CN114065994A

CN114065994A - Energy consumption optimization method, device and equipment for air conditioning system and computer storage medium

Info

Publication number: CN114065994A
Application number: CN202010796389.0A
Authority: CN
Inventors: 孙晓杰; 赵健; 王攀; 杨宏华; 李佳欣
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Group Zhejiang Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Group Zhejiang Co Ltd
Priority date: 2020-08-10
Filing date: 2020-08-10
Publication date: 2022-02-18

Abstract

The embodiment of the invention relates to the technical field of air conditioning heating and ventilation, and discloses an energy consumption optimization method for an air conditioning system, which comprises the following steps: acquiring multi-dimensional controllable variable parameters of an air conditioning system and parameter value ranges of the multi-dimensional controllable variable parameters of each dimension; slicing the controllable variable parameters of the multiple dimensions according to the parameter value ranges to obtain multiple sub-parameter value ranges; respectively combining the controllable variable parameters of multiple dimensions into a plurality of target blocks according to the sub-parameter value ranges; calculating a multi-dimensional controllable variable parameter value which enables total energy consumption of the air conditioning system in a preset time period to be minimum in a target block to serve as an optimal solution of the block; taking the block optimal solution which enables the total energy consumption of the air conditioning system to be minimum in the block optimal solutions as a target optimal solution to obtain a target multi-dimensional controllable variable parameter value; and adjusting each controllable variable parameter of the air conditioning system in a preset time period according to the target multi-dimensional controllable variable parameter value. Through the mode, the embodiment of the invention has the beneficial effect of effectively optimizing the energy consumption of the air conditioning system.

Description

Energy consumption optimization method, device and equipment for air conditioning system and computer storage medium

Technical Field

The embodiment of the invention relates to the technical field of air conditioning heating and ventilation, in particular to an energy consumption optimization method, device and equipment for an air conditioning system and a computer readable storage medium.

Background

In actual production scenes of a data center and a communication machine room, the air conditioning system has very high requirements on safety reliability and accurate temperature control, a control parameter constraint mode is not adopted in the prior art, the air conditioning system is more suitable for scenes with relatively low requirements on temperature and humidity precision and safety stability, such as intelligent buildings and shopping buildings, the prior art is less in actual modeling trial operation on a complex central air conditioning system, a model close to the actual condition is difficult to build by modeling in a normalization mode, the prior art only provides the optimal solution of the model for direct control, safety verification is not carried out on the value, and potential safety hazards exist in system operation.

In addition, because the working state of the on-site air conditioning system shows certain ductility during equipment operation from parameter modification to actual effect, the prior art only optimizes the current moment, and the problems of over-adjustment or untimely adjustment of the system and the like are easily caused, thereby causing poor actual energy-saving effect.

Disclosure of Invention

In view of the above problems, an embodiment of the present invention provides an energy consumption optimization method for an air conditioning system, which is used to solve the technical problem in the prior art that a model has a pseudo-optimal solution due to inaccuracy of the model.

According to an aspect of an embodiment of the present invention, there is provided an energy consumption optimization method for an air conditioning system, the method including:

acquiring multi-dimensional controllable variable parameters of an air conditioning system and parameter value ranges of the multi-dimensional controllable variable parameters of each dimension;

slicing the controllable variable parameters of the multiple dimensions according to the parameter value ranges to obtain multiple sub-parameter value ranges of the controllable variable parameters of the multiple dimensions;

respectively combining the controllable variable parameters of the multiple dimensions into a plurality of target blocks according to the sub-parameter value ranges, wherein the target blocks comprise the multi-dimensional controllable variable parameter values in the sub-parameter value ranges corresponding to the target blocks;

calculating a multi-dimensional controllable variable parameter value which enables total energy consumption of the air conditioning system to be minimum in a preset time period in each target block to serve as a block optimal solution of each target block;

taking the block optimal solution which enables the total energy consumption of the air conditioning system to be minimum in the block optimal solutions of all the target blocks as a target optimal solution to obtain a target multi-dimensional controllable variable parameter value;

and adjusting each controllable variable parameter of the air conditioning system in the preset time period according to the target multi-dimensional controllable variable parameter value.

In an optional manner, after calculating a multidimensional controllable variable parameter value that minimizes the total energy consumption of the air conditioning system in each target block within a preset time period as a block optimal solution of each target block, the method further includes:

respectively calculating the distance between the optimal block solution of each target block and the current controllable variable parameter value corresponding to the moment before the preset time period;

when the distance between the optimal block solution of a first block and the current controllable variable parameter value corresponding to the time before the preset time period is greater than a preset distance threshold, determining that the optimal block solution of the first block is a pseudo-optimal solution, wherein the first block is any one target block in the target blocks;

and removing the pseudo-optimal solution from the block optimal solution of each target block, and updating the block optimal solution of each target block.

In an optional manner, calculating a multidimensional controllable variable parameter value in each target block to minimize total energy consumption of the air conditioning system within a preset time period as a block optimal solution of each target block includes:

acquiring a parameter value of each multidimensional controllable variable in the target block in a traversing manner;

calculating the total energy consumption of the air conditioning system in the preset time period according to each multi-dimensional controllable variable parameter value and each uncontrollable variable parameter value;

and taking the multidimensional controllable variable parameter value which enables the total energy consumption of the air conditioning system to be minimum in a preset time period in the target blocks as the block optimal solution of each target block.

In an alternative mode, calculating the multidimensional controllable variable parameter value in each target block, which minimizes the total energy consumption of the air conditioning system within a preset time period, as the block optimal solution of each target block, includes:

obtaining a model fitness function, wherein the model fitness function represents a functional relation between total energy consumption of the air conditioning system and multi-dimensional controllable variable parameter values and uncontrollable variable parameter values of the target block in the preset time period;

randomly initializing a particle swarm of each target block, wherein the particle swarm comprises M particles;

calculating an adaptive value of each particle in the target block according to the model fitness function, and updating a local optimal solution and a global optimal solution of the target block;

updating the speed and position of the particles in the target block;

and recalculating the adaptive value of each particle, updating the local optimal solution and the global optimal solution of the target block, and updating the speed and the position of the particles in the target block until the maximum iteration times or multiple iterations converge to obtain the block optimal solution of the target block.

In an optional mode, the uncontrollable variable parameter value in the preset time period is obtained by predicting through a pre-established parameter prediction model; the parameter prediction model is obtained by training in advance according to the historical time and the value of the historical uncontrollable variable parameter corresponding to the historical time.

In an optional manner, taking the optimal block solution that minimizes the total energy consumption of the air conditioning system from among the optimal block solutions of the target blocks as a target optimal solution, and after obtaining a target multidimensional controllable variable parameter value, the method further includes:

calculating the distance between the target optimal solution and the current controllable variable parameter value corresponding to the moment before the preset time period;

and when the distance between the target optimal solution and the current controllable variable parameter value corresponding to the time before the preset time period is greater than a preset distance threshold, setting the controllable variable parameter value of the air conditioning system in the preset time period as the current controllable variable parameter value corresponding to the time before the preset time period.

According to another aspect of the embodiments of the present invention, there is provided an energy consumption optimization apparatus for an air conditioning system, including:

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring the multi-dimensional controllable variable parameters of the air conditioning system and the parameter value ranges of the controllable variable parameters of all dimensions;

the slicing module is used for slicing the controllable variable parameters of the multiple dimensions according to the parameter value ranges to obtain multiple sub-parameter value ranges of the controllable variable parameters of the multiple dimensions;

a block module, configured to combine the controllable variable parameters of multiple dimensions into multiple target blocks according to the sub-parameter value ranges, where the target blocks include multi-dimensional controllable variable parameter values in the sub-parameter value ranges corresponding to the target blocks;

the first calculation module is used for calculating a multi-dimensional controllable variable parameter value which enables the total energy consumption of the air conditioning system to be minimum in a preset time period in each target block to serve as the block optimal solution of each target block;

the determining module is used for taking the optimal block solution which enables the total energy consumption of the air conditioning system to be minimum in the optimal block solutions of all target blocks as a target optimal solution to obtain a target multi-dimensional controllable variable parameter value;

and the adjusting module is used for adjusting each controllable variable parameter of the air conditioning system in the preset time period according to the target multi-dimensional controllable variable parameter value.

According to another aspect of an embodiment of the present invention, there is provided an air conditioning system including: the air conditioning system comprises an air conditioner and the energy consumption optimizing device of the air conditioning system.

According to another aspect of the embodiments of the present invention, there is provided an air conditioning system energy consumption optimizing apparatus including:

the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation of the air conditioning system energy consumption optimization method.

According to another aspect of the embodiments of the present invention, there is provided a computer-readable storage medium having at least one executable instruction stored therein, which when running on an air conditioning system energy consumption optimizing device/apparatus, causes the air conditioning system energy consumption optimizing device/apparatus to perform the operations of the air conditioning system energy consumption optimizing method described above.

The embodiment of the invention slices the parameter value ranges of the plurality of multidimensional controllable variables to optimize the parameter values in a small range, thereby avoiding direct output of a pseudo-optimal solution caused by inaccurate model and enabling the output to be more accurate. In addition, by setting the preset time period, the total energy consumption of the air conditioning system in the preset time period is calculated to be optimal, the overall energy consumption of the air conditioning system is effectively optimized, frequent switching is avoided, the air conditioning system is enabled to run more stably, and the overall energy-saving effect is achieved.

The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.

Drawings

The drawings are only for purposes of illustrating embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 is a schematic flow chart illustrating an energy consumption optimization method for an air conditioning system according to an embodiment of the present invention;

FIG. 2 is a block optimal solution calculation process according to an embodiment of the present invention;

FIG. 3 is a diagram illustrating the practical effects of energy consumption optimization of the air conditioning system according to the embodiment of the present invention;

FIG. 4 is a schematic structural diagram of an energy consumption optimization device of an air conditioning system according to an embodiment of the present invention;

fig. 5 shows a schematic structural diagram of an energy consumption optimization device of an air conditioning system according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein.

Fig. 1 is a flowchart illustrating an embodiment of an energy consumption optimizing method for an air conditioning system according to the present invention, which is performed by an energy consumption optimizing apparatus for an air conditioning system. The energy consumption optimization equipment of the air conditioning system can be equipment such as computer equipment and terminals, and can also be equipment integrated in the air conditioning system. The energy consumption optimization method of the air conditioning system is suitable for production scenes such as a data center and a communication machine room which have very high requirements on the safety reliability and the accurate temperature control of the air conditioning system, and the energy saving and consumption reducing effects are confirmed to be good by testing the actual production scenes.

Step 110: the method comprises the steps of obtaining controllable variable parameters of multiple dimensions of the air conditioning system and parameter value ranges of the controllable variable parameters of all the dimensions.

The embodiment of the invention takes a data center central air conditioner as an analysis object, and divides parameters influencing the energy consumption of an air conditioning system into three categories according to a neural network deep learning prediction model, wherein the three categories comprise an operation variable parameter of internal equipment of the air conditioning system, an outdoor environment parameter and an indoor demand parameter. Among the three variables, the operation variable parameters of the internal equipment of the air conditioning system are free controllable variables; the outdoor environment parameters are environment uncontrollable variables and are determined by climate conditions; the indoor demand parameters are semi-controllable variables meeting the demand, are determined by the indoor business demand, and can be partially adjusted.

In the embodiment of the invention, the parameters are divided into controllable variable parameters and uncontrollable variable parameters according to the parameter characteristics and the model requirements and according to the controllability characteristics and the model requirements of the three types of parameters.

The controllable variable parameters can include the outlet water temperature of chilled water, the setting parameters of a chilled water pump (chilled water supply and return water pressure difference setting value, the minimum operating frequency of the chilled water pump and other settable values), the setting parameters of the tail end of an air conditioner (air supply/return temperature, air supply/return relative humidity, valve opening and other settable values), the setting parameters of a cooling water pump (cooling water supply and return water pressure difference setting value, cooling water supply and return water temperature difference setting value and cooling water pump minimum operating frequency), the setting parameters of a cooling tower (cooling water outlet water temperature and fan minimum operating frequency), indoor environment temperature control parameters and the like. The uncontrollable variable parameters comprise outdoor temperature parameters, outdoor relative humidity parameters, wind speed parameters, solar radiation parameters, other environment parameters, indoor heat dissipation parameters, indoor environment humidity control parameters and the like.

In the embodiment of the invention, the controllable variable parameter is obtained according to a BA control system. Different data center production scenes are provided with different BA control systems, and monitoring parameters and equipment controllable parameters of the different BA control systems are different, so that corresponding controllable variable parameters and uncontrollable variable parameters can be determined according to the specific BA control systems. That is, the model of the embodiment of the present invention may select different controllable variable parameters and uncontrollable variable parameters as the modeling objects of the neural network.

Therefore, for the total energy consumption of the air conditioning system in the preset time period, the relation is as follows:

wherein, P represents the total energy consumption of the air conditioning system,

representing a multi-dimensional controllable variable parameter value, D representing the dimension of the controllable variable parameter, D being 1,2, 3. H represents time, H ═ 1,2,3,. and H;

representing a multi-dimensional uncontrollable variable parameter value, K representing the dimension of the uncontrollable variable parameter, K being 1,2, 3. H represents time, H ═ 1,2, 3. p is a radical of_i＝f(X_d,Y_k) The black box function of the energy consumption prediction model of the air conditioning system can predict the energy consumption p corresponding to the air conditioning system at the ith moment through the energy consumption prediction model_iNamely, the air conditioner energy consumption at each moment can be predicted through the model. For the embodiment of the invention, the energy consumption prediction model is a model trained in advance according to sample data, wherein the sample data can be obtained by processing the historical controllable variable parameters, the historical uncontrollable variable parameters and the corresponding historical energy consumption of the air conditioning system.

The embodiment of the invention also obtains the parameter value range of the controllable variable parameter, wherein the parameter value range is the safe operation range of the parameter. That is, different production scenarios of the data center have different BA control systems, and monitoring parameters and controllable variable parameters of the equipment are different, and for different production scenarios, safe operation ranges of the controllable variable parameters are also different. For example, the air supply/return temperature in the set parameter for the air conditioner terminal may cause the equipment to operate abnormally if the temperature of the set parameter is too high for the data center.

The embodiment of the present invention does not limit the specific implementation manner of obtaining the parameter value range of the controlled variable parameter. For example, in one embodiment of the invention, the operating range may be derived from historical controllable parameter variables. For another example, the safe operating range of the controllable parameter variable can be predicted by the energy consumption prediction model. As another example, it can also be obtained from historical experience by those skilled in the art.

Wherein, after obtaining the parameter value range of the controllable variable parameter, the multidimensional controllable variable parameter can be obtained

The constraint of (2) is:

d1, 2, 3., D, wherein,

and

respectively, a controlled variable parameter x_dMinimum and maximum values of.

Step 120: and slicing the controllable variable parameters of the multiple dimensions according to the parameter value ranges to obtain multiple sub-parameter value ranges of the controllable variable parameters of the various dimensions.

The slicing according to the parameter value ranges of the plurality of controllable variable parameters refers to splitting the parameter value range of the controllable variable parameter of each dimension into a plurality of pieces to obtain sub-parameter value ranges of the controllable variable parameters.

In the embodiment of the invention, the parameter value range of the controllable variable parameter can be divided into S pieces. That is, for

Respectively dividing each dimension into controllable variable parameters

.., and

the parameter value range of (2) is sliced to obtain the sub-parameter value range of each controllable variable parameter. In one embodiment of the present invention, S ═ 2.

For example, for a controllable variable parameter, the parameter value range is 0-10, and after the controllable variable parameter is divided into 2 pieces, the sub-parameter values range from 0-5 and 5-10.

Step 130: and respectively combining the controllable variable parameters of the multiple dimensions into a plurality of target blocks according to the sub-parameter value ranges, wherein the target blocks comprise the multi-dimensional controllable variable parameter values in the sub-parameter value ranges corresponding to the target blocks.

After each controllable variable parameter is divided into S slices, S sub-parameter value ranges of each dimension of controllable variable parameter are obtained, the sub-parameter value ranges of each dimension of controllable variable parameter are combined with the sub-parameter value ranges of other controllable variable parameters respectively, and the total N is obtained as S^DAnd (5) a target block. The constraint range of the target block is a combination of sub-parameter value ranges of each dimension controllable variable parameter.

After the uniform segmentation into S slices, the constraint range of the target block is the combination of the sub-parameter value ranges of each dimension of the controllable variable parameter, which is expressed as:

or

Taking the nth target block as an example, after being divided into 2 blocks, the constraint range of the nth target block is a combination of sub-parameter value ranges of each dimension of the controllable variable parameter, and is expressed as:

it is to be understood that the above-mentioned nth target block is only one combination of sub-parameter value ranges of the plurality of dimension controllable variable parameters. The constrained range of the target block is also expressed as:

alternatively, it is expressed as:

wherein j and l both belong to values in the range of (0-d).

In the above embodiments of the present invention, the parameter value range is divided into several equal sub-parameter ranges, and it can be understood that the sub-parameter ranges may be distributed unequally.

In one embodiment of the present invention, each controlled variable parameter is divided into 2 pieces, so as to obtain N-2^DAnd (5) a target block. For two-dimensional values of controlled variable parameters

The range of the parameter value is (0-10),

the parameter value range of (20-40), after being respectively cut into 2 pieces,

the sub-parameter values of (1) are (0-5) and (5-10),

has a parameter value in the range of (20-30) and (30-40), and therefore, will be

Sub-parameter value ranges of (A) and (B) respectively

The sub-parameter value ranges are combined to obtain 4 target blocks, and the constraint range of each target block is as follows: [ (0 to 5), (20 to 30)]、[(5～10),(20～30)]、[(0～5),(30～40)]And [ (5 to 10), (30 to 40)]。

Step 140: and taking the block optimal solution which enables the total energy consumption of the air conditioning system to be minimum in the block optimal solutions of all the target blocks as a target optimal solution to obtain a target multi-dimensional controllable variable parameter value.

The block optimal solution refers to the particles which minimize the energy consumption of the air conditioning system in the target block, and the particles are the corresponding multi-dimensional controllable variable parameter values. The energy consumption of the air conditioning system in the preset time period is calculated in the embodiment of the invention, so that the working condition of the next time period (namely the preset time period) at the current moment is predicted in advance by combining the operation characteristics of the BA automatic control system, the total energy consumption in the whole time period is optimized, and the frequent change of parameters of the system to cause the frequent switching of the air conditioning system is avoided, thereby achieving the purposes of saving energy and reducing consumption of the whole system. In the embodiment of the present invention, the preset time period may be the last 6 hours, the last 12 hours, and the like of the current time.

In an embodiment of the present invention, calculating a multidimensional controllable variable parameter value in each target block, which minimizes total energy consumption of an air conditioning system within a preset time period, as a block optimal solution for each target block, includes:

and acquiring the parameter value of each multidimensional controllable variable in the target block in a traversing mode.

And calculating the total energy consumption of the air conditioning system in the preset time period according to each multi-dimensional controllable variable parameter value and each uncontrollable variable parameter value.

In an embodiment of the present invention, the calculation process of the block optimal solution is described by taking the nth target block as an example. Calculating a multidimensional controllable variable parameter value which enables total energy consumption of the air conditioning system to be minimum in a preset time period in each target block to serve as a block optimal solution of each target block, and the method comprises the following steps:

step 1401: and obtaining a model fitness function, wherein the model fitness function represents the functional relation between the total energy consumption of the air conditioning system and the particles and the uncontrollable variable parameters of the target block in the preset time period. In the embodiment of the present invention, the specific form of the model is not specifically limited, and the model fitness function is set accordingly. Because the relationship between the input and the output of the trained model is known, that is, the output corresponding to the input is known, the output value corresponding to each particle can be calculated according to the fitness function corresponding to the model.

In the above example, the nth target block is taken as an example, where the model fitness function of the nth target block can be represented as:

and for the D-dimensional controllable variable parameter, the number of independent variables of the model fitness function is D. By f (X)_d,Y_k) To characterize the pre-set model. Wherein the content of the first and second substances,

the parameter prediction model is obtained by performing prediction according to a pre-established parameter prediction model, wherein the parameter prediction model is obtained by training according to historical time and the value of the historical uncontrollable variable parameter corresponding to the historical time. For example, for the temperature and humidity parameters, a preset LSTM or time series algorithm neural network model may be input to train according to the historical temperature and historical humidity corresponding to each time in the day, so as to obtain a prediction model for predicting the temperature and humidity in H time periods in the future. Uncontrollable variable parameterAnd predicting in advance according to the parameter prediction model, and using the predicted parameters as model constants. It will be appreciated by those skilled in the art that for the nth block, the constraint range is as shown by the model fitness function described above. However, for other target blocks with different constraint ranges, the model fitness function is adjusted accordingly.

Step 1402: and randomly initializing the particle swarm of each target block.

Setting the particle swarm size of the nth target block to be M, namely selecting M particles as the number of the particles of the nth target block; setting the maximum iteration number as T and the ith particle current position vector as X_i＝(x_i,1,x_i,2,x_i,3,…,x_i,D) 1,2,3, ·, M; the flight velocity of the ith particle is V_i＝(v_i,1,v_i,2,v_i,3,…,v_i,D) 1,2, 3. Randomly initializing the positions of the particles in the nth target block and randomly initializing the flight speed of each particle. In the embodiment of the present invention, the value of M is not specifically limited, for example, the general value of M is between 10 and 40; according to the parameter situation, 10 particles are selected for most problems. For the case that the controlled variable parameter is more complex, the number of particles may be 100-. The larger the particle size, the more accurate the calculation, but the higher the performance requirements of the system and the slower the calculation speed. The range of the particles is the sub-parameter value range corresponding to the controllable variable parameter in different target blocks. The maximum flight speed of a particle is generally the range width of the particle, that is, the range width of the sub-parameter values corresponding to the controllable variable parameters in different target blocks.

Step 1403: and calculating the adaptive value of each particle in the target block according to the model fitness function, and updating the local optimal solution and the global optimal solution of the target block.

Calculating the adaptive value of each particle in the nth target block according to the model fitness function, thereby finding out the optimal position P of the ith particle searched at present_i＝(p_i,1,p_i,2,p_i,3,…,p_i,D) 1,2, 3. The optimum positionI.e. the locally optimal solution.

Step 1404: and updating the speed and the position of the particles in the target block until the maximum iteration times are reached or the multiple iterations are not updated, and obtaining the block optimal solution of the target block.

Wherein, the position and the speed of the particles are updated by adopting the following formula:

where t denotes the current number of iterations, c₁And c₂As an acceleration factor, γ₁And gamma₂Is [0,1 ]]W is the inertial weight, w ═ w_up-t*(w_up-w_low)/N。c₁And c₂Typically between 0 and 4.

The iterative update step of steps 1403-1404 is re-performed by updating the velocity and position of the particle in the target block, and in each iteration the particle updates itself by tracking two "extrema". The first is the optimal solution found by the particle itself

Another extreme is the optimal solution found for the entire population

And obtaining the global optimal solution of the nth target block at the moment as the block optimal solution of the target block until the maximum iteration times is reached or the value after multiple iterations is not changed (namely converged).

The above steps are described by taking the nth target block as an example, and it can be understood that the above settings can be adjusted accordingly for different target blocks.

In one embodiment of the inventionFor a data center air conditioning system, the BA manipulated variable for the air conditioning system is selected as: the system comprises 5 controllable variable parameters such as the outlet water temperature of the chilled water of the host, the wet bulb temperature deviation of the cooling tower, the supply and return water pressure difference of a cooling water pump and the like, wherein the uncontrollable variable parameters are the environment temperature and humidity and the IT load, and are predicted in advance according to a parameter prediction model and can be used as model constants. The energy consumption optimization process comprises the following steps: each of the controlled variable parameters was sliced into 2 pieces according to the above-mentioned parameter ranges of 5 controlled variable parameters, i.e., the safe operating range, and thus 32 blocks were formed. Setting the number of particles of each block as 10, the maximum iteration number as 500 and a learning factor c₁＝1.5,c₂＝1.2,w_up＝1,w_lowWhen the block is found to be the optimal solution, the block is found from 32 blocks, and the block optimal solution is obtained as shown in fig. 2. As can be seen from the figure, the optimization trajectory of the optimization algorithm is continuously close to the block optimal solution. And after the optimal solution of each block is obtained, optimizing according to the optimal solution of each block to obtain a target optimal solution, and adjusting 5 parameters of the air conditioning system according to the target optimal solution. Referring to fig. 3, a diagram showing an actual effect of energy consumption optimization according to an embodiment of the present invention is shown, where the optimization process starts at point a, and after the optimization method according to the embodiment of the present invention is performed, the energy consumption of the air conditioning system is significantly reduced when the ambient temperatures are close to each other.

In the embodiment of the present invention, after calculating the multidimensional controllable variable parameter value that minimizes the total energy consumption of the air conditioning system in the preset time period in each target block as the block optimal solution of each target block, the method further includes:

and respectively calculating the distance between the optimal block solution of each target block and the current controllable variable parameter value corresponding to the moment before the preset time period.

And calculating the distance between the optimal block solution of each target block and the current controllable variable parameter value corresponding to the moment before the preset time period by adopting the following Euclidean calculation formula:

and when the distance between the optimal block solution of the first block and the current controllable variable parameter value corresponding to the time before the preset time period is greater than a preset distance threshold, determining that the optimal block solution of the first block is a pseudo-optimal solution, wherein the first block is any one target block in the target blocks. In the embodiment of the invention, the preset distance threshold is obtained by analyzing and calculating according to the difference between the optimal solution of the historical block and the historical current controllable variable parameter value.

Since the variation of the uncontrollable variable parameters such as the external objective environmental conditions is generally fluctuation variation and less abrupt change occurs, the value of the multidimensional controllable variable parameters in the block optimal solution theoretically does not have great abrupt change, and therefore, the pseudo optimal solution can be effectively distinguished through the distance calculation process. Although the accuracy of the model can be improved by continuously increasing the data feeding, the data width and the data accuracy of the model in general, certain inaccurate data still exist, so that the influence of partial discrete points on the overall accuracy of the model is possibly not large, but for an optimization algorithm, the optimization is very easy to obtain a pseudo-optimal solution, and the pseudo-optimal solution not only cannot achieve the purpose of system optimization, but also can influence the safe and stable operation of the system. Therefore, the optimal solution of the block is searched for each target block in a slicing and blocking mode, and the occurrence of a pseudo-optimal solution to a certain degree can be overcome. In addition, the distance calculation is carried out between the current controllable variable parameter value of the air conditioning system, the secondary verification optimization is carried out, and the problem of a pseudo-optimal solution generated by overfitting of a neural network model is further solved.

Step 150: and taking the block optimal solution which enables the total energy consumption of the air conditioning system to be minimum in the block optimal solutions of all the target blocks as a target optimal solution to obtain a target multi-dimensional controllable variable parameter value.

After the block optimal solution of each target block is obtained, calculating the energy consumption of the air conditioning system corresponding to each block optimal solution, taking the block optimal solution with the minimum energy consumption of the air conditioning system as the target optimal solution, and taking the controllable variable parameter value corresponding to the target optimal solution as the target multi-dimensional controllable variable parameter value.

Step 160: and adjusting each controllable variable parameter of the air conditioning system in the preset time period according to the target multi-dimensional controllable variable parameter value.

In the embodiment of the present invention, after the target optimal solution is obtained through calculation, a distance between the target optimal solution and the current controllable variable parameter value corresponding to the time before the preset time period may also be calculated. If the distance is too large, the target optimal solution is a pseudo optimal solution, in order to ensure the safe and stable operation of the system, the parameter adjustment of the air conditioning system is not carried out, and the controllable variable parameter value of the air conditioning system in a preset time period is set as the current controllable variable parameter value corresponding to the time before the preset time period.

The embodiment of the invention slices the parameter value ranges of the plurality of multidimensional controllable variables to optimize the parameter values in a small range, thereby avoiding direct output of a pseudo-optimal solution caused by inaccurate model and enabling the output to be more accurate. In addition, by setting the preset time period, the total energy consumption of the air conditioning system in the preset time period is calculated to be optimal, frequent switching is avoided, the air conditioning system is enabled to run more stably, and the overall energy-saving effect is achieved.

Fig. 4 is a schematic structural diagram illustrating an embodiment of the energy consumption optimization device of the air conditioning system according to the present invention. As shown in fig. 4, the apparatus 200 includes: an acquisition module 210, a slicing module 220, a blocking module 230, a first calculation module 240, a determination module 250, and an adjustment module 260.

The obtaining module 210 is configured to obtain multiple dimensions of controllable variable parameters of the air conditioning system and parameter value ranges of the controllable variable parameters of each dimension;

the slicing module 220 is configured to slice the controllable variable parameters of the multiple dimensions according to the parameter value ranges to obtain multiple sub-parameter value ranges of the controllable variable parameters of each dimension;

a block module 230, configured to combine the controllable variable parameters of multiple dimensions into multiple target blocks according to the sub-parameter value ranges, where the target blocks include multi-dimensional controllable variable parameter values in the sub-parameter value ranges corresponding to the target blocks;

a first calculating module 240, configured to calculate a multidimensional controllable variable parameter value that minimizes total energy consumption of the air conditioning system within a preset time period in each target block, as a block optimal solution of each target block;

a determining module 250, configured to use, as a target optimal solution, a block optimal solution that minimizes the total energy consumption of the air conditioning system from among block optimal solutions of each target block, to obtain a target multidimensional controllable variable parameter value;

and the adjusting module 260 is configured to adjust each controllable variable parameter of the air conditioning system within the preset time period according to the target multidimensional controllable variable parameter value.

updating the speed and position of the particles in the target block;

The specific working process of the energy consumption optimization device 300 of the air conditioning system in the embodiment of the present invention is the same as the specific steps of the energy consumption optimization method of the air conditioning system, and is not described herein again.

Fig. 5 is a schematic structural diagram illustrating an embodiment of an energy consumption optimization device of an air conditioning system according to the present invention, and the specific embodiment of the present invention is not limited to the specific implementation of the energy consumption optimization device of the air conditioning system.

As shown in fig. 5, the air conditioning system energy consumption optimizing apparatus may include: a processor (processor)402, a Communications Interface 404, a memory 406, and a Communications bus 408.

Wherein: the processor 402, communication interface 404, and memory 406 communicate with each other via a communication bus 408. A communication interface 404 for communicating with network elements of other devices, such as clients or other servers. The processor 402 is configured to execute the program 410, and may specifically execute the relevant steps in the embodiment of the method for optimizing energy consumption of an air conditioning system.

In particular, program 410 may include program code comprising computer-executable instructions.

The processor 402 may be a central processing unit CPU or an application Specific Integrated circuit asic or one or more Integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the energy consumption optimization device of the air conditioning system can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.

And a memory 406 for storing a program 410. Memory 406 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

Specifically, the program 410 may be invoked by the processor 402 to cause the air conditioning system energy consumption optimization device to perform the following operations:

updating the speed and position of the particles in the target block;

The specific working process of the energy consumption optimization device of the air conditioning system in the embodiment of the present invention is the same as the specific steps of the energy consumption optimization method of the air conditioning system, and is not described herein again.

The embodiment of the invention provides a computer-readable storage medium, wherein the storage medium stores at least one executable instruction, and when the executable instruction runs on an air conditioning system energy consumption optimization device/apparatus, the air conditioning system energy consumption optimization device/apparatus executes the air conditioning system energy consumption optimization method in any method embodiment.

The executable instructions may be specifically configured to cause the air conditioning system energy consumption optimization device/apparatus to perform the following operations:

updating the speed and position of the particles in the target block;

The specific working process of the computer-readable storage medium in the embodiment of the present invention is the same as the specific steps of the above-mentioned method for optimizing energy consumption of an air conditioning system, and is not described herein again.

The embodiment of the invention provides an energy consumption optimization device of an air conditioning system, which is used for executing the energy consumption optimization method of the air conditioning system.

Embodiments of the present invention provide a computer program, where the computer program can be called by a processor to enable an air conditioning system energy consumption optimization device to execute the air conditioning system energy consumption optimization method in any of the above method embodiments.

Embodiments of the present invention provide a computer program product, including a computer program stored on a computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are run on a computer, the computer is caused to execute the method for optimizing energy consumption of an air conditioning system in any of the above method embodiments.

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.

Claims

1. An energy consumption optimization method for an air conditioning system is characterized by comprising the following steps:

2. The method of claim 1, wherein after calculating the minimum multidimensional controllable variable parameter value that enables total energy consumption of the air conditioning system in each target block within a preset time period as the block optimal solution of each target block, the method further comprises:

3. The method of claim 1, wherein calculating the multidimensional controllable variable parameter value in each target block, which minimizes the total energy consumption of the air conditioning system within a preset time period, as the block optimal solution of each target block comprises:

4. The method as claimed in claim 1, wherein calculating the multidimensional controllable variable parameter value which minimizes the total energy consumption of the air conditioning system within the preset time period in each target block as the block optimal solution of each target block comprises:

updating the speed and position of the particles in the target block;

5. The method according to claim 4, wherein the uncontrollable variable parameter values in the preset time period are obtained by prediction through a pre-established parameter prediction model; the parameter prediction model is obtained by training in advance according to the historical time and the value of the historical uncontrollable variable parameter corresponding to the historical time.

6. The method of claim 5, wherein the step of taking the optimal block solution that minimizes the total energy consumption of the air conditioning system from among the optimal block solutions of the target blocks as the optimal target solution, and after obtaining the target multidimensional controllable variable parameter value, further comprises:

7. An apparatus for optimizing energy consumption of an air conditioning system, the apparatus comprising:

8. An air conditioning system, characterized in that the air conditioning system comprises an air conditioner and the energy consumption optimization device of the air conditioning system as claimed in claim 7.

9. An air conditioning system energy consumption optimizing apparatus, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation of the air conditioning system energy consumption optimization method according to any one of claims 1-6.

10. A computer-readable storage medium, wherein the storage medium has stored therein at least one executable instruction, which when executed on an air conditioning system energy consumption optimizing device/apparatus, causes the air conditioning system energy consumption optimizing device/apparatus to perform the operations of the air conditioning system energy consumption optimizing method according to any one of claims 1 to 6.