A building energy efficiency optimization system and method

Abstract

This application relates to the fields of artificial intelligence and energy efficiency control, and discloses a building energy efficiency optimization system and method. The method includes: acquiring historical load data, real-time operating status data, and meteorological data at a target time for the HVAC system; inputting the historical load data, real-time operating status data, and meteorological data at the target time into a dual-core optimization model constructed based on Transformer-genetic algorithm and expert rules to obtain the optimal control strategy; the optimal control strategy corresponds to the lowest power consumption; controlling the HVAC system to execute the optimal control strategy, constructing a "dual-core driven" decision-making system, organically combining deterministic control logic based on expert knowledge with deep learning optimization algorithms based on massive data to form complementary advantages, serving as the control center for system operation, and simultaneously improving the energy efficiency optimization effect corresponding to the control strategy, achieving a control strategy output with low energy efficiency, high comfort, and high safety.

Description

Technical Field

[0001] This disclosure generally relates to the fields of artificial intelligence and energy efficiency control, and specifically to a building energy efficiency optimization system and method. Background Technology

[0002] Public building energy systems are complex, generally categorized into air conditioning, lighting and sockets, elevators, power systems, and special equipment. Among these, the Heating, Ventilation, and Air Conditioning (HVAC) system is the largest energy-consuming system in public buildings, accounting for 40%-60% of total power consumption. Furthermore, due to issues such as redundant system design, complex equipment operation, lack of control strategies, and insufficient professional personnel, the HVAC system also represents the system with the greatest potential for energy conservation in public buildings. Currently, mainstream energy management systems in the industry all focus on the power consumption of HVAC systems.

[0003] In related technologies, energy management systems mostly remain at the "visual but not intelligent" stage, with their core functions limited to data dashboard display and standardized report generation. However, for key needs such as concealing abnormal power consumption and generating optimization strategies, the system often only provides "excessive energy consumption" alarms. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the existing technology, it is desired to provide a building energy efficiency optimization system and method, construct a "dual-core driven" decision-making system, organically combine deterministic control logic based on expert knowledge with deep learning optimization algorithms based on massive data to form complementary advantages, the control center of system operation, and improve the energy efficiency optimization effect of the control strategy, so as to achieve the output of control strategy with low energy efficiency, high comfort and high safety.

[0005] In a first aspect, embodiments of this application provide a method for optimizing building energy efficiency, including:

[0006] Acquire historical load data, real-time operating status data, and meteorological data for the target time of the HVAC system;

[0007] The historical load data, the real-time operating status data, and the meteorological data at the target time are input into a dual-core optimization model constructed based on the Transformer-Genetic Algorithm and expert rules to obtain the optimal control strategy. The optimal control strategy corresponds to the lowest power consumption. The dual-core optimization model includes a Transformer-Genetic Algorithm sub-model and an expert rule sub-model. The Transformer-Genetic Algorithm sub-model is used to predict the predicted load at the target time based on the historical load data, the real-time operating status data, and the meteorological data at the target time, and uses a genetic algorithm to optimize the control strategy based on the predicted load. The expert rule sub-model is used to correct the control strategy during the optimization process using the genetic algorithm based on the predicted load, based on preset expert rules.

[0008] Control the HVAC system to execute the optimal control strategy.

[0009] In some embodiments, the optimization of the control strategy based on the predicted load using a genetic algorithm includes:

[0010] A first preset number of initial control strategies are randomly generated, and the fitness score corresponding to each initial control strategy is obtained;

[0011] Randomly extract a second preset number of the initial control strategies, and select the initial control strategy with the highest fitness score as the genetic parent control strategy, until a third preset number of the genetic parent control strategies are obtained.

[0012] Randomly select any two of the genetic parent control strategies and perform cross-inheritance to obtain the genetic offspring control strategies corresponding to the genetic parent control strategies, until a fourth preset number of the genetic offspring control strategies are obtained.

[0013] Obtain the power consumption value of the offspring corresponding to each of the genetic offspring control strategies in the current round, and perform the next round of cross-genesis until the difference between the power consumption value of the offspring in the current round and the power consumption value of the offspring in the previous round is less than a preset error.

[0014] In some embodiments, obtaining the fitness score corresponding to each initial control strategy includes:

[0015] The power consumption of the chiller, chilled water pump, cooling water pump and cooling tower under the initial control strategy is obtained respectively, and the total power consumption of the initial control strategy is calculated.

[0016] Calculate the first rule penalty factor and the second rule penalty factor corresponding to the initial control strategy according to the preset expert rules, and determine the expert rule penalty item according to the first rule penalty factor and the second rule penalty factor;

[0017] The fitness score is determined based on the total power consumption and the expert rule penalty.

[0018] In some embodiments, the step of modifying the control strategy during the optimization process based on preset expert rules includes:

[0019] In the process of randomly extracting any two of the genetic parent control strategies and performing cross-genesis to obtain the genetic offspring control strategies corresponding to the genetic parent control strategies, the two genetic parent control strategies are subjected to safety-guided cross-genesis based on the preset expert rules.

[0020] In some embodiments, the safe-guided cross-inheritance of the two genetic parent control strategies includes:

[0021] Select any one of the two genetic parent control strategies, and perform a safety assessment on a gene-segment-by-gene basis based on the preset expert rules to obtain the safety assessment value corresponding to each gene segment of the genetic parent control strategy;

[0022] Based on the aforementioned safety assessment values, select the intersection point;

[0023] Based on the crossover point, the two genetic parent control strategies are swapped to obtain two genetic offspring control strategies.

[0024] In some embodiments, selecting the intersection point based on the security assessment value includes:

[0025] According to the preset expert rules, the dependency relationships between the gene segments are obtained;

[0026] Based on the dependency relationship, determine the gene segment group with the dependency relationship and the gene location of each gene segment in the gene segment group;

[0027] The crossover point is selected based on the gene location of each gene segment in the gene segment group.

[0028] Secondly, embodiments of this application provide a building energy efficiency optimization system, including:

[0029] The acquisition module is used to acquire historical load data, real-time operating status data, and meteorological data for the target time of the HVAC system.

[0030] A dual-core drive module is used to input the historical load data, the real-time operating status data, and the meteorological data at the target time into a dual-core optimization model constructed based on Transformer-Genetic Algorithm and expert rules to obtain the optimal control strategy; the optimal control strategy corresponds to the lowest power consumption; wherein, the dual-core optimization model includes a Transformer-Genetic Algorithm sub-model and an expert rule sub-model; the Transformer-Genetic Algorithm sub-model is used to predict the predicted load at the target time based on the historical load data, the real-time operating status data, and the meteorological data at the target time, and uses a genetic algorithm to optimize the control strategy based on the predicted load; the expert rule sub-model is used to correct the control strategy during the optimization process by the Transformer-Genetic Algorithm sub-model using the genetic algorithm based on the predicted load based on preset expert rules;

[0031] The control module is used to control the HVAC system to execute the optimal control strategy.

[0032] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in embodiments of this application.

[0033] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in embodiments of this application.

[0034] Fifthly, embodiments of this application provide a computer program product, including a computer program, characterized in that, when the computer program is executed by a processor, it implements the method described in embodiments of this application.

[0035] This application provides a building energy efficiency optimization system and method. By acquiring historical load data, real-time operating status data, and meteorological data at a target time from the HVAC system, the system inputs these data into a dual-core optimization model constructed based on Transformer-genetic algorithm and expert rules to obtain an optimal control strategy. The optimal control strategy corresponds to the lowest power consumption. The system then controls the HVAC system to execute the optimal control strategy, achieving a control strategy output that is low in energy efficiency, high in comfort, and high in safety.

[0036] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0037] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0038] Figure 1 The diagram illustrates the implementation environment architecture of the building energy efficiency optimization method provided in this application embodiment;

[0039] Figure 2 A schematic flowchart of a building energy efficiency optimization method according to an embodiment of this application is shown;

[0040] Figure 3 A flowchart illustrating a building energy efficiency optimization method according to another embodiment of this application is shown;

[0041] Figure 4 A schematic diagram of the structure of a building energy efficiency optimization system provided in an embodiment of this application is shown;

[0042] Figure 5 A schematic diagram of the structure of a computer system suitable for implementing an electronic device or server according to embodiments of this application is shown. Detailed Implementation

[0043] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0044] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0045] The total energy consumption of buildings nationwide was 11.9 tce, accounting for 22% of the country's total energy consumption. The carbon emissions from building operations nationwide were 2.31 billion tco2, accounting for 21.7% of the country's energy-related carbon emissions. Among these, public buildings accounted for 490 million tce (41%) of the energy consumption and 940 million tco2 (41%) of the carbon emissions, making them the primary source of both energy consumption and carbon emissions from building operations. Driven by the dual carbon goals, low-carbon operation of public buildings has become a key battleground for reducing overall societal carbon emissions.

[0046] Currently, the mainstream energy management systems in the industry include Honeywell's Building Energy Management Suite (Honeywell BeMS), Siemens' SSE-EMS, and Schneider Electric's EMS (Energy Management System). Honeywell's intelligent building energy management system, as an integrated solution, combines energy management with energy-saving measures. It monitors the status of high-power equipment such as HVAC, lighting, water supply and drainage, and power distribution within buildings, provides equipment protection and operation management, and evaluates and analyzes power consumption data. The system features energy flow analysis and display, multi-dimensional indicator statistical comparison, power consumption alarms, and demand control. The SSEP-EMS system records all power consumption data in the factory through various field instruments or sensors, such as smart meters and water meters, and uses intuitive load curves to quickly and accurately display energy consumption. The system also features energy flow analysis and display, peak-valley-flat management, and power consumption alarms. Schneider EMS is a software platform specifically designed for energy efficiency management. It helps users ensure safer, more reliable, and more efficient electricity use by calculating, modeling, predicting, and tracking performance indicators for all energy sources (including electricity, water, and gas) through energy visualization and analytics tools. Schneider EMS assists users in energy audits, indicator analysis, and cost allocation to further evaluate, advance, and validate energy-saving effects, and promptly identify abnormal energy usage throughout the process.

[0047] It is evident that current energy management systems remain at the "visible but not intelligent" stage. When an alarm for "excessive energy consumption" is triggered, professional technicians are required to analyze the situation and resolve the fault.

[0048] Based on this, this application eliminates a building energy efficiency optimization system and method, and constructs a "dual-core driven" decision-making system. It organically combines deterministic control logic based on expert knowledge with deep learning optimization algorithms based on massive data to form a complementary advantage and a control center for system operation. At the same time, it improves the energy efficiency optimization effect corresponding to the control strategy and achieves the output of control strategies with low energy efficiency, high comfort, and high safety.

[0049] For the specific implementation environment of the building energy efficiency optimization method proposed in this application, please refer to [link / reference needed]. Figure 1 . Figure 1 The diagram illustrates the implementation environment architecture of the building energy efficiency optimization method provided in this application embodiment.

[0050] like Figure 1 As shown, the implementation environment architecture includes: an energy efficiency management system 101 and a building automation system 102.

[0051] The Building Automation System (BAS) 102 is used to collect the operating status and sensor parameters (such as water pipe temperature, valve opening, fan frequency, etc.) of each device in the building HVAC system in real time and send them to the Energy Efficiency Management System (EMS) 101. The Energy Efficiency Management System 101 is used to execute the building energy efficiency optimization method proposed in the embodiments of this application, determine the optimal control strategy with the best energy efficiency, and send the optimal control strategy to the Building Automation System 102 for precise execution by the Building Automation System 102.

[0052] The energy efficiency management system 101 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0053] The energy efficiency management system 101 is directly or indirectly connected to the building automation system 102 via wired or wireless communication. Optionally, the aforementioned wireless or wired network uses standard communication technologies and / or protocols. The network is typically the Internet, but can also be any network, including but not limited to any combination of Local Area Network (LAN), Metropolitan Area Network (MAN), Wide Area Network (WAN), mobile, wired or wireless networks, private networks, or virtual private networks.

[0054] The building energy efficiency optimization method proposed in this application can be implemented by a building energy efficiency optimization device, which can be installed on a terminal device or a server.

[0055] To further illustrate the technical solutions provided in the embodiments of this application, a detailed description is provided below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of this application provide method operation instruction steps as shown in the following embodiments or drawings, the method may include more or fewer operation instruction steps based on conventional or non-creative effort. In steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order provided in the embodiments of this application. In actual processing or when the device executes the method, it may be executed sequentially or in parallel according to the method shown in the embodiments or drawings.

[0056] It should be noted that the acquisition or use of data in the embodiments of this application requires the user's consent. The relevant data can only be obtained after the user's authorization, and the acquisition or use of the data complies with the provisions of relevant laws and regulations.

[0057] Please refer to Figure 2 , Figure 2 A schematic flowchart of a building energy efficiency optimization method according to an embodiment of this application is shown. Figure 2 As shown, the method includes:

[0058] Step 201: Obtain historical load data, real-time operating status data, and meteorological data for the target time of the HVAC system.

[0059] It should be noted that, since existing technologies typically focus on "visible" information, they often only consider time-series data of total power consumption, lacking insight into the driving factors behind energy consumption behavior. Based on this, this application proposes using multi-dimensional data to predict the regularity of load at target times.

[0060] Historical load data includes historical equipment operation data, historical environmental parameter data, and historical power consumption time-series data. Historical equipment operation data includes the start-up and shutdown status, operating power, frequency, and duration of equipment such as HVAC main units, water pumps, fans, and lighting circuits; historical environmental parameter data includes indoor and outdoor temperature, humidity, light intensity, CO2 concentration, and population density; and power consumption time-series data includes historical power consumption data for electricity, water, and gas in various regions, categories, and sub-items.

[0061] Step 202: Input historical load data, real-time operating status data, and meteorological data at the target time into a dual-core optimization model constructed based on Transformer-Genetic Algorithm and expert rules to obtain the optimal control strategy. The dual-core optimization model includes a Transformer-Genetic Algorithm sub-model and an expert rule sub-model. The Transformer-Genetic Algorithm sub-model is used to predict the target time load based on historical load data, real-time operating status data, and meteorological data at the target time, and uses the genetic algorithm to optimize the control strategy based on the predicted load. The expert planning sub-model is used to correct the control strategy during the optimization process of the Transformer-Genetic Algorithm sub-model using the genetic algorithm based on the predicted load, based on expert rules.

[0062] Step 203: Control the HVAC system to execute the optimal control strategy.

[0063] Specifically, this application constructs a "dual-core driven" decision-making system, which organically combines deterministic control logic based on expert knowledge with deep learning optimization algorithms based on massive historical data to form a control center that complements each other's strengths and operates collaboratively.

[0064] The first driving core is the expert rule sub-model, which provides expert rules and basic strategies. This driver provides basic safety for the system and control strategies based on preset expert rules. Specifically, the expert rules and basic strategies provided by the expert rule sub-model are the "safety cornerstone" and "experience foundation" of the entire system. Its core task is to define a high-safety, high-reliability operating boundary for the system and to provide industry-recognized and effective basic energy-saving strategies. Utilizing preset expert rules to optimize the control strategies during the optimization process effectively ensures that the control measures generated during optimization will not trigger dangerous operations, solves the cold start problem when the system lacks sufficient training data, and provides clear and traceable interpretability for the system's basic operating logic.

[0065] The second driving core is a Transformer-Genetic Algorithm sub-model, used to predict the load at the target time using the Transformer model and optimize the control strategy based on the predicted load using the genetic algorithm. In building energy management systems, short-term forecasting of cooling load is the foundation of proactive optimization control. Accurately predicting future cooling load trends helps to achieve dynamic optimization control of chiller group start-up and shutdown strategies, cold storage system charging and discharging, and primary / secondary pump flow regulation, thereby effectively improving the system's energy efficiency and response flexibility. Especially when the load exhibits obvious nonlinearity, periodicity, and is driven by multiple factors (such as weather, time of day, and operating mode), relying on traditional rules or linear models is difficult to achieve ideal prediction accuracy.

[0066] Cooling load forecasting is characterized by significant temporal, periodic, and multi-source driving features. Its variations are influenced not only by weather factors (such as outdoor temperature and humidity) but also by user behavior patterns, operational strategies, and historical load conditions within the building itself. To accurately characterize the impact of these complex factors on future loads, forecasting models need strong sequence modeling capabilities and multivariate feature fusion capabilities. The Transformer model, initially applied in natural language processing, is based on a self-attention mechanism, enabling it to model global dependencies between any points in a sequence without relying on temporal order. In recent years, the Transformer has gradually demonstrated superior performance in time series forecasting tasks and has been widely applied in fields such as power, transportation, and meteorology. This application introduces it into building cooling load forecasting. The Transformer model, with its self-attention mechanism at its core, can establish direct information pathways between any two time points in a sequence, effectively capturing dependencies over long time spans. This characteristic allows it to model periodic disturbances and responses to sudden events without relying on explicit temporal order, making it particularly suitable for modeling nonlinear processes like cooling load that are significantly affected by factors such as sunlight, time of day, and behavior. Furthermore, the Transformer's structure allows for input of multiple feature channels, and its multi-head attention mechanism can simultaneously learn the interaction relationships between features from different dimensions, demonstrating excellent high-dimensional feature fusion capabilities. Combined with appropriate embedding encoding methods, the Transformer can input meteorological data, historical loads, operational status, timestamps, and other information together, completing feature representation and dependency modeling within a unified structure, effectively avoiding the problem of insufficient integration of multi-source information in traditional models.

[0067] Genetic algorithms, based on the principles of natural selection and nuclear genetics, offer advantages such as strong global search capabilities, wide applicability, high parallelism, robustness, and ease of expansion. This application utilizes genetic algorithms to modify control strategies based on predicted loads during the optimization process, employing pre-defined expert rules. This achieves genetic optimization based on safety-oriented operators, significantly improving the safety and efficiency of the control strategy optimization process.

[0068] Therefore, the building energy efficiency optimization method provided in this application obtains historical load data, real-time operating status data, and meteorological data at the target time of the HVAC system. It then inputs these data into a dual-core optimization model constructed based on Transformer-genetic algorithm and expert rules to obtain the optimal control strategy, which corresponds to the lowest power consumption. The method then controls the HVAC system to execute the optimal control strategy, achieving a control strategy output that is low in energy efficiency, high in comfort, and high in safety.

[0069] In some embodiments, such as Figure 3 As shown, the control strategy based on predicted load optimization using a genetic algorithm includes:

[0070] Step 301: Randomly generate a first preset number of initial control strategies and obtain the fitness score corresponding to each initial control strategy.

[0071] It should be noted that the initial control strategy is the initial solution used for genetic optimization. Each initial control strategy includes the complete control strategy and the control scheme for all control variables in all time periods before the target time.

[0072] For example, control strategy X can be expressed as follows:

[0073]

[0074] in, Indicates the state of the i-th device 1, 2…k, Represents the state of the j-th parameter. 1, 2…m.

[0075] It should also be noted that the first preset quantity is set according to the actual situation of the building's HVAC system, so that the initial control strategy of the first preset quantity can cover the feasible solution space of the HVAC system control strategy, providing a spatial basis for the subsequent optimization process.

[0076] Furthermore, this application also performs fitness score calculation for each initial control strategy to calculate the power consumption and constraint violation of each initial control strategy, and gives a comprehensive score. The higher the score, the better the strategy, that is, it can reduce power consumption and meet the constraints.

[0077] In some embodiments, obtaining the fitness score corresponding to each initial control strategy includes: obtaining the power consumption of the chiller, chilled water pump, cooling water pump and cooling tower under the initial control strategy, and calculating the total power consumption of the initial control strategy; calculating the first rule penalty factor and the second rule penalty factor corresponding to the initial control strategy according to preset expert rules, and determining the expert rule penalty item according to the first rule penalty factor and the second rule penalty factor; and determining the fitness score according to the total power consumption and the expert rule penalty item.

[0078] For chiller units, the power consumption can be expressed as:

[0079]

[0080] in, The power consumption of the oth chiller unit. The rated power of the oth chiller unit. Let be the partial load rate of the o-th chiller unit at time t. The temperature of the cooling water inlet for the o-th chiller unit is .

[0081] For chilled water pumps or cooling water pumps, their power consumption can be expressed as:

[0082]

[0083] in, The power of the water pump refers to the pump's capacity; the water pumps include chilled water pumps and cooling water pumps. The density of water, It is the acceleration due to gravity. and These are the instantaneous flow rate and head of the p-th pump at time t, respectively. Let be the overall hydraulic efficiency of the p-th pump under the initial control strategy.

[0084] For a cooling tower, its power consumption can be expressed as:

[0085]

[0086] in, For the qth cooling tower at the rated frequency The power below, Let be the operating frequency of the q-th cooling tower at time t under the initial control strategy.

[0087] Therefore, the total power consumption can be expressed as:

[0088]

[0089] in, Let be the total power consumption at time t under the initial control strategy. This represents the start-up and shutdown status of the o-th chiller unit at time t. This represents the total number of chiller units. For chilled water pumps, This refers to the total number of chilled water pumps. For cooling water pumps, This refers to the total number of cooling water pumps. This represents the total number of cooling towers.

[0090] Preferably, time t is the target time, i.e. This represents the total power consumption at the target time under the initial control strategy.

[0091] Furthermore, the first rule is a pre-defined expert rule that must never be violated, while the second rule is a pre-defined expert rule that can be disregarded. For example, the first rule could be that if the water pump is turned off, the valve will close, or the temperature limit for chilled water, etc., while the second rule could be the building's internal temperature, etc.

[0092] For example, an expert rule penalty term can be represented as:

[0093]

[0094] in, For expert rule penalty items, Let a be the penalty weight for the a-th first rule. Let be the first rule constraint function of the a-th first rule. The total number of rules in the first rule. Let b be the penalty weight of the second rule for the second rule. Let b be the constraint function of the second rule. For the target value corresponding to the b-th second rule, The initial control strategy is as follows, where, > .

[0095] Therefore, the fitness score can be expressed as:

[0096]

[0097] in, For fitness scoring, Total power consumption, This is a dynamic penalty coefficient. For expert rule penalty items, It is a smoothing constant to prevent division by zero.

[0098] In some preferred embodiments, the dynamic penalty coefficient It can be dynamically adjusted; for example, it can be related to the outdoor temperature, and the expression can be:

[0099]

[0100] in, This is a dynamic penalty coefficient. Basic penalty coefficient, For temperature sensitivity coefficient, This refers to the outdoor temperature deviation (the deviation between the outdoor temperature and the reference temperature).

[0101] In some embodiments, before obtaining the fitness score corresponding to each initial control strategy, initial abnormal control strategies that do not meet the preset expert rules are identified from the initial control strategies, the initial abnormal control strategies are removed, and the initial control strategies are regenerated until no initial control strategies are identified from the initial control strategies and the first preset number is met.

[0102] In other words, this application discloses a safety-oriented screening method for initial control strategies. After obtaining the initial control strategy, the method first uses preset expert rules to delete the initial control strategies that do not meet the preset expert rules, and then scores the fitness of the initial control strategy. This effectively ensures the safety of the genetic parent control strategy in subsequent cross-genesis while evaluating the fitness of the initial control strategy.

[0103] Step 302: Randomly extract a second preset number of initial control strategies, select the initial control strategy with the highest fitness score as the genetic parent control strategy, until a third preset number of genetic parent control strategies are obtained.

[0104] In other words, in this embodiment of the application, in order to further improve the optimization efficiency of the control strategy, the application uses a random screening mechanism to select the initial control strategy with the highest fitness from the initial control strategies.

[0105] In some embodiments, the second preset number can be 3. That is, 3 initial control strategies can be randomly selected from a large number of initial control strategies, and then the fitness scores corresponding to the 3 initial control strategies are obtained. The initial control strategy with the highest fitness score is used as the genetic parent control strategy.

[0106] It should be understood that, in the embodiments of this application, the third preset number of genetic parent control strategies can be repeated, that is, the genetic parent control strategies can be random selection with replacement, thereby effectively improving the fitness score of the control strategy used for cross-genesis, and thus improving the optimization efficiency of control strategy optimization.

[0107] In some embodiments, before randomly extracting a second preset number of initial control strategies, the fitness scores of all initial control strategies can be obtained, and then the first preset number of initial control strategies can be selected from all initial control strategies as genetic parent control strategies to increase the proportion of excellent genetic parent control strategies and promote the evolutionary direction of control strategy optimization.

[0108] Step 303: Randomly extract any two parent genetic control strategies and perform cross-genesis to obtain the corresponding offspring genetic control strategies, until a fourth preset number of offspring genetic control strategies are obtained.

[0109] It should be noted that crisscross inheritance involves exchanging gene segments from the control strategies of two parent genes. These gene segments represent portions of the control strategies.

[0110] In some embodiments, during the process of randomly extracting two genetic parent control strategies for cross-genesis to obtain the genetic offspring control strategies corresponding to the genetic parent control strategies, the two genetic parent control strategies are subjected to safety-guided cross-genesis based on preset expert rules.

[0111] In other words, in this embodiment of the application, in addition to screening the control strategy for cross-genesis, the optimization process is further guided in a safe manner to improve the optimization efficiency of the control strategy.

[0112] In some embodiments, safety-guided cross-inheritance of two genetic parent control strategies includes: selecting any one of the two genetic parent control strategies, performing a safety assessment on a gene segment basis based on preset expert rules to obtain a safety assessment value corresponding to each gene segment of the genetic parent control strategy, selecting a crossover point based on the safety assessment value, and exchanging gene segments of the two genetic parent control strategies based on the crossover point to obtain two genetic offspring control strategies.

[0113] It should be noted that, in this embodiment of the application, security assessment is performed based on preset expert rules for gene segments, specifically by judging the control strategies of the two genetic parents from the first gene segment onwards. Gene segment - number The safety of genetic offspring control models generated after gene segment crossover substitution.

[0114] It should be understood that HVAC systems are complex systems that require multiple devices to work together, and have linkage control strategies such as valves needing to close when a water pump is turned off. In other words, some control strategies are dependent on each other. When two parent control strategies are cross-substituted, the control scheme in the other parent control strategy may cause new unsafe factors in the cross-substituted offspring control strategy. Therefore, in the embodiments of this application, a safety prediction of the cross-substitution result is performed before the cross-substitution.

[0115] For example, the following formula can be used for security assessment:

[0116]

[0117] in, For two genetic parental control strategies from the first Gene segment - number Safety assessment values ​​for cross-inheritance of gene segments. For a pre-defined set of expert rules , and For two genetic parental control strategies from the first Gene segment - number Gene segment.

[0118] Furthermore, in some embodiments, selecting crossover points based on safety assessment values ​​may include exchanging gene segments using α and β, which have the highest safety assessment values, as crossover points.

[0119] As mentioned above, some control schemes are dependent on each other. In order to further avoid ignoring the gene segment dependencies that slightly reduce the safety assessment value due to the increase in safety assessment value caused by the replacement of other control schemes within the gene segment, this application further proposes: to obtain the dependencies between gene segments according to preset expert rules, to determine the gene segment group with dependencies and the gene position of each gene segment in the gene segment group according to the dependencies, and to select the intersection point according to the gene position of each gene segment in the gene segment.

[0120] In other words, the first gene segment and the first Comparing gene segments with gene locations determined by gene segment dependencies, if according to the first... Gene segment - number If gene segment replacement satisfies the dependencies between gene segments (i.e., it does not split at least two dependent gene segments), then it can be done according to the... Gene segment - number Gene segments are subjected to crisscross inheritance. If not, the crossover point is changed and the evaluation continues.

[0121] Therefore, this application can maintain the safety of the control strategy throughout the optimization process, effectively avoid generating control strategies with unsafe factors, and provide safety guidance during the cross-genetic process. While ensuring the safety of the control strategy of the genetic offspring, it can effectively avoid the reduction in the space and number of control strategies caused by, for example, eliminating control strategies according to preset expert rules after obtaining the genetic offspring control strategy, thus ensuring the reliability of finding the optimal control strategy.

[0122] Step 304: Obtain the current power consumption value of each offspring corresponding to the control strategy of each offspring in the current round, and perform the next round of cross-genesis until the difference between the power consumption value of the offspring in the current round and the power consumption value of the offspring in the previous round is less than the preset difference.

[0123] It should be noted that the power consumption value of the offspring can be based on the aforementioned total power consumption. The calculation method is as follows, which will not be elaborated here.

[0124] Specifically, this application obtains a third preset number of genetic offspring control strategies through cross-genesis based on a third preset number of genetic parent control strategies. Then, it calculates the current offspring power consumption value for each of the third preset number of genetic offspring control strategies, i.e., the total power consumption corresponding to each genetic offspring control strategy. Next, the third preset number of genetic offspring control strategies for the current offspring are used as the genetic parent control strategies for the next iteration round. Cross-genesis is then used to obtain the third preset number of genetic offspring control strategies for the next iteration round. The total power consumption corresponding to each of the third preset number of genetic offspring control strategies for the next iteration round is further calculated. Then, it is determined whether the difference between the total power consumption corresponding to the genetic offspring control strategies in two iteration rounds is less than a preset error. If it is not less, the genetic offspring control strategies of the next iteration round are used as the genetic parent control strategies for the next iteration round, and cross-genesis is performed until the difference between the total power consumption of the genetic offspring control strategies in two consecutive iteration rounds is less than the preset error.

[0125] It should be understood that the crossover genetic process in this application embodiment also includes prioritizing the selection of the genetic offspring control strategy with the lowest total power consumption as the genetic parent control strategy for the next iteration round during the iteration process, so as to ensure the energy consumption optimization needs during the iteration process. This application does not make specific limitations in this regard.

[0126] For example, a second preset number of genetic offspring control strategies can be randomly extracted in each iteration round, and the genetic offspring control strategy with the lowest total power consumption can be selected as the genetic parent control strategy, until a third preset number of genetic parent control strategies are obtained.

[0127] It should be noted that although the operation of the method of the present invention is described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in that specific order, or that all the operations shown must be performed in order to achieve the desired result.

[0128] Figure 4 A schematic diagram of the structure of a building energy efficiency optimization system provided in an embodiment of this application is shown.

[0129] like Figure 4 As shown, the building energy efficiency optimization system 10 includes:

[0130] The acquisition module 11 is used to acquire historical load data, real-time operating status data and meteorological data for the target time of the HVAC system;

[0131] The dual-core drive module 12 is used to input the historical load data, the real-time operating status data, and the meteorological data at the target time into a dual-core optimization model constructed based on the Transformer-genetic algorithm and expert rules to obtain the optimal control strategy; the optimal control strategy corresponds to the lowest power consumption; wherein, the dual-core optimization model includes a Transformer-genetic algorithm sub-model and an expert rule sub-model; the Transformer-genetic algorithm sub-model is used to predict the predicted load at the target time based on the historical load data, the real-time operating status data, and the meteorological data at the target time, and to optimize the control strategy based on the predicted load using a genetic algorithm; the expert rule sub-model is used to correct the control strategy during the optimization process based on preset expert rules during the optimization process of the control strategy by the Transformer-genetic algorithm sub-model using the genetic algorithm based on the predicted load.

[0132] The control module 13 is used to control the HVAC system to execute the optimal control strategy.

[0133] In some embodiments, the dual-core driver module 12 is specifically used for:

[0134] A first preset number of initial control strategies are randomly generated, and the fitness score corresponding to each initial control strategy is obtained;

[0135] Randomly extract a second preset number of the initial control strategies, and select the initial control strategy with the highest fitness score as the genetic parent control strategy, until a third preset number of the genetic parent control strategies are obtained.

[0136] Randomly select any two of the genetic parent control strategies and perform cross-inheritance to obtain the genetic offspring control strategies corresponding to the genetic parent control strategies, until a fourth preset number of the genetic offspring control strategies are obtained.

[0137] Obtain the power consumption value of the offspring corresponding to each of the genetic offspring control strategies in the current round, and perform the next round of cross-genesis until the difference between the power consumption value of the offspring in the current round and the power consumption value of the offspring in the previous round is less than a preset error.

[0138] In some embodiments, the dual-core driver module 12 is specifically used for:

[0139] The power consumption of the chiller, chilled water pump, cooling water pump and cooling tower under the initial control strategy is obtained respectively, and the total power consumption of the initial control strategy is calculated.

[0140] Calculate the first rule penalty factor and the second rule penalty factor corresponding to the initial control strategy according to the preset expert rules, and determine the expert rule penalty item according to the first rule penalty factor and the second rule penalty factor;

[0141] The fitness score is determined based on the total power consumption and the expert rule penalty.

[0142] In some embodiments, the dual-core driver module 12 is specifically used for:

[0143] In the process of randomly extracting any two of the genetic parent control strategies and performing cross-genesis to obtain the genetic offspring control strategies corresponding to the genetic parent control strategies, the two genetic parent control strategies are subjected to safety-guided cross-genesis based on the preset expert rules.

[0144] In some embodiments, the dual-core driver module 12 is specifically used for:

[0145] Select any one of the two genetic parent control strategies, and perform a safety assessment on a gene-segment-by-gene basis based on the preset expert rules to obtain the safety assessment value corresponding to each gene segment of the genetic parent control strategy;

[0146] Based on the aforementioned safety assessment values, select the intersection point;

[0147] Based on the crossover point, the two genetic parent control strategies are swapped to obtain two genetic offspring control strategies.

[0148] In some embodiments, the dual-core driver module 12 is specifically used for:

[0149] According to the preset expert rules, the dependency relationships between the gene segments are obtained;

[0150] Based on the dependency relationship, determine the gene segment group with the dependency relationship and the gene location of each gene segment in the gene segment group;

[0151] The crossover point is selected based on the gene location of each gene segment in the gene segment group.

[0152] It should be understood that the modules or modules described in the Building Energy Efficiency Optimization System 10 are similar to those in the reference. Figure 2The steps in the described method correspond to each other. Therefore, the operations and features described above for the method are also applicable to the building energy efficiency optimization system 10 and the modules contained therein, and will not be repeated here. The building energy efficiency optimization system 10 can be pre-implemented in the browser or other security applications of an electronic device, or it can be loaded into the browser or other security applications of an electronic device by means of downloading. The corresponding modules in the building energy efficiency optimization system 10 can cooperate with the modules in the electronic device to implement the solution of the embodiments of this application.

[0153] The division of modules or units mentioned in the detailed description above is not mandatory. In fact, according to the embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0154] The following is for reference. Figure 5 , Figure 5 A schematic diagram of the structure of a computer system suitable for implementing the embodiments of this application is shown.

[0155] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. RAM 503 also stores various programs and data required for the system's operating instructions. CPU 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0156] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0157] Specifically, according to embodiments of this application, the flowchart above refers to... Figure 2The described process can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program contains program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs the functions defined in the system of this application.

[0158] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0159] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operational instructions of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two connected blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified functions or operational instructions, or using a combination of dedicated hardware and computer instructions.

[0160] In another aspect, this application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments, or may exist independently and not assembled into the electronic device. The aforementioned computer-readable storage medium stores one or more programs that, when used by one or more processors, execute a building energy efficiency optimization method described in this application.

[0161] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for optimizing building energy efficiency, characterized in that, include: Acquire historical load data, real-time operating status data, and meteorological data for the target time of the HVAC system; The historical load data, the real-time operating status data, and the meteorological data at the target time are input into a dual-core optimization model constructed based on the Transformer-Genetic Algorithm and expert rules to obtain the optimal control strategy. The optimal control strategy corresponds to the lowest power consumption. The dual-core optimization model includes a Transformer-Genetic Algorithm sub-model and an expert rule sub-model. The Transformer-Genetic Algorithm sub-model is used to predict the predicted load at the target time based on the historical load data, the real-time operating status data, and the meteorological data at the target time, and uses a genetic algorithm to optimize the control strategy based on the predicted load. The expert rule sub-model is used to correct the control strategy during the optimization process using the genetic algorithm based on the predicted load, based on preset expert rules. Control the HVAC system to execute the optimal control strategy; The method of optimizing the control strategy based on the predicted load using a genetic algorithm includes: A first preset number of initial control strategies are randomly generated, and the fitness score corresponding to each initial control strategy is obtained; Randomly extract a second preset number of the initial control strategies, and select the initial control strategy with the highest fitness score as the genetic parent control strategy, until a third preset number of the genetic parent control strategies are obtained. Randomly select any two of the genetic parent control strategies and perform cross-inheritance to obtain the genetic offspring control strategies corresponding to the genetic parent control strategies, until a fourth preset number of the genetic offspring control strategies are obtained. Obtain the power consumption value of the offspring corresponding to each of the genetic offspring control strategies in the current round, and perform the next round of cross-genesis until the difference between the power consumption value of the offspring in the current round and the power consumption value of the offspring in the previous round is less than a preset error; The step of obtaining the fitness score corresponding to each initial control strategy includes: The power consumption of the chiller, chilled water pump, cooling water pump and cooling tower under the initial control strategy is obtained respectively, and the total power consumption of the initial control strategy is calculated. Calculate the first rule penalty factor and the second rule penalty factor corresponding to the initial control strategy according to the preset expert rules, and determine the expert rule penalty item according to the first rule penalty factor and the second rule penalty factor; The fitness score is determined based on the total power consumption and the expert rule penalty.

2. The building energy efficiency optimization method according to claim 1, characterized in that, The process of modifying the control strategy during the optimization process based on preset expert rules includes: In the process of randomly extracting any two of the genetic parent control strategies and performing cross-genesis to obtain the genetic offspring control strategies corresponding to the genetic parent control strategies, the two genetic parent control strategies are subjected to safety-guided cross-genesis based on the preset expert rules.

3. The building energy efficiency optimization method according to claim 2, characterized in that, The safe-guided cross-inheritance of the two genetic parent control strategies includes: Select any one of the two genetic parent control strategies, and perform a safety assessment on a gene-segment-by-gene basis based on the preset expert rules to obtain the safety assessment value corresponding to each gene segment of the genetic parent control strategy; Based on the aforementioned safety assessment values, select the intersection point; Based on the crossover point, the two genetic parent control strategies are swapped to obtain two genetic offspring control strategies.

4. The building energy efficiency optimization method according to claim 3, characterized in that, The step of selecting the intersection point based on the security assessment value includes: According to the preset expert rules, the dependency relationships between the gene segments are obtained; Based on the dependency relationship, determine the gene segment group with the dependency relationship and the gene location of each gene segment in the gene segment group; The crossover point is selected based on the gene location of each gene segment in the gene segment group.

5. A building energy efficiency optimization system, characterized in that, include: The acquisition module is used to acquire historical load data, real-time operating status data, and meteorological data for the target time of the HVAC system. A dual-core drive module is used to input the historical load data, the real-time operating status data, and the meteorological data at the target time into a dual-core optimization model constructed based on Transformer-Genetic Algorithm and expert rules to obtain the optimal control strategy; the optimal control strategy corresponds to the lowest power consumption; wherein, the dual-core optimization model includes a Transformer-Genetic Algorithm sub-model and an expert rule sub-model; the Transformer-Genetic Algorithm sub-model is used to predict the predicted load at the target time based on the historical load data, the real-time operating status data, and the meteorological data at the target time, and uses a genetic algorithm to optimize the control strategy based on the predicted load; the expert rule sub-model is used to correct the control strategy during the optimization process by the Transformer-Genetic Algorithm sub-model using the genetic algorithm based on the predicted load based on preset expert rules; The control module is used to control the HVAC system to execute the optimal control strategy; The method of optimizing the control strategy based on the predicted load using a genetic algorithm includes: A first preset number of initial control strategies are randomly generated, and the fitness score corresponding to each initial control strategy is obtained; Randomly extract a second preset number of the initial control strategies, and select the initial control strategy with the highest fitness score as the genetic parent control strategy, until a third preset number of the genetic parent control strategies are obtained. Randomly select any two of the genetic parent control strategies and perform cross-inheritance to obtain the genetic offspring control strategies corresponding to the genetic parent control strategies, until a fourth preset number of the genetic offspring control strategies are obtained. Obtain the power consumption value of the offspring corresponding to each of the genetic offspring control strategies in the current round, and perform the next round of cross-genesis until the difference between the power consumption value of the offspring in the current round and the power consumption value of the offspring in the previous round is less than a preset error; The step of obtaining the fitness score corresponding to each initial control strategy includes: The power consumption of the chiller, chilled water pump, cooling water pump and cooling tower under the initial control strategy is obtained respectively, and the total power consumption of the initial control strategy is calculated. Calculate the first rule penalty factor and the second rule penalty factor corresponding to the initial control strategy according to the preset expert rules, and determine the expert rule penalty item according to the first rule penalty factor and the second rule penalty factor; The fitness score is determined based on the total power consumption and the expert rule penalty.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the building energy efficiency optimization method as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the building energy efficiency optimization method as described in any one of claims 1-4.

8. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the building energy efficiency optimization method according to any one of claims 1-4.

Images