outputs one or more of the following: equipment start-up and shutdown time, number of units in operation, outlet water temperature setpoint, and water pump frequency.

2. The control method for an adaptive load demand building heating and cooling source system according to claim 1, characterized in that, Establishing a building load forecasting model includes: Based on the building's historical operational data and physical characteristics, data collected through at least one sensor is cleaned and repaired to eliminate outliers and missing data. The data cleaning and repair process involves removing outlier data points, filling in missing data, and smoothing the data.

3. The control method for an adaptive load demand building heating and cooling source system according to claim 1, characterized in that, The generation of the hourly load curve includes: By combining the physical characteristics of the building, real-time meteorological data, and personnel flow data, the hourly cooling or heating load demand is calculated through the building load prediction model, and the hourly load curve is generated. The hourly load curves are generated based on the heat transfer performance of the building envelope, the fresh air load, and the impact of indoor occupant activities on the thermal environment.

4. The control method for an adaptive load demand building heating and cooling source system according to claim 1, characterized in that, The dynamic adjustment of cooling or heating load demand includes: By acquiring real-time meteorological data and building occupancy data, the hourly load forecast results are dynamically corrected. Adjust the cooling or heating curves of the cold and heat source system based on the revised load forecast results. During the correction process, the immediate impact of meteorological data and population movement on heating and cooling loads is taken into account.

5. The control method for an adaptive load demand building heating and cooling source system according to claim 1, characterized in that, The output device control parameters include: Based on the optimized control strategy, determine one or more of the following: equipment start-up and shutdown time, number of operating units, outlet water temperature setpoint, and water pump frequency. Based on preset energy efficiency ratio, operational stability, and indoor environmental comfort, control parameters are determined using a multi-objective optimization strategy.

6. A control device for a building heating and cooling source system that adapts to load demand, characterized in that, include: A module is established to acquire historical operating data, physical characteristics, and equipment system data of the building, and to establish the building load prediction model to provide an accurate estimate of future load demand. The calculation module is used to calculate the hourly load demand of the building based on the historical operating data and the building load prediction model, generate the hourly load curve, and predict the cooling or heating demand for each future period based on the curve. The generation module is used to acquire real-time meteorological data and personnel flow data, and dynamically adjust the cooling or heating load demand based on the hourly load forecast results to generate corresponding cooling or heating curves. The output module is used to construct a machine learning algorithm based on the device mechanism model, optimize the control strategy of the cold and heat source system based on the historical operating data of the device, and output the control parameters of the device, including any one or more of the following: start and stop time, number of operating units, outlet water temperature setpoint and water pump frequency. The output module is also used to establish cooling capacity curves and energy efficiency curves of the cold and heat source system based on the equipment mechanism model and historical operating data of the equipment; train a machine learning model through historical data to optimize the equipment control strategy and select optimal operating parameters; analyze the equipment operating conditions based on historical operating data and extract feature parameters; collect historical operating data from the cold and heat source equipment, including cooling capacity, load rate data, cooling water system data, equipment COP energy efficiency curves, and water pump power and flow curves at different outlet water temperatures; correlate the performance parameters of each device with environmental temperature and humidity data according to different seasonal characteristics; and generate cooling capacity curves and energy efficiency curves at different outlet water temperatures, cooling loads, and cooling water temperatures based on the equipment mechanism model and the historical operating data of the equipment. Historical operating data is used to train a machine learning model, and the operating conditions of the equipment are analyzed and feature parameters are extracted based on the historical operating data. An equipment knowledge graph is constructed through equipment performance analysis and data learning. The equipment knowledge graph is based on the physical associations and operating rules between equipment, and rules are configured for water pumps, cooling towers and chillers, and standard operating conditions, comfort operating conditions and energy-saving operating conditions are set. According to the current load demand of the building and environmental conditions, the equipment combination and operating parameters corresponding to the current operating conditions are matched from the equipment knowledge graph. In the comfort operating condition, the equipment combination with sufficient cooling capacity is selected first, and in the energy-saving operating condition, the equipment combination with higher energy efficiency is selected first. The equipment combination is determined according to the equipment COP energy efficiency curve, and one or more of the following are output: equipment start-up and shutdown time, number of units in operation, outlet water temperature setpoint and water pump frequency.

7. The control device for an adaptive load demand building heating and cooling source system as described in claim 6, characterized in that: The establishment module, the calculation module, the generation module, and the output module are controlled to execute the control method for an adaptive load demand building heating and cooling source system according to any one of claims 2-5.

8. An electronic device, characterized in that, include: Communication interface, processor, memory; The memory stores program instructions, which, when executed by the processor connected to the memory via the communication interface, enable the electronic device to implement the control method for an adaptive load demand building heating and cooling source system as described in any one of claims 1 to 5.

9. A computer-readable storage medium having program instructions stored thereon, characterized in that, When the program instructions are executed by a computer, the computer implements the control method for an adaptive load demand building heating and cooling source system as described in any one of claims 1 to 5.

Images