Building air conditioner control strategy generation method, device, equipment and medium

Abstract

The invention relates to a building air conditioner control strategy generation method and device, equipment and a medium. The method comprises the steps that state data, operation states and operation scenes of different areas in a building are obtained; calculating an influence factor score of the corresponding region; adjusting a weight coefficient of the influence factor score; calculating a comprehensive score of the current area according to the influence factor score and the corresponding weight coefficient; comparing the comprehensive scores of different areas with a preset grading threshold value, and determining the importance level of the corresponding area; and generating different control strategies according to the importance levels of the different areas and issuing the control strategies to the corresponding areas. According to the method, comprehensive scoring of different regions is realized by combining the score of the influence factor with dynamic weight adjustment, so that region importance is accurately quantified, and a basis is provided for generating a differentiated control strategy. Compared with a traditional timing control or single parameter control mode, the method can more accurately reflect the actual demand of each area, and unreasonable energy waste is avoided.

Description

Technical Field

[0001] The present application relates to the technical field of building energy management, and in particular to a method, device, and medium for generating a building air-conditioning control strategy. Background Art

[0002] Air conditioning load is one of the main causes of peak power grid loads in summer, and its regulation and energy conservation are becoming increasingly important. This is particularly true in office buildings, where traditional air conditioning control systems often face a core dilemma: balancing energy consumption with comfort, due to diverse spatial functions, frequent personnel turnover, and significant fluctuations in equipment startups and shutdowns. Current building air conditioning control strategies suffer from the following drawbacks: First, the limited computing power of control terminals makes it difficult to execute complex optimization algorithms, limiting them to basic temperature control functions. Second, traditional air conditioning control systems typically employ fixed control methods based on physical layout or piping divisions, failing to adapt to dynamically changing building usage patterns and functional requirements. This can lead to overcooling or overheating in some areas, resulting in significant variations in user experience. Third, there is a lack of coordination between zones, with air conditioning control systems in different areas typically operating relatively independently. This lack of effective coordination prevents global energy optimization, resulting in energy waste and inefficient systems. Finally, traditional control systems are slow to respond to personnel movements and abnormal situations, making it difficult to perceive and predict activity patterns. This results in untimely responses to emergencies (such as impromptu meetings or large gatherings), impacting user experience. Summary of the Invention

[0003] To overcome the above-mentioned deficiencies of the prior art, the present application provides a building air conditioning control strategy generation method, apparatus, device and medium, which specifically adopts the following technical solutions:

[0004] A method for generating a building air conditioning control strategy, the method comprising the following steps:

[0005] Obtain status data for different areas within the building, as well as the overall operating status and operating scenario of the building; the status data includes at least the number of people in the current area i at time t, the ambient temperature, and the air conditioning power;

[0006] Calculate the impact factor scores of the corresponding areas based on the obtained status data, including the personnel density score, function importance score, energy efficiency score, and time factor score;

[0007] Adjust the weight coefficient of the influencing factor score according to the overall operating status and operating scenario of the building;

[0008] The comprehensive score of the current area is calculated based on the scores of different influencing factors and the corresponding weight coefficients;

[0009] Compare the comprehensive scores of different areas with the preset classification thresholds to determine the importance level of the corresponding areas;

[0010] Different control strategies are generated according to the importance levels of different areas and distributed to the corresponding areas.

[0011] Optional: The step of calculating the personnel density scores of the corresponding areas according to the obtained status data includes:

[0012] Obtain the maximum number of people that can accommodate the corresponding area, the continuous occupancy time, and the average number of people in the same period in history;

[0013] The first factor parameter of the current area at time t is calculated based on the number of people and the maximum number of people that can be accommodated in the corresponding area at time t;

[0014] The second factor parameter of the current area at time t is calculated based on the continuous occupancy time of the corresponding area at time t;

[0015] The third factor parameter of the current region at time t is calculated based on the number of people in the corresponding region at time t and the average number of people in the same period in history;

[0016] The first factor parameter, the second factor parameter, and the third factor parameter are weighted and summed to obtain the population density score of the current area at time t.

[0017] Optional: The step of calculating the functional importance scores of the corresponding regions according to the obtained status data includes:

[0018] Get the regional function level of the corresponding area and the time period type at time t;

[0019] Calculate the functional basic score of the current area according to the regional functional level of the corresponding area;

[0020] Obtain the adjustment ratio of the corresponding time period type according to the time period type at time t in the corresponding area;

[0021] Calculate the time adjustment factor at time t according to the adjustment ratio of the time period type at time t;

[0022] The functional importance score of the current region at time t is calculated based on the functional basic score of the corresponding region and the time adjustment factor at time t.

[0023] Optionally, the step of calculating the energy efficiency scores of the corresponding areas according to the obtained status data further includes:

[0024] Get the total number of zones in the building and the area of ​​different zones;

[0025] The first unit area energy consumption of the current area at time t is calculated based on the air conditioning power and area of ​​the corresponding area at time t;

[0026] Calculate the sum of the air conditioning power of all areas in the building and the sum of the area of ​​all areas in the building at time t;

[0027] The second energy consumption per unit area is calculated based on the sum of the air conditioning powers and the sum of the area of ​​all areas in the building at time t;

[0028] Comparing the first energy consumption per unit area with the second energy consumption per unit area: when the first energy consumption per unit area is less than or equal to the second energy consumption per unit area, determining that the current area is at a high efficiency level; when the first energy consumption per unit area is greater than the second energy consumption per unit area, determining that the current area is at a low efficiency level;

[0029] Select the corresponding calculation coefficient according to the efficiency level of the current area;

[0030] The energy efficiency score of the current area at time t is obtained according to the corresponding calculation coefficient, the first energy consumption per unit area, and the second energy consumption per unit area.

[0031] Optionally, the step of calculating the time factor scores of the corresponding areas according to the obtained status data includes:

[0032] Get the maximum time score, actual usage time, and time period weight of the corresponding area;

[0033] The time base score of the current area is calculated based on the maximum time score of the corresponding area and the time period weight corresponding to time t;

[0034] Calculate the usage time coefficient of the current area based on the actual usage time of the corresponding area;

[0035] The time factor score of the current area at time t is calculated based on the time base score of the corresponding area and the usage duration coefficient.

[0036] Optional: The step of adjusting the weight coefficient of the influencing factor score according to the overall operating status and operating scenario of the building includes:

[0037] Calculating the overall building operating status indicators respectively, wherein the operating status indicators include load rate indicators, comfort indicators, energy efficiency indicators and environmental indicators;

[0038] The overall operating status index of the building is used as the feature vector of the operating scenario, and the current operating scenario is determined in combination with the scenario judgment rules;

[0039] Obtain the adjustment coefficient of each influencing factor score under the current operating scenario according to the current operating scenario;

[0040] The state response parameters of each influencing factor score are obtained by calculating the response strength and sensitivity of each influencing factor score in the current operation scenario in the corresponding area;

[0041] The adjustment weight of the corresponding influencing factor score is obtained by calculating the adjustment coefficient of the corresponding area in the current operating scenario, the state response parameter and the original weight of each influencing factor score.

[0042] Optionally, the step of comparing the comprehensive scores of different regions with preset grading thresholds to determine the importance levels of corresponding regions includes:

[0043] Obtain the comprehensive score of the corresponding area at time t, and obtain the preset classification threshold;

[0044] Smoothing the comprehensive score of the corresponding area at time t to obtain a revised comprehensive score;

[0045] Compare the revised comprehensive score with the preset grading threshold to determine the threshold range to which it belongs;

[0046] The importance level of the corresponding area is obtained according to the threshold interval.

[0047] Optionally, the scene judgment rule is optimized by machine learning, and the specific optimization steps include:

[0048] Acquiring historical operating data of the building, the historical operating data including at least feature vectors of different operating scenarios, determined operating scenarios, and operating performance;

[0049] Use the historical operating data of the building to train the classifier, and extract judgment rules through the trained classifier;

[0050] The extracted judgment rules are converted into a threshold comparison form to obtain the judgment threshold of the corresponding operation scenario.

[0051] Optional: After obtaining the adjustment weight of the corresponding influencing factor score, the adjustment weight needs to be time-smoothed. During the time smoothing process, the value range of the smoothing coefficient is set to [0.1, 0.5], and when the operation scene is switched, the smoothing coefficient approaches 0.5; when the operation scene is stable, the smoothing coefficient approaches 0.1.

[0052] In addition, the present application also discloses a building air conditioning control strategy generation device, the device comprising:

[0053] A data acquisition module is used to obtain status data of different areas within the building, as well as the overall operating status and operating scenario of the building; the status data includes at least the number of people in the current area i at time t, the ambient temperature, and the air conditioning power;

[0054] A score calculation module is used to calculate the influencing factor scores of the corresponding areas according to the obtained status data, wherein the influencing factor scores include the personnel density score, the function importance score, the energy efficiency score and the time factor score;

[0055] A weight calculation module, used to adjust the weight coefficient of the influencing factor score according to the overall operating status and operating scenario of the building;

[0056] The scoring calculation module is used to calculate the comprehensive score of the current area based on the scores of different influencing factors and the corresponding weight coefficients;

[0057] An importance level determination module is used to compare the comprehensive scores of different areas with preset classification thresholds to determine the importance level of the corresponding area;

[0058] The strategy generation module is used to generate different control strategies according to the importance levels of different areas and issue them to the corresponding areas.

[0059] Furthermore, the present application also discloses an electronic device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the building air conditioning control strategy generating method as described above.

[0060] Furthermore, the present application discloses a readable storage medium having a program or instruction stored thereon, and when the program or instruction is executed by a processor, the building air conditioning control strategy generating method as described above is implemented.

[0061] Beneficial effects

[0062] The technical solution of this application has the following beneficial effects:

[0063] The building air conditioning control strategy generation method of the present application establishes a scoring model for different influencing factors and combines it with a dynamic weight adjustment mechanism to achieve a comprehensive scoring of different areas, thereby accurately quantifying the importance of the areas and providing a basis for generating differentiated control strategies. The dynamic weight adjustment mechanism enables building air conditioning control to adapt to different operating scenarios and environmental conditions, paying more attention to energy efficiency during periods of high energy-saving demand, and considering user needs more during normal operating periods, thus achieving a dynamic balance between energy saving and comfort. Compared with traditional timing control or single parameter control methods, this method can more accurately reflect the actual needs of each area and avoid unreasonable energy waste. In addition, this method is suitable for building applications of different sizes and types, can adapt to different usage patterns and control requirements, and realize intelligent building energy-saving control. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a flow chart of a building air conditioning control strategy generation method in an embodiment of the present application.

[0065] Figure 2 This is a flow chart of the dynamic weight adjustment mechanism in an embodiment of the present application.

[0066] Figure 3 This is a structural diagram of a building air conditioning control strategy generating device in an embodiment of the present application.

[0067] Figure 4 This is a structural diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0068] The present application will be further described below in conjunction with the accompanying drawings. The following examples are only used to more clearly illustrate the technical solutions of the present application and are not intended to limit the scope of protection of the present application. It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application.

[0069] Specifically, this embodiment discloses a method for generating building air conditioning control strategies. The method is implemented based on a three-layer collaborative architecture consisting of a perception layer, an edge computing layer, and a cloud platform layer. In actual deployment, distributed perception control terminals serve as the core devices of the perception layer and are deployed in various functional areas of the building, such as offices, conference rooms, and halls. Each distributed perception control terminal integrates at least a occupancy sensor, a temperature sensor, and a power metering module, enabling real-time collection of area occupancy and environmental parameters. The edge computing layer, acting as a local intelligent decision-making center, executes a four-dimensional dynamic scoring algorithm and a dynamic weight adjustment mechanism on the perception layer data, enabling real-time assessment of the importance of each area and intelligent generation of control strategies. The edge computing layer employed in this embodiment ensures real-time responsiveness of building control, enabling intelligent operation of the building's air conditioning system to be maintained even if communication between the edge computing layer and the cloud platform is interrupted. The cloud platform layer is responsible for global optimization and long-term strategy formulation for building air conditioning control. By collecting and analyzing operational data reported by each edge computing layer, the cloud platform can identify the building's energy usage patterns, optimize system parameter configurations, and push updated control strategies to edge devices. The above three-layer architecture has clear division of labor and close collaboration. Through the orderly flow and processing of data between layers, an efficient and intelligent building air-conditioning control system is formed.

[0070] Specifically, such as Figure 1 As shown, the building air conditioning control strategy generation method of this embodiment includes the following steps:

[0071] First, collect data:

[0072] In this embodiment, the status data of different areas in the building are obtained separately through distributed sensing control terminals deployed in the building, and the overall operating status and operating scenario of the building are obtained at the same time; the status data includes at least the number of people N(i, t) in the current area i at time t, the ambient temperature T(i, t) and the air conditioning power P(i, t).

[0073] Then the four-dimensional score calculation is performed:

[0074] Specifically, this embodiment calculates the impact factor scores of the corresponding areas based on the obtained status data. The impact factor scores include the personnel density score S p (i, t), function importance score S f (i, t), energy efficiency score S e (i, t) and time factor score S t (i,t).

[0075] (1) This embodiment calculates the personnel density scores of the corresponding areas based on the obtained status data:

[0076] First, obtain the maximum number of people C that can accommodate the corresponding area i max (i) Continuous occupancy time T occ (i, t) and the average number of people N in the same period of history hist (i,t).

[0077] Then, according to the number of people N(i,t) and the maximum number of people C in the corresponding area i at time t, max (i) Calculate the first factor parameter of the current region i at time t, that is, the regional density factor D c (i, t), the specific calculation formula is:

[0078]

[0079] It should be noted that the regional density factor calculated in this embodiment takes into account the ratio of the current number of people in the area to the area's maximum capacity. This factor primarily reflects the degree of crowding within the area and accurately captures dynamic changes in the area's density. For example, in an office building's conference room, when a meeting is underway, the number of people increases dramatically, and the regional density factor rises rapidly. Based on this, the system can determine that the area is experiencing high-density usage.

[0080] Then, according to the continuous occupancy time T of the corresponding area i at time t occ (i, t) calculates the second factor parameter of the current area i at time t, that is, the continuous occupancy factor D d (i, t), the specific calculation formula is:

[0081]

[0082] Where T ref The continuous occupancy factor of this embodiment reflects the continuous use of the current area by comparing the continuous occupancy time with the reference time, which can effectively avoid the problem of frequent adjustment of air conditioning parameters due to the short-term passing of people.

[0083] Secondly, according to the number of people N(i,t) in the corresponding area i at time t and the historical average number of people N hist (i, t) calculates the third factor parameter of the current region i at time t, that is, the historical comparison factor D h (i, t), the specific calculation formula is:

[0084]

[0085] The historical comparison factor of this embodiment can identify abnormal gatherings of people and improve the adaptability of the system by comparing the current number of people with the average number of people in the same historical period.

[0086] Finally, the first factor parameter, the second factor parameter, and the third factor parameter are weighted and summed to obtain the personnel density score S of the current area i at time t p (i, t), the specific calculation formula is:

[0087] S p (i,t)=α1·D c (i,t)+α2·D d (i,t)+α3·D h (i,t);

[0088] In the above formula, α1+α2+α3=1 and α>0, and α1, α2, and α3 are the combination weight coefficients. These three factors are weighted together using configurable combination weight coefficients, enabling the system to flexibly adjust based on the usage characteristics of different buildings.

[0089] (2) This embodiment calculates the functional importance score S of the corresponding region i based on the obtained status data. f (i,t):

[0090] First, obtain the regional function level L(i) corresponding to area i and the time period type at time t; in this embodiment, each area is assigned a corresponding regional function level. For example, key areas such as data centers and important conference rooms are assigned higher regional function levels to ensure that these areas can obtain sufficient air-conditioning services under any circumstances.

[0091] Then, the functional basic score F of the current region i is calculated based on the regional functional level L(i) of the corresponding region. base(i)

[0092] F base (i) = F0 + (L(i) - 1)·F step ;

[0093] Where F0 is the lowest functional score, F step is the score step size.

[0094] Then, the adjustment ratio R of the corresponding time period type is obtained according to the time period type at time t in the corresponding area i. period (t);

[0095] Secondly, the adjustment ratio R is based on the time period type at time t. period (t) Calculate the time adjustment factor K at time t time (t):

[0096] K time (t) = K0·R period (t);

[0097] The time adjustment factor of this embodiment is calculated based on the basic time coefficient and the time period type adjustment ratio, so that the system can dynamically adjust the importance score of each area according to time period types such as working hours and holidays.

[0098] Finally, according to the functional basic score F of the corresponding area i base (i) and the time adjustment factor K at time t time (t) Calculate the functional importance score S of the current region i at time t f (i,t):

[0099] S f (i,t)=F base (i) K time (t).

[0100] (3) This embodiment calculates the energy efficiency score S of the corresponding area i based on the obtained status data e (i,t):

[0101] First, obtain the total number of regions M in the building and the area A(i) of different regions i;

[0102] Then, the first unit area energy consumption E of the current area i at time t is calculated based on the air conditioning power P(i, t) of the corresponding area i at time t and the area A(i) i (t), the specific calculation formula is:

[0103]

[0104] Then calculate the total air conditioning power of all areas in the building at time t and the total area of ​​all areas in the building, that is, calculate the air conditioning power P(i,t) of different areas i at time t separately, and add them up to get the total air conditioning power And calculate the area A(i) of different regions i separately, and add them up to get the total area

[0105] According to the total air conditioning power of all areas in the building at time t and the sum of the regional areas Calculate the second energy consumption per unit area E avg (t), the specific calculation formula is:

[0106]

[0107] Then compare the first unit area energy consumption E i (t) and the second energy consumption per unit area E avg (t): When the first unit area energy consumption E i (t) is less than or equal to the second energy consumption per unit area E avg (t), it is judged that the current area i is at a high efficiency level; when the energy consumption per unit area E i (t) is greater than the second energy consumption per unit area E avg (t), it is judged that the current region i is at a low efficiency level.

[0108] The corresponding calculation coefficient is selected according to the efficiency level of the current area i: when the current area i is judged to be at a high efficiency level, the high efficiency reward coefficient β is selected; when the current area i is judged to be at a low efficiency level, the low efficiency penalty coefficient γ is selected.

[0109] Finally, according to the corresponding calculation coefficient, the first unit area energy consumption E i (t) and the second energy consumption per unit area E avg (t) Calculate the energy efficiency score S of the current region i at time t e (i,t):

[0110]

[0111] In the above formula, 0 < γ < β. The energy efficiency score in this embodiment uses a relative comparison evaluation method, comparing the energy consumption per unit area of ​​each area with the average unit energy consumption of the building. When the energy consumption per unit area of ​​an area is lower than the average level of the building, the system increases its efficiency score by applying a high-efficiency reward coefficient. Conversely, when the energy consumption is higher than the average level, the system decreases its efficiency score by applying a low-efficiency penalty coefficient, thereby lowering its priority in the subsequent comprehensive scoring. This effectively encourages efficient energy use and promotes the optimization of the building's overall energy consumption level.

[0112] (4) This embodiment calculates the time factor score S of the corresponding area i based on the obtained status data t (i,t):

[0113] First, obtain the maximum time score T corresponding to area i max , actual usage time T actual (i) and the time period weight W of the time period to which time t belongs period (t);

[0114] Then, according to the maximum time score T of the corresponding area i max And the time period weight W corresponding to time t period (t) Calculate the time base score T of the current area i base (t):

[0115] T base (t) = T max W period (t);

[0116] Then, according to the actual usage time T of the corresponding area i actual (i) Calculate the usage time coefficient U of the current area i pattern (i)

[0117]

[0118] Finally, according to the time base score T of the corresponding area i base (t) and usage duration coefficient U pattern (i) Calculate the time factor score S of the current region i at time t t (i,t):

[0119] S t (i,t)=T base (t)·U period (t).

[0120] The time factor score in this embodiment comprehensively considers the influence of time period weights and regional usage patterns. By analyzing the historical usage data of each area, the usage patterns of different areas can be identified. For example, some conference rooms are mainly used in the morning, while some office areas still have overtime demand after get off work. The time factor score is calculated through a comprehensive calculation of the time base score, the maximum time score, the time period weight, and the usage duration coefficient. The usage pattern factor is determined based on the ratio of actual usage duration to standard usage duration, thereby achieving a more accurate regional importance assessment.

[0121] Then the dynamic weight adjustment mechanism is carried out:

[0122] This embodiment adjusts the weight coefficient of the influencing factor score according to the overall operating status and operating scenario of the building. Figure 2 As shown, the specific steps are as follows

[0123] First, the overall building operating status indicators are calculated separately. These operating status indicators include load rate indicators, comfort indicators, energy efficiency indicators, and environmental indicators. In this embodiment, the load rate indicator reflects the load of the building air conditioning system by averaging the ratio of actual power to rated power in each area. The comfort index comprehensively considers the impact of temperature deviation and occupant density, and is calculated by weighting the deviation between the actual temperature and the set temperature, as well as the ratio of the actual number of people to the designed capacity. The energy efficiency index reflects the system's energy utilization efficiency by comparing the current unit energy consumption to the benchmark unit energy consumption. The environmental indicator considers the impact of outdoor temperature and humidity on the air conditioning load and is calculated by the degree of deviation between the outdoor temperature and humidity and the standard value.

[0124] (1) Load rate index:

[0125]

[0126] Where P(i,t) is the actual power of region i at time t, P max (i) is the rated power of area i, and M is the total number of areas.

[0127] (2) Comfort index:

[0128]

[0129] Where T(i,t) is the actual temperature of the current region i at time t, T set (i, t) is the set temperature of the current area i at time t, T tol To allow temperature deviation, N(i,t) is the actual number of people in the current area i at time t, and C(i) is the design capacity of the current area i.

[0130] (3) Energy efficiency indicators:

[0131]

[0132] Among them E cur (t) is the current unit energy consumption, E ref It is the benchmark unit energy consumption.

[0133] (4) Environmental indicators:

[0134]

[0135] Where T out (t) is the outdoor temperature, H out (t) is the outdoor humidity, T std and Hstd are the standard values ​​of outdoor temperature and humidity, T range and H range are the normal ranges of outdoor temperature and humidity respectively, a1 and a2 are weight coefficients, and a1+a2=1.

[0136] Then, the overall operating status index of the building is used as the feature vector V(t) of the operating scenario, and the current operating scenario S(t) is determined in combination with the scenario judgment rules. The feature vector of the operating scenario can be expressed as:

[0137] V(t)=[L(t),C(t),E(t),W(t)] T ;

[0138] It should be noted that this embodiment forms a characteristic vector of the operating scenario based on the above four operating status indicators, and the system determines the current operating scenario through preset scenario judgment rules. This embodiment predefines five typical operating scenarios, including peak load, comfort priority, energy saving priority, extreme weather, and normal operation. Each scenario corresponds to a different control strategy and weight configuration. For example, when the load rate exceeds the threshold and the outdoor environment is harsh, the system determines it as a peak load scenario; when the comfort index is lower than the threshold, it is determined to be a comfort priority scenario; at night or during holidays, the system is more inclined to determine it as an energy saving priority scenario.

[0139] The scene judgment rules of this embodiment can be optimized by machine learning. The specific optimization steps include:

[0140] First, obtain the historical operation data of the building The historical operation data at least includes feature vectors V of different operation scenarios (k) , Determined operating scenario S (k) And the running performance P (k) ;

[0141] The classifier is trained using the historical operating data of the building, and judgment rules are extracted through the trained classifier; for example, this embodiment preferably uses a decision tree or support vector machine algorithm, with the state vector V(t) as input and the scene category S(t) as output.

[0142] The extracted judgment rules are converted into a threshold comparison form to obtain the judgment threshold of the corresponding operation scenario.

[0143] Then, according to the current operating scenario S(t), the adjustment coefficient of each influencing factor score in the current operating scenario can be obtained according to the preset form rules, that is, the current operating scenario adjustment coefficient vector K S It can be expressed as:

[0144]

[0145] Where k1, k2, k3, and k4 represent the personnel density scores S in the current operating scenario. p (i, t), function importance score S f (i, t), energy efficiency score S e (i, t) and time factor score S t The adjustment factor for (i,t).

[0146] Secondly, the state response parameters of each influencing factor score are calculated based on the response strength and sensitivity of each influencing factor score in the current operating scenario within the corresponding area i:

[0147]

[0148] where b ji is the response intensity coefficient, c ji is the sensitivity coefficient, V i is the i-th component in the eigenvector V(t).

[0149] Finally, the adjustment weight of the corresponding influencing factor score is calculated based on the adjustment coefficient, state response parameter and original weight of each influencing factor score of the corresponding area i in the current operation scenario:

[0150]

[0151] Where v = 1, 2, 3, 4 represent the personnel density score S respectively. p (i, t), function importance score S f (i, t), energy efficiency score S e (i, t) and time factor score S t (i, t). The original weight vector of each influencing factor score can be expressed as:

[0152] W0=[α1,α2,α3,α4] T ;

[0153] in α v It is the basic original weight of each influencing factor score.

[0154] This embodiment uses a state response function to calculate the adjustment weights of the scores of each influencing factor, which realizes nonlinear weight adjustment through the hyperbolic tangent function. In the system of this embodiment, a basic weight vector is set for each weight dimension, and the adjustment coefficient vector of the corresponding operating scenario is obtained by looking up the table according to the identified operating scenario, and then fine-tuned through the state response function. The design of the state response function in this embodiment makes the weight adjustment relatively smooth when the state change is small, and can respond quickly when the state deviates significantly from the normal range. The response intensity coefficient and sensitivity coefficient determine the degree of influence of each state indicator on the weight. These parameters can be continuously optimized through historical data analysis and adaptive learning mechanism.

[0155] In addition, it should be noted that in this embodiment, the adjustment weights of the scores of the influencing factors obtained according to the above dynamic weight adjustment process need to be normalized:

[0156]

[0157] Then, time smoothing is performed on the adjustment weights of the normalized scores of each influencing factor:

[0158]

[0159] During the time smoothing process, the value range of the smoothing coefficient τ is set to [0.1, 0.5], and when the operation scene is switched, the smoothing coefficient is close to 0.5; when the operation scene is stable, the smoothing coefficient is close to 0.1.

[0160] Finally, the adjustment weight output by this embodiment can be expressed as:

[0161]

[0162] That is, the weight coefficient w of the personnel density score is obtained p (t), weight coefficient w of function importance score f (t), weight coefficient w of energy efficiency score e (t), the weight coefficient w of the time factor score t (t).

[0163] This embodiment uses temporal smoothing to avoid disturbances to the system caused by frequent weight fluctuations. The smoothing coefficient is adaptively adjusted based on the scene switching. A larger smoothing coefficient is used immediately after a scene switch to quickly adapt to the new scene, while a smaller smoothing coefficient is used after the scene stabilizes to improve system stability.

[0164] Then the comprehensive score calculation and grading decision are carried out:

[0165] This embodiment calculates the comprehensive score of the current area based on the scores of different influencing factors and the corresponding weight coefficients. Specifically, this embodiment can calculate the comprehensive score of the current area based on the weighted sum of the scores of the above four influencing factors and the corresponding weight coefficients:

[0166] S(i,t)=w p (t)·S p (i,t)+w f (t)·S f (i,t)+w e (t)·S e (i,t)+w t (t)·S t (i,t);

[0167] The comprehensive score is then smoothed to obtain a smoothed comprehensive score S smooth (i, t) to avoid frequent fluctuations in the score. The smoothing method used in this step is the exponential moving average method, which calculates the final smoothed comprehensive score by taking the weighted average of the current score and the historical smoothed score.

[0168] In this embodiment, based on the smoothed comprehensive score, the system adopts a four-level classification strategy to determine the regional importance level. Specifically, the comprehensive score of different regions can be compared with the preset classification threshold to determine the importance level of the corresponding region. The detailed process is as follows:

[0169] First, the comprehensive score of the corresponding area i at time t is obtained, and the preset classification threshold is obtained.

[0170] Then, the comprehensive score of the corresponding area at time t is smoothed to obtain a corrected comprehensive score.

[0171] Then compare the revised comprehensive score with the preset grading threshold to determine the threshold range to which it belongs.

[0172] Finally, the importance level of the corresponding area is obtained according to the threshold interval.

[0173] For example, in this embodiment, the preset grading thresholds include three levels: high threshold, medium-high threshold and low threshold. Subsequently, when the comprehensive score is higher than the high threshold, the current area is rated as A (high importance); when the comprehensive score is between the medium-high threshold and the high threshold, it is rated as B (medium-high importance); when the comprehensive score is between the low threshold and the medium-high threshold, it is rated as C (medium-low importance); when the score is lower than the low threshold, it is rated as D (low importance).

[0174] Finally, generate the differentiated control strategy:

[0175] This embodiment generates and distributes different control strategies based on the importance of different areas. For example, for Class A areas, the system prioritizes environmental comfort, maintaining optimal temperature settings while allowing for higher energy consumption to ensure a better user experience. For Class B areas, moderate energy conservation is employed while ensuring basic comfort levels. Temperature settings can be relaxed and wind speeds can be reduced. For Class C areas, a more proactive energy conservation strategy is adopted, allowing for a wider range of temperature fluctuations and further reducing wind speeds. For Class D areas, the system uses the lowest energy consumption mode, even completely shutting down the air conditioning during unoccupied hours.

[0176] It's important to note that the building air conditioning control strategy generation method of this embodiment not only considers the current comprehensive rating but also incorporates historical regional operating data and usage forecasts. For example, if a conference room is predicted to be occupied within the next hour, pre-cooling or pre-heating will be implemented to ensure comfort during use, even if the current rating is low. This control mechanism effectively improves the user experience while avoiding temporary high-power operation.

[0177] This embodiment takes a typical scenario of an office building as an example to illustrate the working process of the building air conditioning control strategy generation method of the present application.

[0178] Assume that at 10:30 am on a weekday, a meeting is being held in an important conference room with 8 participants. The indoor temperature is 24°C and the air conditioning power is 3.2kW.

[0179] The control system first calculated the occupancy density score. The base density coefficient was 8 people divided by the design capacity of 12, which yielded a score of 0.667. Since the meeting had lasted 45 minutes, the occupancy continuity coefficient was 0.75. Compared to the historical average of 6 people for the same period, the historical comparison coefficient was 1.33. Combining these three coefficients and applying a weighted approach yielded a occupancy density score of 81.7.

[0180] The functional importance score is based on the base score of 95 for important meeting rooms, with an adjustment factor of 1.0 for core working hours, resulting in a final score of 95.

[0181] The energy efficiency score is calculated by dividing the energy consumption per unit area of ​​3.2kW by 36 square meters. After comparing it with the average level of the building, it is slightly higher than the average and is given a score of 0.

[0182] The time factor score is based on the core working time base score of 100 points, combined with the usage pattern coefficient of 1.1 for this area, and the final score is 100 points.

[0183] Regarding weight adjustment, assuming the current building load rate is 85%, the system determines that the energy conservation demand is moderate. The weights of each dimension are adjusted accordingly and normalized. The final comprehensive score is calculated as the weighted sum of each score, which, after smoothing, is 68.9 points, classifying the area as a Class B area.

[0184] Based on the B-level score, the system generates a corresponding control strategy, raising the set temperature by 1°C to 25°C in summer cooling mode and adjusting the wind speed to 90% of the standard, achieving moderate energy saving while ensuring basic comfort.

[0185] The method of this embodiment has the ability to continuously optimize, and it continuously improves the control strategy through the accumulation of long-term operating data. The weight parameters will be fine-tuned according to the actual energy-saving effect. When it is found that a certain weight configuration can bring better energy-saving effects, the system will gradually adjust the basic weight value. The regional usage pattern coefficient will also be dynamically updated according to actual usage to reflect changes in building usage patterns. Functional type classification also supports adaptive adjustment. When the actual usage frequency of an area deviates from its functional positioning for a long time, the system will recommend adjusting its functional type classification to ensure that the scoring system is consistent with actual usage. This self-learning mechanism enables the system to adapt to changes in building usage patterns and maintain long-term optimization effects.

[0186] In addition, this embodiment takes the application of the above method in a commercial complex as an example. Commercial complexes contain multiple functional areas such as offices, shops, restaurants, and entertainment, and there are significant differences in the usage patterns and importance evaluation criteria of each area. The method of this embodiment can first set corresponding basic scores and time adjustment modes for different areas by expanding the functional type classification. For example, the office area continues the traditional working time mode, and the core working time obtains the highest time coefficient. The shop area is adjusted according to the business hours, and the time coefficient is higher during the peak business period. The catering area has obvious meal time characteristics, and the time coefficient is significantly improved during the peak meal period. The entertainment area is mainly active in the evening and weekends, and the time distribution pattern is adjusted accordingly.

[0187] The evaluation of personnel density also needs to adapt to the characteristics of different business formats. For example, the personnel mobility in shops and catering areas is relatively high. The method of this embodiment can use a shorter time window to calculate the occupancy continuity to avoid scoring deviations caused by the rapid flow of personnel. At the same time, historical comparison benchmarks are also established according to business formats to ensure the accuracy of the evaluation. Large complexes are usually divided into multiple independent air-conditioning zones, and each zone may use a different air-conditioning system. The method of this embodiment can support independent scoring and control by region, and perform relative scoring within each zone to avoid the impact of equipment differences between different zones on the fairness of scoring. The edge computing layer can manage multiple zones at the same time and maintain an independent scoring system and weight parameters for each zone. Information sharing between zones helps to optimize the global energy-saving strategy. When the load on a certain zone is light, it can appropriately bear the cooling and heating loads of other zones to achieve overall energy consumption optimization.

[0188] In addition, commercial complexes have obvious peak periods of passenger flow, such as weekends, holidays, and special promotions. The method of this embodiment can identify peak periods in advance through passenger flow forecasting and adjust the scoring strategy and control parameters accordingly. During peak passenger flow periods, the weight of personnel density will be appropriately reduced to avoid excessive bias in scoring towards densely populated areas due to excessive concentration of personnel. At the same time, the weight of functional importance is increased to ensure the environmental quality of key service areas such as customer service centers and security passages. The weight of energy efficiency will also be adjusted accordingly to achieve energy saving goals while ensuring service quality.

[0189] In addition, Figure 3 As shown, the present application also discloses a building air conditioning control strategy generation device, the device comprising:

[0190] A data acquisition module is used to obtain status data of different areas within the building, as well as the overall operating status and operating scenario of the building; the status data includes at least the number of people in the current area i at time t, the ambient temperature, and the air conditioning power;

[0191] A score calculation module is used to calculate the influencing factor scores of the corresponding areas according to the obtained status data, wherein the influencing factor scores include the personnel density score, the function importance score, the energy efficiency score and the time factor score;

[0192] A weight calculation module, used to adjust the weight coefficient of the influencing factor score according to the overall operating status and operating scenario of the building;

[0193] The scoring calculation module is used to calculate the comprehensive score of the current area based on the scores of different influencing factors and the corresponding weight coefficients;

[0194] An importance level determination module is used to compare the comprehensive scores of different areas with preset classification thresholds to determine the importance level of the corresponding area;

[0195] The strategy generation module is used to generate different control strategies according to the importance levels of different areas and issue them to the corresponding areas.

[0196] The device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented in the method embodiment will not be described here.

[0197] like Figure 4 As shown, the embodiment of the present application also provides an electronic device, including a processor and a memory, a program or instruction stored in the memory and capable of running on the processor, and when the program or instruction is executed by the processor, the following is achieved: Figure 1 The various processes of the method embodiment shown in the figure can achieve the same technical effect. To avoid repetition, they will not be described here.

[0198] The embodiment of the present application also provides a readable storage medium on which a program or instruction is stored, and when the program or instruction is executed by the processor, the above Figure 1 The various processes of the method embodiments described above can achieve the same technical effects, and will not be described again here to avoid repetition.

[0199] The present application also provides a computer program product including computer instructions, which, when executed by a processor, implement the above Figure 1 The various processes of the method embodiments described above can achieve the same technical effects, and will not be described again here to avoid repetition.

[0200] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

[0201] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0202] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another device, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0203] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0204] In addition, all functional units in the embodiments of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the above-mentioned integrated units can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0205] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, and other media that can store program codes.

[0206] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a device (which can be a terminal or platform, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks or optical disks.

[0207] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A building air conditioning control strategy generation method, characterized in that: The method comprises the following steps: Obtain status data for different areas within the building, as well as the overall operating status and operating scenario of the building; the status data includes at least the number of people in the current area i at time t, the ambient temperature, and the air conditioning power; Calculate the impact factor scores of the corresponding areas based on the obtained status data, including the personnel density score, function importance score, energy efficiency score, and time factor score; Adjust the weight coefficient of the influencing factor score according to the overall operating status and operating scenario of the building; The comprehensive score of the current area is calculated based on the scores of different influencing factors and the corresponding weight coefficients; Compare the comprehensive scores of different areas with the preset classification thresholds to determine the importance level of the corresponding areas; Different control strategies are generated according to the importance levels of different areas and distributed to the corresponding areas.

2. The method for generating a building air conditioning control strategy according to claim 1, wherein: The steps of calculating the personnel density scores of the corresponding areas according to the obtained status data include: Obtain the maximum number of people that can accommodate the corresponding area, the continuous occupancy time, and the average number of people in the same period in history; The first factor parameter of the current area at time t is calculated based on the number of people and the maximum number of people that can be accommodated in the corresponding area at time t; The second factor parameter of the current area at time t is calculated based on the continuous occupancy time of the corresponding area at time t; The third factor parameter of the current region at time t is calculated based on the number of people in the corresponding region at time t and the average number of people in the same period in history; The first factor parameter, the second factor parameter, and the third factor parameter are weighted and summed to obtain the population density score of the current area at time t.

3. The method for generating a building air conditioning control strategy according to claim 2, wherein: The steps of calculating the functional importance scores of the corresponding regions according to the obtained status data include: Get the regional function level of the corresponding area and the time period type at time t; Calculate the functional basic score of the current area according to the regional functional level of the corresponding area; Obtain the adjustment ratio of the corresponding time period type according to the time period type at time t in the corresponding area; Calculate the time adjustment factor at time t according to the adjustment ratio of the time period type at time t; The functional importance score of the current region at time t is calculated based on the functional basic score of the corresponding region and the time adjustment factor at time t.

4. The method for generating a building air conditioning control strategy according to claim 1, wherein: The step of calculating the energy efficiency scores of the corresponding areas according to the obtained status data further includes: Get the total number of zones in the building and the area of ​​different zones; The first unit area energy consumption of the current area at time t is calculated based on the air conditioning power and area of ​​the corresponding area at time t; Calculate the sum of the air conditioning power of all areas in the building and the sum of the area of ​​all areas in the building at time t; The second energy consumption per unit area is calculated based on the sum of the air conditioning powers and the sum of the area of ​​all areas in the building at time t; Comparing the first energy consumption per unit area with the second energy consumption per unit area: when the first energy consumption per unit area is less than or equal to the second energy consumption per unit area, determining that the current area is at a high efficiency level; when the first energy consumption per unit area is greater than the second energy consumption per unit area, determining that the current area is at a low efficiency level; Select the corresponding calculation coefficient according to the efficiency level of the current area; The energy efficiency score of the current area at time t is obtained according to the corresponding calculation coefficient, the first energy consumption per unit area, and the second energy consumption per unit area.

5. The method for generating a building air conditioning control strategy according to claim 1, wherein: The steps of respectively calculating the time factor scores of corresponding areas according to the obtained status data include: Get the maximum time score, actual usage time, and time period weight of the corresponding area; The time base score of the current area is calculated based on the maximum time score of the corresponding area and the time period weight corresponding to time t; Calculate the usage time coefficient of the current area based on the actual usage time of the corresponding area; The time factor score of the current area at time t is calculated based on the time base score of the corresponding area and the usage duration coefficient.

6. The building air conditioning control strategy generation method according to claim 1, characterized in that: The step of adjusting the weight coefficient of the influencing factor score according to the overall operating status and operating scenario of the building includes: Calculating the overall building operating status indicators respectively, wherein the operating status indicators include load rate indicators, comfort indicators, energy efficiency indicators and environmental indicators; The overall operating status index of the building is used as the feature vector of the operating scenario, and the current operating scenario is determined in combination with the scenario judgment rules; Obtain the adjustment coefficient of each influencing factor score under the current operating scenario according to the current operating scenario; The state response parameters of each influencing factor score are obtained by calculating the response strength and sensitivity of each influencing factor score in the current operation scenario in the corresponding area; The adjustment weight of the corresponding influencing factor score is obtained by calculating the adjustment coefficient of the corresponding area in the current operating scenario, the state response parameter and the original weight of each influencing factor score.

7. The method for generating a building air conditioning control strategy according to claim 1, wherein: The step of comparing the comprehensive scores of different areas with the preset classification thresholds to determine the importance level of the corresponding areas includes: Obtain the comprehensive score of the corresponding area at time t, and obtain the preset classification threshold; Smoothing the comprehensive score of the corresponding area at time t to obtain a revised comprehensive score; Compare the revised comprehensive score with the preset grading threshold to determine the threshold range to which it belongs; The importance level of the corresponding area is obtained according to the threshold interval.

8. The method for generating a building air conditioning control strategy according to claim 6, wherein: The scene judgment rules are optimized by machine learning. The specific optimization steps include: Acquiring historical operating data of the building, the historical operating data including at least feature vectors of different operating scenarios, determined operating scenarios, and operating performance; Use the historical operating data of the building to train the classifier, and extract judgment rules through the trained classifier; The extracted judgment rules are converted into a threshold comparison form to obtain the judgment threshold of the corresponding operation scenario.

9. The method for generating a building air conditioning control strategy according to claim 6, wherein: After obtaining the adjustment weight of the corresponding influencing factor score, the adjustment weight needs to be time-smoothed. During the time-smoothing process, the value range of the smoothing coefficient is set to [0.1, 0.5], and when the operation scene is switched, the smoothing coefficient approaches 0.5; when the operation scene is stable, the smoothing coefficient approaches 0.

1.

10. A building air conditioning control strategy generating device, characterized in that: The device comprises: A data acquisition module is used to obtain status data of different areas within the building, as well as the overall operating status and operating scenario of the building; the status data includes at least the number of people in the current area i at time t, the ambient temperature, and the air conditioning power; A score calculation module is used to calculate the influencing factor scores of the corresponding areas according to the obtained status data, wherein the influencing factor scores include the personnel density score, the function importance score, the energy efficiency score and the time factor score; A weight calculation module, used to adjust the weight coefficient of the influencing factor score according to the overall operating status and operating scenario of the building; The scoring calculation module is used to calculate the comprehensive score of the current area based on the scores of different influencing factors and the corresponding weight coefficients; An importance level determination module is used to compare the comprehensive scores of different areas with preset classification thresholds to determine the importance level of the corresponding area; The strategy generation module is used to generate different control strategies according to the importance levels of different areas and issue them to the corresponding areas.

11. An electronic device comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein: When the program or instruction is executed by a processor, the building air-conditioning control strategy generating method according to any one of claims 1 to 9 is implemented.

12. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by a processor, the building air-conditioning control strategy generating method according to any one of claims 1 to 9 is implemented.

Images