CN116009622A - System control method, device, equipment and storage medium - Google Patents

Abstract

The application discloses a system control method, device, equipment and storage medium. The method includes: obtaining target data respectively; according to preset multiple frequency ranges and multiple temperature ranges, randomly sampling the operating frequencies in the target data within the preset multiple frequency ranges; Randomly sample the temperature within multiple preset temperature ranges to obtain the sampling data group; calculate the power consumption of the device according to the operating frequency and temperature; calculate the first fitness function value according to the relationship between power consumption and fitness function value; determine the first The operating frequency and temperature corresponding to the smallest first fitness function value in the fitness function value are initial energy-saving parameters, and the operating frequency and temperature corresponding to a preset number of smaller fitness function values are determined as candidate energy-saving parameters except for the initial energy-saving parameters; Determining target energy-saving parameters according to the initial energy-saving parameters and candidate energy-saving parameters; controlling the system according to the target energy-saving parameters.

Description

A system control method, device, equipment and storage medium

Technical Field

The present application belongs to the field of energy-saving technology, and in particular, relates to a system control method, device, equipment and storage medium.

Background Art

With the progress of industrial automation and informatization, in order to ensure the constant temperature of the production environment, it is often necessary to adjust the ambient temperature through a temperature control system, which results in a large amount of energy consumption. In order to reduce energy consumption while ensuring the stability of the production environment, it is necessary to optimize the control parameters of related energy-consuming equipment and search for the optimal control parameters to control the temperature control system. In related technologies, heuristic algorithms are usually used to search for the optimal control parameters, and the search is often performed within the entire safe value range of the control parameters of the equipment.

However, for data centers, since they have a large number of related energy-consuming devices, when using existing heuristic algorithms for search, the data center requires a long time of test calculations, and the calculation cost is high. In addition, since data centers usually need to be in production operation, a large amount of test calculations can easily bring safety risks.

Summary of the invention

The embodiments of the present application provide a system control method, device, equipment and storage medium, which can reduce the search and calculation time for obtaining optimal energy-saving parameters.

In a first aspect, an embodiment of the present application provides a system control method, including:

Obtain target data, including refrigeration pump frequency, cooling pump frequency, and cooling tower outlet water temperature;

According to the preset multiple frequency bands and multiple temperature ranges, randomly sampling the operating frequencies in the target data that are respectively within the preset multiple frequency bands and randomly sampling the temperatures in the target data that are respectively within the preset multiple temperature ranges, to obtain multiple sampling data groups;

Calculate the power consumption of the device based on the operating frequency and temperature in the sampled data set;

Calculating a first fitness function value according to a relationship between power consumption and fitness function value;

Determine the operating frequency and temperature in the data group corresponding to the minimum first fitness function value in the first fitness function values as the initial energy-saving parameters, and determine the operating frequency and temperature in the data group corresponding to a preset number of smaller fitness function values other than the initial energy-saving parameters as candidate energy-saving parameters;

Determine a target energy-saving parameter according to the initial energy-saving parameter and the candidate energy-saving parameter;

Control the system according to target energy-saving parameters.

In a possible implementation of the embodiment of the present application, before randomly sampling the operating frequencies in the target data of each device that are respectively within the preset multiple frequency bands and the temperatures in the target data of each device that are respectively within the preset multiple temperature ranges according to the preset multiple frequency bands and multiple temperature ranges, and obtaining the sampled data groups of the multiple devices, the method further includes:

According to the frequency in the target data of each device, the frequency of the target data is divided into a plurality of first frequency bands of different preset lengths;

According to the temperature in the target data of each device, the temperature in the target data is divided into a plurality of first temperature ranges of different preset lengths.

According to the temperature in the target data, the temperature in the target data is divided into a plurality of first temperature ranges of different preset lengths and according to a plurality of preset frequency bands and a plurality of temperature ranges, the operating frequencies in the target data whose operating frequencies are respectively within the plurality of preset frequency bands are randomly sampled and the temperatures in the target data whose temperatures are respectively within the plurality of preset temperature ranges are randomly sampled to obtain a plurality of sampling data groups, the method further comprising:

Dividing each first frequency band into a plurality of second frequency bands to obtain a plurality of preset frequency bands;

Each first temperature range is equally divided into a plurality of second temperature ranges to obtain a plurality of preset temperature ranges.

In a possible implementation of the embodiment of the present application, determining the target energy-saving parameter according to the initial energy-saving parameter and the candidate energy-saving parameter includes:

Calculate the target first parameter corresponding to each candidate energy-saving parameter according to the deviation between each candidate energy-saving parameter and the initial energy-saving parameter;

Calculate the device power consumption corresponding to the target first parameter respectively, and determine the second fitness function value corresponding to each power consumption according to the relationship between the device power consumption and the fitness function;

Determine the target operating frequency and target temperature corresponding to the smallest second fitness function value among the second fitness function values as the target initial energy-saving parameters, and determine the operating frequencies and temperatures corresponding to a preset number of smaller second fitness function values than the target operating frequency and the target temperature as candidate target energy-saving parameters;

Calculate the target second parameter corresponding to each candidate target energy-saving parameter according to the frequency deviation and temperature deviation of each candidate target energy-saving parameter from the target initial energy-saving parameter;

Calculate the device power consumption corresponding to the target second parameter respectively, and determine the third fitness function value corresponding to each power consumption according to the relationship between the device power consumption and the fitness function;

When the number of times the third fitness function values are calculated reaches a preset number of iterative updates, the operating frequency and temperature corresponding to the smallest third fitness function value among the third fitness function values are determined as target energy-saving parameters.

In a possible implementation of the embodiment of the present application, according to the frequency deviation and temperature deviation between each candidate target energy-saving parameter in the candidate target energy-saving parameters and the target initial energy-saving parameter, the target second parameter corresponding to each candidate target energy-saving parameter is calculated respectively, including:

Obtaining search parameters corresponding to each candidate target energy-saving parameter in the candidate target energy-saving parameters, the search parameters including a search probability value, a first preset coefficient, a second preset coefficient, and a curvature value;

When the search probability value is less than the first preset probability value, calculating the target second parameter corresponding to each candidate target energy-saving parameter according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter;

When the search probability value is greater than the second preset probability value, the target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the candidate target energy-saving parameter, the first preset coefficient, the curvature value and the target initial energy-saving parameter.

In a possible implementation of the embodiment of the present application, according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter, the target second parameter corresponding to each candidate target energy-saving parameter is calculated, including:

Calculate the target second parameter corresponding to each candidate target energy-saving parameter according to the first corresponding relationship;

其中，

为目标第二参数，

为第一预设系数，

为第二预设系数，t为当前迭代更新次数，

为候选目标节能参数，

为目标初始节能参数。The first corresponding relationship is

in,

is the second parameter of the target,

is the first preset coefficient,

is the second preset coefficient, t is the current iteration update number,

is the candidate target energy saving parameter,

is the target initial energy saving parameter.

In a possible implementation of the embodiment of the present application, according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter, the target second parameter corresponding to each candidate target energy-saving parameter is calculated, including:

Calculate the target second parameter corresponding to each candidate energy-saving parameter according to the second corresponding relationship;

且

其中，

为目标第二参数，

为第一预设系数，

为目标初始节能参数和候选目标节能参数的之差，t为当前迭代更新次数，

为候选目标节能参数，

为目标初始节能参数，l为曲率值。The second corresponding relationship is

and

in,

is the second parameter of the target,

is the first preset coefficient,

is the difference between the target initial energy-saving parameter and the candidate target energy-saving parameter, t is the current iterative update number,

is the candidate target energy saving parameter,

is the target initial energy-saving parameter, and l is the curvature value.

In a possible implementation of the embodiment of the present application, the search parameter further includes a first random value; when the search probability value is less than the first preset probability value, the target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient, and the target initial energy-saving parameter, including:

When the search probability value is less than the first preset probability value and the absolute value of the first random value is less than the preset threshold, the target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter;

When the search probability value is less than the first preset probability value and the absolute value of the first random value is greater than or equal to the first preset threshold, a random candidate parameter is randomly obtained according to the candidate target energy-saving parameter, and the target second parameter corresponding to each candidate energy-saving parameter is calculated according to the random candidate parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter.

In a second aspect, an embodiment of the present application provides a control device, the device comprising:

A first acquisition module is used to acquire target data, the target data including refrigeration pump frequency, cooling pump frequency, and cooling tower outlet water temperature;

A sampling module, for randomly sampling the operating frequencies in the target data that are respectively within the preset multiple frequency bands and the temperatures in the target data that are respectively within the preset multiple temperature ranges, according to the preset multiple frequency bands and the preset multiple temperature ranges, to obtain multiple sampling data groups;

A first calculation module, used for calculating the power consumption of the device according to the operating frequency and temperature in the sample data group;

A second calculation module, used for calculating the fitness function value according to the relationship between the power consumption and the fitness function value;

A second acquisition module is used to determine the operating frequency and temperature in the data group corresponding to the minimum first fitness function value in the fitness function values as the initial energy-saving parameters, and to determine the operating frequency and temperature in the data group corresponding to a preset number of smaller fitness function values other than the initial energy-saving parameters as candidate energy-saving parameters;

An optimization module, used for determining a target energy-saving parameter according to the initial energy-saving parameter and the candidate energy-saving parameter;

A control module is used to control the system according to target energy-saving parameters.

In a third aspect, an embodiment of the present application provides a control device, the device comprising:

a processor and a memory storing computer program instructions;

When the processor executes the computer program instructions, the control method of the first aspect is implemented.

In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the control method of the first aspect is implemented.

In a control method, device, equipment and storage medium of a system in an embodiment of the present application, by obtaining the freezing pump frequency, cooling pump frequency and cooling tower outlet water temperature as target data, randomly sampling the working frequencies in the target data within the preset multiple frequency bands according to the preset multiple frequency bands, and at the same time, randomly sampling the temperatures in the target data within the preset temperature range according to the preset multiple temperature ranges, thereby obtaining multiple sampled data groups. By calculating the power consumption of the device according to the working frequency and temperature in each sampled data group, and then calculating the fitness function value of each device according to the relationship between the power consumption and the fitness function value, determining the working frequency and temperature in the data group corresponding to the minimum first fitness function value in the fitness function value as the initial energy-saving parameters, and determining the working frequency and temperature in the data group corresponding to the preset number of smaller fitness function values other than the initial energy-saving parameters as candidate energy-saving parameters. Then, determine the target energy-saving parameters according to the initial energy-saving parameters and the candidate energy-saving parameters, and control the system according to the target energy-saving parameters. Because, when obtaining the sampling data group, the target data is randomly sampled according to the preset multiple frequency bands and the preset multiple temperature ranges, so that when the initial energy-saving parameters and the candidate energy-saving parameters determine the target energy-saving parameters, different search probabilities can be given to the operating frequencies in different frequency bands and the temperatures in different temperature ranges, thereby reducing blind searches. In the process of determining the target energy-saving parameters based on the initial energy-saving parameters and the candidate energy-saving parameters, the time required for the search calculation is reduced, thereby reducing the calculation cost.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

FIG1 is a flow chart of a control method of a system provided in an embodiment of the present application;

FIG2 is a second flow chart of a control method of a system provided in an embodiment of the present application;

FIG3 is a schematic diagram of the structure of a control device provided in an embodiment of the present application;

FIG. 4 is a schematic diagram of the structure of a control device provided in an embodiment of the present application.

DETAILED DESCRIPTION

The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

For ease of understanding, some contents involved in the embodiments of the present application are described below:

With the progress of industrial automation and informatization, in order to ensure the constant temperature of the production environment, it is often necessary to use a sampling temperature control system to adjust the ambient temperature, which results in a large amount of energy consumption. In order to reduce energy consumption while ensuring the stability of the production environment, it is necessary to optimize the control parameters of related equipment and search for the optimal control parameters to control the temperature system. Heuristic optimization algorithms in parameter optimization methods are becoming more and more popular in engineering applications because they rely on fairly simple concepts, are easy to implement, do not require gradient data, can bypass local optimality, and can be used for a wide range of problems involving different disciplines.

Existing heuristic algorithms mainly include ant colony algorithm, genetic algorithm, simulated annealing, particle swarm algorithm and other algorithms. However, these algorithms usually search within the entire safe value range of the control parameters of the device during the search. This search method requires a large number of optimization attempts. For example, in the particle swarm algorithm, when the number of particles is 30 and the number of iterations is set to 300, 30×300=9000 samples are required to find the approximate optimal result. In practice, for systems with more devices, if the particle algorithm is used to sample 9000 times, it will take up to one year of data test sampling time, which is computationally expensive.

For example, for a data center, it takes 30 minutes to set parameters for dozens of devices at a time and obtain the optimal control parameters after a single parameter adjustment. For optimization methods such as genetic algorithms that require thousands of calculations, it takes data centers months or even years to conduct experiments to complete the search for the optimal control parameters. The time cost is very expensive, and data centers are generally in production operation. A large amount of test calculations also brings great challenges to the safe operation of data centers.

In order to solve the above problems, the embodiments of the present application provide a system control method, device, equipment and computer storage medium.

The present application embodiment provides a system control method, as shown in FIG1 , as follows:

S110, obtaining target data, where the target data includes cooling pump frequency, freezing pump frequency, and cooling tower outlet water temperature.

In some embodiments, the target data may include multiple devices, each of which may include one or more. Taking the cold source system of a data center as an example, the cold source system may include multiple cold source devices such as a cooling pump, a freezing pump, and a cooling tower, wherein the number of cooling pumps, freezing pumps, and cooling towers may be one or more. The following is an introduction using the cooling pump frequency, freezing pump frequency, and cooling tower outlet water temperature of the cold source system of a data center as an example, and the cooling pump frequency, freezing pump frequency, and cooling tower outlet water temperature in the cold source system are obtained as target data.

S120, according to the preset multiple frequency bands and multiple temperature ranges, randomly sample the operating frequencies in the target data that are respectively within the preset multiple frequency bands and randomly sample the temperatures in the target data that are respectively within the preset multiple temperature ranges, to obtain multiple sampling data groups.

In some embodiments, by presetting multiple frequency bands and multiple temperature ranges, different preset frequency bands and temperature ranges have different sampling weights, i.e., sampling intervals, so that the frequencies in the target data whose operating frequencies are respectively within the preset multiple frequency bands and the temperatures in the target data whose temperatures are respectively within different preset temperature ranges are randomly sampled, and it is more likely to obtain important frequency values and temperature values, i.e., it is more likely to obtain frequency values and temperature values that make the device power consumption lower. Specifically, it can be to give a higher sampling weight, i.e., a smaller sampling interval, to the lower frequency part. Each sampling requires random sampling of the cooling pump frequency, the freezing pump frequency, and the cooling tower outlet water temperature, and the cooling pump frequency, the freezing pump frequency, and the cooling tower outlet water temperature obtained in each sampling are combined into a sampling data group, i.e., a multidimensional vector, and the frequency or temperature of a device is one dimension.

S130: Calculate the power consumption of the device according to the operating frequency and temperature in the sampled data group.

In some embodiments, the power consumption of each device is calculated based on the operating frequency and temperature in the sampled data group. For example, the power consumption of the corresponding cooling pump, freezing pump and cooling tower is calculated based on the operating frequency of the cooling pump, the operating frequency of the freezing pump and the cooling tower outlet water temperature obtained by random sampling, and then the total power consumption of the cold source room in the cold source system of the data center is calculated based on the power consumption of the cooling pump, freezing pump and cooling tower.

S140. Calculate a first fitness function value of each device according to a relationship between power consumption and fitness function value.

In some embodiments, the smaller the fitness function value is, the closer the parameter corresponding to the fitness function value is to the optimal control parameter, and the better the energy-saving optimization effect is.

For ease of understanding, the fitness function of the present application is introduced by taking the cold source system of a data center as an example. The energy-consuming equipment of a data center may include an IT computer room, terminal precision air conditioners, and a cold source computer room. If the energy-saving target is set to meet the minimum cold source computer room power consumption under a given IT computer room power consumption, the fitness function Object = P _IT / P _cool , where P _IT is the IT computer room power consumption and P _cool is the cold source computer room power consumption. The refrigeration equipment of the cold source computer room is mainly composed of refrigeration equipment such as a chiller, a refrigeration pump, a cooling pump, and a cooling tower. There may be multiple chillers, refrigeration pumps, cooling pumps, and cooling towers. Therefore, the power consumption P _cool of the cold source computer room can be calculated by equations (1) to (4):

P _{Refrigeration Pump} = f _{Refrigeration Pump} (x _{Refrigeration Pump Frequency} ) Formula (2)

_{Pcooling pump} = _{fcooling pump} (x _{cooling pump frequency} ) Formula (3)

P _{cooling tower} = f _{cooling tower} (x _{cooling tower outlet water temperature} ) Formula (4)

Among them, _{xrefrigeration pump frequency} is the frequency of the refrigeration pump, xcooling _{pump frequency} is the frequency of the cooling pump, xcooling _{tower outlet water temperature} is the cooling tower outlet water temperature, _{Prefrigeration pump} is the power consumption of the refrigeration pump, Pcooling _pump is the power consumption of the cooling pump, _{Pcooling tower} is the power consumption of the cooling tower, and _Pother is the power consumption of refrigeration equipment other than the refrigeration pump, cooling pump and cooling tower.

The freezing pump frequency, cooling pump frequency and cooling tower outlet water temperature in the cold source system are obtained as target data, and then the obtained freezing pump frequency and cooling pump frequency are randomly sampled according to a plurality of preset frequency bands, and the obtained cooling tower outlet water temperature is randomly sampled according to a plurality of preset temperature ranges, so as to obtain a plurality of sampling data groups, and then the power consumption of each device is calculated according to the freezing pump frequency, cooling pump frequency and cooling tower outlet water temperature, and then the power consumption P _cool of the cold source machine room is calculated according to formula (1), so as to obtain the fitness function Object=P _IT /P _cool corresponding to each sampling data group, that is, the first fitness function value.

S150, determining the operating frequency and temperature in the data group corresponding to the minimum first fitness function value in the fitness function values as the initial energy-saving parameters, and determining the operating frequency and temperature in the data group corresponding to a preset number of smaller fitness function values other than the initial energy-saving parameters as candidate energy-saving parameters;

Among them, the initial energy-saving parameters and candidate energy-saving parameters are multidimensional vectors composed of the operating frequencies and temperatures of multiple devices, with the frequency or temperature of a device as a dimension. For example, when there is one cooling pump, one freezing pump and one cooling tower respectively, the initial energy-saving parameters and candidate energy-saving parameters are three-dimensional vectors composed of the cooling pump frequency, the freezing pump frequency and the cooling tower outlet water temperature. When there are two cooling pumps, two freezing pumps and two cooling towers respectively, the initial energy-saving parameters and candidate energy-saving parameters are six-dimensional vectors composed of the cooling pump frequency, the freezing pump frequency and the cooling tower outlet water temperature. It is worth noting that the initial energy-saving parameters are the operating frequency and temperature corresponding to the minimum first fitness function in the first fitness function value, and the candidate energy-saving parameters are the operating frequencies and temperatures corresponding to the operating frequencies in the sampling data group corresponding to a preset number of smaller fitness function values except the initial energy-saving parameters. The number of candidate energy-saving parameters can be multiple. As an example, the preset number of candidate energy-saving parameters can be 3 to 7.

As an example, the initial energy-saving parameters of the cold source system of the data center are the cooling pump frequency, refrigeration pump frequency and cooling tower outlet water temperature corresponding to the smallest first fitness function in the first fitness function value, and the candidate energy-saving parameters are the cooling pump frequency, refrigeration pump frequency and cooling tower outlet water temperature in the sampled data group corresponding to the three smaller fitness function values except the initial energy-saving parameters.

S160: Determine a target energy-saving parameter according to the initial energy-saving parameter and the candidate energy-saving parameters.

In some embodiments, the target energy-saving parameter is obtained by iteratively calculating and searching according to the initial energy-saving parameter and the candidate energy-saving parameter. The target search parameter is a vector composed of the operating frequencies and temperatures of multiple devices, with the frequency or temperature of a device as a dimension. For example, the target energy-saving parameter of the cold source system of the data center is a vector composed of the cooling pump frequency, the freezing pump frequency and the cooling tower outlet water temperature. When there is one cooling pump, one freezing pump and one cooling tower respectively, the target energy-saving parameter is a three-dimensional vector composed of the cooling pump frequency, the freezing pump frequency and the cooling tower outlet water temperature. When there are multiple cooling pumps, freezing pumps and cooling towers respectively, for example, when there are two cooling pumps, one freezing pump and one cooling tower respectively, the target energy-saving parameter is a six-dimensional vector composed of the cooling pump frequency, the freezing pump frequency and the cooling tower outlet water temperature.

S170. Control the system according to the target energy-saving parameters.

In some embodiments, in order to reduce energy consumption, each device of the system is set by using target energy-saving parameters to reduce the power consumption of the system. For example, when the target energy-saving parameter is a three-dimensional vector composed of cooling pump frequency, freezing pump frequency and cooling tower outlet water temperature, each frequency value and temperature value in the target energy-saving parameter is sampled to set the corresponding device.

In some embodiments, in order to give a higher sampling weight to the lower frequency part, that is, a smaller sampling interval, before S120, a control method of a system provided in an embodiment of the present application may further include:

According to the frequencies in the target data, the frequencies of the target data are divided into a plurality of first frequency bands of different preset lengths;

According to the temperature in the target data, the temperature in the target data is divided into a plurality of first temperature ranges with different preset lengths.

By first dividing the frequency in the target data into multiple frequency bands of different lengths and dividing the temperature into multiple temperature ranges of different lengths, multiple first frequency bands and multiple first temperature ranges are obtained, so that different preset frequency bands and preset temperature ranges have different sampling intervals.

To increase the possibility of obtaining the optimal control parameters, after dividing the frequency of the target data into a plurality of first frequency ranges with different preset lengths according to the frequency in the target data and dividing the temperature in the target data into a plurality of first temperature ranges with different preset lengths according to the temperature in the target data, before S120, a control method of a system provided in an embodiment of the present application may further include:

Dividing each first frequency band into a plurality of second frequency bands to obtain a plurality of preset frequency bands;

Each first temperature range is equally divided into a plurality of second temperature ranges to obtain a plurality of preset temperature ranges.

Each first frequency range and a plurality of first temperature ranges are further evenly divided into a plurality of second frequency ranges and second temperature ranges, so that the frequency and temperature distribution obtained by sampling is more reasonable.

In some embodiments, the power consumption of the device is generally lower at a lower frequency, so the time for finding the optimal control parameter can be reduced by giving a higher sampling weight to the lower frequency part, that is, a smaller sampling interval. For example, the number of first frequency bands with different preset lengths can be 3, and along the direction from the maximum frequency value to the minimum frequency value in the target data of each device, the ratio of the preset lengths of the first frequency bands with different preset lengths can be 3:2:1.

As an example, the safe operating frequency range of the freezing pump is 30 to 50 Hz, the safe operating frequency range of the cooling pump is 30 to 50 Hz, and the safe temperature range of the cooling tower outlet water temperature is 30 to 50 degrees Celsius. The safe frequency ranges of the freezing pump and the cooling pump are divided into three frequency segments with different interval lengths, specifically, 50 Hz to 40 Hz as a first frequency range, 40 Hz to 33 Hz as a first frequency range, and 33 Hz to 30 Hz as a first frequency range. The division of the temperature range is similar to the division of the frequency range. Specifically, the safe temperature range of the cooling tower outlet water temperature can be divided into three temperature ranges with different interval lengths, specifically, 50 degrees Celsius to 40 degrees Celsius as a first temperature range, 40 degrees Celsius to 33 degrees Celsius as a first temperature range, and 33 degrees Celsius to 30 degrees Celsius as a first temperature range. Then each first frequency range and first temperature range are evenly divided into multiple second frequency ranges and second temperature ranges, thereby obtaining multiple preset frequency ranges and multiple temperature ranges.

Then, the operating frequencies in the target data that fall within different frequency bands are randomly sampled, and the temperatures in the target data that fall within different temperature ranges are randomly sampled, to obtain a sampling data group of multiple devices, wherein the cooling pump operating frequency, the refrigeration pump operating frequency and the cooling tower outlet water temperature obtained in each sampling correspond one to one.

For ease of understanding, the process of searching for the optimal control parameters can be understood as the process of continuously updating the search position to the optimal position. The search position is a position vector composed of the operating frequencies and temperatures of multiple devices. The optimal position is the optimal position vector composed of the operating frequencies and temperatures corresponding to the optimal control parameters. Searching for the optimal control parameters is to continuously update the search position to approach the optimal position. In this process, since the optimal position is not known a priori, in the embodiment of the present application, it is assumed that the current optimal position is close to the optimal position vector, so that the search position is continuously approached to the optimal position by iteratively updating to obtain the optimal control parameters.

Based on this, in some embodiments, as shown in FIG. 2 , S160 may include the following steps:

S161. Calculate the target first parameter corresponding to each candidate energy-saving parameter according to the frequency deviation and temperature deviation of each candidate energy-saving parameter from the initial energy-saving parameter. Specifically, the deviation of the frequency value of each candidate energy-saving parameter from the frequency value of the initial energy-saving parameter and the deviation of the temperature value of each candidate energy-saving parameter from the temperature value of the initial energy-saving parameter may be calculated.

S162: Calculate the device power consumption corresponding to the target first parameter respectively, and determine the second fitness function value corresponding to each power consumption according to the relationship between the device power consumption and the fitness function.

S163. Determine the target operating frequency and target temperature corresponding to the smallest second fitness function value among the second fitness function values as the target initial energy-saving parameters, and determine the operating frequency and temperature corresponding to a preset number of smaller second fitness function values than the target operating frequency and target temperature as candidate target energy-saving parameters.

The position vector corresponding to the initial energy-saving parameter obtained after sampling is taken as the current optimal position, and the frequency deviation and temperature deviation of the initial energy-saving parameter and the candidate energy-saving parameter are calculated to obtain the corresponding target first parameter, that is, the candidate energy-saving parameter is searched around, and the search position is updated to approach the optimal position. Then, the operating frequency and temperature of the target first parameter corresponding to the smallest second fitness function value are taken as the initial target energy-saving parameter, and the preset number of candidate target energy-saving parameters corresponding to the target first parameter with the smallest second fitness function value are taken.

S164. Calculate the target second parameter corresponding to each candidate energy-saving parameter according to the frequency deviation and temperature deviation between each candidate energy-saving parameter in the candidate target energy-saving parameters and the target initial energy-saving parameter.

S165 , respectively calculating the device power consumption corresponding to the target second parameter, and determining a third fitness function value corresponding to each power consumption according to the relationship between the device power consumption and the fitness function.

The position vector corresponding to the target initial energy-saving parameter obtained in S163 is used as the current optimal position for the first execution of steps S164 to S165. The frequency deviation and temperature deviation of the target initial energy-saving parameter and the candidate target energy-saving parameter are calculated to obtain the corresponding target second parameter, that is, the candidate target energy-saving parameter is searched around, and the search position is updated to approach the optimal position. The operating frequency and temperature of the target second parameter corresponding to the smallest third fitness function value are used as the optimal position for the next iterative update, and the preset number of target second parameter operating frequencies and temperature candidate target energy-saving parameters corresponding to the smallest third fitness function value are taken.

S166. When the number of times the third fitness function values are calculated reaches a preset number of iterative updates, determine the operating frequency and temperature corresponding to the smallest third fitness function value among the third fitness function values as the target energy-saving parameters.

By looping through S164 to S165 before reaching the preset number of iterations, the initial target energy-saving parameters and the candidate target energy-saving parameters are continuously updated to parameters that make the fitness function value smaller, so that the search position is continuously close to the optimal position, that is, the searched parameter value is continuously close to the optimal control parameter. When the calculation number of the third fitness function value reaches the preset number of iterations, the operating frequency and temperature corresponding to the minimum third fitness function value obtained by the last iteration is used as the target energy-saving parameter.

In some embodiments, to further reduce the time of searching for the optimal control parameters, S164 may include the following steps:

Obtaining search parameters corresponding to each candidate target energy-saving parameter in the candidate target energy-saving parameters, the search parameters including a search probability value, a first preset coefficient, a second preset coefficient, and a curvature value;

When the search probability value is less than the first preset probability value, calculating the target second parameter corresponding to each candidate target energy-saving parameter according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter;

When the search probability value is greater than the second preset probability value, the target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the candidate target energy-saving parameter, the first preset coefficient, the curvature value and the target initial energy-saving parameter.

In some embodiments, in order to obtain the control parameters that minimize system energy consumption within the entire safe value range, when the search probability value is less than the first preset probability value, the target second parameter corresponding to each candidate energy-saving parameter is calculated based on the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter. When the search probability value is greater than the second preset probability value, the target second parameter corresponding to each candidate target energy-saving parameter is calculated based on the candidate target energy-saving parameter, the first preset coefficient, the curvature value and the target initial energy-saving parameter. The target second parameter is calculated in two ways, which increases the diversity of the target second parameter and makes the final target energy-saving parameter closer to the control parameter that minimizes system energy consumption within the entire safe value range.

Based on this, in some embodiments, according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter, the target second parameter corresponding to each candidate target energy-saving parameter is calculated, which can be specifically:

其中，

为目标第二参数，

为第一预设系数，

为第二预设系数，t为当前迭代更新次数，

为候选目标节能参数，

为目标初始节能参数。The target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the first corresponding relationship. Among them, the first corresponding relationship is

in,

is the second parameter of the target,

is the first preset coefficient,

is the second preset coefficient, t is the current iteration update number,

is the candidate target energy saving parameter,

is the target initial energy saving parameter.

和

可以通过式(5)和式(6)计算获得。in,

and

It can be calculated by equation (5) and equation (6).

由2线性减少至0；r₁和r₂是[0，1]中的随机向量。Throughout the iteration process

decreases linearly from 2 to 0; _r1 and _r2 are random vectors in [0, 1].

In some embodiments, in order to increase the possibility of searching for the control parameter that minimizes the system energy consumption and reduce the search time, the target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient, and the target initial energy-saving parameter. Specifically, it can be:

且

其中，

为目标第二参数，

为第一预设系数，

为目标初始节能参数和候选目标节能参数的之差，t为当前迭代更新次数，

为候选目标节能参数，

为目标初始节能参数，l为曲率值。The target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the second corresponding relationship. The second corresponding relationship is:

and

in,

is the second parameter of the target,

is the first preset coefficient,

is the difference between the target initial energy-saving parameter and the candidate target energy-saving parameter, t is the current iterative update number,

is the candidate target energy saving parameter,

is the target initial energy-saving parameter, and l is the curvature value.

In some embodiments, in order to search for a control parameter that minimizes system energy consumption in a local range, the search parameter may further include a first random value when the search probability value is less than a first preset probability value.

Based on this, according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter, the target second parameter corresponding to each candidate target energy-saving parameter is calculated, including:

When the search probability value is less than the first preset probability value and the absolute value of the first random value is less than the preset threshold, the target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter;

When the search probability value is less than the first preset probability value and the absolute value of the first random value is greater than or equal to the first preset threshold, a random candidate parameter is randomly obtained according to the candidate target energy-saving parameter, and the target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the random candidate parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter.

By adding a random search method during the search process, when the absolute value of the first random value is greater than or equal to the first preset threshold, the target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the random candidate parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter, so that the target energy-saving parameter finally obtained is the control parameter that minimizes the energy consumption of the system within the entire safe value range.

According to the random candidate parameter, the first preset coefficient, the second preset coefficient and the initial target energy-saving parameter, the target second parameter corresponding to each candidate target energy-saving parameter is calculated, which can be specifically:

The target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the third corresponding relationship.

为目标第二参数，

为第一预设系数，

为第二预设系数，t为当前迭代更新次数，

为候选目标节能参数，

为第t+1次迭代更新时获得的随机候选参数，

为第t次迭代更新时获得的随机候选参数。The third corresponding relationship is

is the second parameter of the target,

is the first preset coefficient,

is the second preset coefficient, t is the current iteration update number,

is the candidate target energy saving parameter,

is the random candidate parameter obtained during the t+1th iteration update,

is the random candidate parameter obtained during the t-th iteration update.

It should be noted that the various optional implementations introduced in the embodiments of the present application can be implemented in combination with each other or can be implemented separately if they do not conflict with each other, and the embodiments of the present application are not limited to this.

Based on the control method of a system provided in the above embodiment, the present application also provides a specific implementation of a control device. Please refer to the following embodiment.

Referring to FIG. 3 , the control device provided in the embodiment of the present application may include:

The first acquisition module 301 is used to acquire target data, the target data includes the refrigeration pump frequency, the cooling pump frequency, and the cooling tower outlet water temperature;

The sampling module 302 is used to randomly sample the operating frequencies in the target data that are respectively within the preset multiple frequency bands and the temperatures in the target data that are respectively within the preset multiple temperature ranges according to the preset multiple frequency bands and the preset multiple temperature ranges, so as to obtain multiple sampling data groups;

A first calculation module 303, used to calculate the power consumption of the device according to the operating frequency and temperature in the sample data group;

A second calculation module 304, used to calculate the fitness function value according to the relationship between the power consumption and the fitness function value;

The second acquisition module 305 is used to determine the operating frequency and temperature in the data group corresponding to the minimum first fitness function value in the fitness function values as the initial energy-saving parameters, and to determine the operating frequency and temperature in the data group corresponding to a preset number of smaller fitness function values other than the initial energy-saving parameters as candidate energy-saving parameters;

An optimization module 306, configured to determine a target energy-saving parameter based on the initial energy-saving parameter and the candidate energy-saving parameter;

Control module 307, used to control the system according to the target energy-saving parameters

The control device provided in the embodiment of the present application can implement each step in the method embodiment of Figure 1 and achieve the corresponding technical effect. To avoid repetition, it will not be described here.

The embodiment of the present application further provides a control device, the device comprising: a processor and a memory storing computer program instructions, wherein the processor implements the control method of the first aspect when executing the computer program instructions.

FIG4 shows a schematic diagram of the hardware structure of a control device provided in an embodiment of the present application.

The control device may include a processor 401 and a memory 402 storing computer program instructions.

Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside of an integrated gateway disaster recovery device. In a specific embodiment, memory 402 is a non-volatile solid-state memory.

The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical/tangible memory storage device. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present disclosure.

The processor 401 implements any one of the control methods in the above embodiments by reading and executing computer program instructions stored in the memory 402 .

In one example, the control device may further include a communication interface 403 and a bus 410. As shown in Fig. 3, the processor 401, the memory 402, and the communication interface 403 are connected via the bus 410 and communicate with each other.

The communication interface 403 is mainly used to implement communication between various modules, devices, units and/or equipment in the embodiments of the present application.

Bus 410 includes hardware, software or both, and the components of xx device are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 410 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

In addition, in combination with the control method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the control methods in the above embodiment is implemented.

It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

Aspects of the present disclosure are described above with reference to the flowchart and/or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and/or block diagram and the combination of each box in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function/action specified in one or more boxes of the flowchart and/or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and/or flowchart and the combination of boxes in the block diagram and/or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims (11)

1. A method for controlling a system, comprising: Acquire target data, wherein the target data includes a refrigeration pump frequency, a cooling pump frequency, and a cooling tower outlet water temperature; According to the preset multiple frequency bands and multiple temperature ranges, randomly sampling the operating frequencies in the target data that are respectively within the preset multiple frequency bands and randomly sampling the temperatures in the target data that are respectively within the preset multiple temperature ranges, to obtain multiple sampling data groups; Calculating the power consumption of the device according to the operating frequency and temperature in the sampled data group; Calculating a first fitness function value according to a relationship between power consumption and fitness function value; Determine the operating frequency and temperature in the sampled data group corresponding to the minimum first fitness function value among the first fitness function values as initial energy-saving parameters, and determine the operating frequency and temperature in the sampled data group corresponding to a preset number of smaller fitness function values other than the initial energy-saving parameters as candidate energy-saving parameters; Determine a target energy-saving parameter according to the initial energy-saving parameter and the candidate energy-saving parameter; The system is controlled according to the target energy-saving parameter. 2. The control method according to claim 1 is characterized in that, before randomly sampling the operating frequencies in the target data that are respectively within the preset multiple frequency bands and the temperatures in the target data that are respectively within the preset multiple temperature ranges according to the preset multiple frequency bands and multiple temperature ranges to obtain multiple sampling data groups, the method further comprises: According to the frequencies in the target data, the frequencies in the target data are divided into a plurality of first frequency bands with different preset lengths; According to the temperature in the target data, the temperature in the target data is divided into a plurality of first temperature ranges with different preset lengths. 3. The control method according to claim 2 is characterized in that after dividing the frequency in the target data into a plurality of first frequency bands with different preset lengths according to the frequency in the target data and dividing the temperature in the target data into a plurality of first temperature ranges with different preset lengths according to the temperature in the target data, before randomly sampling the operating frequencies in the target data within the preset multiple frequency bands and randomly sampling the temperatures in the target data within the preset multiple temperature ranges according to the preset multiple frequency bands and multiple temperature ranges to obtain multiple sampling data groups, the method further comprises: Dividing each first frequency band range equally into a plurality of second frequency band ranges to obtain the plurality of preset frequency band ranges; Each first temperature range is equally divided into a plurality of second temperature ranges to obtain the plurality of preset temperature ranges. 4. The control method according to claim 1, characterized in that the step of determining the target energy-saving parameter according to the initial energy-saving parameter and the candidate energy-saving parameter comprises: Calculate the target first parameter corresponding to each candidate energy-saving parameter according to the frequency deviation and temperature deviation of each candidate energy-saving parameter from the initial energy-saving parameter; Calculating the device power consumption corresponding to the target first parameter respectively, and determining the second fitness function value corresponding to each power consumption according to the relationship between the device power consumption and the fitness function; Determine the target operating frequency and target temperature corresponding to the smallest second fitness function value among the second fitness function values as the target initial energy-saving parameters, and determine the operating frequency and temperature corresponding to a preset number of smaller second fitness function values than the target operating frequency and the target temperature as candidate target energy-saving parameters; Calculate the target second parameter corresponding to each candidate target energy-saving parameter according to the frequency deviation and temperature deviation of each candidate target energy-saving parameter from the target initial energy-saving parameter; Calculating the device power consumption corresponding to the target second parameter respectively, and determining the third fitness function value corresponding to each power consumption according to the relationship between the device power consumption and the fitness function; When the number of times the third fitness function values are calculated reaches a preset number of iterative updates, the operating frequency and temperature corresponding to the smallest third fitness function value among the third fitness function values are determined as target energy-saving parameters. 5. The control method according to claim 4, characterized in that the step of calculating the target second parameter corresponding to each candidate target energy-saving parameter according to the frequency deviation and temperature deviation between each candidate target energy-saving parameter and the target initial energy-saving parameter comprises: Acquire search parameters corresponding to each of the candidate target energy-saving parameters, wherein the search parameters include a search probability value, a first preset coefficient, a second preset coefficient, and a curvature value; When the search probability value is less than a first preset probability value, calculating a target second parameter corresponding to each candidate target energy-saving parameter according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter; When the search probability value is greater than a second preset probability value, a target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the candidate target energy-saving parameter, the first preset coefficient, the curvature value and the target initial energy-saving parameter. 6. The control method according to claim 5, characterized in that the step of calculating the target second parameter corresponding to each candidate target energy-saving parameter according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter comprises: Calculate the target second parameter corresponding to each candidate target energy-saving parameter according to the first corresponding relationship; The first corresponding relationship is

in,

is the target second parameter,

is the first preset coefficient,

is the second preset coefficient, t is the current iterative update number,

is the candidate target energy-saving parameter,

is the target initial energy-saving parameter. 7. The control method according to claim 5, characterized in that the step of calculating the target second parameter corresponding to each candidate target energy-saving parameter according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter comprises: Calculate the target second parameter corresponding to each candidate energy-saving parameter according to the second corresponding relationship; The second corresponding relationship is

and

in,

is the target second parameter,

is the first preset coefficient,

is the difference between the target initial energy-saving parameter and the candidate target energy-saving parameter, t is the current iterative update number,

is the candidate target energy-saving parameter,

is the target initial energy-saving parameter, and l is the curvature value. 8. The energy-saving control method according to claim 5, characterized in that the search parameter further includes a first random value; when the search probability value is less than a first preset probability value, the target second parameter corresponding to each candidate target energy-saving parameter is calculated according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter, comprising: When the search probability value is less than a first preset probability value and the absolute value of the first random value is less than a preset threshold, calculating the target second parameter corresponding to each candidate target energy-saving parameter according to the candidate target energy-saving parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter; When the search probability value is less than a first preset probability value and the absolute value of the first random value is greater than or equal to a first preset threshold, a random candidate parameter is randomly obtained according to the candidate target energy-saving parameter, and the target second parameter corresponding to each candidate energy-saving parameter is calculated according to the random candidate parameter, the first preset coefficient, the second preset coefficient and the target initial energy-saving parameter. 9. A control device, characterized in that the device comprises: A first acquisition module is used to acquire target data, wherein the target data includes a freezing pump frequency, a cooling pump frequency, and a cooling tower outlet water temperature; A sampling module, for randomly sampling the operating frequencies in the target data that are respectively within the preset multiple frequency bands and the temperatures in the target data that are respectively within the preset multiple temperature ranges, according to the preset multiple frequency bands and the preset multiple temperature ranges, to obtain multiple sampling data groups; A first calculation module, used for calculating the power consumption of the device according to the operating frequency and temperature in the sample data group; A second calculation module, used for calculating the fitness function value according to the relationship between the power consumption and the fitness function value; A second acquisition module is used to determine the operating frequency and temperature in the data group corresponding to the minimum first fitness function value in the fitness function values as the initial energy-saving parameters, and to determine the operating frequency and temperature in the sampled data group corresponding to a preset number of smaller fitness function values other than the initial energy-saving parameters as candidate energy-saving parameters; An optimization module, configured to determine a target energy-saving parameter according to the initial energy-saving parameter and the candidate energy-saving parameter; A control module is used to control the system according to the target energy-saving parameters. 10. A control device, characterized in that the device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the control method according to any one of claims 1 to 8 is implemented. 11. A computer-readable storage medium, characterized in that computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by a processor, the control method according to any one of claims 1 to 8 is implemented.

Images