Method, device and equipment for operating a temperature regulating device, and storage medium

Abstract

The embodiment of the application provides a kind of temperature regulating equipment operation control method, device, equipment and storage medium, the method comprises: obtaining the first running parameter of communication equipment in communication machine room at first time;According to the first running parameter and the first constraint condition and the second constraint condition that have been determined, the first target function that has been constructed is solved, and the power consumption prediction value of the first temperature regulating equipment in communication machine room is obtained;The first target function takes the minimum of the power consumption prediction value of the first temperature regulating equipment as target;First constraint condition is used to indicate that the power consumption value of the first temperature regulating equipment is within the first range, and the second constraint condition is used to indicate that at least one parameter in the second running parameter of the second temperature regulating equipment is within the corresponding second range;According to the power consumption prediction value obtained by solving, the second running parameter is adjusted.

Description

Technical Field

[0001] This invention relates to the field of mobile communication technology, and in particular to a method, apparatus, device, and storage medium for operating a temperature regulation device. Background Technology

[0002] Communication equipment rooms typically house multiple communication devices, each with specific temperature requirements for operation. These temperature requirements highlight the importance of maintaining stable equipment performance, which is crucial for ensuring uninterrupted communication.

[0003] Currently, the temperature inside communication equipment rooms can be regulated using temperature control devices (such as air conditioners) to maintain the equipment within the range required for normal operation. However, some temperature control devices, such as air conditioners, consume electricity, and these devices are among the key energy-consuming components in communication equipment rooms. Statistics show that air conditioners account for 30%-50% of the total electricity consumption in communication equipment rooms.

[0004] Currently, to save on the electricity consumption of temperature control equipment such as air conditioners, air cooling, water cooling, and other new energy-saving methods can be used. However, these methods require significant investment and are not suitable for all environmental conditions. Therefore, these new energy-saving methods are not suitable for small and medium-sized computer rooms with energy-saving needs. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for controlling the operation of a temperature control device, in order to solve the problem that the existing methods of using air cooling and water cooling to reduce the power consumption of temperature control devices in communication equipment rooms are costly and therefore unsuitable for small and medium-sized equipment rooms.

[0006] In a first aspect, embodiments of this application provide an operation control method for a temperature regulating device, the method comprising:

[0007] Obtain the first operating parameters of the communication equipment in the communication room at the first moment;

[0008] Based on the first operating parameters and the determined first and second constraints, the constructed first objective function is solved to obtain the predicted power consumption value of the first temperature control device in the communication equipment room. The first objective function aims to minimize the predicted power consumption value of the first temperature control device, and it indicates that there is a functional relationship between the input parameters and the predicted power consumption value of the first temperature control device through a power consumption prediction model. The input parameters include the first operating parameters and the second operating parameters of the second temperature control device in the communication equipment room. The first constraint indicates that the power consumption value of the first temperature control device is within a first range, and the second constraint indicates that at least one of the second operating parameters of the second temperature control device is within a corresponding second range.

[0009] Based on the power consumption prediction value obtained from the solution, the second operating parameters are adjusted so that the difference between the power consumption value of the first temperature regulating device at the second time and the power consumption prediction value obtained from the solution is less than or equal to the first threshold.

[0010] Secondly, embodiments of this application provide an operation control device for a temperature regulating device, the device comprising:

[0011] The first acquisition module is used to acquire the first operating parameters of the communication equipment in the communication room at the first moment.

[0012] The solution module is used to solve the constructed first objective function based on the first operating parameters and the determined first and second constraints to obtain the predicted power consumption value of the first temperature control device in the communication equipment room. The first objective function aims to minimize the predicted power consumption value of the first temperature control device, and it indicates that there is a functional relationship between the input parameters and the predicted power consumption value of the first temperature control device through a power consumption prediction model. The input parameters include the first operating parameters and the second operating parameters of the second temperature control device in the communication equipment room. The first constraint indicates that the power consumption value of the first temperature control device is within a first range, and the second constraint indicates that at least one of the second operating parameters of the second temperature control device is within a corresponding second range.

[0013] The adjustment control module is used to adjust the second operating parameters according to the power consumption prediction value obtained by the solution, so that the difference between the power consumption value of the first temperature regulating device at the second time and the power consumption prediction value obtained by the solution is less than or equal to the first threshold.

[0014] Thirdly, embodiments of this application provide an electronic device, including a memory, a transceiver, and a processor:

[0015] The memory is used to store computer programs; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer programs in the memory and execute the operation control method of the temperature regulating device described in the first aspect above.

[0016] Fourthly, embodiments of this application provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the operation control method for the temperature regulating device described in the first aspect.

[0017] In this embodiment, the first operating parameters of the communication equipment in the communication room at a first time can be obtained. Based on the first operating parameters and the determined first and second constraints, the constructed first objective function is solved to obtain the predicted power consumption value of the first temperature regulating device in the communication room. Then, based on the solved predicted power consumption value, the second operating parameters are adjusted so that the difference between the power consumption value of the first temperature regulating device at a second time and the solved predicted power consumption value is less than or equal to a first threshold.

[0018] The first objective function aims to minimize the predicted power consumption of the first temperature control device, and it indicates that there is a functional relationship between the input parameters and the predicted power consumption of the first temperature control device through a power consumption prediction model. The input parameters include the first operating parameters and the second operating parameters of the second temperature control device in the communication room. The first constraint condition indicates that the power consumption of the first temperature control device is within a first range, and the second constraint condition indicates that at least one of the second operating parameters of the second temperature control device is within a corresponding second range.

[0019] As can be seen, in this embodiment, the predicted power consumption of the first temperature regulating device can be minimized, ensuring that the power consumption of the first temperature regulating device is within a first range, and that at least one parameter of the second operating parameters of the second temperature regulating device is within a corresponding second range. The power consumption of the first temperature regulating device is related to the temperature inside the communication equipment room. If the power consumption of the first temperature regulating device is within the first range, the temperature inside the communication equipment room is within the temperature range required for the normal operation of the communication equipment. Thus, based on the calculated predicted power consumption, the second operating parameters of the second temperature regulating device are automatically adjusted. This ensures that the temperature inside the communication equipment room is within the temperature range required for the normal operation of the communication equipment, and that the second operating parameters are within a reasonable range, while minimizing the power consumption of the first temperature regulating device. The entire process does not involve additional equipment such as air cooling or water cooling. Therefore, the embodiment of this application can solve the problem that the existing methods of using air cooling or water cooling to reduce the power consumption of temperature regulating devices in communication equipment rooms are costly and unsuitable for small and medium-sized equipment rooms. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating the operation control method of the temperature regulating device provided in this application embodiment;

[0022] Figure 2 This is a schematic diagram of the structure of the CNN temporal feature input layer in an embodiment of this application;

[0023] Figure 3 This is a schematic diagram of the CNN convolutional pooling layer structure in the embodiments of this application;

[0024] Figure 4 This is a schematic diagram of the CNN fully connected layer structure in an embodiment of this application;

[0025] Figure 5 This is a flowchart illustrating the multi-strategy constrained differential evolution algorithm based on population partitioning in an embodiment of this application.

[0026] Figure 6 This is a schematic diagram illustrating a specific implementation of the operation control method for the temperature regulating device in this application.

[0027] Figure 7 A structural block diagram of the operation control device for a temperature regulating device provided in the embodiments of this application;

[0028] Figure 8 A structural block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0029] In the embodiments of this application, the term "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0030] In the embodiments of this application, the term "multiple" refers to two or more, and other quantifiers are similar.

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0032] This application provides a method, apparatus, device, and storage medium for operating and controlling a temperature control device, in order to solve the problem that the existing methods of using air cooling and water cooling to reduce the power consumption of temperature control devices in communication equipment rooms are costly and therefore unsuitable for small and medium-sized equipment rooms.

[0033] The method and apparatus are based on the same concept of the application. Since the methods and apparatus solve problems in similar ways, the implementation of the apparatus and methods can refer to each other, and the repeated parts will not be described again.

[0034] See Figure 1 As shown, an embodiment of this application provides an operation control method for a temperature regulating device, the method including the following steps 101 to 103:

[0035] Step 101: Obtain the first operating parameters of the communication equipment in the communication room at the first moment.

[0036] The first operating parameter may include at least one of the following: the current value of the communication equipment, the temperature of the environment in which the communication equipment is located (i.e., inside the communication equipment room), and the temperature outside the communication equipment room.

[0037] The communication equipment may include at least one of the following: device A (i.e., access layer device), device B (i.e., aggregation layer device), optical line terminal (OLT), broadband remote access server (BRAS), wavelength division multiplexing (WDM) equipment, building base band unit (BBU), remote radio unit (RRU), and switch.

[0038] In addition, the first time can be the current time.

[0039] Step 102: Based on the first operating parameters and the determined first and second constraints, solve the constructed first objective function to obtain the predicted power consumption value of the first temperature control device in the communication room.

[0040] Wherein, the first objective function aims to minimize the predicted power consumption of the first temperature regulating device, and the first objective function is used to indicate that there is a functional relationship between the input parameters and the predicted power consumption of the first temperature regulating device through a power consumption prediction model. The input parameters include the first operating parameters and the second operating parameters of the second temperature regulating device in the communication equipment room. The first constraint condition is used to indicate that the power consumption of the first temperature regulating device is within a first range, and the second constraint condition is used to indicate that at least one of the second operating parameters of the second temperature regulating device is within a corresponding second range.

[0041] As can be seen, in this embodiment of the application, the first constraint condition can ensure that the power consumption of the first temperature regulating device is within a reasonable range during the process of solving the minimum power consumption prediction value of the first temperature regulating device; the second constraint condition can ensure that at least one parameter of the second operating parameters of the second temperature regulating device is within a reasonable range during the process of solving the minimum power consumption prediction value of the first temperature regulating device, so as to ensure the normal operation of the second temperature regulating device.

[0042] In addition, the first temperature regulating device can be an air conditioner; the second temperature regulating device can include at least the first temperature regulating device, or the second temperature regulating device can include temperature regulating devices other than the first temperature regulating device; for example, the second temperature regulating device can include at least one of an air conditioner, a computer room fan, and a duct switch. In this case, the second operating parameter can include at least one of the following: air conditioner setting value, computer room fan speed, and duct switch opening degree.

[0043] It is understandable that each of the devices included in the second temperature regulation device may have at least one corresponding parameter in the second operating parameters.

[0044] It should be noted that the power consumption of the first temperature regulating device is related to the temperature inside the communication equipment room. The first range is determined based on the temperature range required for the normal operation of the communication equipment inside the communication equipment room. Thus, when the power consumption of the first temperature regulating device is within the first range, it indicates that the temperature inside the communication equipment room is within the temperature range required for the normal operation of the communication equipment.

[0045] Furthermore, in this embodiment, the input to the power consumption prediction model includes: the first operating parameters of the first temperature regulating device and the second operating parameters of the second temperature regulating device, and the output includes: the predicted power consumption value of the first temperature regulating device. The power consumption prediction model can be pre-trained using training samples, which may include: the first operating parameters of the first temperature regulating device, the second operating parameters of the second temperature regulating device, and the actual power consumption value of the first temperature regulating device. It is understood that the process of training the power consumption prediction model based on the training samples can employ existing training methods, which will not be elaborated here.

[0046] Step 103: Adjust the second operating parameters according to the power consumption prediction value obtained by solving, so that the difference between the power consumption value of the first temperature regulating device at the second time and the power consumption prediction value obtained by solving is less than or equal to the first threshold.

[0047] If the difference between the power consumption value of the first temperature regulating device at the second time and the power consumption prediction value obtained by the solution is less than or equal to the first threshold, it means that the power consumption value of the first temperature regulating device at the second time is close to the power consumption prediction value, or can be approximately equal to the power consumption prediction value.

[0048] As can be seen from steps 101 to 103 above, in this embodiment of the application, the first operating parameters of the communication equipment in the communication room at the first time can be obtained. Then, based on the first operating parameters and the already determined first and second constraints, the constructed first objective function is solved to obtain the power consumption prediction value of the first temperature regulating device in the communication room. Then, based on the power consumption prediction value obtained by the solution, the second operating parameters are adjusted so that the difference between the power consumption value of the first temperature regulating device at the second time and the power consumption prediction value obtained by the solution is less than or equal to the first threshold.

[0049] The first objective function aims to minimize the predicted power consumption of the first temperature control device, and it indicates that there is a functional relationship between the input parameters and the predicted power consumption of the first temperature control device through a power consumption prediction model. The input parameters include the first operating parameters and the second operating parameters of the second temperature control device in the communication room. The first constraint condition indicates that the power consumption of the first temperature control device is within a first range, and the second constraint condition indicates that at least one of the second operating parameters of the second temperature control device is within a corresponding second range.

[0050] As can be seen, in this embodiment, the predicted power consumption of the first temperature regulating device can be minimized, ensuring that the power consumption of the first temperature regulating device is within a first range, and that at least one parameter of the second operating parameters of the second temperature regulating device is within a corresponding second range. The power consumption of the first temperature regulating device is related to the temperature inside the communication equipment room. If the power consumption of the first temperature regulating device is within the first range, the temperature inside the communication equipment room is within the temperature range required for the normal operation of the communication equipment. Thus, based on the calculated predicted power consumption, the second operating parameters of the second temperature regulating device are automatically adjusted. This ensures that the temperature inside the communication equipment room is within the temperature range required for the normal operation of the communication equipment, and that the second operating parameters are within a reasonable range, while minimizing the power consumption of the first temperature regulating device. The entire process does not involve additional equipment such as air cooling or water cooling. Therefore, the embodiment of this application can solve the problem that the existing methods of using air cooling or water cooling to reduce the power consumption of temperature regulating devices in communication equipment rooms are costly and unsuitable for small and medium-sized equipment rooms.

[0051] Optionally, the power consumption prediction model is a Convolutional Neural Network (CNN) model. It is understood that other types of deep learning models can also be used for power consumption prediction, which will not be elaborated upon here.

[0052] CNN is a deep learning model widely used in image and video recognition, recommendation systems, and natural language processing. In this embodiment, the CNN model is used to predict the power consumption of the first temperature regulating device.

[0053] To facilitate understanding of the specific computational processes involved in CNN models, the following example is provided:

[0054] First, the input to the CNN model includes a first set of operating parameters and a second set of operating parameters. For example, the first set of operating parameters includes the current values ​​x of the eight communication devices, the indoor temperature t of the communication equipment room, and the outdoor temperature d of the communication equipment room. The second set of operating parameters includes the air conditioning setpoint r1, the equipment room fan speed r1, and the duct switch r1. Figure 2 As shown, the values ​​of the above parameters can be collected at the current time k; then the input data of the CNN model can be represented as follows:

[0055]

[0056] Secondly, the CNN model includes convolutional layers, pooling layers, fully connected layers, and an integrated output layer. These layers are described in detail below:

[0057] I. Convolutional Layer:

[0058] Convolutional layers extract features by perceiving local features of data through convolutional kernels. In this embodiment, a convolutional kernel of dimension h×1 can be used with a stride of 1, indicating that the kernel rotates in a loop of one step at a time. The specific formula is: u z =σ relu (ω z *A+b z ); where z = 1, 2, 3...n, n represents the number of convolutional kernels; A is the input data of the CNN model. It can be seen that the input data and the convolutional kernel ω... z Perform convolution calculations and compare with the bias b. z Accumulate. Finally, use the activation function σ. relu (.) activates the calculated data; the activated u z The data will then enter the pooling layer for the next step of calculation.

[0059] in,

[0060] ω z This indicates that the z-th dimension is an h×1 convolution kernel vector, and the value of z ranges from 1 to n, indicating that there are n different convolution kernels to extract different features.

[0061] Additionally, as mentioned above, the dimension of A is 13×1, ω z If the dimension is h×1, then ω z The dimension of A is (13-h+1)×(1-1+1), which is (12-h)×1; then b z The bias vector corresponding to the z-th convolution kernel also has n different biases, b z The dimension is (12-h)×1, and ω z *Dimension A is the same.

[0062] Furthermore, the activation function mentioned above can be σ. relu (x) = max(0,x).

[0063] II. Regarding pooling layers:

[0064] Pooling layers are used for feature dimensionality reduction, which can compress data volume, reduce parameters, reduce overfitting, and improve model tolerance. The specific structure is as follows: Figure 3 As shown.

[0065] The pooling layer uses average pooling, and the specific formula is as follows:

[0066]

[0067] x τ This represents the τth pooled data (i.e., the u output of the convolutional layer). z (a part of the pooling), where τ takes values ​​from 1 to k, and k represents the number of data to be pooled (i.e., k = n); it should be noted that the embodiments of this application can adopt a one-dimensional pooling calculation method, so k can also represent the size of the pooling window, which is k × 1.

[0068] III. Regarding fully connected layers:

[0069] Fully connected layers act as "classifiers" in the entire CNN network. They weight the features of the pooling layer outputs. The specific structure is as follows: Figure 4 As shown.

[0070] The relevant formulas for the fully connected layer are shown below:

[0071] Y f =σ relu (w f *F+b f )

[0072] F represents the input data of the fully connected layer (i.e., the output data of the pooling layer), w f b represents the weight of the f-th fully connected neuron. f This represents the bias of the f-th fully connected neuron, where f takes values ​​from 1 to n.

[0073] IV. Regarding the integrated output layer:

[0074] By integrating the data output from the fully connected layer, the predicted power consumption value is obtained, as shown in the following formula:

[0075]

[0076] Among them, Y f This represents the data output by the fully connected layer. y represents the power consumption prediction value output by the CNN model. The degree to which y is close to the true value can reflect the accuracy of the prediction model.

[0077] As can be seen from the above, the power consumption prediction model in this embodiment can be expressed as:

[0078] y=f(x1, x2, x3, x4, x5, x6, x7, x8, r1, r2, r3, t, d).

[0079] Furthermore, as mentioned above, the first constraint condition is used to indicate that the power consumption of the first temperature regulating device is within a first range. Therefore, in the above example, the first constraint condition can be expressed as: Indicates the lower and upper limits of the first range;

[0080] The second constraint condition is used to indicate that at least one of the second operating parameters of the second temperature regulating device is within a corresponding second range. In the above example, the second constraint condition can be expressed as:

[0081]

[0082] This represents the lower and upper limits of the second range corresponding to r1 (e.g., It can be 16℃. (Can be 28℃);

[0083] This represents the lower and upper limits of the second range corresponding to r2;

[0084] This represents the lower and upper limits of the second range corresponding to r3.

[0085] Correspondingly, based on the above examples, the first objective function and its constraints in the embodiments of this application can be expressed as follows:

[0086]

[0087] Optionally, in step 102 above, the step of solving the constructed first objective function based on the first operating parameters and the determined first and second constraints to obtain the predicted power consumption value of the first temperature control device in the communication equipment room includes the following step A-1:

[0088] Step A-1: ​​Using a multi-strategy constrained differential evolution algorithm based on population partitioning, the first objective function is solved according to the first operating parameters, the first constraint condition, and the second constraint condition to obtain the predicted power consumption value of the first temperature regulation device in the communication equipment room.

[0089] Therefore, in this embodiment of the application, a multi-strategy constrained differential evolution algorithm based on population partitioning can be used to solve the first objective function. This multi-strategy constrained differential evolution algorithm based on population partitioning is an efficient optimization algorithm that combines various mutation and crossover strategies to solve single-objective optimization problems. This algorithm, based on stochastic optimization techniques of population optimization, has advantages such as simple structure, ease of implementation, and strong robustness.

[0090] It is understandable that other algorithms from existing related technologies can be used to solve single-objective optimization problems based on constraints, which will not be listed here.

[0091] Optionally, in step A-1, the use of a multi-strategy constrained differential evolution algorithm based on population partitioning to solve the first objective function according to the first operating parameters, the first constraint condition, and the second constraint condition to obtain the predicted power consumption value of the first temperature regulation device in the communication equipment room includes the following steps A-1.1 to A-1.13:

[0092] Step A-1.1: Initialize the second operating parameters to obtain an initial population (optionally, the second operating parameters can be initialized according to the second constraint conditions mentioned above, that is, the second operating parameters within the second range indicated by the second constraint conditions can be randomly generated);

[0093] Step A-1.2: When v is an integer from 1 to V, input the first running parameter and the second running parameter corresponding to the vth individual in the initial population into the power consumption prediction model to obtain the fitness of the vth individual, where V represents the number of individuals in the initial population;

[0094] Step A-1.3: Based on the fitness of the first to V individuals, divide the initial population into a dominant population and a subdominant population;

[0095] Step A-1.4: Use the dominance mutation strategy to mutate the dominant population to obtain the first population to be treated, and use the disadvantage mutation strategy to mutate the disadvantaged population to obtain the second population to be treated.

[0096] Step A-1.5: Perform a crossover operation between the dominant population and the first population to be treated to obtain a third population to be treated, and perform a crossover operation between the inferior population and the second population to be treated to obtain a fourth population to be treated;

[0097] Step A-1.6: Based on the first constraint and the second constraint, adjust the second operating parameters and fitness of each individual in the third population to be processed to obtain the fifth population to be processed;

[0098] Step A-1.7: Based on the first constraint and the second constraint, adjust the second operating parameters and fitness of each individual in the fourth population to be processed to obtain the sixth population to be processed;

[0099] Step A-1.8: Determine the offspring population corresponding to the dominant population based on the fitness of each individual in the dominant population and the fifth untreated population;

[0100] Step A-1.9: Determine the offspring population corresponding to the disadvantaged population based on the fitness of each individual in the disadvantaged population and the sixth population to be treated;

[0101] Step A-1.10: Let x = 2, and determine whether x is less than the maximum number of iterations;

[0102] Step A-1.11: When x is less than the maximum number of iterations, merge the offspring populations corresponding to the dominant population and the offspring populations corresponding to the suboptimal population, re-divide the merged population into a dominant population and a suboptimal population, and return to step A-1.4 (i.e., the step of using a dominant mutation strategy to mutate the dominant population to obtain the first population to be processed, and using a suboptimal mutation strategy to mutate the suboptimal population to obtain the second population to be processed).

[0103] Step A-1.12: Let x = x + 1, and repeat the step of determining whether x is less than the maximum number of iterations;

[0104] Step A-1.13: When x equals the maximum number of iterations, among the fitness of each individual in the offspring population corresponding to the obtained dominant population, obtain the minimum fitness and determine the minimum fitness as the predicted power consumption value of the first temperature regulation device in the communication equipment room.

[0105] To facilitate understanding of steps A-1.1 to A-1.13 above, the following example is provided:

[0106] For example, the first running parameters include x1, x2, x3, x4, x5, x6, x7, x8, t, and d as mentioned above; the second running parameters include r1, r2, and r3 as mentioned above, and the initial population size is 10 (it should be noted that the initial population size here is just an example, and other values ​​can also be used, which can be determined according to the actual situation).

[0107] So, the execution process is as follows: Figure 5 As shown, it includes the following process:

[0108] Perform the first iteration:

[0109] Population initialization is performed, which means initializing the second running parameters (for example, generating 10 random values ​​for each second running parameter, which are used as the second running parameters for each individual in the initial population). In this way, each individual in the initial population has corresponding values ​​of r1, r2, and r3.

[0110] The values ​​of x1, x2, x3, x4, x5, x6, x7, x8, t, and d collected at the current time, as well as the values ​​of r1, r2, and r3 corresponding to each individual in the initial population, can be input into the power consumption prediction model mentioned above. Then, the power consumption prediction value corresponding to each individual can be output, and the power consumption prediction value can be used as the fitness of the individual.

[0111] Then, based on the fitness of the 10 individuals in the initial population, these 10 individuals can be divided into a dominant population and a subdominant population. For example, the dominant population may contain 7 individuals and the subdominant population may contain 3 individuals. Subsequently, the 7 individuals in the dominant population are subjected to mutation, crossover, and constraint processing (i.e., processing according to the first and second constraint conditions) in sequence, and the 3 individuals in the subdominant population are subjected to mutation, crossover, and constraint processing in sequence.

[0112] Then, a selection operation is performed, namely, based on the dominant population and the population obtained by mutation, crossover and constraint processing of the dominant population, the offspring population of the dominant population is further obtained, and based on the inferior population and the population obtained by mutation, crossover and constraint processing of the inferior population, the offspring population of the inferior population is further obtained.

[0113] This completes the first iteration.

[0114] Then, a second iteration is performed:

[0115] The two offspring populations obtained in the first iteration are merged, and the merged population is re-divided into a dominant population and a subdominant population. The subsequent processing of the newly obtained dominant and subdominant populations is the same as that in the first iteration, and will not be repeated here.

[0116] After the final iteration, the minimum fitness is selected from the fitness of each individual in the offspring population corresponding to the dominant population obtained in the last iteration. This minimum fitness is then the predicted power consumption value obtained from the solution.

[0117] It should be noted that the purpose of mutation is to expand the search range of the population in the solution space, thereby increasing the probability of the algorithm converging to the global optimum; the purpose of crossover is to retain the superior genes in the parent individuals and further ensure the overall convergence of the algorithm.

[0118] Therefore, it can be seen that the multi-strategy constrained differential evolution algorithm (PD-MSCDE) used in the embodiments of this application is based on the classic differential evolution. It initializes the population, adaptively generates two subpopulations, and the two subpopulations enter the next generation after mutation, crossover and selection operations. Finally, the two subpopulations are redistributed until the maximum number of iterations is reached or other termination conditions are met.

[0119] During the iteration process, the population initially splits into two subpopulations, which co-evolve. The dominant subpopulation uses its superior individuals to find even better individuals, and its size gradually increases with the number of iterations. The subpopulation is used to explore unknown regions in the solution space, enhancing population diversity. Since the subpopulation is larger at the beginning of the iteration, it can increase the algorithm's solution selection space, thereby avoiding getting trapped in local optima.

[0120] In addition, in the embodiments of this application, different mutation strategies are adopted for the dominant population and the suboptimal population when performing mutation operations. The dominant mutation strategy can accelerate the convergence of the algorithm, while the suboptimal mutation strategy can expand the solution space.

[0121] Optionally, in step A-1.3, the individuals in the initial population can be sorted in ascending order of fitness. Then, based on the first number of individuals in the dominant population, the top-ranked individuals are selected to form the dominant population, and the remaining individuals form the subordinate population. In a given iteration, the ratio of the number of individuals in the dominant population to the number of individuals in the subordinate population can be calculated using the following formula, thereby allowing the calculation of the number of each individual in the dominant population: Where ITE represents the current iteration number, ITE MAX This indicates the maximum number of iterations.

[0122] Optionally, in step A-1.4 above, the second operating parameters include N parameters; the step of using a dominance mutation strategy to mutate the dominant population to obtain the first population to be treated includes:

[0123] Select the first individual with the lowest fitness from the dominant population;

[0124] For each integer v from 1 to V, perform the following process to obtain the first population to be processed, consisting of V individuals:

[0125] From the individuals in the dominant population other than the first individual, a second and a third individual are randomly selected;

[0126] For each integer i from 1 to N, the i-th parameter r of the first individual is... 1i The i-th parameter r of the second individual 2iThe i-th parameter r of the third body 3i Substituting into the first formula, we obtain the i-th parameter r of an individual in the first population to be processed. 待1i ;

[0127] The first formula is: r 待1i =r 1i +F1(r 2i -r 3i ), where F1 represents the scaling factor.

[0128] In addition, the F1 value is generally chosen between [0, 2], and usually F1 = 0.5. If the population converges too early, the value of F1 can be increased, or the number of individuals in the population can be increased.

[0129] To facilitate understanding of the specific mutation operation process for the dominant population in step A-1.4, the following example illustrates the process using a dominant population consisting of 7 individuals:

[0130] Each individual in the dominant population has a corresponding fitness, so the individual with the lowest fitness can be selected. Then, from the individuals in the dominant population other than the individual with the lowest fitness, two individuals are randomly selected. Then, the same second running parameter of these three individuals is substituted into the first formula mentioned above to obtain a new second running parameter, which is a mutated individual. This process is repeated 7 times to obtain 7 mutated individuals, thus completing the mutation operation on the dominant population.

[0131] It is understandable that if there are multiple individuals with the lowest fitness in the dominant population, then one of these individuals with the lowest fitness can be randomly selected as the first individual.

[0132] Optionally, in step A-1.4 above, the second operating parameters include N parameters; the step of using a disadvantageous mutation strategy to mutate the disadvantaged population to obtain a second population to be treated includes:

[0133] For each integer v from 1 to V, perform the following process to obtain the second population to be processed, consisting of V individuals:

[0134] The fourth, fifth, and sixth individuals were randomly selected from the inferior population.

[0135] For each integer i from 1 to N, the i-th parameter r of the fourth individual is... 4i The i-th parameter r of the fifth individual 5i The i-th parameter r of the sixth individual 6i Substituting into the second formula, we obtain the i-th parameter r of an individual in the second population to be processed. 待2i ;

[0136] The second formula is: r 待2i =r 4i +F2(r 5i -r 6i ), where F2 represents the scaling factor.

[0137] In addition, the choice of F2 is generally between [0, 2], usually F2 = 0.5. If the population converges too early, the value of F2 can be increased, or the number of individuals in the population can be increased.

[0138] To facilitate understanding of the specific mutation operation process for the inferior population in step A-1.4, the following example illustrates the process using an inferior population consisting of 3 individuals:

[0139] Each individual in the disadvantaged population has its corresponding fitness. If three individuals are randomly selected from the disadvantaged population, and the same second operating parameter of these three individuals is substituted into the second formula mentioned above, a new second operating parameter can be obtained. This new second operating parameter is a mutated individual. This process is repeated 3 times to obtain 3 mutated individuals, thus completing the mutation operation on the disadvantaged population.

[0140] Optionally, step A-1.5 above, the step of performing a crossover operation on the dominant population and the first population to be treated to obtain a third population to be treated, includes:

[0141] Based on the second operating parameters of each individual in the dominant population, a first matrix is ​​obtained (that is, the second operating parameters of each individual in the dominant population are used as values ​​in the first matrix, so that the element r in the v-th row and i-th column of the first matrix is...). v,i , which represents the i-th parameter in the second operating parameters corresponding to the v-th individual in the dominant population;

[0142] Based on the second operating parameters of each individual in the first population to be processed, a second matrix is ​​obtained (that is, the second operating parameters of each individual in the first population to be processed are used as the values ​​in the second matrix, so that the element r′ in the v-th row and i-th column of the second matrix is...). v,i , which represents the i-th parameter in the second running parameters corresponding to the v-th individual in the first population to be processed;

[0143] Based on the fifth formula, the first matrix, and the second matrix, the third matrix is ​​obtained, where the fifth formula is: r″ v,i rand represents the element in the v-th row and i-th column of the third matrix. v,i C represents the random number corresponding to the position in the v-th row and i-th column of either the first or second matrix. r Indicates the crossover probability;

[0144] Elements in the same row of the third matrix are used as different parameters in the second running parameters corresponding to the same individual, and these constitute the third population to be processed.

[0145] Among them, rand v,i It can be a random number between 0 and 1, C r It can be a probability between 0 and 1.

[0146] To better understand the specific process of the crossover operation, let's take an example with a dominant population consisting of 7 individuals and the second running parameters r1, r2, and r3:

[0147] The values ​​of the three second operating parameters of the seven individuals in the dominant population can be used to obtain a 7×3 first matrix; similarly, the values ​​of the three second operating parameters of the seven individuals in the first untreated population can be used to obtain a 7×3 second matrix; 21 random numbers are generated. For the first random number, if it is less than the predetermined crossover probability C... r If the first element of the second matrix is ​​selected as the first element of the third matrix, then the first element of the first matrix is ​​selected as the first element of the third matrix; otherwise, the first element of the first matrix is ​​selected as the first element of the third matrix. This process is repeated to obtain the third matrix. The three values ​​in the same row of the third matrix belong to the same individual, r1, r2, and r3. Thus, the third population to be processed can be obtained based on the third matrix.

[0148] It should be noted that the element numbers in the first, second, and third matrices are determined in ascending order of row number and column number.

[0149] It is understandable that the specific process of performing a cross-operation between the inferior population and the second population to be treated to obtain a fourth population to be treated is similar to the specific process of performing a cross-operation between the superior population and the first population to be treated to obtain a third population to be treated, and will not be repeated here.

[0150] Optionally, in step A-1.6 above, adjusting the second operating parameters and fitness corresponding to each individual in the third population to be processed according to the first constraint and the second constraint to obtain the fifth population to be processed includes at least one of the following:

[0151] If a seventh individual exists in the third population to be processed, the fitness of the seventh individual is set to a first preset value, wherein the fitness of the seventh individual is outside the first range and less than a second threshold, and the difference between the first preset value and the upper limit of the first range is greater than a third threshold.

[0152] If an eighth individual exists in the third population to be processed, the parameters of the eighth individual that are outside the second range are adjusted to be within the second range, wherein at least one of the second operating parameters of the eighth individual is outside the corresponding second range.

[0153] It should be noted that if the fitness of the seventh individual is outside the first range and less than the second threshold, it means that the fitness of the seventh individual is too low and unreasonable. In this case, the fitness of the seventh individual can be set to be higher. This way, the probability of the seventh individual being selected in the subsequent process of determining the offspring population will be greatly reduced, thereby avoiding the occurrence of incorrect solutions.

[0154] Therefore, by applying the first and second constraints to the third and fourth populations to be treated, the fitness and second operating parameters of the individuals can be adjusted to a reasonable range, so that the power consumption of the first temperature control device is within a reasonable range (thus ensuring that the temperature in the communication room is within the range required for the normal operation of the communication equipment) and the second temperature control device can be ensured to operate normally.

[0155] Optionally, in step A-1.8 above, determining the offspring population corresponding to the dominant population based on the fitness of each individual in the dominant population and the fifth untreated population includes:

[0156] For each integer v from 1 to V, the following process is performed to obtain the offspring population corresponding to the dominant population, which includes V individuals:

[0157] The first fitness of the vth individual in the dominant population is compared with the second fitness of the vth individual in the fifth untreated population;

[0158] If the first fitness is less than the second fitness, the vth individual in the dominant population shall be taken as the vth individual in the offspring population corresponding to the dominant population.

[0159] If the first fitness is greater than the second fitness, the vth individual in the fifth population to be processed is taken as the vth individual in the offspring population corresponding to the dominant population.

[0160] When the first fitness is equal to the second fitness, one of the v-th individuals in the dominant population and the v-th individuals in the fifth unprocessed population is randomly selected as the v-th individual in the offspring population corresponding to the dominant population.

[0161] Therefore, when obtaining the offspring population of the dominant population based on the dominant population and the fifth population to be processed (i.e., the population obtained after mutation, crossover, and constraint processing of the dominant population), the fitness of two individuals with the same index in these two populations can be compared. The individual with the lower fitness is retained. If the two are the same, one is randomly selected to be retained. In this way, the retained individuals constitute the offspring individuals of the dominant population.

[0162] It is understandable that the specific process of determining the offspring population corresponding to the disadvantaged population based on the fitness of each individual in the disadvantaged population and the sixth population to be treated is similar to the process of obtaining the offspring individuals corresponding to the dominant population, and will not be described in detail here.

[0163] Optionally, in step 103 above, adjusting the second operating parameters according to the calculated predicted power consumption value, so that the difference between the power consumption value of the first temperature regulating device at the second time and the calculated predicted power consumption value is less than or equal to the first threshold, includes:

[0164] Based on the target type of the network usage time period of the communication equipment room to which the current time belongs, a predictive control method is adopted to adjust the second operating parameters according to the power consumption prediction value obtained by solving, so that the difference between the power consumption value of the first temperature regulating device at the second time and the power consumption prediction value obtained by solving is less than or equal to the first threshold.

[0165] Due to the unique environment of communication equipment rooms, the large variety of main equipment, the varying operating conditions of each device at different times, and the different allocation of users between ordinary users and dedicated line users, it is possible to categorize the network usage time periods of the communication equipment room. Based on these different categories, predictive control methods can be employed to control the second operating parameters of the second temperature regulation equipment.

[0166] For example, the period from 24:00 to 8:00 the next day is usually the off-peak time for ordinary users to use the network, while other time periods are the peak time periods. Based on this, the network usage time periods of the communication equipment room can be classified.

[0167] Optionally, the step of using predictive control based on the target type of the network usage time period of the communication equipment room to which the current time belongs, and adjusting the second operating parameters according to the calculated power consumption prediction value, so that the difference between the power consumption value of the first temperature regulating device at the second time and the calculated power consumption prediction value is less than or equal to the first threshold, includes:

[0168] When the target type is a first predetermined type, the second objective function is solved to obtain the value that the second running parameter needs to be adjusted to in step P, and the second running parameter is adjusted to the value corresponding to step j when the time corresponding to step j is reached.

[0169] Where j is an integer from 1 to P, and the time interval between two adjacent steps is a fixed value;

[0170] The second objective function aims to minimize the first objective value O1, which is determined by the third formula;

[0171] The third formula is:

[0172] Among them, Y M (k+j) means: the first operating parameter collected at the first time k and the second operating parameter corresponding to the jth step are input into the power consumption prediction model to obtain the power consumption prediction value of the first temperature regulation device at the time corresponding to the jth step.

[0173] h j This represents the error compensation coefficient corresponding to step j;

[0174] e(k)=Y(k)-Y M Y(k) represents the actual power consumption of the first temperature regulating device at the first time k, where Y(k) is the power consumption of the first temperature regulating device at the first time k. M (k) represents the predicted power consumption value of the first temperature control device at the first time k, obtained by inputting the first operating parameter and the second operating parameter collected at the first time k into the power consumption prediction model.

[0175] Y R (k+j)=α j Y(k)+(1-α j )Y * Y * α represents the predicted power consumption value obtained by solving the first objective function. j This represents the smoothness coefficient at step j.

[0176] Optionally, the first pre-defined type is a period of low internet usage.

[0177] The third formula mentioned above is described below:

[0178] Firstly, regarding Y R (k+j):

[0179] In this embodiment of the application, the predicted power consumption value Y is obtained by solving the first objective function. * Then, according to the corresponding rules, a path can be generated from the actual power consumption value Y(k) at time k to Y... * A convergent curve. The generation rules are as follows:

[0180] The reference trajectory curve at time k can be derived from the ideal optimization value Y for the next j steps. R(k+j), j=

[0181] Let Y be represented by 1, 2, ..., P. The future trend can be represented by a first-order exponential form, thus yielding: Y R (k+j)=α j Y(k)+(1-α j )Y * Then [Y] R (k+1),Y R (k+2),……,Y R [(k+P)] is the reference trajectory.

[0182] α j α is the smoothness coefficient, ranging from 0 to 1. Clearly, α... j The smaller the value, the faster the reference trajectory can reach Y. * α j A smaller α value increases the system's adjustment burden and can easily lead to production instability. Conversely, α... j A larger α reduces the system's adjustment burden, but increases adjustment time and can easily lead to resource waste. j The selection of the range is crucial.

[0183] Secondly, regarding Y M (k+j)+h j e(k):

[0184] Among them, Y M (k+j) represents the predicted power consumption value of the first temperature control device at the time corresponding to step j, obtained by inputting the first operating parameter collected at the first time k and the second operating parameter corresponding to step j into the power consumption prediction model; e(k) represents the difference between the actual power consumption value at the first time k and the predicted power consumption value at the first time k. Therefore, in this embodiment, the error between the actual power consumption value and the predicted power consumption value can be compensated or corrected based on the predicted power consumption value corresponding to each step. Thus, Y M (k+j)+h j e(k) represents the corrected power consumption value corresponding to the j-th step;

[0185] From the first and second aspects, we can know that Y M (k+j)+h j e(k)-Y R (k+j) represents the difference between the corrected power consumption value at step j and the ideal optimized value at step j. Therefore, O1 represents the degree of difference between the corrected power consumption values ​​from step 1 to step P and the ideal optimized value. Where Y... MThe calculation of (k+j) involves the second running parameter corresponding to each step. By solving the second objective function with the goal of minimizing O1, we can obtain the specific values ​​of each second running parameter corresponding to each step when O1 is minimized.

[0186] It is understandable that the multi-strategy constrained differential evolution algorithm based on population partitioning described above can also be used to solve the second objective function. The specific solution process is similar to that for the first objective function, and will not be repeated here.

[0187] Optionally, the step of using predictive control based on the target type of the network usage time period of the communication equipment room to which the current time belongs, and adjusting the second operating parameters according to the calculated power consumption prediction value, so that the difference between the power consumption value of the first temperature regulating device at the second time and the calculated power consumption prediction value is less than or equal to the first threshold, includes:

[0188] When the target type is the second predetermined type, the third objective function is solved to obtain the value that the second running parameter needs to be adjusted to in step P, and the second running parameter is adjusted to the value corresponding to step j when the time corresponding to step j is reached.

[0189] Where j is an integer from 1 to P, and the time interval between two adjacent steps is a fixed value;

[0190] The third objective function aims to minimize the second objective value O2, which is determined by the fourth formula.

[0191] The fourth formula is:

[0192] Among them, Y M (k+j) means: the first operating parameter collected at the first time k and the second operating parameter corresponding to the jth step are input into the power consumption prediction model to obtain the power consumption prediction value of the first temperature regulation device at the time corresponding to the jth step.

[0193] h j This represents the error compensation coefficient corresponding to step j;

[0194] e(k)=Y(k)-Y M Y(k) represents the actual power consumption of the first temperature regulating device at the first time k, where Y(k) is the power consumption of the first temperature regulating device at the first time k. M (k) represents the predicted power consumption value of the first temperature control device at the first time k, obtained by inputting the first operating parameter and the second operating parameter collected at the first time k into the power consumption prediction model.

[0195] YT (k+j)=α j Y(k)+(1-α j )Y * Y * α represents the predicted power consumption value obtained by solving the first objective function. j This represents the smoothness coefficient at step j;

[0196] N represents the number of parameters included in the second operating parameter, C i r represents the weight coefficient of the i-th parameter in the second running parameters. i (k+j+1) represents the value of the i-th parameter in the second running parameters corresponding to the (j+1)-th step, r i (k+j) represents the value of the i-th parameter in the second running parameters corresponding to the j-th step.

[0197] Where, q j With C i And related to the ratio of dedicated line users to total users in the data center, q j With C i The choice needs to be made by taking into account various factors.

[0198] Optionally, the second pre-defined type is peak internet usage.

[0199] The fourth formula mentioned above is explained below:

[0200] Thirdly, regarding Y M (k+j)+h j e(k)-Y R (k+j), as detailed in the first and second aspects above, will not be repeated here.

[0201] Fourthly, regarding r i (k+j+1)-r i (k+j):

[0202] r i (k+j+1) represents the value of the i-th parameter in the second running parameters corresponding to the (j+1)-th step, r i (k+j) represents the value of the i-th parameter in the second running parameters corresponding to the j-th step. Therefore, r i (k+j+1)-r i (k+j) represents the difference between the i-th parameter corresponding to two adjacent steps. This indicates the degree of fluctuation of all second running parameters in every two adjacent steps from step 1 to step P.

[0203] Among them, Y MThe calculation of (k+j) involves the second running parameter corresponding to each step, and This content also includes the second running parameters corresponding to each step. By solving the third objective function mentioned above, which aims to minimize O2, we can obtain the specific values ​​of each second running parameter corresponding to each step when O2 is minimized.

[0204] It is understandable that the multi-strategy constrained differential evolution algorithm based on population partitioning described above can also be used to solve the third objective function. The specific solution process is similar to that for the first objective function, and will not be repeated here.

[0205] It should also be noted that during peak internet usage periods, the data center environment should not change too much. Therefore, it is necessary to ensure that the second operating parameter is as small as possible in each step. During off-peak internet usage periods, data center stability does not need to be considered, so the second operating parameter can be adjusted to be larger. Therefore, when the objective type is off-peak internet usage, the O1 of the second objective function can only include This item; when the target type is peak internet usage, the O2 of the third objective function needs to include as well as These two items.

[0206] In summary, the specific implementation method of the operation control method of the temperature regulation device according to the embodiments of this application can be described as follows:

[0207] Preparation phase:

[0208] 1. Construct a power consumption prediction model. The process of training the power consumption prediction model can be described as described above and will not be repeated here.

[0209] 2. Construct constraints (i.e., the first and second constraints mentioned above). The specific content of the constraints is as described above and will not be repeated here.

[0210] 3. Construct the first objective function. The specific details of the first objective function have been described above and will not be repeated here.

[0211] Operation control phase, such as Figure 6 As shown, the process includes the following:

[0212] The first operating parameters of the first temperature regulating device at the current time are collected, and based on the first operating parameters and the first and second constraints, the first objective function is solved to obtain the predicted power consumption value Y of the second temperature regulating device. * ;

[0213] Based on Y * Determine the reference trajectory [Y]R (k+1), Y R (k+2), ..., Y R [(k+P)], where the specific method for determining the reference trajectory can be found in the previous text and will not be repeated here;

[0214] Determine the calculation expression for feedback correction: Y M (k+j)+h j e(k);

[0215] Determine the expression for calculating the difference between two adjacent steps for the same parameter in the second running parameters: r i (k+j+1)-r i (k+j);

[0216] Based on the reference trajectory, the calculation expression of feedback correction, and the calculation expression of the difference between the same parameter in the second running parameters in two adjacent steps, the calculation formulas for the first target value O1 and the second target value O2 are obtained.

[0217] Classification control involves solving a second objective function with the goal of minimizing the first objective value when the current time is during off-peak hours. This yields the values ​​that the second operating parameters need to be adjusted to at each step, and the second operating parameters of the second temperature regulating device are then gradually adjusted to the corresponding values. Conversely, when the current time is during peak hours, solving a third objective function with the goal of minimizing the second objective value yields the values ​​that the second operating parameters need to be adjusted to at each step, and the second operating parameters of the second temperature regulating device are then gradually adjusted to the corresponding values.

[0218] In summary, in the embodiments of this application, by establishing a power consumption prediction model, the first operating parameters of the first temperature regulating device and the second operating parameters of the second temperature regulating device are determined to construct the input layer (i.e., by establishing a power consumption prediction model, complex physical derivations are avoided, and variables related to the power consumption of the first temperature regulating device are determined). Based on the established power consumption model, a first objective function is constructed with the goal of minimizing the power consumption of the first temperature regulating device. The first objective function is solved using the PD-MSCDE algorithm, constrained by the power consumption range of the first temperature regulating device and the range of the second operating parameters of the second temperature regulating device, to obtain the Pareto front that satisfies the conditions. Furthermore, a time-sensitive steady-state operation optimization algorithm based on communication equipment rooms is established. Differentiated network usage time periods for different types of communication equipment rooms are used, and optimization objective functions are designed separately to improve system stability. This allows the equipment room to quickly and stably approach the ideal value while reducing the power consumption of the first temperature regulating device, increasing robustness.

[0219] The above describes the operation control method of the temperature regulating device provided in the embodiments of this application. The operation control device of the temperature regulating device provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0220] See Figure 7 This application embodiment also provides an operation control device for a temperature regulating device, the operation control device 700 for the temperature regulating device comprising:

[0221] The first acquisition module 701 is used to acquire the first operating parameters of the communication equipment in the communication room at the first moment.

[0222] The solution module 702 is used to solve the constructed first objective function based on the first operating parameters and the determined first and second constraints to obtain the predicted power consumption value of the first temperature control device in the communication equipment room; wherein, the first objective function aims to minimize the predicted power consumption value of the first temperature control device, and the first objective function is used to indicate that there is a functional relationship between the input parameters and the predicted power consumption value of the first temperature control device through a power consumption prediction model, and the input parameters include the first operating parameters and the second operating parameters of the second temperature control device in the communication equipment room; the first constraint is used to indicate that the power consumption value of the first temperature control device is within a first range, and the second constraint is used to indicate that at least one of the second operating parameters of the second temperature control device is within a corresponding second range;

[0223] The adjustment control module 703 is used to adjust the second operating parameters according to the power consumption prediction value obtained by the solution, so that the difference between the power consumption value of the first temperature regulating device at the second time and the power consumption prediction value obtained by the solution is less than or equal to the first threshold.

[0224] Optionally, the solution module 702 includes:

[0225] The solution submodule is used to solve the first objective function by employing a multi-strategy constrained differential evolution algorithm based on population partitioning, according to the first operating parameters, the first constraint condition, and the second constraint condition, to obtain the predicted power consumption value of the first temperature regulation device in the communication equipment room.

[0226] Optionally, the solution submodule is specifically used for:

[0227] The second operating parameter is initialized to obtain the initial population;

[0228] For each integer v from 1 to V, the first running parameter and the second running parameter corresponding to the vth individual in the initial population are input into the power consumption prediction model to obtain the fitness of the vth individual, where V represents the number of individuals in the initial population.

[0229] Based on the fitness of the first to V individuals, the initial population is divided into a dominant population and a suboptimal population.

[0230] The dominant population is mutated using a dominance mutation strategy to obtain a first population to be treated, and the inferior population is mutated using a disadvantage mutation strategy to obtain a second population to be treated.

[0231] A third population to be treated is obtained by performing a crossover operation between the dominant population and the first population to be treated; a fourth population to be treated is obtained by performing a crossover operation between the inferior population and the second population to be treated.

[0232] Based on the first constraint and the second constraint, the second operating parameters and the fitness of each individual in the third population to be processed are adjusted to obtain the fifth population to be processed.

[0233] Based on the first constraint and the second constraint, the second operating parameters and the fitness of each individual in the fourth population to be processed are adjusted to obtain the sixth population to be processed.

[0234] Based on the fitness of each individual in the dominant population and the fifth untreated population, the offspring population corresponding to the dominant population is determined;

[0235] Based on the fitness of each individual in the inferior population and the sixth untreated population, the offspring population corresponding to the inferior population is determined.

[0236] Let x = 2, and determine whether x is less than the maximum number of iterations;

[0237] If x is less than the maximum number of iterations, merge the offspring populations corresponding to the dominant population and the offspring populations corresponding to the suboptimal population, re-divide the merged populations into a dominant population and a suboptimal population, and return to the steps of using a dominant mutation strategy to mutate the dominant population to obtain a first population to be processed, and using a suboptimal mutation strategy to mutate the suboptimal population to obtain a second population to be processed.

[0238] Let x = x + 1, and repeat the step of determining whether x is less than the maximum number of iterations;

[0239] When x equals the maximum number of iterations, the minimum fitness is obtained from the fitness of each individual in the offspring population corresponding to the dominant population, and the minimum fitness is determined as the predicted power consumption value of the first temperature control device in the communication room.

[0240] Optionally, the second operating parameters include N parameters; the solution submodule uses a dominance mutation strategy to mutate the dominant population to obtain a first population to be processed, including:

[0241] Select the first individual with the lowest fitness from the dominant population;

[0242] For each integer v from 1 to V, perform the following process to obtain the first population to be processed, consisting of V individuals:

[0243] From the individuals in the dominant population other than the first individual, a second and a third individual are randomly selected;

[0244] For each integer i from 1 to N, the i-th parameter r of the first individual is... 1i The i-th parameter r of the second individual 2i The i-th parameter r of the third body 3i Substituting into the first formula, we obtain the i-th parameter r of an individual in the first population to be processed. 待1i ;

[0245] The first formula is: r 待1i =r 1i +F1(r 2i -r 3i ), where F1 represents the scaling factor.

[0246] Optionally, the second operating parameters include N parameters; the solution submodule uses a disadvantage mutation strategy to mutate the disadvantaged population to obtain a second population to be processed, including:

[0247] For each integer v from 1 to V, perform the following process to obtain the second population to be processed, consisting of V individuals:

[0248] The fourth, fifth, and sixth individuals were randomly selected from the inferior population.

[0249] For each integer i from 1 to N, the i-th parameter r of the fourth individual is... 4i The i-th parameter r of the fifth individual 5i The i-th parameter r of the sixth individual 6i Substituting into the second formula, we obtain the i-th parameter r of an individual in the second population to be processed. 待2i ;

[0250] The second formula is: r 待2i =r 4i +F2(r 5i -r 6i ), where F2 represents the scaling factor.

[0251] Optionally, the solution submodule adjusts the second operating parameters and the fitness corresponding to each individual in the third population to be processed according to the first constraint and the second constraint to obtain a fifth population to be processed, including at least one of the following:

[0252] If a seventh individual exists in the third population to be processed, the fitness of the seventh individual is set to a first preset value, wherein the fitness of the seventh individual is outside the first range and less than a second threshold, and the difference between the first preset value and the upper limit of the first range is greater than a third threshold.

[0253] If an eighth individual exists in the third population to be processed, the parameters of the eighth individual that are outside the second range are adjusted to be within the second range, wherein at least one of the second operating parameters of the eighth individual is outside the corresponding second range.

[0254] Optionally, the solution submodule determines the offspring population corresponding to the dominant population based on the fitness of each individual in the dominant population and the fifth unprocessed population, including:

[0255] For each integer v from 1 to V, the following process is performed to obtain the offspring population corresponding to the dominant population, which includes V individuals:

[0256] The first fitness of the vth individual in the dominant population is compared with the second fitness of the vth individual in the fifth untreated population;

[0257] If the first fitness is less than the second fitness, the vth individual in the dominant population shall be taken as the vth individual in the offspring population corresponding to the dominant population.

[0258] If the first fitness is greater than the second fitness, the vth individual in the fifth population to be processed is taken as the vth individual in the offspring population corresponding to the dominant population.

[0259] When the first fitness is equal to the second fitness, one of the v-th individuals in the dominant population and the v-th individuals in the fifth unprocessed population is randomly selected as the v-th individual in the offspring population corresponding to the dominant population.

[0260] Optionally, the adjustment control module 703 includes:

[0261] The control submodule is used to adjust the second operating parameters according to the target type of the network usage time period of the communication equipment room to which the current time belongs, using a predictive control method and based on the power consumption prediction value obtained by the solution, so that the difference between the power consumption value of the first temperature regulating device at the second time and the power consumption prediction value obtained by the solution is less than or equal to a first threshold.

[0262] Optionally, the control submodule is specifically used for:

[0263] When the target type is a first predetermined type, the second objective function is solved to obtain the value that the second running parameter needs to be adjusted to in step P, and the second running parameter is adjusted to the value corresponding to step j when the time corresponding to step j is reached.

[0264] Where j is an integer from 1 to P, and the time interval between two adjacent steps is a fixed value;

[0265] The second objective function aims to minimize the first objective value O1, which is determined by the third formula;

[0266] The third formula is:

[0267] Among them, Y M (k+j) means: the first operating parameter collected at the first time k and the second operating parameter corresponding to the jth step are input into the power consumption prediction model to obtain the power consumption prediction value of the first temperature regulation device at the time corresponding to the jth step.

[0268] h j This represents the error compensation coefficient corresponding to step j;

[0269] e(k)=Y(k)-Y M Y(k) represents the actual power consumption of the first temperature regulating device at the first time k, where Y(k) is the power consumption of the first temperature regulating device at the first time k. M (k) represents the predicted power consumption value of the first temperature control device at the first time k, obtained by inputting the first operating parameter and the second operating parameter collected at the first time k into the power consumption prediction model.

[0270] Y R (k+j)=α j Y(k)+(1-α j )Y * Y * α represents the predicted power consumption value obtained by solving the first objective function. j This represents the smoothness coefficient at step j.

[0271] Optionally, the control submodule is specifically used for:

[0272] When the target type is the second predetermined type, the third objective function is solved to obtain the value that the second running parameter needs to be adjusted to in step P, and the second running parameter is adjusted to the value corresponding to step j when the time corresponding to step j is reached.

[0273] Where j is an integer from 1 to P, and the time interval between two adjacent steps is a fixed value;

[0274] The third objective function aims to minimize the second objective value O2, which is determined by the fourth formula.

[0275] The fourth formula is:

[0276] Among them, Y M (k+j) means: the first operating parameter collected at the first time k and the second operating parameter corresponding to the jth step are input into the power consumption prediction model to obtain the power consumption prediction value of the first temperature regulation device at the time corresponding to the jth step.

[0277] h j This represents the error compensation coefficient corresponding to step j;

[0278] e(k)=Y(k)-Y M Y(k) represents the actual power consumption of the first temperature regulating device at the first time k, where Y(k) is the power consumption of the first temperature regulating device at the first time k. M (k) represents the predicted power consumption value of the first temperature control device at the first time k, obtained by inputting the first operating parameter and the second operating parameter collected at the first time k into the power consumption prediction model.

[0279] Y R (k+j)=α j Y(k)+(1-α j )Y * Y * α represents the predicted power consumption value obtained by solving the first objective function. j This represents the smoothness coefficient at step j;

[0280] N represents the number of parameters included in the second operating parameter, C i r represents the weight coefficient of the i-th parameter in the second running parameters. i (k+j+1) represents the value of the i-th parameter in the second running parameters corresponding to the (j+1)-th step, r i(k+j) represents the value of the i-th parameter in the second running parameters corresponding to the j-th step.

[0281] It should be noted that the division of units in the embodiments of this application is illustrative and only represents one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units.

[0282] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of this application, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0283] It should be noted that the apparatus provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0284] Embodiments of this application also provide an electronic device, such as... Figure 8 As shown, the electronic device includes a memory 820, a transceiver 810, and a processor 800;

[0285] Memory 820 is used to store computer programs;

[0286] Transceiver 810 is used to receive and send data under the control of processor 800;

[0287] The processor 800 is used to read the computer program in the memory 820 and execute the operation control method of the temperature regulating device described in the first aspect above.

[0288] Among them, Figure 8In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits together, represented by one or more processors (processor 800) and memory (memory 820). The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 810 can be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over transmission media, including wireless channels, wired channels, optical fibers, etc. The processor 800 is responsible for managing the bus architecture and general processing, and the memory 820 can store data used by the processor 800 during operation.

[0289] The processor 800 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor 800 can also adopt a multi-core architecture.

[0290] It should be noted that the electronic device provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Here, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail.

[0291] Embodiments of this application also provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the operation control method of the temperature regulating device described in the first aspect above.

[0292] The computer-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (e.g., compact disks (CDs), digital versatile optical discs (DVDs), Blu-ray discs (BDs), holographic versatile optical discs (HVDs), etc.), and semiconductor storage (e.g., read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), non-volatile memory (NAND FLASH), solid-state disks (SSDs), etc.).

[0293] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0294] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0295] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0296] These processors can execute instructions that can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0297] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for controlling the operation of a temperature regulating device, characterized in that, The method includes: Obtain the first operating parameters of the communication equipment in the communication room at the first moment; Based on the first operating parameters and the determined first and second constraints, the constructed first objective function is solved to obtain the predicted power consumption value of the first temperature control device in the communication equipment room. The first objective function aims to minimize the predicted power consumption value of the first temperature control device, and it indicates that there is a functional relationship between the input parameters and the predicted power consumption value of the first temperature control device through a power consumption prediction model. The input parameters include the first operating parameters and the second operating parameters of the second temperature control device in the communication equipment room. The first constraint indicates that the power consumption value of the first temperature control device is within a first range, and the second constraint indicates that at least one of the second operating parameters of the second temperature control device is within a corresponding second range. Based on the power consumption prediction value obtained from the solution, the second operating parameters are adjusted so that the difference between the power consumption value of the first temperature regulating device at the second time and the power consumption prediction value obtained from the solution is less than or equal to the first threshold. The second operating parameter is initialized to obtain the initial population; For each integer v from 1 to V, the first running parameter and the second running parameter corresponding to the vth individual in the initial population are input into the power consumption prediction model to obtain the fitness of the vth individual, where V represents the number of individuals in the initial population. Based on the fitness of the first to V individuals, the initial population is divided into a dominant population and a suboptimal population. The dominant population is mutated using a dominance mutation strategy to obtain a first population to be treated, and the inferior population is mutated using a disadvantage mutation strategy to obtain a second population to be treated. A third population to be treated is obtained by performing a crossover operation between the dominant population and the first population to be treated; a fourth population to be treated is obtained by performing a crossover operation between the inferior population and the second population to be treated. Based on the first constraint and the second constraint, the second operating parameters and the fitness of each individual in the third population to be processed are adjusted to obtain the fifth population to be processed. Based on the first constraint and the second constraint, the second operating parameters and the fitness of each individual in the fourth population to be processed are adjusted to obtain the sixth population to be processed. Based on the fitness of each individual in the dominant population and the fifth untreated population, the offspring population corresponding to the dominant population is determined; Based on the fitness of each individual in the inferior population and the sixth untreated population, the offspring population corresponding to the inferior population is determined. Let x = 2, and determine whether x is less than the maximum number of iterations; If x is less than the maximum number of iterations, merge the offspring populations corresponding to the dominant population and the offspring populations corresponding to the suboptimal population, re-divide the merged populations into a dominant population and a suboptimal population, and return to the steps of using a dominant mutation strategy to mutate the dominant population to obtain a first population to be processed, and using a suboptimal mutation strategy to mutate the suboptimal population to obtain a second population to be processed. Let x = x + 1, and repeat the step of determining whether x is less than the maximum number of iterations; When x equals the maximum number of iterations, the minimum fitness is obtained from the fitness of each individual in the offspring population corresponding to the dominant population, and the minimum fitness is determined as the predicted power consumption value of the first temperature control device in the communication room.

2. The method according to claim 1, characterized in that, The step of solving the constructed first objective function based on the first operating parameters and the determined first and second constraints to obtain the predicted power consumption value of the first temperature control device in the communication equipment room includes: A multi-strategy constrained differential evolution algorithm based on population partitioning is used to solve the first objective function according to the first operating parameters, the first constraint condition, and the second constraint condition, so as to obtain the predicted power consumption value of the first temperature regulation device in the communication equipment room.

3. The method according to claim 1, characterized in that, The second operating parameters include N parameters; the step of using a dominance mutation strategy to mutate the dominant population to obtain the first population to be treated includes: Select the first individual with the lowest fitness from the dominant population; For each integer v from 1 to V, perform the following process to obtain the first population to be processed, consisting of V individuals: From the individuals in the dominant population other than the first individual, a second and a third individual are randomly selected; For each integer i from 1 to N, the i-th parameter r of the first individual is... 1i The i-th parameter r of the second individual 2i The i-th parameter r of the third body 3i Substituting into the first formula, we obtain the i-th parameter r of an individual in the first population to be processed. 待1i ; The first formula is: r 待1i =r 1i +F1(r 2i -r 3i ), where F1 represents the scaling factor.

4. The method according to claim 1, characterized in that, The second operating parameters include N parameters; the step of using a disadvantage mutation strategy to mutate the disadvantaged population to obtain a second population to be processed includes: For each integer v from 1 to V, perform the following process to obtain the second population to be processed, consisting of V individuals: The fourth, fifth, and sixth individuals were randomly selected from the inferior population. For each integer i from 1 to N, the i-th parameter r of the fourth individual is... 4i The i-th parameter r of the fifth individual 5i The i-th parameter r of the sixth individual 6i Substituting into the second formula, we obtain the i-th parameter r of an individual in the second population to be processed. 待2i ; The second formula is: r 待2i =r 4i +F2(r 5i -r 6i ), where F2 represents the scaling factor.

5. The method according to claim 1, characterized in that, The step of adjusting the second operating parameters and fitness of each individual in the third population to be processed according to the first constraint and the second constraint to obtain the fifth population to be processed includes at least one of the following: If a seventh individual exists in the third population to be processed, the fitness of the seventh individual is set to a first preset value, wherein the fitness of the seventh individual is outside the first range and less than a second threshold, and the difference between the first preset value and the upper limit of the first range is greater than a third threshold. If an eighth individual exists in the third population to be processed, the parameters of the eighth individual that are outside the second range are adjusted to be within the second range, wherein at least one of the second operating parameters of the eighth individual is outside the corresponding second range.

6. The method according to claim 1, characterized in that, The step of determining the offspring population corresponding to the dominant population based on the fitness of each individual in the dominant population and the fifth untreated population includes: For each integer v from 1 to V, the following process is performed to obtain the offspring population corresponding to the dominant population, which includes V individuals: The first fitness of the vth individual in the dominant population is compared with the second fitness of the vth individual in the fifth untreated population; If the first fitness is less than the second fitness, the vth individual in the dominant population shall be taken as the vth individual in the offspring population corresponding to the dominant population. If the first fitness is greater than the second fitness, the vth individual in the fifth population to be processed is taken as the vth individual in the offspring population corresponding to the dominant population. When the first fitness is equal to the second fitness, one of the v-th individuals in the dominant population and the v-th individuals in the fifth unprocessed population is randomly selected as the v-th individual in the offspring population corresponding to the dominant population.

7. The method according to any one of claims 1 to 6, characterized in that, The step of adjusting the second operating parameters based on the calculated predicted power consumption value, so that the difference between the power consumption value of the first temperature regulating device at the second time and the calculated predicted power consumption value is less than or equal to the first threshold, includes: Based on the target type of the network usage time period of the communication equipment room to which the current time belongs, a predictive control method is adopted to adjust the second operating parameters according to the power consumption prediction value obtained by solving, so that the difference between the power consumption value of the first temperature regulating device at the second time and the power consumption prediction value obtained by solving is less than or equal to the first threshold.

8. The method according to claim 7, characterized in that, The step of using predictive control based on the target type of the network usage time period of the communication equipment room to which the current time belongs, and adjusting the second operating parameters according to the calculated power consumption prediction value, so that the difference between the power consumption value of the first temperature regulating device at the second time and the calculated power consumption prediction value is less than or equal to a first threshold, includes: When the target type is a first predetermined type, the second objective function is solved to obtain the value that the second running parameter needs to be adjusted to in step P, and the second running parameter is adjusted to the value corresponding to step j when the time corresponding to step j is reached. Where j is an integer from 1 to P, and the time interval between two adjacent steps is a fixed value; The second objective function aims to minimize the first objective value O1, which is determined by the third formula; The third formula is: Among them, Y M (k+j) means: the first operating parameter collected at the first time k and the second operating parameter corresponding to the jth step are input into the power consumption prediction model to obtain the power consumption prediction value of the first temperature regulation device at the time corresponding to the jth step. h j This represents the error compensation coefficient corresponding to step j; e(k)=Y(k)-Y M Y(k) represents the actual power consumption of the first temperature regulating device at the first time k, where Y(k) is the power consumption of the first temperature regulating device at the first time k. M (k) represents the predicted power consumption value of the first temperature control device at the first time k, obtained by inputting the first operating parameter and the second operating parameter collected at the first time k into the power consumption prediction model. Y R (k+j)=α j Y(k)+(1-α j )Y * Y * α represents the predicted power consumption value obtained by solving the first objective function. j This represents the smoothness coefficient at step j.

9. The method according to claim 7, characterized in that, The step of using predictive control based on the target type of the network usage time period of the communication equipment room to which the current time belongs, and adjusting the second operating parameters according to the calculated power consumption prediction value, so that the difference between the power consumption value of the first temperature regulating device at the second time and the calculated power consumption prediction value is less than or equal to a first threshold, includes: When the target type is the second predetermined type, the third objective function is solved to obtain the value that the second running parameter needs to be adjusted to in step P, and the second running parameter is adjusted to the value corresponding to step j when the time corresponding to step j is reached. Where j is an integer from 1 to P, and the time interval between two adjacent steps is a fixed value; The third objective function aims to minimize the second objective value O2, which is determined by the fourth formula. The fourth formula is: Among them, Y M (k+j) means: the first operating parameter collected at the first time k and the second operating parameter corresponding to the jth step are input into the power consumption prediction model to obtain the power consumption prediction value of the first temperature regulation device at the time corresponding to the jth step. h j This represents the error compensation coefficient corresponding to step j; e(k)=Y(k)-Y M Y(k) represents the actual power consumption of the first temperature regulating device at the first time k, where Y(k) is the power consumption of the first temperature regulating device at the first time k. M (k) represents the predicted power consumption value of the first temperature control device at the first time k, obtained by inputting the first operating parameter and the second operating parameter collected at the first time k into the power consumption prediction model. Y R (k+j)=α j Y(k)+(1-α j )Y * Y * α represents the predicted power consumption value obtained by solving the first objective function. j This represents the smoothness coefficient at step j; N represents the number of parameters included in the second operating parameter, C i r represents the weight coefficient of the i-th parameter in the second running parameters. i (k+j+1) represents the value of the i-th parameter in the second running parameters corresponding to the (j+1)-th step, r i (k+j) represents the value of the i-th parameter in the second running parameters corresponding to the j-th step.

10. An operation control device for a temperature regulating equipment, characterized in that, The device includes: The first acquisition module is used to acquire the first operating parameters of the communication equipment in the communication room at the first moment. The solution module is used to solve the constructed first objective function based on the first operating parameters and the determined first and second constraints to obtain the predicted power consumption value of the first temperature control device in the communication equipment room. The first objective function aims to minimize the predicted power consumption value of the first temperature control device, and it indicates that there is a functional relationship between the input parameters and the predicted power consumption value of the first temperature control device through a power consumption prediction model. The input parameters include the first operating parameters and the second operating parameters of the second temperature control device in the communication equipment room. The first constraint indicates that the power consumption value of the first temperature control device is within a first range, and the second constraint indicates that at least one of the second operating parameters of the second temperature control device is within a corresponding second range. The adjustment control module is used to adjust the second operating parameters according to the power consumption prediction value obtained by the solution, so that the difference between the power consumption value of the first temperature regulating device at the second time and the power consumption prediction value obtained by the solution is less than or equal to the first threshold. The solution module includes a solution submodule, which is specifically used for: The second operating parameter is initialized to obtain the initial population; For each integer v from 1 to V, the first running parameter and the second running parameter corresponding to the vth individual in the initial population are input into the power consumption prediction model to obtain the fitness of the vth individual, where V represents the number of individuals in the initial population. Based on the fitness of the first to V individuals, the initial population is divided into a dominant population and a suboptimal population. The dominant population is mutated using a dominance mutation strategy to obtain a first population to be treated, and the inferior population is mutated using a disadvantage mutation strategy to obtain a second population to be treated. A third population to be treated is obtained by performing a crossover operation between the dominant population and the first population to be treated; a fourth population to be treated is obtained by performing a crossover operation between the inferior population and the second population to be treated. Based on the first constraint and the second constraint, the second operating parameters and the fitness of each individual in the third population to be processed are adjusted to obtain the fifth population to be processed. Based on the first constraint and the second constraint, the second operating parameters and the fitness of each individual in the fourth population to be processed are adjusted to obtain the sixth population to be processed. Based on the fitness of each individual in the dominant population and the fifth untreated population, the offspring population corresponding to the dominant population is determined; Based on the fitness of each individual in the inferior population and the sixth untreated population, the offspring population corresponding to the inferior population is determined. Let x = 2, and determine whether x is less than the maximum number of iterations; If x is less than the maximum number of iterations, merge the offspring populations corresponding to the dominant population and the offspring populations corresponding to the suboptimal population, re-divide the merged populations into a dominant population and a suboptimal population, and return to the steps of using a dominant mutation strategy to mutate the dominant population to obtain a first population to be processed, and using a suboptimal mutation strategy to mutate the suboptimal population to obtain a second population to be processed. Let x = x + 1, and repeat the step of determining whether x is less than the maximum number of iterations; When x equals the maximum number of iterations, the minimum fitness is obtained from the fitness of each individual in the offspring population corresponding to the dominant population, and the minimum fitness is determined as the predicted power consumption value of the first temperature control device in the communication room.

11. An electronic device, characterized in that, Includes memory, transceiver, and processor: Memory, used to store computer programs; Transceiver, used to send and receive data under the control of the processor; A processor is configured to read a computer program from the memory and execute the operation control method of the temperature regulating device as described in any one of claims 1 to 9.

12. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions, which, when executed by a processor, implement the operation control method of the temperature regulating device as described in any one of claims 1 to 9.

Images