Intelligent control method, device, medium and product of optical storage system

Abstract

The application provides a kind of intelligent control method, equipment, medium and product of light storage system.The light storage system includes photovoltaic module, energy storage module and heat pump load.The intelligent control method includes: obtaining the operation data of light storage system, the operation data includes the photovoltaic output power of photovoltaic module, outdoor environment temperature, actual indoor temperature and the like;Obtain the decision reference factor of light storage system, the decision reference factor includes the preset energy efficiency ratio curve of heat pump load and the like;Determine the operation strategy of light storage system according to preset target function, the operation strategy includes the working power of heat pump load, the charge-discharge power of energy storage module and the interactive power of light storage system and external public grid, the weight coefficient value of each term of preset target function is determined by the intelligent decision model constructed in advance according to operation data and decision reference factor;According to the determined operation strategy, control light storage system runs, help to improve the comprehensive benefit of each equipment of light storage system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of optical storage, in particular to an intelligent control method, device, medium and product of an optical storage system. BACKGROUND

[0002] Green electricity technology, as a core technology path to respond to global energy transformation, has been more and more widely used, and optical storage technology is a key technology form in green electricity technology. The core value of optical storage technology lies in converting solar energy resources through photovoltaic modules, relying on energy storage modules to smooth photovoltaic output fluctuations and realize peak-shaving utilization of electric energy. In recent years, in response to the development of optical storage technology, optical storage systems integrating photovoltaic modules, energy storage modules and various types of electrical loads have begun to appear more and more in home residences, shopping malls and other scenarios. However, the modules in the current optical storage system run independently, or a single index is used for system control, so that the synergy between the modules of the photovoltaic system is not high, and the overall comprehensive benefits of the optical storage system need to be further improved. SUMMARY

[0003] An object of the present application is to provide an intelligent control method, device, medium and product of an optical storage system that helps to improve the energy utilization efficiency, economic benefits and user experience of the optical storage system.

[0004] In particular, the present application provides an intelligent control method of an optical storage system, the optical storage system comprising a photovoltaic module, an energy storage module and a heat pump load. The intelligent control method comprises:

[0005] obtaining operation data of the optical storage system, the operation data comprising photovoltaic output power of the photovoltaic module, outdoor environment temperature, actual indoor temperature, set indoor temperature, real-time electricity price and state of charge of the energy storage module;

[0006] obtaining decision reference factors of the optical storage system, the decision reference factors comprising a preset energy efficiency ratio curve of the heat pump load, a health state value of the energy storage module and a difference between the actual indoor temperature and the set indoor temperature;

[0007] determining an operation strategy of the optical storage system according to a preset target function, the operation strategy comprising working power of the heat pump load, charging and discharging power of the energy storage module and interaction power of the optical storage system and an external public power grid, and each weight coefficient value of the preset target function being determined by a pre-constructed intelligent decision model according to the operation data and the decision reference factors;

[0008] controlling the optical storage system to operate according to the determined operation strategy.

[0009] Optionally, the preset target function is:

[0010] ;

[0011] wherein, denotes the minimum value; denotes the electricity cost in the set time period; denotes the actual indoor temperature after the set time period; denotes the set indoor temperature; denotes the discharge depth of the energy storage module after the set time period; 、 、 respectively denote the electricity cost weight coefficient, the temperature control weight coefficient and the energy storage safety weight coefficient.

[0012] Optionally, the construction process of the intelligent decision-making model comprises:

[0013] receiving a plurality of sets of training basic data, the training basic data comprising photovoltaic output power of the photovoltaic module, outdoor environment temperature, actual indoor temperature, set indoor temperature, real-time electricity price, state of charge of the energy storage module, preset energy efficiency ratio curve of the heat pump load, health state value of the energy storage module, and difference between the actual indoor temperature and the set indoor temperature;

[0014] obtaining a preset allowable value range of each weight coefficient value of each set of the training basic data;

[0015] calculating, by using a preset algorithm, an optimal each weight coefficient value corresponding to a minimum value of the preset target function corresponding to each set of the training basic data;

[0016] training a to-be-trained model by taking the plurality of sets of training basic data as model input values of the to-be-trained model and taking the optimal each weight coefficient value corresponding to each set of the training basic data as model output values of the to-be-trained model, to obtain the intelligent decision-making model.

[0017] Optionally, a trigger event for ending the running strategy is obtained;

[0018] The steps of obtaining the running data of the photovoltaic-thermal energy storage system, obtaining the decision-making reference factors of the photovoltaic-thermal energy storage system, and determining the running strategy of the photovoltaic-thermal energy storage system according to the preset target function are re-executed.

[0019] Optionally, after the step of obtaining the trigger event for ending the running strategy, the method further comprises:

[0020] obtaining used electricity cost of the running strategy, actual indoor temperature, discharge depth of the energy storage module, and actual value of the preset target function;

[0021] If a ratio of an absolute value of a difference between an actual value of the preset target function and an original predicted value of the preset target function and the original predicted value of the preset target function exceeds a preset threshold value, the running data corresponding to the running strategy and the decision reference factor are taken as supplementary training basis data, and a supplementary optimal weight coefficient value corresponding to a preset target function minimum value is calculated, and the supplementary training basis data and the supplementary optimal weight coefficient value are taken as model input values and model output values respectively to perform supplementary training on the intelligent decision model.

[0022] Optionally, the step of determining the running strategy according to the preset target function further includes:

[0023] determining the running strategy in combination with the preset target function and a preset constraint condition;

[0024] the preset constraint condition includes:

[0025] controlling grid reverse power to be less than a preset power threshold value, the grid reverse power being power transmitted by the optical storage system to the external public grid;

[0026] controlling a difference value between an actual indoor temperature after the set time period and the set indoor temperature to be within a preset temperature fluctuation range;

[0027] controlling a state of charge of the energy storage module after the set time period to be within a preset state of charge range.

[0028] Optionally, the health state value of the energy storage module is determined by a preset energy storage health model.

[0029] the preset energy storage health model is:

[0030] ;

[0031] wherein, is the health state value; is an initial attenuation coefficient of the energy storage module; is a natural constant; is an attenuation rate coefficient of the energy storage module, and is a negative number; is a cycle number of the energy storage module.

[0032] Optionally, the decision reference factor further includes a user instruction.

[0033] in the process of determining the running strategy of the optical storage system according to the preset target function:

[0034] if the user instruction is a preset power saving priority instruction, the electricity price weight coefficient is set to be maximum.

[0035] If the user instruction is a preset comfort-first instruction, set the temperature control weighting coefficient to the maximum.

[0036] If the user instruction is a preset safety priority instruction, the energy storage safety weight coefficient is set to the maximum.

[0037] According to another aspect of the present invention, a computer device is also provided, including a memory, a processor, and a computer-executable program stored in the memory and running on the processor, wherein the processor executes the computer-executable program to implement the intelligent control method of the optical storage system according to any one of the preceding claims.

[0038] According to another aspect of the present invention, a computer-readable storage medium is also provided, on which a computer-executable program is stored, wherein the computer-executable program, when executed by a processor, implements the intelligent control method of the optical storage system according to any one of the preceding claims.

[0039] According to another aspect of the present invention, a computer program product is also provided, comprising a computer executable program that, when executed by a processor, implements the intelligent control method for the optical storage system according to any one of the preceding claims.

[0040] The intelligent control method, device, medium, and product of the photovoltaic-storage system of the present invention acquires the operating data of the photovoltaic-storage system, including the photovoltaic output power of the photovoltaic module, outdoor ambient temperature, actual indoor temperature, set indoor temperature, real-time electricity price, and state of charge of the energy storage module. It also acquires decision reference factors for the photovoltaic-storage system, including the preset energy efficiency ratio curve of the heat pump load, the health status value of the energy storage module, and the difference between the actual indoor temperature and the set indoor temperature. Then, it determines the operating strategy of the photovoltaic-storage system according to a preset objective function. The operating strategy includes the working power of the heat pump load, the charging and discharging power of the energy storage module, and the interaction power between the photovoltaic-storage system and the external public power grid. The weight coefficients of each item in the preset objective function are determined by a pre-constructed intelligent decision-making model based on the operating data and decision reference factors. Finally, it controls the operation of the photovoltaic-storage system according to the determined operating strategy. Therefore, this solution can quickly and intelligently generate an operating strategy that achieves a good balance between electricity costs, user comfort, and the safety of energy storage modules by acquiring sufficient decision-making data and comprehensively considering the three factors of electricity costs, user comfort, and the safety of energy storage modules. This operating strategy takes into account the benefits of electricity costs, user comfort, and the safety of energy storage modules, thereby helping to improve the synergy of various devices in the photovoltaic-energy storage system, and ultimately improving the overall benefits of the photovoltaic-energy storage system in terms of energy utilization efficiency, economic benefits, and user experience.

[0041] The above and other objects, advantages and features of the present application will become more apparent after a reading of the following detailed description of the embodiments thereof, taken in conjunction with the annexed drawings. BRIEF DESCRIPTION OF DRAWINGS

[0042] Some specific embodiments of the present application will be described in detail in the following with reference to the attached drawings, which are given by way of example and are not limitative of the present application. In the drawings, like reference numerals indicate identical or similar components or parts throughout the various figures. It should be understood that the drawings are not necessarily to scale. In the drawings:

[0043] Figure 1 is a schematic architecture diagram of an optical storage system according to an embodiment of the present application;

[0044] Figure 2 is a schematic flow chart of an intelligent control method of an optical storage system according to an embodiment of the present application;

[0045] Figure 3 is a schematic flow chart of constructing an intelligent decision model in an intelligent control method of an optical storage system according to an embodiment of the present application;

[0046] Figure 4 is a schematic flow chart of an intelligent control method of an optical storage system according to another embodiment of the present application;

[0047] Figure 5 is a schematic flow chart of an intelligent control method of an optical storage system according to yet another embodiment of the present application;

[0048] Figure 6 is a schematic flow chart of an intelligent control method of an optical storage system according to yet another embodiment of the present application;

[0049] Figure 7 is a schematic diagram of a computer device according to an embodiment of the present application;

[0050] Figure 8 is a schematic diagram of a computer readable storage medium according to an embodiment of the present application;

[0051] Figure 9 is a schematic diagram of a computer program product according to an embodiment of the present application. DETAILED DESCRIPTION

[0052] It should be understood by those skilled in the art that the embodiments described below are only a part of the embodiments of the present application, and are not intended to limit the protection scope of the present application. Based on the embodiments provided by the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor shall fall within the protection scope of the present application.

[0053] It should be noted that, in the description of this invention, each functional module can be a physical module composed of multiple structures, components, or electronic devices, or a virtual module composed of multiple programs; each functional module can be an independent module or a module divided from a whole module according to its function. Those skilled in the art should understand that, provided the technical solution described in this invention can be implemented, any changes in the configuration, implementation, or positional relationship of the functional modules will not deviate from the technical principles of this invention, and therefore should all fall within the protection scope of this invention.

[0054] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0055] The flowchart provided in this embodiment is not intended to indicate that the operations of the method will be performed in any particular order, or that all operations of the method are included in every case. Furthermore, the method may include additional operations. Within the scope of the technical concept provided by the method in this embodiment, additional variations can be made to the above method.

[0056] like Figure 1 As shown, in one embodiment, the photovoltaic-storage system includes a photovoltaic module 100, an energy storage module 200, and a heat pump load 300. The photovoltaic module 100 is a photovoltaic power generation component including photovoltaic panels and related electrical equipment (such as combiner boxes). The energy storage module 200 is an energy storage battery. The heat pump load 300 is a device used for heating and cooling indoor spaces. The electricity generated by the photovoltaic module 100 can be supplied to the heat pump load 300, thereby driving the heat pump load 300 to operate. Simultaneously, when the photovoltaic module 100 generates excess electricity, it can also charge the energy storage module 200 and transmit power to the external public power grid 400. The energy storage module 200 can store electrical energy, and the stored electrical energy can be supplied to the heat pump load 300 to drive its operation. Additionally, the external public power grid 400 can also supply power to the heat pump load 300, thereby driving its operation.

[0057] The optical storage system also includes a control module 500, which includes a memory and a processor. The memory stores a machine-executable program, which, when executed by the processor, implements the intelligent control method of the optical storage system according to any of the following embodiments.

[0058] As Figure 2 shown, in one embodiment, the intelligent control method of the light storage system generally comprises:

[0059] Step S201, obtaining the operation data of the light storage system. The operation data includes the photovoltaic output power of the photovoltaic module, the outdoor environment temperature, the actual indoor temperature, the set indoor temperature, the real-time electricity price and the state of charge of the energy storage module.

[0060] Specifically, the photovoltaic output power can be the real-time photovoltaic output power directly detected, or the photovoltaic output power in a set time period predicted according to a pre-built photovoltaic power generation model. The pre-built photovoltaic power generation model can be a model, such as a neural network model, etc., which is trained by taking atmospheric environmental information such as illumination intensity, temperature, wind direction, humidity, etc. as input data and taking the photovoltaic output power in a set time period as output data. Moreover, the model for predicting the photovoltaic output power is prior art, and the construction process will not be described in more detail here.

[0061] The outdoor environment temperature and the actual indoor temperature can be obtained according to the temperature sensors arranged in the corresponding environment, and the set indoor temperature is the temperature set by the user. The real-time electricity price is the electricity price in the current time period. The state of charge of the energy storage module, i.e. the SOC (State of Charge) of the battery, is represented by a value of 0%~100%.

[0062] Step S202, obtaining the decision reference factors of the light storage system. The decision reference factors include the preset energy efficiency ratio curve of the heat pump load, the health state value of the energy storage module, and the difference between the actual indoor temperature and the set indoor temperature.

[0063] Specifically, the energy efficiency ratio curve of the heat pump load is a curve formed by taking the outdoor environment temperature as the horizontal coordinate and the energy efficiency ratio of the heat pump as the vertical coordinate. The energy efficiency ratio curve corresponding to various working powers of the heat pump load is pre-stored in the memory. The energy efficiency ratio curve of the heat pump load can be used to calculate the indoor temperature value changed by the heat pump load after working at a certain working power for a set time period, and to more accurately determine the electricity used by the heat pump load after working at a certain working power for a set time period.

[0064] The health state value of the energy storage module is determined by a pre-stored energy storage health model. The pre-stored energy storage health model is:

[0065] ;

[0066] wherein, is the health state value; is the initial attenuation coefficient of the energy storage module; is a natural constant; is a decay rate coefficient of the energy storage module, which is a negative number; is a cycle number of the energy storage module. The initial decay coefficient and the decay rate coefficient can be obtained through a product parameter table or experiment.

[0067] That is, the health state value of the energy storage module is a parameter value that is dynamically updated with the use time of the energy storage module.

[0068] In step S203, an operation strategy of the optical energy storage system is determined according to a preset target function. The operation strategy includes a working power of the heat pump load, a charge and discharge power of the energy storage module, and an interaction power of the optical energy storage system and the external public power grid. The weight coefficient values of each item of the preset target function are determined by a pre-constructed intelligent decision model according to operation data and decision reference factors.

[0069] Specifically, the working power of the heat pump load is how much power the heat pump load runs at. The charge and discharge power of the energy storage module is whether the energy storage module is charging or discharging, and the power of charging and the power of discharging. The interaction power of the optical energy storage system and the external public power grid is whether the optical energy storage system sends power to the external public power grid or takes power from the external public power grid.

[0070] Further, the preset target function is:

[0071] ;

[0072] wherein, represents a minimum value; represents an electricity cost in a set time period; represents an actual indoor temperature after the set time period; represents a set indoor temperature; represents a discharge depth of the energy storage module after the set time period, and the discharge depth of the energy storage module and the state of charge (SOC) value of the energy storage module add up to 100%. , , respectively represent an electricity cost weight coefficient, a temperature control weight coefficient, and an energy storage safety weight coefficient.

[0073] It should be noted that the term set time period in the present embodiment represents a preset adjustment cycle time of the operation strategy of the photovoltaic system, or in other words, a set operation time of the operation strategy after the operation strategy is determined.

[0074] That is, the operation strategy of the light storage system is determined according to the preset target function, that is, an operation strategy that makes the target function reach the minimum value is obtained by using an exhaustive method or a genetic algorithm. The preset target function is related to the operation strategy as follows: the working power of the heat pump load is related to the actual indoor temperature after the set time period, that is, related to the difference between the actual indoor temperature after the set time period and the set indoor temperature; the charge and discharge power of the energy storage module is related to the depth of discharge of the energy storage module after the set time period; and the interactive power of the light storage system and the external public grid is related to the electricity cost in the set time period.

[0075] In addition, referring to FIG. 8, in an implementation, the construction process of the intelligent decision-making model includes the following steps. Figure 3

[0076] In step S301, a plurality of sets of training basic data are received. The training basic data includes the photovoltaic output power of the photovoltaic module, the outdoor environment temperature, the actual indoor temperature, the set indoor temperature, the real-time electricity price, the state of charge of the energy storage module, the preset energy efficiency ratio curve of the heat pump load, the health state value of the energy storage module, and the difference between the actual indoor temperature and the set indoor temperature. Specifically, the operation data and the decision-making reference factors are used as the training basic data.

[0077] In step S302, the preset allowed value range of each weight coefficient value of each set of training basic data is obtained. Specifically, when the training basic data is input, the preset allowed value range of each weight coefficient value corresponding to each set of training basic data is input, so as to avoid deviation of each weight coefficient from the actual demand.

[0078] For example, under the condition that the real-time electricity price is the preset peak electricity price, the electricity cost weight coefficient needs to be greater than a set value, so as to ensure that the electricity cost is saved to reduce the target function value, instead of excessively reducing the electricity cost weight coefficient to reduce the target function value; under the condition that the difference between the actual indoor temperature and the set indoor temperature is greater than a preset temperature threshold, the temperature control weight coefficient needs to be greater than a set value, so as to ensure the importance of quickly reducing the difference between the actual indoor temperature and the set indoor temperature; and under the condition that the health state value of the energy storage module is less than a preset health threshold, the energy storage safety weight coefficient needs to be greater than a set value, so as to ensure the importance of protecting the energy storage module.

[0079] In other words, for the preset allowed value range of each weight coefficient value, the electricity cost weight coefficient is positively correlated with the real-time electricity price, the temperature control weight coefficient is positively correlated with the difference between the actual indoor temperature and the set indoor temperature, and the energy storage safety weight coefficient is negatively correlated with the health state value of the energy storage module.

[0080] ​In step S303, an optimal weight coefficient value corresponding to a preset target function minimum value of each set of training basic data is calculated by using a preset algorithm. Specifically, the preset algorithm can be an exhaustive method, a Gauss-Newton algorithm, a genetic algorithm, or the like.

[0081] In step S304, a plurality of sets of training basic data are taken as model input values of a to-be-trained model, and the optimal weight coefficient value corresponding to each set of training basic data is taken as a model output value of the to-be-trained model, and the to-be-trained model is trained to obtain an intelligent decision-making model. Specifically, the intelligent decision-making model can be a neural network model.

[0082] In step S204, the operation of the optical storage system is controlled according to the determined operation strategy. Specifically, this is to control the operation of each device according to the operation power of each device in the operation strategy.

[0083] In the scheme of the embodiment, by obtaining operation data of the optical storage system, the operation data including photovoltaic output power of a photovoltaic module, outdoor environment temperature, actual indoor temperature, set indoor temperature, real-time electricity price, and state of charge of the energy storage module, and obtaining decision reference factors of the optical storage system, the decision reference factors including a preset energy efficiency ratio curve of a heat pump load, a health state value of the energy storage module, and a difference between the actual indoor temperature and the set indoor temperature, then determining an operation strategy of the optical storage system according to a preset target function, the operation strategy including working power of the heat pump load, charging and discharging power of the energy storage module, and interactive power of the optical storage system and an external public power grid, each weight coefficient value of the preset target function being determined by an intelligent decision-making model constructed in advance, and finally controlling the operation of the optical storage system according to the determined operation strategy. Therefore, the scheme can obtain sufficient decision-related data, comprehensively consider three factors of electricity cost, user comfort, and safety of the energy storage module, quickly and intelligently generate an operation strategy that well balances the electricity cost, the user comfort, and the safety of the energy storage module, so that the operation strategy takes into account the benefits of the electricity cost, the user comfort, and the safety of the energy storage module in multiple aspects, thereby helping to improve the collaborative ability of each device of the optical storage system, and further helping to improve the comprehensive benefits of energy utilization efficiency, economic benefits, and user experience of the optical storage system.

[0084] In addition, by constructing the intelligent decision-making model to determine each weight coefficient value of the preset target function, each weight coefficient value can be determined more quickly, and the decision-making efficiency is improved. By pre-setting the energy storage health model to determine the health state value of the energy storage module, the system can dynamically update the health state value in real time according to the use of the energy storage module, so that the health state value of the energy storage module has better timeliness and accuracy.

[0085] It should be noted that in other embodiments, the health state value of the energy storage module can also be changed by the user in the system periodically.

[0086] It should be noted that other electrical loads in addition to the heat pump can exist in the optical storage system, such as refrigerator, lamp and other electrical loads, and in the decision-making process, the working power of other electrical loads can be set within the respective allowed working power range.

[0087] As shown in Figure 4 In one embodiment, the intelligent control method of the optical storage system generally includes:

[0088] Step S401, obtaining the operation data of the optical storage system.

[0089] Step S402, obtaining the decision reference factors of the optical storage system.

[0090] Step S403, determining the operation strategy of the optical storage system according to the preset target function.

[0091] Step S404, controlling the operation of the optical storage system according to the determined operation strategy.

[0092] The contents of steps S401 to S404 are described with reference to steps S201 to S204.

[0093] Step S405, obtaining the trigger event for ending the operation strategy. Specifically, the trigger event can be that the operation strategy reaches the preset operation time, i.e., the time of the set time period described above. Alternatively, it can also be that the preset operation parameter of the optical storage system reaches the set parameter threshold, such as that the state of charge of the energy storage module reaches the minimum allowable value, or the state of charge of the energy storage module reaches the maximum allowable value, or that the absolute value of the difference between the real-time photovoltaic output power in the execution process of the operation strategy and the photovoltaic output power adopted in the determination of the operation strategy reaches the set parameter threshold. In addition, it can also be that the set indoor temperature changes.

[0094] The steps of obtaining the operation data of the optical storage system, obtaining the decision reference factors of the optical storage system, and determining the operation strategy of the optical storage system according to the preset target function are re-executed. That is, steps S401 to S404 are re-executed, a new operation strategy is generated, and the optical storage system is controlled to operate according to the new operation strategy.

[0095] In the scheme of the present embodiment, by re-executing the steps of obtaining the operation data of the optical storage system, obtaining the decision reference factors of the optical storage system, and determining the operation strategy of the optical storage system according to the preset target function after obtaining the trigger event for ending the operation strategy. That is, the optical storage system can dynamically update the operation strategy according to the trigger event for ending the operation strategy and control the optical storage system to operate according to the new operation strategy, thereby improving the flexibility of the operation strategy and enabling the operation strategy to better cope with unexpected situations.

[0096] AsFigure 5 As shown, in one embodiment, the step of obtaining the triggering event for ending the running strategy further comprises: obtaining the used electricity fee of the running strategy, the actual indoor temperature, the discharge depth of the energy storage module, and the actual value of the preset target function; if the ratio of the absolute value of the difference between the actual value of the preset target function and the original predicted value of the preset target function to the original predicted value of the preset target function exceeds a preset threshold value, taking the running data and the decision reference factors corresponding to the running strategy as supplementary training basic data and calculating the supplementary optimal weight coefficient value corresponding to the minimum value of the preset target function, and performing compensation training on the intelligent decision model by taking the supplementary training basic data and the supplementary optimal weight coefficient value as the model input value and the model output value, respectively.

[0097] Specifically, in the embodiment, the intelligent control method of the optical energy storage system generally comprises:

[0098] Step S501, obtaining the triggering event for ending the running strategy. The triggering event is that the running strategy reaches a preset running time.

[0099] Step S502, obtaining the used electricity fee of the running strategy, the actual indoor temperature, the discharge depth of the energy storage module, and the actual value of the preset target function. Specifically, it is to obtain the used electricity fee within the time period from the start of the running according to the running strategy to the obtaining of the triggering event for ending the running strategy, to obtain the actual indoor temperature at the time of the obtaining of the triggering event for ending the running strategy, to obtain the discharge depth of the energy storage module at the time of the obtaining of the triggering event for ending the running strategy, and to obtain the actual value of the preset target function at the time of the obtaining of the triggering event for ending the running strategy according to the difference between the used electricity fee, the actual indoor temperature, and the set indoor temperature and the discharge depth of the energy storage module.

[0100] If it is detected that the ratio of the absolute value of the difference between the actual value of the preset target function and the original predicted value of the preset target function to the original predicted value of the preset target function exceeds a preset threshold value, step S503 is performed. Specifically, the original predicted value of the preset target function is the preset target function value calculated when the running strategy is determined.

[0101] Step S503, taking the running data and the decision reference factors corresponding to the running strategy as supplementary training basic data and calculating the supplementary optimal weight coefficient value corresponding to the minimum value of the preset target function.

[0102] Step S504, performing supplementary training on the intelligent decision model by taking the supplementary training basic data and the supplementary optimal weight coefficient value as the model input value and the model output value, respectively.

[0103] Specifically, it is to refer to Figure 3 The flow shown uses the supplementary training basic data and the supplementary optimal weight coefficient value to perform supplementary training on the intelligent decision model.

[0104] In addition, in step S503, the allowable value range of the electricity price weight coefficient of the supplementary training basic data is determined according to the used electricity price, the original predicted electricity price of the operation strategy (the electricity price when the operation strategy is determined) and the original electricity price weight coefficient of the operation strategy. For example, if the used electricity price exceeds the original predicted electricity price of the operation strategy by a large margin, the allowable value range is set in a manner that the minimum value of the allowable value range is greater than the original electricity price weight coefficient.

[0105] The allowable value range of the temperature control weight coefficient of the supplementary training basic data is determined according to the actual indoor temperature, the original predicted indoor temperature of the operation strategy (the indoor temperature that is predicted to be reached after the operation set time period is determined when the operation strategy is determined) and the original temperature control weight coefficient of the operation strategy. For example, if the operation strategy is to increase the indoor temperature, the actual indoor temperature does not reach the original predicted indoor temperature and the difference is large, the allowable value range is set in a manner that the minimum value of the allowable value range is greater than the original temperature control weight coefficient.

[0106] The allowable value range of the energy storage safety weight coefficient of the supplementary training basic data is determined according to the discharge depth of the energy storage module, the original predicted discharge depth of the energy storage module of the operation strategy (the discharge depth of the energy storage module that is predicted to be reached after the operation set time period is determined when the operation strategy is determined) and the original energy storage safety weight coefficient of the operation strategy. For example, if the operation strategy is to discharge the energy storage module, the actual discharge depth is greater than the original predicted discharge depth and the difference is large, the allowable value range is set in a manner that the minimum value of the allowable value range is greater than the original energy storage safety weight coefficient.

[0107] In the scheme of the embodiment, the used electricity price, the actual indoor temperature, the discharge depth of the energy storage module and the actual value of the preset target function of the operation strategy are obtained after the trigger event of ending the operation strategy is obtained. If the absolute value of the difference between the actual value of the preset target function and the original predicted value of the preset target function and the original predicted value of the preset target function exceed the preset threshold value, the operation data and the decision reference factor corresponding to the operation strategy are taken as the supplementary training basic data and the supplementary optimal weight coefficient value corresponding to the minimum value of the preset target function is calculated. Then the supplementary training basic data and the supplementary optimal weight coefficient value are taken as the model input value and the model output value respectively to supplement the training of the intelligent decision model. Thus, the intelligent decision model can be continuously optimized and the accuracy of the decision of the intelligent decision model can be improved.

[0108] As Figure 6As shown, in one embodiment, the step of determining the operation strategy according to the preset target function further comprises: determining the operation strategy in combination with the preset target function and preset constraint conditions; the preset constraint conditions comprise: controlling the grid reverse power to be less than a preset power threshold, the grid reverse power being the power sent by the light-storage system to the external public grid; controlling the difference between the actual indoor temperature after a set time period and the indoor set temperature to be within a preset temperature fluctuation range; and controlling the state of charge of the energy storage module after the set time period to be within a preset state of charge range.

[0109] As shown, Figure 6 in this embodiment, the intelligent control method of the light-storage system generally comprises:

[0110] Step S601: Obtain operation data of the light-storage system.

[0111] Step S602: Obtain decision reference factors of the light-storage system.

[0112] The contents of steps S601 to S602 are described with reference to steps S201 to S202.

[0113] Step S603: Determine the operation strategy in combination with the preset target function and preset constraint conditions. The preset constraint conditions comprise:

[0114] controlling the grid reverse power to be less than a preset power threshold, the grid reverse power being the power sent by the light-storage system to the external public grid. Specifically, by controlling the grid reverse power to be less than the preset power threshold, the stability of the grid operation is avoided from being affected due to the excessively large grid reverse power. At the same time, the utilization rate of photovoltaic power generation is improved.

[0115] controlling the difference between the actual indoor temperature after a set time period and the indoor set temperature to be within a preset temperature fluctuation range. This is conducive to guaranteeing the comfort requirement of the user and improving the user experience.

[0116] controlling the state of charge of the energy storage module after the set time period to be within a preset state of charge range. This is helpful to avoid overcharging or overdischarging of the energy storage module.

[0117] Step S604: Control the light-storage system to operate according to the determined operation strategy.

[0118] In addition, in one embodiment, the decision reference factors further comprise user instructions. In the process of determining the operation strategy of the light-storage system according to the preset target function:

[0119] If the user instruction is the preset power saving priority instruction, the electricity price weight coefficient is set to be maximum; if the user instruction is the preset comfort priority instruction, the temperature control weight coefficient is set to be maximum; if the user instruction is the preset safety priority instruction, the energy storage safety weight coefficient is set to be maximum. By configuring the user instruction as the decision reference factor, the man-machine interaction between the light storage system and the user is improved, and the operation strategy is more in line with the user demand.

[0120] The embodiment further provides a computer device and a computer readable storage medium. Figure 7 Fig. 1 is a schematic diagram of a computer device according to an embodiment of the present application. Figure 8 Fig. 2 is a schematic diagram of a computer readable storage medium according to an embodiment of the present application.

[0121] The computer device 10 can include a memory 110, a processor 120, and a computer executable program 11 stored in the memory 110 and running on the processor 120, and the processor 120 implements the intelligent control method of the light storage system of any of the above embodiments when executing the computer executable program 11.

[0122] The computer readable storage medium 20 has the computer executable program 11 stored thereon, and the computer executable program 11 implements the intelligent control method of the light storage system of any of the above embodiments when executed by the processor.

[0123] The embodiment further provides a computer program product. Figure 9 Fig. 3 is a schematic diagram of a computer program product according to an embodiment of the present application. The computer program product 30 includes a computer executable program 11, and the computer executable program 11 implements the intelligent control method of the light storage system of any of the above embodiments when executed by the processor 120.

[0124] Specifically, the computer executable program 11 for executing the operation of the present application can be assembly instructions, instruction set architecture (ISA) instructions, computer instructions, computer related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages.

[0125] For the description of this embodiment, the computer-readable storage medium 20 can be any apparatus that can contain, store, communicate, propagate or transport the program for use by or in connection with the instruction execution system, apparatus or device. More specific examples (non-exhaustive list) of the computer-readable medium include the following: electrical connection having one or more wires (electronic apparatus), portable computer diskette (magnetic apparatus), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber device, and portable compact disc read-only memory (CD ROM). In addition, the computer-readable storage medium 20 can even be paper or other suitable medium on which the program can be printed, because the program can be electronically obtained, for example, by optically scanning the paper or other medium, then editing, interpreting or otherwise processing the optically scanned data to produce the electronic program, and then storing the electronic program in a computer memory.

[0126] It should be understood that parts of the application can be implemented in hardware, software, firmware or a combination thereof. In the above-described embodiments, a number of steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.

[0127] The computer device 10 can be, for example, a server, a desktop computer, a notebook computer, a tablet computer or a smartphone. In some examples, the computer device 10 can be a cloud acquisition node. The computer device 10 can be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules can include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer device 10 can be implemented in a distributed cloud acquisition environment where tasks are performed by remote processing devices that are linked through a communication network. In a distributed cloud acquisition environment, program modules can be located on local or remote acquisition system storage media including memory storage devices.

[0128] The computer device 10 can include a processor 120 suitable for executing stored instructions, a memory 110 that provides temporary storage space for the operations of the instructions during operation. The processor 120 can be a single-core processor, a multi-core processor, a cluster of acquisition or any number of other configurations. The memory 110 can include random access memory (RAM), read-only memory, flash memory or any other suitable storage system.

[0129] The processor 120 can be connected through the system interconnect (e.g., PCI, PCI-Express, etc.) to an I / O interface (input / output interface) adapted to connect the computer device 10 to one or more I / O devices (input / output devices). The I / O devices can include, for example, a keyboard and a pointing device, where the pointing device can include a touchpad or a touchscreen, among others. The I / O devices can be built-in components of the computer device 10 or can be devices externally connected to the computer device.

[0130] The processor 120 can also be linked through the system interconnect to a display interface adapted to connect the computer device 10 to a display device. The display device can include a display screen that is a built-in component of the computer device 10. The display device can also include a computer monitor, a television, or a projector, among others, that is externally connected to the computer device 10. Further, a network interface controller (NIC) can be adapted to connect the computer device 10 to a network through the system interconnect. In some embodiments, the NIC can use any suitable interface or protocol (such as Internet Small Computer System Interface, among others) to transfer data. The network can be a cellular network, a radio network, a wide area network (WAN), a local area network (LAN), or the Internet, among others. Remote devices can be connected to the computer device through the network.

[0131] To this end, those skilled in the art will recognize that the foregoing description has been presented for purposes of illustration and description only. It is not intended to be exhaustive or to limit the application to the precise form described, and obviously many modifications and variations are possible in light of the above teachings. The described embodiments were chosen and described in order to best explain the principles of the application and its best mode practical application. It is intended that the scope of the application be defined by the claims appended hereto, and their equivalents.

Claims

1. A smart control method for a photovoltaic-energy storage system, the photovoltaic-energy storage system comprising a photovoltaic module, an energy storage module, and a heat pump load, characterized in that, The intelligent control method includes: The system acquires operational data of the photovoltaic-storage system, including the photovoltaic output power of the photovoltaic module, outdoor ambient temperature, actual indoor temperature, set indoor temperature, real-time electricity price, and state of charge of the energy storage module. The decision reference factors for the photovoltaic-storage system are obtained. The decision reference factors include the preset energy efficiency ratio curve of the heat pump load, the health status value of the energy storage module, and the difference between the actual indoor temperature and the set indoor temperature. The preset energy efficiency ratio curve is a curve formed with the outdoor ambient temperature as the horizontal axis and the energy efficiency ratio of the heat pump as the vertical axis. The operation strategy of the photovoltaic-storage system is determined according to a preset objective function. The operation strategy includes the working power of the heat pump load, the charging and discharging power of the energy storage module, and the interaction power between the photovoltaic-storage system and the external public power grid. The weight coefficients of each item of the preset objective function are determined by a pre-constructed intelligent decision-making model based on the operation data and the decision reference factors. The photovoltaic energy storage system is controlled to operate according to the determined operating strategy. The preset objective function is: ; in, This indicates finding the minimum value; This indicates the electricity cost for the specified time period; This indicates the actual indoor temperature after a set time period. Indicates the set indoor temperature; This indicates the depth of discharge of the energy storage module after a set time period. , , These represent the electricity cost weighting coefficient, the temperature control weighting coefficient, and the energy storage safety weighting coefficient, respectively. The construction process of the intelligent decision-making model includes: Receive multiple sets of training basic data, including the photovoltaic output power of the photovoltaic module, outdoor ambient temperature, actual indoor temperature, set indoor temperature, real-time electricity price, state of charge of the energy storage module, preset energy efficiency ratio curve of the heat pump load, health status value of the energy storage module, and the difference between the actual indoor temperature and the set indoor temperature. Obtain the preset allowed range of values ​​for each weight coefficient of each group of the training base data; The optimal weight coefficients corresponding to the minimum value of the preset objective function for each set of training data are calculated using a preset algorithm. The intelligent decision-making model is obtained by using the multiple sets of training data as the model input values ​​of the model to be trained, and using the optimal weight coefficient values ​​corresponding to each set of training data as the model output values ​​of the model to be trained.

2. The intelligent control method for a photovoltaic energy storage system according to claim 1, characterized in that... Obtain the trigger event that terminates the aforementioned running strategy; Re-execute the steps of acquiring the operating data of the photovoltaic storage system, acquiring the decision reference factors of the photovoltaic storage system, and determining the operating strategy of the photovoltaic storage system according to the preset objective function.

3. The intelligent control method for a photovoltaic energy storage system according to claim 2, characterized in that... The step of obtaining the trigger event for ending the running strategy further includes: Obtain the electricity cost used for the operation strategy, the actual indoor temperature, the depth of discharge of the energy storage module, and the actual value of the preset objective function; If the absolute value of the difference between the actual value and the original predicted value of the preset objective function and the ratio of the original predicted value of the preset objective function exceeds a preset threshold, the running data and the decision reference factors corresponding to the running strategy are used as supplementary training data, and the supplementary optimal weight coefficient values ​​corresponding to the minimum value of the preset objective function are calculated. The supplementary training data and the supplementary optimal weight coefficient values ​​are used as model input values ​​and model output values, respectively, to supplement the training of the intelligent decision model.

4. The intelligent control method for a photovoltaic energy storage system according to claim 1, characterized in that... The step of determining the operation strategy of the photovoltaic storage system according to the preset objective function further includes: The operating strategy is determined by combining the preset objective function and preset constraints; The preset constraints include: The reverse power of the power grid is controlled to be less than a preset power threshold, wherein the reverse power of the power grid is the power transmitted by the photovoltaic energy storage system to the external public power grid; The difference between the actual indoor temperature after the set time period and the set indoor temperature is controlled to be within a preset temperature fluctuation range. The energy storage module is controlled to maintain its state of charge within a preset range after a set time period.

5. The intelligent control method for a photovoltaic energy storage system according to claim 1, characterized in that... The health status value of the energy storage module is determined by a pre-set energy storage health model; The pre-built energy storage health model is as follows: ;in, The health status value; The initial attenuation coefficient of the energy storage module; It is a natural constant; The attenuation rate coefficient of the energy storage module is a negative number. The number of cycles for the energy storage module.

6. The intelligent control method for a photovoltaic energy storage system according to claim 1, characterized in that... The decision-making reference factors also include user instructions; In the process of determining the operation strategy of the photovoltaic energy storage system according to the preset objective function: If the user instruction is a preset power-saving priority instruction, the electricity cost weighting coefficient is set to the maximum. If the user instruction is a preset comfort-first instruction, set the temperature control weighting coefficient to the maximum. If the user instruction is a preset safety priority instruction, the energy storage safety weight coefficient is set to the maximum.

7. A computer device, characterized in that, The system includes a memory, a processor, and a computer-executable program stored in the memory and running on the processor, wherein the processor executes the computer-executable program to implement the intelligent control method for the optical storage system according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, It stores a computer-executable program, which, when executed by a processor, implements the intelligent control method of the optical storage system according to any one of claims 1 to 6.

9. A computer program product, characterized in that, It includes a computer-executable program, which, when executed by a processor, implements the intelligent control method for the optical storage system according to any one of claims 1 to 6.

Images