Central air conditioner management and control method and system based on load prediction

Abstract

The invention discloses a central air conditioner management and control method and system based on load prediction, relates to the technical field of central air conditioner control, and solves the problems that in the prior art, flexible adjustment cannot be carried out according to the load condition and the comfort degree after control, so that energy is wasted, and comfort is reduced. The method comprises the following steps: firstly, acquiring an instruction set and acquiring cost under each instruction; then predicting the load in the future control period and obtaining the temperature change condition in the future control period; and finally, the temperature change condition and the cost in the control period under each instruction are obtained, an optimal instruction is obtained based on the temperature change and the cost minimization principle, the optimal instruction is applied to complete control over the central air conditioner in the control period till the control period is finished, and the optimal instruction continues to be obtained in the next control period. Therefore, balance temperature control and cost control are comprehensively considered, and the cost can be controlled to a certain extent while the comfort degree is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of central air-conditioning control, and in particular to a central air-conditioning control method and system based on load forecasting. Background Art

[0002] A central air conditioning system provides centralized cooling and heating for large buildings or multiple rooms. It generates cooling or heating air through one or more large units and distributes this air to various areas via ducts or air ducts to maintain a comfortable indoor environment. This system offers the advantages of high efficiency, energy saving, and the ability to meet the needs of multiple areas simultaneously. It is widely used in commercial buildings, hospitals, schools, and large residences. It not only regulates temperature but also controls humidity, ventilation, and air quality, providing users with a comprehensive comfort experience. The design and operation of a central air conditioning system requires comprehensive consideration of multiple factors, including the building's structure, usage, occupant activity, and the external environment, to ensure efficient and stable operation and meet the needs of diverse users.

[0003] However, current central air conditioning control systems typically rely on real-time temperature measurements to generate temperature increase or decrease commands, failing to adequately consider comfort and cost efficiency. This control approach primarily focuses on ensuring the current temperature reaches the setpoint, while ignoring factors such as the rate of temperature change, indoor humidity, occupancy distribution, and equipment operating costs. For example, rapid temperature increases or decreases can lead to significant indoor temperature fluctuations, impacting occupant comfort. Furthermore, frequent equipment startups and shutdowns increase energy consumption and equipment wear, raising operating costs. Furthermore, this control approach struggles to adapt to the individual needs of different locations and lacks the flexibility to adjust based on load conditions and the desired comfort level, resulting in energy waste and reduced comfort. Therefore, current central air conditioning control systems lack the ability to balance temperature control and cost efficiency, requiring further optimization and improvement to achieve more intelligent, energy-efficient, and user-friendly operation.

[0004] In view of this, a central air-conditioning control method and system based on load forecasting is needed. Summary of the Invention

[0005] In response to the problem in the existing technology that it is impossible to flexibly adjust according to the load conditions and the comfort level after control, thus leading to energy waste and reduced comfort, the present invention provides a central air conditioning control method and system based on load prediction, which can predict the load in the future control cycle and, based on the load prediction in the future control cycle and the central air conditioning control situation under each instruction, derive the temperature change in the future control cycle. Finally, based on the principle of temperature change and cost minimization, the optimal instruction is obtained, which comprehensively considers the balanced temperature control and cost control aspects, and can control costs to a certain extent while improving the comfort level. The specific technical solution is as follows:

[0006] A central air conditioning control method based on load forecasting includes the following steps:

[0007] Obtain an instruction set and obtain the cost of each instruction, which is an instruction for controlling the operating state of the central air conditioner;

[0008] Predict loads within future control periods;

[0009] Based on the load forecast in the future control cycle and the central air-conditioning control status under each instruction, the temperature change in the future control cycle is obtained;

[0010] Obtain the temperature change and cost within the control cycle under each instruction, and derive the optimal instruction based on the principle of minimizing temperature change and cost;

[0011] The optimal instruction is applied to complete the control of the central air conditioner within the control cycle until the control cycle ends, and then the optimal instruction is continued to be obtained in the next control cycle.

[0012] Preferably, the process of obtaining the temperature change in the future control period is as follows:

[0013] Based on the load forecast, the control instructions of the central air conditioning system, and the thermal physical characteristics of the building, the temperature change within the future control period T is calculated as follows:

[0014]

[0015] Where, t represents time, W(t) represents the indoor temperature at time t; L(t) represents the load at time t; Q(t) represents the cooling or heating capacity of the central air-conditioning system at time t; C r Represents the heat capacity of the building.

[0016] Preferably, the calculation process of the cooling or heating capacity of the central air-conditioning system is as follows:

[0017] Q c (t)=S(t)×Q c,rated ×ηc (t)

[0018] Q h (t)=S(t)×Q h,rated ×η h (t)

[0019] Where Q c (t) represents the cooling capacity, Q h (t) represents the heating capacity; S(t) represents the system status at time t, with a value of 1 indicating on and a value of 0 indicating off; Q c,rated Indicates the rated cooling capacity of the central air-conditioning system; Q h,rated Indicates the rated heating capacity of the central air-conditioning system; η c (t) represents the cooling efficiency at time t; η h (t) represents the heating efficiency at time t.

[0020] Preferably, the cooling efficiency η c (t) and heating efficiency η h The calculation formula of (t) is as follows:

[0021] η c (t) = η c,basc ×(1-α c ×|W(t)-W s (t)|)×(1+β c ×F(t))

[0022] η h (t) = η c,basc ×(1-α h ×|W(t)-W s (t)|)×(1+β h ×F(t))

[0023] Among them, η c,basc Indicates the basic refrigeration efficiency; η h,basc Indicates basic heating efficiency; α c Indicates the coefficient of influence of temperature difference on efficiency in cooling mode; α h Indicates the coefficient of influence of temperature difference on efficiency in heating mode; β c In cooling mode, the coefficient of wind speed on efficiency; β h In heating mode, the coefficient of wind speed on efficiency; W s (t) represents the set temperature; F(t) represents the wind speed.

[0024] Preferably, the temperature change and cost within the control cycle under each instruction are represented by a temperature-cost comprehensive function, and the calculation formula of the temperature-cost comprehensive function is as follows:

[0025]

[0026] Among them, μ1 and μ2 are weight coefficients, is the average temperature within the control period T, W(t) represents the indoor temperature at time t, T is the control period, C 电费 Indicates the cost of electricity.

[0027] Preferably, the electricity cost calculation is shown as follows:

[0028]

[0029] Among them, C 电费 Indicates the electricity cost, F 额定_i represents the rated power of the i-th central air conditioner. There are n central air conditioners in total. δ i represents the adjustment coefficient of the i-th central air conditioner, T represents the control period, R d Indicates the unit electricity price.

[0030] Preferably, the specific steps of predicting the load in the future control period are as follows:

[0031] Collect historical data: The data includes at least indoor temperature, outdoor temperature, central air conditioning system operating status, operating mode, set temperature, wind speed, number of people indoors, indoor equipment usage, and weather conditions;

[0032] Data preprocessing: Data preprocessing includes data cleaning, data standardization, and data segmentation. Data segmentation divides the data into training and test sets.

[0033] Build and train the prediction model: select the prediction model and adjust the model parameters during the training process, by continuously adjusting the model parameters and optimizing the training process;

[0034] Model validation: Use test set data to validate the model;

[0035] Input future conditions: After completing model training and validation, the conditions within the future control period T are input into the prediction model;

[0036] Predicting future load: After inputting future conditions into the prediction model, the model will output the load L(t) within the future control period T.

[0037] A central air conditioning control system based on load forecasting, applied to the above method, comprises:

[0038] An instruction generation unit is configured to obtain an instruction set and a cost of each instruction, wherein the instruction is an instruction for controlling the operation state of the central air conditioner, and the instruction includes at least one or more of the following: turning on the central air conditioner system, turning off the central air conditioner system, operating mode, set temperature, and wind speed;

[0039] Load forecasting unit, which builds and trains a forecasting model to predict the load L(t) in the future control period;

[0040] The temperature change prediction unit calculates the temperature change in the future control cycle based on the load prediction in the future control cycle and the central air conditioning control status under each instruction;

[0041] The optimal instruction output unit obtains the temperature change and cost within the control cycle under each instruction, and derives the optimal instruction based on the principle of minimizing temperature change and cost.

[0042] A computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the central air-conditioning control method based on load forecasting as described above.

[0043] A processor is used to run a program, wherein when the program is run, the central air-conditioning control method based on load forecasting as described above is executed.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention first obtains an instruction set and obtains the cost under each instruction, which is an instruction for controlling the operating state of the central air conditioner; then predicts the load in the future control cycle and, based on the load prediction in the future control cycle and the central air conditioner control status under each instruction, obtains the temperature change in the future control cycle; finally, obtains the temperature change and cost in the control cycle under each instruction, and obtains the optimal instruction based on the principle of minimizing temperature change and cost, applies the optimal instruction to complete the control of the central air conditioner in the control cycle, and continues to obtain the optimal instruction in the next control cycle until the control cycle ends. Therefore, the present invention comprehensively considers the aspects of balancing temperature control and cost control, and can control costs to a certain extent while improving comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly describes the drawings required for the specific embodiments or the description of the prior art. Similar elements or parts are generally identified by similar reference numerals throughout the drawings. Elements or parts in the drawings are not necessarily drawn to scale.

[0047] Figure 1 Flow chart of the method of the present invention. DETAILED DESCRIPTION

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0049] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0050] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0051] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0052] In one embodiment of the present invention, a central air conditioning control method based on load forecasting is provided. Figure 1 As shown, the following steps are included:

[0053] Step 1: Get the instruction set;

[0054] The command set described above is for controlling the central air conditioner, and includes at least one or more of the following: system on / off, operating mode (cooling, heating, ventilation, etc.), set temperature, and wind speed. If a building contains multiple central air conditioner units, a single command controls multiple units, and similarly, includes at least one or more of the following: system on / off, operating mode (cooling, heating, ventilation, etc.), set temperature, and wind speed.

[0055] Step 2: Obtain the cost of each instruction. In this embodiment, the cost is the electricity cost.

[0056] For each instruction, the cost under the instruction (i.e., a certain operating state of the central air conditioner) is calculated. In this embodiment, the cost of the central air conditioner under the instruction is represented by the electricity cost. The calculation is shown as follows:

[0057]

[0058] Among them, C 电费 Indicates the electricity cost, F 额定_i represents the rated power of the i-th central air conditioner. There are n central air conditioners in total. δ i represents the adjustment coefficient of the i-th central air conditioner, T represents the control period, R d Indicates the unit electricity price.

[0059] Step 3: Forecast the load in the future control period;

[0060] The load within the future control period can be predicted by building a prediction model using existing models, such as a linear regression model, a polynomial regression model, an artificial neural network model, a support vector machine model, a random forest model, a time series model (such as an ARIMA model), etc. It should be understood that those skilled in the art can select and build a prediction model based on actual conditions, and the present invention does not limit this.

[0061] For example, a method for predicting the load in a future control period is given below. The specific steps are as follows:

[0062] S1: Collect historical data: It is necessary to collect load data from the building over a period of time. This data includes, but is not limited to, indoor temperature, outdoor temperature, central air conditioning system operating status (on, off), operating mode (cooling, heating, ventilation), set temperature, wind speed, number of occupants indoors, indoor equipment usage, and weather conditions (such as solar radiation, wind speed, humidity, etc.). This data can be obtained from sources such as the building's automated control system, weather stations, and sensors. The collected data should be as detailed and accurate as possible to provide sufficient information for subsequent prediction models.

[0063] S2: Data preprocessing: Data preprocessing includes data cleaning, data standardization and data segmentation. The purpose of data cleaning is to remove outliers in the data and fill missing values. Outliers are identified and removed by statistical analysis methods (such as box plots). Missing values ​​can be filled by interpolation methods (such as linear interpolation) or using the average value of adjacent data points. The purpose of data standardization is to convert the data into a unified unit and range so that data from different sources can be compared and analyzed. The purpose of data segmentation is to divide the data into a training set and a test set. The training set is used to train the prediction model, and the test set is used to verify the prediction accuracy and generalization ability of the model. Exemplarily, this embodiment uses 70% of the data as a training set and 30% as a test set.

[0064] S3: Select a forecasting model: You can choose from a variety of forecasting models, including linear regression models, polynomial regression models, artificial neural network models, support vector machine models, random forest models, and time series models (such as ARIMA models).

[0065] S4: Training the prediction model: Adjust the model parameters during the training process so that the model can accurately fit the historical data. For linear regression models, the model parameters can be estimated using the least squares method. For artificial neural network models, the network weights need to be optimized using the backpropagation algorithm and gradient descent method. For support vector machine models, it is necessary to select a suitable kernel function and adjust the regularization parameters. For random forest models, it is necessary to determine the number and depth of decision trees. During the training process, it is also necessary to use methods such as cross-validation to evaluate the performance of the model to avoid overfitting or underfitting problems. By continuously adjusting the model parameters and optimizing the training process, the prediction model can be better adapted to historical data and the prediction accuracy can be improved.

[0066] S5: Model Validation: The model is validated using the test set data. Common validation indicators include mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The mean square error (MSE) is the average of the squares of the differences between the predicted value and the actual value, and is used to measure the magnitude of the prediction error. The root mean square error (RMSE) is the square root of the MSE, which is consistent with the unit of the original data and more intuitively reflects the magnitude of the prediction error. The mean absolute error (MAE) is the average of the absolute values ​​of the differences between the predicted value and the actual value and is insensitive to outliers. The coefficient of determination (R2) reflects the degree of fit of the model to the data. The closer the value is to 1, the better the fit. Through these validation indicators, the performance of the model can be comprehensively evaluated, and the model with the best performance can be selected for subsequent load forecasting.

[0067] S6: Input future conditions: After model training and validation, the conditions for the future control period T are input into the prediction model. These conditions include weather forecasts (such as outdoor temperature, solar radiation, wind speed, and humidity), building usage plans (such as indoor occupancy and equipment usage), and central air conditioning system operation plans (such as set temperature and operating mode). These conditions can be obtained through weather forecast data, building management systems, and user input.

[0068] Step 7: Forecasting Future Load: After inputting future conditions into the forecasting model, the model outputs the load L(t) for the future control period T. The forecast results can be presented in the form of load curves or load tables. The load curve visually displays the load trend over time, helping users understand peak and trough periods. The load table provides detailed load data for further analysis and processing. The accuracy of the forecast results depends on the model selection, training, and validation process, as well as the accuracy of the input conditions.

[0069] Step 4: Based on the load forecast in the future control cycle and the central air conditioning control status under each instruction, the temperature change in the future control cycle is obtained;

[0070] In this embodiment, based on the load forecast, the control instructions of the central air conditioning system, and the thermophysical characteristics of the building, the temperature change in the future control period T is calculated as follows:

[0071]

[0072] Where, t represents time, W(t) represents the indoor temperature at time t (unit: °C), L(t) represents the load at time t (unit: kW), and Q(t) represents the cooling or heating capacity of the central air-conditioning system at time t (unit: kW) obtained from step 3. r Indicates the heat capacity of a building (unit: kWh / ℃).

[0073] The above formula takes into account a variety of influencing factors and can more accurately reflect the actual situation. First, based on the principle of energy conservation, the formula links the heat change of the building (determined by the load L(t) and the cooling or heating capacity Q(t) of the central air-conditioning system) with the temperature change, and calculates the heat capacity C r To quantify this relationship, it is possible to predict the temperature change over time. Secondly, the formula takes into account the actual operating state of the central air-conditioning system (determined by the control instructions S(t), M(t), T s The influence of the cooling or heating capacity on the building is determined by the following parameters: S(t): system status at time t (1 means on, 0 means off); M(t): operating mode at time t (cooling, heating, ventilation); Ts(t): set temperature at time t (unit: °C); F(t): wind speed at time t (unit: m / s); and the influence of the building's thermal physical characteristics (such as heat capacity C r and thermal resistance R r ), making the prediction results closer to actual operating conditions. However, it should be noted that in actual applications, the thermal physical characteristics of buildings may be more complex and there may be other interfering factors. Therefore, it may be necessary to adjust and optimize the model according to the specific situation to improve the accuracy of the prediction.

[0074] Heat capacity of the building C rThermal capacity refers to the total amount of heat stored or released by a building per unit temperature change, typically expressed in kWh / °C. It reflects a building's "inertia" to temperature changes: buildings with large thermal capacity experience relatively slow temperature changes for the same heat input or output, while buildings with small thermal capacity experience rapid temperature changes. Thermal capacity depends primarily on factors such as the building's structure, materials, and volume. For example, thick walls and larger interior spaces increase a building's thermal capacity. Thermal capacity is a key parameter when calculating future temperature changes within a control period, T. It determines the rate of temperature change for a given heat exchange rate, thus influencing predicted temperature changes.

[0075] The calculation process of the cooling or heating capacity of the central air conditioning system is as follows:

[0076] Q c (t)=S(t)×Q c,rated ×η c (t)

[0077] Q h (t)=S(t)×Q h,rated ×η h (t)

[0078] Where Q c (t) represents the cooling capacity, Q h (t) represents the heating capacity; S(t) represents the system status at time t, with a value of 1 indicating on and a value of 0 indicating off; Q c,rated Indicates the rated cooling capacity of the central air-conditioning system (unit: kW); Q h,rated Indicates the rated heating capacity of the central air-conditioning system (unit: kW); η c (t) represents the cooling efficiency at time t, which is usually a coefficient less than 1 and represents the ratio of the actual cooling capacity to the rated cooling capacity; η h (t) represents the heating efficiency at time t, which is usually a coefficient less than 1, indicating the ratio of actual heating capacity to rated heating capacity.

[0079] In this embodiment, the cooling efficiency η c (t) and heating efficiency η h The factors of (t) only consider the set temperature, wind speed and indoor and outdoor temperature difference. Therefore, the cooling efficiency η c (t) and heating efficiency η h The calculation formula of (t) is as follows:

[0080] η c (t) = η c,basc ×(1-α c ×|W(t)-W s (t)|)×(1+β c×F(t))

[0081] η h (t) = η c,basc ×(1-α h ×|W(t)-W s (t)|)×(1+β h ×F(t))

[0082] Among them, η c,basc represents the basic refrigeration efficiency (usually close to 1, and is taken as 1 in this embodiment); η h,basc represents the basic heating efficiency (usually close to 1, and is taken as 1 in this embodiment); α c Indicates the coefficient of influence of temperature difference on efficiency in cooling mode (unit: 1 / ℃); α h Indicates the coefficient of influence of temperature difference on efficiency in heating mode (unit: 1 / ℃); β c In cooling mode, the coefficient of wind speed on efficiency (unit: 1 / (m / s)); β h In heating mode, the coefficient of wind speed on efficiency (unit: 1 / (m / s)); W s (t) represents the set temperature, which can be obtained from the instruction; F(t) represents the wind speed, which can be obtained from the instruction.

[0083] Step 5: Obtain the temperature-cost comprehensive function for each instruction, and derive the optimal instruction based on the principle of temperature change and cost minimization;

[0084] The temperature-cost comprehensive function is expressed as follows:

[0085]

[0086] Among them, μ1 and μ2 are weight coefficients, is the average temperature within the control period T.

[0087] The temperature-cost comprehensive function corresponding to each instruction in the instruction set is calculated, and the instruction with the smallest temperature-cost comprehensive function is selected as the final central air-conditioning control instruction.

[0088] Step 6: Apply the optimal instruction to complete the control of the central air conditioner within the control cycle. When the control cycle ends, repeat the above steps in the next control cycle to obtain the control instruction for that cycle.

[0089] In one embodiment of the present invention, a central air conditioning control system based on load forecasting is provided, which is applied to the above method and includes:

[0090] An instruction generation unit is configured to obtain an instruction set and a cost of each instruction, wherein the instruction is an instruction for controlling the operation state of the central air conditioner, and the instruction includes at least one or more of the following: turning on the central air conditioner system, turning off the central air conditioner system, operating mode, set temperature, and wind speed;

[0091] Load forecasting unit, which builds and trains a forecasting model to predict the load L(t) in the future control period;

[0092] The temperature change prediction unit calculates the temperature change in the future control cycle based on the load prediction in the future control cycle and the central air conditioning control status under each instruction;

[0093] The optimal instruction output unit obtains the temperature change and cost within the control cycle under each instruction, and derives the optimal instruction based on the principle of minimizing temperature change and cost.

[0094] In summary, the present invention first obtains an instruction set and obtains the cost under each instruction, which is an instruction for controlling the operating state of the central air conditioner; then predicts the load in the future control cycle and, based on the load prediction in the future control cycle and the central air conditioner control situation under each instruction, obtains the temperature change in the future control cycle; finally, obtains the temperature change and cost in the control cycle under each instruction, and obtains the optimal instruction based on the principle of minimizing temperature change and cost, applies the optimal instruction to complete the control of the central air conditioner in the control cycle, until the control cycle ends, and then continues to obtain the optimal instruction in the next control cycle. Therefore, the present invention comprehensively considers the aspects of balancing temperature control and cost control, and can control costs to a certain extent while improving comfort.

[0095] Those skilled in the art will appreciate that the units of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0096] In the embodiments provided by the present invention, it should be understood that the division of units is merely a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0097] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0098] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nly Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc., various media that can store program code.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention.

Claims

1. A central air conditioning control method based on load forecasting, characterized in that: The following steps are involved: Obtain an instruction set and obtain the cost of each instruction, which is an instruction for controlling the operating state of the central air conditioner; Predict loads within future control periods; Based on the load forecast in the future control cycle and the central air-conditioning control status under each instruction, the temperature change in the future control cycle is obtained; Obtain the temperature change and cost within the control cycle under each instruction, and derive the optimal instruction based on the principle of minimizing temperature change and cost; The optimal instruction is applied to complete the control of the central air conditioner within the control cycle until the control cycle ends, and then the optimal instruction is continued to be obtained in the next control cycle.

2. A central air conditioning control method based on load forecasting according to claim 1, characterized in that: The process of obtaining the temperature change in the future control cycle is as follows: Based on the load forecast, the control instructions of the central air conditioning system, and the thermal physical characteristics of the building, the temperature change within the future control period T is calculated as follows: Where, t represents time, W(t) represents the indoor temperature at time t; L(t) represents the load at time t; Q(t) represents the cooling or heating capacity of the central air-conditioning system at time t; C r Represents the heat capacity of the building.

3. A central air conditioning control method based on load forecasting according to claim 2, characterized in that: The calculation process of the cooling or heating capacity of the central air conditioning system is as follows: Q c (t)=S(t)×Q c,rated ×η c (t) Q h (t)=S(t)×Q h,rated ×η h (t) Where Q c (t) represents the cooling capacity, Q h (t) represents the heating capacity; S(t) represents the system status at time t, with a value of 1 indicating on and a value of 0 indicating off; Q c,rated Indicates the rated cooling capacity of the central air-conditioning system; Q h,rated Indicates the rated heating capacity of the central air-conditioning system; η c (t) represents the cooling efficiency at time t; η h (t) represents the heating efficiency at time t.

4. A central air conditioning control method based on load forecasting according to claim 3, characterized in that: Refrigeration efficiency η c (t) and heating efficiency η h The calculation formula of (t) is as follows: or c (t)=η c,basc ×(1-a c ×|W(t)-W s (t)|)×(1+β c ×F(t)) or h (t)=η c,basc ×(1-a h ×|W(t)-W s (t)|)×(1+β h ×F(t)) Among them, η c,basc Indicates the basic refrigeration efficiency; η h,basc Indicates basic heating efficiency; α c Indicates the coefficient of influence of temperature difference on efficiency in cooling mode; α h Indicates the coefficient of influence of temperature difference on efficiency in heating mode; β c In cooling mode, the coefficient of wind speed on efficiency; β h In heating mode, the coefficient of wind speed on efficiency; W s (t) represents the set temperature; F(t) represents the wind speed.

5. The central air conditioning control method based on load forecasting according to claim 1 is characterized in that: The temperature change and cost within the control cycle of each instruction are expressed by the temperature-cost comprehensive function. The calculation formula of the temperature-cost comprehensive function is as follows: Among them, μ1 and μ2 are weight coefficients, is the average temperature within the control period T, W(t) represents the indoor temperature at time t, T is the control period, C 电费 Indicates the cost of electricity.

6. A central air conditioning control method based on load forecasting according to claim 1, characterized in that: The electricity cost calculation is as follows: Among them, C 电费 Indicates the electricity cost, F 额定_i represents the rated power of the i-th central air conditioner. There are n central air conditioners in total. δ i represents the adjustment coefficient of the i-th central air conditioner, T represents the control period, R d Indicates the unit electricity price.

7. A central air conditioning control method based on load forecasting according to claim 1, characterized in that: The specific steps for predicting the load in the future control period are as follows: Collect historical data: The data includes at least indoor temperature, outdoor temperature, central air conditioning system operating status, operating mode, set temperature, wind speed, number of people indoors, indoor equipment usage, and weather conditions; Data preprocessing: Data preprocessing includes data cleaning, data standardization, and data segmentation. Data segmentation divides the data into training and test sets. Build and train the prediction model: select the prediction model and adjust the model parameters during the training process, by continuously adjusting the model parameters and optimizing the training process; Model validation: Use test set data to validate the model; Input future conditions: After completing model training and validation, the conditions within the future control period T are input into the prediction model; Predicting future load: After inputting future conditions into the prediction model, the model will output the load L(t) within the future control period T.

8. A central air conditioning control system based on load forecasting, characterized in that: The method applied to any one of claims 1 to 7, comprising: An instruction generation unit is configured to obtain an instruction set and a cost of each instruction, wherein the instruction is an instruction for controlling the operation state of the central air conditioner, and the instruction includes at least one or more of the following: turning on the central air conditioner system, turning off the central air conditioner system, operating mode, set temperature, and wind speed; Load forecasting unit, which builds and trains a forecasting model to predict the load L(t) in the future control period; The temperature change prediction unit calculates the temperature change in the future control cycle based on the load prediction in the future control cycle and the central air conditioning control status under each instruction; The optimal instruction output unit obtains the temperature change and cost within the control cycle under each instruction, and derives the optimal instruction based on the principle of minimizing temperature change and cost.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the central air-conditioning control method based on load forecasting according to any one of claims 1 to 7.

10. A processor, characterized in that: The processor is used to run a program, wherein when the program is run, the central air-conditioning control method based on load forecasting according to any one of claims 1 to 7 is executed.

Images