Energy-saving control method and device

Abstract

The invention relates to the field of air conditioners, and provides an energy-saving control method and device.The method comprises the steps that equipment operation data and outdoor unit target air suction pressure at a target moment are obtained, and the outdoor unit target air suction pressure is used for representing the optimal outdoor unit target air suction pressure corresponding to the last target moment before the target moment; according to the equipment operation data and the outdoor unit target air suction pressure, the optimal outdoor unit target air suction pressure is obtained through a power prediction model and a preset particle swarm optimization algorithm; wherein the power prediction model is constructed based on historical operation data of the equipment; and controlling the air conditioner to operate according to the optimal outdoor unit target air suction pressure. The problem that energy consumption may be increased due to the fact that energy is saved by sacrificing the refrigerating or heating capacity is solved, it is ensured that the air conditioner outdoor unit operates under the efficient working condition, energy waste caused by unreasonable air suction pressure is avoided, and the energy-saving effect is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioners, and in particular, to an energy-saving control method and device. Background Art

[0002] With the development of air conditioner technology, air conditioners are widely used in ordinary families, offices, office buildings, stores, shopping malls, leisure and entertainment venues, factories and other scenarios. While bringing comfort and convenience to our lives, air conditioners also consume a large amount of national, social and user funds and energy every year. In traditional multi-connected air conditioners, there are energy waste situations such as overcooling or overheating during refrigeration and heating, and the compressor may not always operate at the optimal state, which is also likely to cause energy waste.

[0003] Currently, energy conservation is mainly achieved by sacrificing refrigeration or heating capacity. Generally, users can control the refrigeration or heating capacity by adjusting the temperature or turning off the energy-saving mode according to the refrigeration or heating effect.

[0004] However, when sacrificing refrigeration or heating capacity, the indoor temperature may not quickly reach the comfortable temperature range expected by the user, and the user may need to frequently switch between the energy-saving mode and the normal mode, which may instead increase energy consumption, cause certain wear and tear to key components such as the compressor, reduce the operating efficiency of the equipment, and affect the service life of the equipment. Summary of the Invention

[0005] The present invention provides an energy-saving control method and device to solve the defect that energy conservation by sacrificing refrigeration or heating capacity in the prior art may instead increase energy consumption, ensure that the outdoor unit of the air conditioner operates under efficient working conditions, avoid energy waste caused by unreasonable suction pressure, and achieve the effect of energy conservation.

[0006] The present invention provides an energy-saving control method, including: obtaining device operation data and an outdoor unit target suction pressure at a target moment, where the outdoor unit target suction pressure is used to represent the optimal outdoor unit target suction pressure corresponding to the previous target moment prior to the target moment; according to the device operation data and the outdoor unit target suction pressure, using a power prediction model and a preset particle swarm optimization algorithm to obtain the optimal outdoor unit target suction pressure; wherein, the power prediction model is constructed based on device historical operation data; controlling the operation of the air conditioner according to the optimal outdoor unit target suction pressure.

[0007] It should be noted that by obtaining the device operation data and the target suction pressure of the outdoor unit at the target moment, and using the power prediction model and the particle swarm optimization algorithm, the optimal target suction pressure of the outdoor unit can be dynamically and accurately found according to the actual situation, so as to control the operation of the air conditioner according to the optimal target suction pressure of the outdoor unit, ensure that the outdoor unit of the air conditioner operates under efficient working conditions, avoid energy waste caused by unreasonable suction pressure, and achieve the effect of energy saving. In addition, by obtaining the device operation data at the target moment, it is convenient to perform personalized adaptation according to the actual situation, and better meet the personalized needs of users for comfort indicators such as indoor temperature and humidity.

[0008] According to the present invention, an energy-saving control method is provided. According to the device operation data and the target suction pressure of the outdoor unit, using the power prediction model and the preset particle swarm optimization algorithm, the optimal target suction pressure of the outdoor unit is obtained, including: generating the suction pressures that meet the target quantity according to the target suction pressure of the outdoor unit and the preset fluctuation range, and encoding each suction pressure to obtain the particles corresponding to each suction pressure and the particle swarm composed of each particle; randomly generating the initial positions and velocities of each particle to initialize each particle, and for each particle, inputting the corresponding suction pressure and the device operation data into the power prediction model to obtain the predicted instantaneous power of the outdoor unit of the corresponding particle output by the power prediction model; using the preset particle swarm optimization algorithm to perform an optimization exploration on the particles according to the predicted instantaneous power of the outdoor unit corresponding to each particle and the first indoor unit operation capacity obtained in advance based on the device operation data, to obtain the optimal target suction pressure of the outdoor unit; wherein, the indoor unit operation capacity is used to represent the cooling or heating capacity under the corresponding air conditioner operation mode.

[0009] It should be noted that by generating the suction pressures that meet the target quantity according to the target suction pressure of the outdoor unit and the preset fluctuation range, and constructing a particle swarm, to comprehensively explore various possible values of the suction pressure, avoid the limitation of only considering a single or a few suction pressure values, increase the possibility of finding the global optimal solution subsequently, and introduce the indoor unit operation capacity as a constraint condition or an evaluation factor in the optimization process of the particle swarm optimization algorithm, ensure that while pursuing the optimization of the predicted instantaneous power of the outdoor unit, the cooling or heating capacity of the indoor unit will not be sacrificed, so that the performance optimization of the entire air conditioner system starts from the perspective of the coordinated operation of the indoor and outdoor units, avoid the problem of overall performance imbalance caused by local optimization, improve the practicality and effectiveness of the optimization result, and ensure that the air conditioner operates efficiently and energy-savingly under the premise of meeting the cooling or heating demand.

[0010] An energy-saving control method provided by the present invention, based on the predicted instantaneous power of the outdoor unit corresponding to each particle and the first indoor unit operating capacity obtained in advance based on equipment operation data, uses a preset particle swarm optimization algorithm to perform an optimization exploration on the particles to obtain the optimal outdoor unit target suction pressure, including: updating the individual positions of the corresponding particles according to the predicted instantaneous power of the outdoor unit corresponding to each particle, the first indoor unit operating capacity, and the second indoor unit operating capacity of each particle obtained in advance, and determining the global optimal position according to the updated individual positions of each particle; based on a preset speed update strategy and a preset position update strategy, updating the positions and speeds of the updated particles again, and for each updated particle, inputting the updated particle and equipment operation data into a power prediction model to obtain the predicted instantaneous power of the outdoor unit corresponding to the updated particle output by the power prediction model, updating the individual positions of each updated particle according to the predicted instantaneous power of the outdoor unit corresponding to each updated particle, the first indoor unit operating capacity, and the second indoor unit operating capacity of each updated particle obtained in advance, and re-determining the global optimal position according to the individual positions of each particle after the second update, repeating the iteration until the number of iterations meets the preset number or the particle swarm converges, and outputting the global optimal position obtained in the last iteration; obtaining the optimal outdoor unit target suction pressure according to the suction pressure corresponding to the global optimal position.

[0011] It should be noted that by jointly incorporating the predicted instantaneous power of the outdoor unit corresponding to each particle, the first indoor unit operating capacity, and the second indoor unit operating capacity into the optimization process, not only the energy consumption performance of the outdoor unit is concerned, but also the actual capacity of the indoor unit during the refrigeration or heating process is closely combined, ensuring that the performance of the indoor unit will not be damaged due to the one-sided pursuit of the efficiency of the outdoor unit when optimizing the suction pressure, thus comprehensively balancing the coordinated operation of the indoor and outdoor units of the air conditioner. And a preset speed update strategy and a preset position update strategy are used to perform multiple updates and iterative calculations on the particles, so that in each iteration, the particles update their positions and speeds according to their own historical optimal positions, global optimal positions, and speed information, ensuring rapid positioning to a better area within a large search space and gradually converging to the vicinity of the global optimal solution as the number of iterations increases, thereby more effectively using computing resources and finding the optimal outdoor unit target suction pressure that meets the requirements in a shorter time.

[0012] An energy-saving control method provided by the present invention updates the individual positions of corresponding particles according to the predicted instantaneous power of the outdoor unit corresponding to each particle, the operating capacity of the first indoor unit, and the operating capacity of the second indoor unit of each particle obtained previously, and determines the global optimal position according to the updated individual positions of each particle, including: for each particle, estimating the corresponding operating capacity of the second indoor unit; determining whether the operating capacity of the second indoor unit of each particle is lower than that of the first indoor unit; based on the operating capacity of the second indoor unit of the particle being lower than that of the first indoor unit, comparing the predicted instantaneous power of the outdoor unit of the particle with a preset power. If the predicted instantaneous power of the outdoor unit of the particle is less than the preset power, the predicted instantaneous power of the outdoor unit is used as the optimal power of the corresponding particle, and the individual position of the particle is updated. Otherwise, the individual position of the corresponding particle is not updated; based on the operating capacity of the second indoor unit of the particle not being lower than that of the first indoor unit, the individual position of the corresponding particle is not updated; according to the updated individual positions of the particles and / or the non-updated individual positions of the particles, an updated particle swarm is obtained, and the individual position corresponding to the minimum optimal power in the updated particle swarm is selected as the global optimal position.

[0013] It should be noted that by simultaneously considering the predicted instantaneous power of the outdoor unit corresponding to the particle, the operating capacity of the first indoor unit, and the operating capacity of the second indoor unit obtained based on each suction pressure, a comprehensive system for evaluating the pros and cons of particles is constructed. When updating the individual position of the particle, it is not simply based on a single factor such as the predicted instantaneous power of the outdoor unit or the operating capacity of the indoor unit, but a careful balance is made between the two. The particle position is updated only when the operating capacity of the second indoor unit is not lower than that of the first indoor unit and the predicted instantaneous power of the outdoor unit is less than the preset power. This multi-factor comprehensive decision-making mechanism can ensure that neither the cooling and heating effect of the indoor unit is sacrificed due to excessive pursuit of low power, nor the energy consumption is ignored due to one-sided emphasis on the performance of the indoor unit during the optimization process. Thus, it can accurately balance the performance and energy consumption of the indoor and outdoor units of the air-conditioning system, enabling the air-conditioning to operate efficiently and energy-savingly while ensuring good use comfort.

[0014] An energy-saving control method provided by the present invention, before inputting the corresponding suction pressure and equipment operation data into the power prediction model for each particle, includes: obtaining a cloud model, which is previously constructed by the cloud based on equipment historical operation data. The equipment historical operation data includes operation data corresponding to at least one historical moment, and the operation data includes compressor frequency, outdoor unit expansion valve opening, outdoor unit suction pressure, outdoor unit discharge pressure, outdoor unit ambient temperature, outdoor unit instantaneous power, the on / off states of each indoor unit, the trachea temperature of each indoor unit, and the liquid pipe temperature of each indoor unit; converting and loading the cloud model to obtain a power prediction model.

[0015] It should be noted that by obtaining the model constructed by the cloud based on the historical operation data of the device, and transforming and loading the data obtained from the cloud, while quickly realizing the localization of the model, it is ensured that the latest and most optimized power prediction model can be applied in a timely manner, which helps to improve the implementation efficiency of the entire optimization process, enabling the air conditioning system to more quickly optimize the operation parameters based on this model. Additionally, by making full use of multiple historical moments and various detailed operation parameters stored in the cloud, such as compressor frequency, outdoor expansion valve opening, suction pressure, discharge pressure, ambient temperature, instantaneous power, and relevant indoor unit temperatures and startup states, etc., the complex operation laws of the device under different working conditions and different operation conditions can be better captured, making the constructed power prediction model more general and accurate compared to local construction, capable of more accurately predicting the instantaneous power of the outdoor unit, and thus providing a reliable basis for subsequent particle swarm optimization exploration.

[0016] According to an energy-saving control method provided by the present invention, transforming and loading the cloud model to obtain a power prediction model includes: transforming the cloud model based on a preset model format to obtain a model to be loaded; obtaining node parameters according to the model to be loaded, where the node parameters are used to represent the parameters of the basic operation units of the model to be loaded; quantifying the node parameters and combining with a preset compilation template to generate and load a compilation file to obtain a power prediction model.

[0017] It should be noted that transforming the cloud model based on a preset model format to ensure the compatibility of the model with the operating environment and related software and hardware systems of the local device. Through this standardized transformation process, the model obtained from the cloud can be smoothly adapted to the local environment, avoiding problems such as unable to load or running errors due to inconsistent formats, improving the generality and stability of model application, and ensuring the smooth implementation of the entire air conditioning operation optimization process based on the power prediction model.

[0018] According to an energy-saving control method provided by the present invention, before using a preset particle swarm optimization algorithm to perform optimization exploration on particles based on the predicted instantaneous power of the outdoor unit corresponding to each particle and the first indoor unit operation ability obtained in advance based on the device operation data, it includes: searching the operation database according to the device operation data to obtain the indoor unit operation ability; where the operation database is constructed in advance based on the indoor unit operation ability corresponding to the device operation data under different operation modes of the air conditioner, and the indoor unit operation ability is used to represent the cooling or heating ability under the corresponding operation mode.

[0019] It should be noted that the operating capacity of the indoor unit is obtained by querying the operation database, so as to quickly obtain the required information and save computing resources and time costs. In addition, since the operation database is constructed based on a large amount of equipment operation data under different operating modes of the air conditioner, and these data reflect the true performance of the indoor unit under different working conditions during the actual operation of the air conditioner, the operating capacity of the indoor unit obtained by querying the operation database can accurately reflect the cooling or heating capacity of the indoor unit under the current equipment operation state, providing an accurate data basis for the subsequent exploration of the particle swarm optimization algorithm by combining the prediction of the instantaneous power of the outdoor unit, and helping to find the optimal target suction pressure of the outdoor unit that better meets the actual needs and can balance the performance of the indoor and outdoor units.

[0020] The present invention also provides an energy-saving control device, including: a data acquisition module, which acquires the equipment operation data and the target suction pressure of the outdoor unit at the target moment, and the target suction pressure of the outdoor unit is used to represent the optimal target suction pressure of the outdoor unit corresponding to the previous target moment prior to the target moment; a pressure optimization module, which obtains the optimal target suction pressure of the outdoor unit according to the equipment operation data and the target suction pressure of the outdoor unit by using a power prediction model and a preset particle swarm optimization algorithm; wherein, the power prediction model is constructed based on the historical operation data of the equipment; an energy-saving control module, which controls the operation of the air conditioner according to the optimal target suction pressure of the outdoor unit.

[0021] It should be noted that the equipment operation data and the target suction pressure of the outdoor unit at the target moment are acquired by the data acquisition module, and the pressure optimization module uses the power prediction model and the particle swarm optimization algorithm to dynamically and accurately find the optimal target suction pressure of the outdoor unit according to the actual situation. Then, the energy-saving control module controls the operation of the air conditioner according to the optimal target suction pressure of the outdoor unit, ensuring that the outdoor unit of the air conditioner operates under efficient working conditions, avoiding energy waste caused by unreasonable suction pressure, and achieving the effect of energy saving. In addition, by acquiring the equipment operation data at the target moment, it is convenient to perform personalized adaptation according to the actual situation, and better meet the personalized needs of users for comfort indicators such as indoor temperature and humidity.

[0022] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the energy-saving control method as described in any one of the above are implemented.

[0023] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the energy-saving control method as described in any one of the above are implemented. Description of the Drawings

[0024] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0025] Figure 1 is a schematic flowchart of the energy-saving control method provided by the present invention; Figure 2 is a schematic structural diagram of the energy-saving control device provided by the present invention; Figure 3 is a schematic structural diagram of the electronic device provided by the present invention. Detailed Embodiments

[0026] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0027] Figure 1 A schematic flowchart of an energy-saving control method of the present invention is described. The method includes: S11. Obtain the device operation data at the target moment and the target suction pressure of the outdoor unit. The target suction pressure of the outdoor unit is used to represent the optimal target suction pressure of the outdoor unit corresponding to the previous target moment prior to the target moment; S12. According to the device operation data and the target suction pressure of the outdoor unit, use the power prediction model and the preset particle swarm optimization algorithm to obtain the optimal target suction pressure of the outdoor unit; wherein, the power prediction model is constructed based on the historical operation data of the device; S13. Control the operation of the air conditioner according to the optimal target suction pressure of the outdoor unit.

[0028] It should be noted that the step numbers "S1N" in this specification do not represent the sequence of the energy-saving control method. The following specifically describes the energy-saving control method of the present invention.

[0029] In step S11, obtain the device operation data at the target moment and the target suction pressure of the outdoor unit. The target suction pressure of the outdoor unit is used to represent the optimal target suction pressure of the outdoor unit corresponding to the previous target moment prior to the target moment.

[0030] It should be noted that the target moment can be determined according to the actual energy-saving control requirements and the preset time interval. For example, if the previous target moment is t and the preset time interval is 5 minutes, then the next target moment is t + 5, and no further limitation is made here.

[0031] In addition, in the initial state, the target suction pressure of the outdoor unit can be set according to prior experience or actual design requirements. In other states, the target suction pressure of the outdoor unit can be the optimal target suction pressure of the outdoor unit at the previous target moment. The optimal target suction pressure of the outdoor unit at the previous target moment can be obtained according to the following method or determined based on prior experience, and no further limitation is made here.

[0032] Step S12: According to the device operation data and the target suction pressure of the outdoor unit, use the power prediction model and the preset particle swarm optimization algorithm to obtain the optimal target suction pressure of the outdoor unit; among them, the power prediction model is constructed based on the historical operation data of the device.

[0033] In this embodiment, according to the device operation data and the target suction pressure of the outdoor unit, using the power prediction model and the preset particle swarm optimization algorithm to obtain the optimal target suction pressure of the outdoor unit includes: generating the suction pressures that meet the target quantity according to the target suction pressure of the outdoor unit and the preset fluctuation range, and encoding each suction pressure to obtain the particles corresponding to each suction pressure and the particle swarm composed of each particle; randomly generating the initial positions and velocities of each particle to initialize each particle, and for each particle, inputting the corresponding suction pressure and the device operation data into the power prediction model to obtain the predicted instantaneous power of the outdoor unit corresponding to the particle output by the power prediction model; according to the predicted instantaneous power of the outdoor unit corresponding to each particle and the first indoor unit operation capacity obtained in advance based on the device operation data, using the preset particle swarm optimization algorithm to perform an optimization search on the particles to obtain the optimal target suction pressure of the outdoor unit; among them, the indoor unit operation capacity is used to characterize the cooling or heating capacity under the corresponding air-conditioning operation mode.

[0034] It should be noted that by generating the suction pressures that meet the target quantity according to the target suction pressure of the outdoor unit and the preset fluctuation range and constructing a particle swarm to comprehensively explore various possible values of the suction pressure, the limitation of only considering a single or a few suction pressure values is avoided, increasing the possibility of finding the global optimal solution in the follow-up. And in the optimization search process of the particle swarm optimization algorithm, the indoor unit operation capacity is introduced as a constraint condition or evaluation factor to ensure that while pursuing the optimization of the predicted instantaneous power of the outdoor unit, the cooling or heating capacity of the indoor unit will not be sacrificed, so that the performance optimization of the entire air-conditioning system starts from the perspective of the coordinated operation of the indoor and outdoor units, avoiding the problem of overall performance imbalance caused by local optimization, improving the practicality and effectiveness of the optimization result, and ensuring that the air-conditioning can achieve efficient energy-saving operation while meeting the cooling or heating requirements.

[0035] In addition, the power prediction model is constructed based on the historical operation data of the device in advance, making the entire optimization process have the intelligent characteristics of data-driven. Through the learning and analysis of a large amount of historical data, the model can capture the complex relationship between the device operation data, the suction pressure of the outdoor unit, and the power. Furthermore, it provides accurate power prediction information for the particle swarm optimization algorithm, assisting it to quickly and effectively find the optimal solution, thus automatically adapting to different device operation conditions and environmental changes without frequent manual intervention and complex parameter adjustment, improving the intelligent level and self-adaptability of the air conditioning system. In addition, the preset fluctuation range can be configured based on the actual optimization design requirements or prior experience, such as ±10%, ±20%, etc., and no further limitation is made here.

[0036] It should be added that machine learning algorithms or deep learning architectures can be used to construct the power prediction model to improve the prediction accuracy and generalization ability of the model. For example, the long short-term memory network (LSTM) can be adopted to process the temporal information in the device operation data to better capture the dynamic characteristics of the air conditioning system at different time steps, thereby providing more accurate power prediction results for the particle swarm optimization algorithm and helping to find a better target suction pressure for the outdoor unit. In addition, ensemble learning of the model can also be considered, combining the prediction results of multiple different basic models (such as neural networks, support vector machines, etc.) to further reduce the prediction error and improve the optimization effect.

[0037] In addition, an adaptive parameter adjustment strategy can be adopted to dynamically adjust the values of the parameters (such as inertia weight, learning factor, number of particles, etc.) in the particle swarm optimization algorithm according to the search progress during the optimization process. For example, at the initial stage of optimization, the inertia weight can be appropriately increased to enable the particles to explore in a larger search space and avoid premature convergence to local optima; at the later stage of optimization, the inertia weight is gradually reduced to enhance the convergence speed of the particles to the local and global optimal positions. The adaptive parameter adjustment strategy can be configured based on the actual design requirements or prior experience. By optimizing the parameters in the particle swarm optimization algorithm using the adaptive parameter adjustment strategy, the search efficiency and optimization quality of the particle swarm optimization algorithm can be improved, and the optimal target suction pressure for the outdoor unit can be found more quickly.

[0038] Specifically, according to the predicted instantaneous power of the outdoor unit corresponding to each particle and the first indoor unit operating capacity obtained based on the prior device operation data, using the preset particle swarm optimization algorithm to perform an optimization exploration on the particles to obtain the optimal suction pressure of the outdoor unit target, including: updating the individual positions of the corresponding particles according to the predicted instantaneous power of the outdoor unit, the first indoor unit operating capacity, and the second indoor unit operating capacity of each particle obtained previously, and determining the global optimal position based on the updated individual positions of each particle; based on the preset velocity update strategy and the preset position update strategy, updating the positions and velocities of the updated particles again, and for each updated particle, inputting the updated particle and the device operation data into the power prediction model to obtain the predicted instantaneous power of the outdoor unit corresponding to the updated particle output by the power prediction model, updating the individual positions of each updated particle according to the predicted instantaneous power of the outdoor unit, the first indoor unit operating capacity, and the second indoor unit operating capacity of each updated particle obtained previously, and re-determining the global optimal position based on the individual positions of each particle after the second update, repeating the iteration until the number of iterations meets the preset number or the particle swarm converges, and outputting the global optimal position obtained in the last iteration; obtaining the optimal suction pressure of the outdoor unit target according to the suction pressure corresponding to the global optimal position.

[0039] It should be noted that by jointly incorporating the predicted instantaneous power of the outdoor unit, the first indoor unit operating capacity, and the second indoor unit operating capacity corresponding to each particle into the optimization process, not only the energy consumption performance of the outdoor unit is concerned, but also the actual capacity of the indoor unit during the refrigeration or heating process is closely combined, ensuring that the performance of the indoor unit will not be damaged due to unilaterally pursuing the efficiency of the outdoor unit when optimizing the suction pressure, thus comprehensively balancing the collaborative work of the indoor and outdoor units of the air conditioner. And using the preset velocity update strategy and the preset position update strategy to perform multiple updates and iterative calculations on the particles, so that in each iteration, the particles update their positions and velocities according to their own historical optimal positions, global optimal positions, and velocity information, ensuring to quickly locate the optimal area in a large search space and gradually converge to the vicinity of the global optimal solution as the number of iterations increases, thereby more effectively using computing resources and finding the optimal suction pressure of the outdoor unit target that meets the requirements in a shorter time.

[0040] Furthermore, according to the predicted instantaneous power of the external machine corresponding to each particle, the operating capacity of the first internal machine, and the operating capacity of the second internal machine of each particle obtained previously, update the individual positions of the corresponding particles, and determine the global optimal position according to the updated individual positions of each particle, including: for each particle, estimate the corresponding operating capacity of the second internal machine; determine whether the operating capacity of the second internal machine of each particle is lower than that of the first internal machine; based on the operating capacity of the second internal machine of the particle being lower than that of the first internal machine, compare the predicted instantaneous power of the external machine of the particle with the preset power. If the predicted instantaneous power of the external machine of the particle is less than the preset power, then use the predicted instantaneous power of the external machine as the optimal power of the corresponding particle and update the individual position of the particle, otherwise, do not update the individual position of the corresponding particle; based on the operating capacity of the second internal machine of the particle not being lower than that of the first internal machine, do not update the individual position of the corresponding particle; according to the updated individual positions of the particles and / or the individual positions of the particles that are not updated, obtain the updated particle swarm, and select the individual position corresponding to the minimum optimal power in the updated particle swarm as the global optimal position.

[0041] It should be noted that by simultaneously considering the predicted instantaneous power of the external machine corresponding to the particle, the operating capacity of the first internal machine, and the operating capacity of the second internal machine obtained based on each suction pressure, a comprehensive system for evaluating the quality of particles is constructed. When updating the individual position of the particle, it is not simply based on a single factor such as the predicted instantaneous power of the external machine or the operating capacity of the internal machine, but a careful balance is made between the two. Only when the operating capacity of the second internal machine is not lower than that of the first internal machine and the predicted instantaneous power of the external machine is less than the preset power will the particle position be updated. This multi-factor comprehensive decision-making mechanism can ensure that in the optimization process, neither the cooling and heating effects of the internal machine will be sacrificed due to excessive pursuit of low power, nor will the energy consumption be ignored due to one-sided emphasis on the performance of the internal machine, thus accurately balancing the performance and energy consumption of the internal and external machines of the air-conditioning system, enabling the air-conditioning to operate efficiently and energy-savingly while ensuring good user comfort.

[0042] It should be added that the preset power can be set according to the actual operating conditions of the air-conditioning to enable the air-conditioning system to more flexibly balance the energy consumption and the cooling and heating performance under different operating conditions, improving the overall adaptability of the system and the user experience. For example, in the case of a relatively high ambient temperature and a large indoor heat load, a slightly larger preset power can be set based on prior experience to allow the external machine to operate at a slightly higher power for a short time, so as to ensure that the cooling capacity of the internal machine can meet the requirements and avoid poor cooling effect due to excessive power limitation. On the contrary, in a period with a relatively mild ambient temperature and a small indoor heat load, a slightly smaller preset power threshold can be set based on prior experience to further pursue the energy-saving effect. In addition, the method for obtaining the operating capacity of the second internal machine corresponding to each particle can refer to the operating capacity of the first internal machine below, and will not be repeated here.

[0043] Accordingly, based on the predicted instantaneous power of the outdoor unit, the operating capacity of the first indoor unit, and the operating capacity of the second indoor unit of each updated particle obtained previously, update the individual positions of each updated particle, and based on the individual positions of each particle after re-updating, re-determine the global optimal position, including: for each updated particle, estimate the corresponding operating capacity of the second indoor unit; determine whether the operating capacity of the second indoor unit of each updated particle is lower than the operating capacity of the first indoor unit; based on the operating capacity of the second indoor unit of the updated particle being lower than the operating capacity of the first indoor unit, compare the predicted instantaneous power of the outdoor unit of the updated particle and the optimal power determined in the previous iteration. If the predicted instantaneous power of the outdoor unit of the updated particle is less than the preset power, update the optimal power of the corresponding particle with the predicted instantaneous power of the outdoor unit and update the individual position of the updated particle again, otherwise, do not update the individual position of the corresponding updated particle; based on the operating capacity of the second indoor unit of the updated particle not being lower than the operating capacity of the first indoor unit, do not update the individual position of the corresponding updated particle; according to the updated individual positions of the updated particles, obtain the updated particle swarm, and select the individual position corresponding to the minimum optimal power in the updated particle swarm as the global optimal position.

[0044] In an alternative embodiment, before inputting the corresponding suction pressure and equipment operation data into the power prediction model for each particle, it includes: obtaining a cloud model, which is previously constructed by the cloud based on equipment historical operation data. The equipment historical operation data includes operation data corresponding to at least one historical moment, and the operation data includes compressor frequency freq, outdoor unit expansion valve opening PMV, outdoor unit suction pressure P s , outdoor unit discharge pressure P d , outdoor unit ambient temperature Tao, outdoor unit instantaneous power Power, the on / off states of each indoor unit, the trachea temperature Tc1 of each indoor unit, and the liquid pipe temperature Tc2 of each indoor unit; transform and load the cloud model to obtain the power prediction model.

[0045] It should be noted that by obtaining the model constructed by the cloud based on the historical operation data of the device, and transforming and loading the data obtained from the cloud, while quickly realizing the localization of the model, it is ensured that the latest and most optimized power prediction model can be applied in a timely manner, which helps to improve the implementation efficiency of the entire optimization process, enabling the air-conditioning system to more quickly optimize the operation parameters based on this model. In addition, by making full use of multiple historical moments and various detailed operation parameters stored in the cloud, such as compressor frequency, outdoor expansion valve opening, suction pressure, discharge pressure, ambient temperature, instantaneous power, and indoor unit related temperature and startup status, etc., the complex operation laws of the device under different working conditions and different operation conditions can be better captured, making the constructed power prediction model more general and accurate than the locally constructed one, and being able to more accurately predict the instantaneous power of the outdoor unit, thereby providing a reliable basis for the subsequent particle optimization exploration.

[0046] Furthermore, transforming and loading the cloud model to obtain the power prediction model includes: transforming the cloud model based on a preset model format to obtain a model to be loaded; obtaining node parameters according to the model to be loaded, where the node parameters are used to represent the parameters of the basic operation units of the model to be loaded; quantifying the node parameters and combining with a preset compilation template to generate and load a compilation file to obtain the power prediction model.

[0047] It should be noted that transforming the cloud model based on a preset model format to ensure the compatibility of the model with the operating environment and related software and hardware systems of the local device. Through this standardized transformation process, the model obtained from the cloud can be smoothly adapted to the local environment, avoiding problems such as being unable to load or running errors due to inconsistent formats, improving the generality and stability of model application, and ensuring the smooth implementation of the entire air-conditioning operation optimization process based on the power prediction model.

[0048] In addition, the preset model format can be determined according to the possible requirements of different devices and application scenarios for the model format, and the preset compilation template can be compiled based on the programming language that meets the usage requirements of the local device, which will not be further limited here.

[0049] It should be added that obtaining node parameters according to the model to be loaded includes: searching the model structure knowledge base according to the model to be loaded to obtain the nodes of the model to be loaded; where the model structure knowledge base is previously constructed based on the model structure and the nodes corresponding to the model structure; disassembling the model to be loaded according to the nodes of the model to be loaded to obtain the node parameters.

[0050] In addition, before converting the cloud model based on a preset model format to obtain the model to be loaded, it includes: identifying the type and format of the cloud model, and automatically selecting an appropriate preset model format according to the configuration of the local device. Specifically, when receiving the cloud model, its features are quickly analyzed, and then the most appropriate model format is matched from a variety of pre-stored conversion rules and formats for automatic conversion, without manual intervention, reducing the risk of conversion failure caused by human operation errors, and improving the convenience and accuracy of the entire conversion and loading process.

[0051] In an alternative embodiment, before optimizing the particles using a preset particle swarm optimization algorithm based on the predicted instantaneous power of the outdoor unit corresponding to each particle and the first indoor unit operation ability obtained in advance based on the device operation data, it includes: according to the device operation data, searching the operation database to obtain the indoor unit operation ability; wherein, the operation database is constructed in advance based on the indoor unit operation ability corresponding to the device operation data under different operation modes of the air conditioner, and the indoor unit operation ability is used to characterize the cooling ability or heating ability under the corresponding operation mode.

[0052] It should be noted that by querying the operation database to obtain the indoor unit operation ability, the required information can be quickly obtained, saving computing resources and time costs. In addition, since the operation database is constructed based on a large amount of device operation data under different operation modes of the air conditioner, these data reflect the true performance of the indoor unit under different working conditions during the actual operation of the air conditioner. Therefore, the indoor unit operation ability obtained by querying the operation database can accurately reflect the cooling or heating ability of the indoor unit under the current device operation state, providing an accurate data basis for the subsequent optimization exploration of the particle swarm optimization algorithm in combination with the predicted instantaneous power of the outdoor unit, and helping to find the optimal target suction pressure of the outdoor unit that better meets the actual needs and can balance the performance of the indoor and outdoor units.

[0053] Step S13, control the operation of the air conditioner according to the optimal target suction pressure of the outdoor unit.

[0054] In summary, in the embodiment of the present invention, by obtaining the device operation data and the target suction pressure of the outdoor unit at the target moment, and using the power prediction model and the particle swarm optimization algorithm, the optimal target suction pressure of the outdoor unit can be dynamically and accurately found according to the actual situation, so as to control the operation of the air conditioner according to the optimal target suction pressure of the outdoor unit, ensuring that the outdoor unit of the air conditioner operates under efficient working conditions, avoiding energy waste caused by unreasonable suction pressure, and achieving the effect of energy saving. In addition, by obtaining the device operation data at the target moment, it is convenient to perform personalized adaptation according to the actual situation, better meeting the personalized needs of users for comfort indicators such as indoor temperature and humidity.

[0055] Next, the energy-saving control device provided by the present invention will be described. The energy-saving control device described below can be mutually referred to with the energy-saving control method described above.

[0056] Figure 2 The structural schematic diagram of an energy-saving control device is shown. The device includes: A data acquisition module 21, which acquires the device operation data at the target moment and the target suction pressure of the outdoor unit, where the target suction pressure of the outdoor unit is used to represent the optimal target suction pressure of the outdoor unit corresponding to the previous target moment prior to the target moment; A pressure optimization module 22, which obtains the optimal target suction pressure of the outdoor unit according to the device operation data and the target suction pressure of the outdoor unit by using a power prediction model and a preset particle swarm optimization algorithm; among them, the power prediction model is constructed based on the device historical operation data; An energy-saving control module 23, which controls the operation of the air conditioner according to the optimal target suction pressure of the outdoor unit.

[0057] In this embodiment, the pressure optimization module 22 includes: a particle generation unit, which generates the suction pressures meeting the target quantity according to the target suction pressure of the outdoor unit and a preset fluctuation range, and encodes each suction pressure to obtain the particles corresponding to each suction pressure and the particle swarm composed of each particle; an initialization unit, which randomly generates the initial positions and velocities of each particle to initialize each particle, and inputs the corresponding suction pressure and the device operation data into the power prediction model for each particle to obtain the predicted instantaneous power of the outdoor unit of the corresponding particle output by the power prediction model; an iterative optimization unit, which performs an optimization exploration on the particles by using the preset particle swarm optimization algorithm according to the predicted instantaneous power of the outdoor unit corresponding to each particle and the first indoor unit operation capacity obtained in advance based on the device operation data to obtain the optimal target suction pressure of the outdoor unit; among them, the indoor unit operation capacity is used to represent the cooling or heating capacity under the corresponding air conditioner operation mode.

[0058] Specifically, the iterative optimization unit includes: an optimal position determination subunit, which updates the individual positions of the corresponding particles according to the predicted instantaneous power of the outdoor unit corresponding to each particle, the operating capacity of the first indoor unit, and the operating capacity of the second indoor unit of each particle obtained previously, and determines the global optimal position according to the updated individual positions of the particles; an optimal position update subunit, which re-updates the positions and velocities of the updated particles based on a preset velocity update strategy and a preset position update strategy, and for each updated particle, inputs the updated particle and the device operation data into the power prediction model to obtain the predicted instantaneous power of the outdoor unit corresponding to the updated particle output by the power prediction model, updates the individual positions of the updated particles according to the predicted instantaneous power of the outdoor unit corresponding to each updated particle, the operating capacity of the first indoor unit, and the operating capacity of the second indoor unit of each updated particle obtained previously, and re-determines the global optimal position according to the individual positions of the particles after the re-update, repeats the iteration until the number of iterations meets the preset number or the particle swarm converges, and outputs the global optimal position obtained in the last iteration; a result determination subunit, which obtains the optimal target suction pressure of the outdoor unit according to the suction pressure corresponding to the global optimal position.

[0059] Furthermore, the optimal position determination subunit includes: an ability estimation grandchild unit, which estimates the operating capacity of the corresponding second indoor unit for each particle; an ability judgment grandchild unit, which determines whether the operating capacity of the second indoor unit of each particle is lower than the operating capacity of the first indoor unit; an update judgment grandchild unit, based on the fact that the operating capacity of the second indoor unit of the particle is lower than the operating capacity of the first indoor unit, compares the predicted instantaneous power of the outdoor unit of the particle with a preset power, and a result execution grandchild unit, if the predicted instantaneous power of the outdoor unit of the particle is less than the preset power, then takes the predicted instantaneous power of the outdoor unit as the optimal power of the corresponding particle and updates the individual position of the particle, otherwise, does not update the individual position of the corresponding particle; the result execution grandchild unit is also used to, based on the fact that the operating capacity of the second indoor unit of the particle is not lower than the operating capacity of the first indoor unit, not update the individual position of the corresponding particle.

[0060] Correspondingly, the result determination subunit is also used to: obtain the updated particle swarm according to the individual positions of the updated particles and / or the individual positions of the non-updated particles, and select the individual position corresponding to the minimum optimal power in the updated particle swarm as the global optimal position.

[0061] In addition, the optimal position update subunit is further configured to: for each updated particle, estimate the corresponding second indoor unit operation ability; determine whether the second indoor unit operation ability of each updated particle is lower than the first indoor unit operation ability; based on the fact that the second indoor unit operation ability of the updated particle is lower than the first indoor unit operation ability, compare the predicted instantaneous power of the outdoor unit of the updated particle with the optimal power determined in the previous iteration. If the predicted instantaneous power of the outdoor unit of the updated particle is less than the preset power, update the optimal power of the corresponding particle with the predicted instantaneous power of the outdoor unit, and update the individual position of the updated particle again. Otherwise, do not update the individual position of the corresponding updated particle; based on the fact that the second indoor unit operation ability of the updated particle is not lower than the first indoor unit operation ability, do not update the individual position of the corresponding updated particle; according to the updated individual positions of the updated particles, obtain the updated particle swarm, and select the individual position corresponding to the minimum optimal power in the updated particle swarm as the global optimal position.

[0062] In an alternative embodiment, the device further includes: a model acquisition module, which acquires a cloud model before inputting the corresponding suction pressure and device operation data into the power prediction model for each particle. The cloud model is previously constructed by the cloud based on device historical operation data, and the device historical operation data includes operation data corresponding to at least one historical moment. The operation data includes compressor frequency freq, outdoor unit expansion valve opening PMV, outdoor unit suction pressure P s , outdoor unit discharge pressure P d , outdoor unit ambient temperature Tao, outdoor unit instantaneous power Power, the startup status of each indoor unit, the trachea temperature Tc1 of each indoor unit, and the liquid pipe temperature Tc2 of each indoor unit; a localization processing module, which transforms and loads the cloud model to obtain a power prediction model.

[0063] Furthermore, the localization processing module includes: a transformation unit, which transforms the cloud model based on a preset model format to obtain a model to be loaded; a parameter acquisition unit, which obtains node parameters according to the model to be loaded. The node parameters are used to represent the parameters of the basic operation units of the model to be loaded; a localization processing unit, which quantifies the node parameters and combines a preset compilation template to generate and load a compilation file to obtain a power prediction model.

[0064] It should be added that the parameter acquisition unit is configured to: according to the model to be loaded, search a model structure knowledge base to obtain the nodes of the model to be loaded; where the model structure knowledge base is previously constructed based on the model structure and the nodes corresponding to the model structure; according to the nodes of the model to be loaded, disassemble the model to be loaded to obtain node parameters.

[0065] In addition, the localization processing module further includes a format determination unit. Before converting the cloud model based on a preset model format to obtain a model to be loaded, the type and format of the cloud model are identified, and an appropriate preset model format is automatically selected according to the configuration of the local device. Specifically, the format determination unit is configured to: when receiving the cloud model, quickly analyze its features, and then match the most appropriate model format from a variety of pre-stored conversion rules and formats for automatic conversion without manual intervention, reducing the risk of conversion failure caused by human operation errors and improving the convenience and accuracy of the entire conversion and loading process.

[0066] In an alternative embodiment, the pressure optimization module 22 further includes an operating capacity acquisition unit. Before optimizing and exploring the particles using a preset particle swarm optimization algorithm based on the predicted instantaneous power of the external unit corresponding to each particle and the first internal unit operating capacity obtained in advance based on the device operation data, the operating capacity of the internal unit is obtained by searching the operation database according to the device operation data; wherein, the operation database is constructed in advance based on the operating capacity of the internal unit corresponding to the device operation data under different operating modes of the air conditioner, and the operating capacity of the internal unit is used to represent the cooling capacity or heating capacity under the corresponding operating mode.

[0067] In summary, in the embodiment of the present invention, the data acquisition module acquires the device operation data and the target suction pressure of the external unit at the target moment, and the pressure optimization module uses the power prediction model and the particle swarm optimization algorithm to dynamically and accurately find the optimal target suction pressure of the external unit according to the actual situation. Then, the energy-saving control module controls the operation of the air conditioner according to the optimal target suction pressure of the external unit, ensuring that the air conditioner external unit operates under efficient working conditions, avoiding energy waste caused by unreasonable suction pressure, and achieving the effect of energy saving. In addition, by acquiring the device operation data at the target moment, it is convenient to perform personalized adaptation according to the actual situation, better meeting the personalized needs of users for comfort indicators such as indoor temperature and humidity.

[0068] Figure 3 Illustrates a schematic physical structure diagram of an electronic device, such as Figure 3As shown in the figure, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call the logical instructions in the memory 330 to execute an energy-saving control method, which includes: obtaining the device operation data at the target moment and the target suction pressure of the outdoor unit, where the target suction pressure of the outdoor unit is used to represent the optimal target suction pressure of the outdoor unit corresponding to the previous target moment prior to the target moment; according to the device operation data and the target suction pressure of the outdoor unit, using a power prediction model and a preset particle swarm optimization algorithm to obtain the optimal target suction pressure of the outdoor unit; where the power prediction model is constructed based on the device historical operation data; controlling the operation of the air conditioner according to the optimal target suction pressure of the outdoor unit.

[0069] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0070] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the energy-saving control method provided by the above-mentioned various methods. The method includes: obtaining the device operation data at the target moment and the target suction pressure of the outdoor unit, where the target suction pressure of the outdoor unit is used to represent the optimal target suction pressure of the outdoor unit corresponding to the previous target moment prior to the target moment; according to the device operation data and the target suction pressure of the outdoor unit, using a power prediction model and a preset particle swarm optimization algorithm to obtain the optimal target suction pressure of the outdoor unit; where the power prediction model is constructed based on the device historical operation data; controlling the operation of the air conditioner according to the optimal target suction pressure of the outdoor unit.

[0071] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the energy-saving control method provided above. The method includes: obtaining device operation data at a target moment and an outdoor unit target suction pressure, where the outdoor unit target suction pressure is used to represent the optimal outdoor unit target suction pressure corresponding to the previous target moment prior to the target moment; according to the device operation data and the outdoor unit target suction pressure, using a power prediction model and a preset particle swarm optimization algorithm to obtain the optimal outdoor unit target suction pressure; wherein the power prediction model is constructed based on the device historical operation data; controlling the operation of the air conditioner according to the optimal outdoor unit target suction pressure.

[0072] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative work.

[0073] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. An energy-saving control method, characterized in that, Including: Obtain the device operation data at the target moment and the target suction pressure of the outdoor unit, where the target suction pressure of the outdoor unit is used to represent the optimal target suction pressure of the outdoor unit corresponding to the previous target moment prior to the target moment; According to the device operation data and the target suction pressure of the outdoor unit, use the power prediction model and the preset particle swarm optimization algorithm to obtain the optimal target suction pressure of the outdoor unit; wherein, the power prediction model is constructed based on the device historical operation data; Control the operation of the air conditioner according to the optimal target suction pressure of the outdoor unit.

2. The energy-saving control method according to claim 1, wherein According to the device operation data and the target suction pressure of the outdoor unit, using the power prediction model and the preset particle swarm optimization algorithm to obtain the optimal target suction pressure of the outdoor unit, including: Generate the suction pressures that meet the target quantity according to the target suction pressure of the outdoor unit and the preset fluctuation range, and encode each of the suction pressures to obtain the particles corresponding to each of the suction pressures and the particle swarm composed of each of the particles; Randomly generate the initial positions and velocities of each of the particles to initialize each of the particles, and for each of the particles, input the corresponding suction pressure and the device operation data into the power prediction model to obtain the predicted instantaneous power of the outdoor unit of the corresponding particle output by the power prediction model; According to the predicted instantaneous power of the outdoor unit corresponding to each of the particles and the first indoor unit operation capacity obtained in advance based on the device operation data, use the preset particle swarm optimization algorithm to perform an optimization exploration on the particles to obtain the optimal target suction pressure of the outdoor unit; wherein, the indoor unit operation capacity is used to represent the cooling or heating capacity under the corresponding air conditioner operation mode.

3. The energy-saving control method according to claim 2, wherein According to the predicted instantaneous power of the outdoor unit corresponding to each of the particles and the first indoor unit operation capacity obtained in advance based on the device operation data, use the preset particle swarm optimization algorithm to perform an optimization exploration on the particles to obtain the optimal target suction pressure of the outdoor unit, including: Update the individual positions of the corresponding particles according to the predicted instantaneous power of the outdoor unit corresponding to each of the particles, the first indoor unit operation capacity, and the second indoor unit operation capacity of each of the particles obtained in advance, and determine the global optimal position according to the updated individual positions of each of the particles; Based on the preset velocity update strategy and the preset position update strategy, update the positions and velocities of each of the updated particles again, and for each updated particle, input the updated particle and the device operation data into the power prediction model to obtain the predicted instantaneous power of the outdoor unit of the corresponding updated particle output by the power prediction model. According to the predicted instantaneous power of the outdoor unit corresponding to each of the updated particles, the first indoor unit operation capacity, and the second indoor unit operation capacity of each of the updated particles obtained in advance, update the individual positions of each of the updated particles, and according to the individual positions of each of the particles after the re-update, re-determine the global optimal position, and repeat the iteration until the number of iterations meets the preset number or the particle swarm converges, and output the global optimal position obtained in the last iteration; Obtain the optimal target suction pressure of the outdoor unit according to the suction pressure corresponding to the global optimal position.

4. The energy-saving control method according to claim 3, wherein Update the individual positions of the corresponding particles according to the predicted instantaneous power of the external machine corresponding to each particle, the operating capacity of the first internal machine, and the operating capacity of the second internal machine of each particle obtained previously, and determine the global optimal position according to the updated individual positions of each particle, including: For each particle, estimate the corresponding operating capacity of the second internal machine; Determine whether the operating capacity of the second internal machine of each particle is lower than the operating capacity of the first internal machine; Based on the operating capacity of the second internal machine of the particle being lower than the operating capacity of the first internal machine, compare the predicted instantaneous power of the external machine of the particle with a preset power. If the predicted instantaneous power of the external machine of the particle is less than the preset power, then use the predicted instantaneous power of the external machine as the optimal power of the corresponding particle and update the individual position of the particle; otherwise, do not update the individual position of the corresponding particle; Based on the operating capacity of the second internal machine of the particle not being lower than the operating capacity of the first internal machine, do not update the individual position of the corresponding particle; According to the updated individual positions of the particles and / or the non-updated individual positions of the particles, obtain an updated particle swarm, and select the individual position corresponding to the minimum optimal power in the updated particle swarm as the global optimal position.

5. The energy-saving control method according to claim 2, characterized in that Before inputting the corresponding suction pressure and the device operation data for each particle into the power prediction model, it includes: Obtain a cloud model, which is previously constructed by the cloud based on device historical operation data. The device historical operation data includes operation data corresponding to at least one historical moment, and the operation data includes compressor frequency, external machine expansion valve opening, external machine suction pressure, external machine discharge pressure, external machine ambient temperature, external machine instantaneous power, the on / off states of each internal machine, the trachea temperature of each internal machine, and the liquid pipe temperature of each internal machine; Transform and load the cloud model to obtain a power prediction model.

6. The energy-saving control method according to claim 5, characterized in that Transform and load the cloud model to obtain a power prediction model, including: Based on a preset model format, transform the cloud model to obtain a model to be loaded; According to the model to be loaded, obtain node parameters, and the node parameters are used to characterize the parameters of the basic operation units of the model to be loaded; Quantify the node parameters, and combine with a preset compilation template to generate a compilation file and load it to obtain a power prediction model.

7. The energy-saving control method according to any one of claims 2-6, characterized in that, Before using a preset particle swarm optimization algorithm to perform an optimization search on particles according to the predicted instantaneous power of the external machine corresponding to each particle and the operating capacity of the first internal machine obtained previously based on the device operation data, it includes: According to the device operation data, search the operation database to obtain the operating capacity of the internal machine; wherein, the operation database is previously constructed based on the operating capacity of the internal machine corresponding to the device operation data under different operation modes of the air conditioner, and the operating capacity of the internal machine is used to characterize the refrigeration capacity or heating capacity under the corresponding operation mode.

8. An energy-saving control device, characterized in that, It includes: A data acquisition module that acquires the device operation data at the target moment and the target suction pressure of the external machine. The target suction pressure of the external machine is used to characterize the optimal target suction pressure of the external machine corresponding to the previous target moment before the target moment. A pressure optimization module, according to the device operation data and the target suction pressure of the outdoor unit, uses a power prediction model and a preset particle swarm optimization algorithm to obtain the optimal target suction pressure of the outdoor unit; wherein, the power prediction model is constructed based on the historical operation data of the device; An energy-saving control module controls the operation of the air conditioner according to the optimal target suction pressure of the outdoor unit.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the energy-saving control method according to any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the energy-saving control method according to any one of claims 1 to 7 are implemented.

Images