A method and device for online monitoring of photovoltaic new energy storage system
Through the combination of online monitoring devices and photovoltaic monitoring models, photovoltaic module data is obtained for fault diagnosis and loss prediction, solving the problem of untimely fault handling in the photovoltaic new energy storage system, and achieving efficient and accurate online monitoring and automatic repair .
Patent Information
- Application Number
- CN202410993080.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-07-24
AI Technical Summary
The monitoring method of the existing photovoltaic new energy energy storage system cannot handle multiple fault instructions simultaneously, resulting in untimely maintenance and even property losses.
The energy storage data and environmental data of photovoltaic modules are obtained through an online monitoring device, fault diagnosis and loss prediction are used to use photovoltaic monitoring models, self-repair and adjustment solutions are provided, and photovoltaic modules are controlled for self-repair and automatic adjustment based on these results.
Automatic monitoring and diagnosis of photovoltaic modules is realized, the continuous and stable operation of photovoltaic modules is ensured, the problem of untimely maintenance is avoided, and the online monitoring efficiency and accuracy of photovoltaic new energy energy storage system is improved.
Smart Images

Figure CN118573115B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of online monitoring of photovoltaic energy storage systems, and specifically provides a method and device for online monitoring of photovoltaic new energy storage systems. Background Art
[0002] With the widespread application and continuous development of new energy technologies, photovoltaic new energy is subject to the influence of weather and has the characteristics of volatility and intermittency. Therefore, new energy storage systems have become the key to the application of photovoltaic new energy technologies.
[0003] However, the monitoring method of the energy storage system in the prior art is generally as follows: when a fault is detected in the energy storage system, a fault alarm is issued to the management personnel regardless of the difficulty of the fault situation. Moreover, since the distribution range of the energy storage system is generally large, the management personnel cannot perform multi-location operation and maintenance synchronously after receiving multiple fault instructions of the energy storage system, which leads to untimely maintenance of the energy storage system and even property losses.
[0004] Accordingly, the art needs a new online monitoring solution for photovoltaic new energy storage systems to solve the above problems. Summary of the invention
[0005] In order to overcome the above-mentioned defects, the present invention is proposed to provide a method and device for online monitoring of photovoltaic new energy storage systems to solve or at least partially solve the technical problem that the monitoring method of the prior art can only send fault alarms to management personnel according to the faults of the energy storage system, and because the distribution range of the energy storage system is generally large, the management personnel cannot synchronously perform multi-location operation and maintenance after receiving multiple fault instructions of the energy storage system, which leads to untimely maintenance of the energy storage system and even property losses.
[0006] In a first aspect, the present invention provides an online monitoring method for a photovoltaic new energy storage system, the method being applied to an online monitoring device of a photovoltaic new energy storage system, the photovoltaic new energy storage system comprising at least a plurality of photovoltaic modules, the photovoltaic new energy storage system being communicatively connected to the online monitoring device, the method comprising the following steps:
[0007] In response to a monitoring instruction, energy storage data of each group of photovoltaic components matching the monitoring instruction and environmental data of each group of photovoltaic components are acquired, wherein the energy storage data includes different types of monitoring data of energy storage photovoltaic modules in the photovoltaic components and the current operating status of the energy storage photovoltaic modules, and the environmental data includes different types of environmental data of the photovoltaic components at present and within a preset time period;
[0008] Substituting the energy storage data and environmental data of each group of photovoltaic components into the photovoltaic monitoring model, so that based on the energy storage data and environmental data of each group of photovoltaic components, the fault condition and / or estimated loss condition of each group of photovoltaic components are obtained, and then the monitoring results corresponding to each group of photovoltaic components are obtained, wherein the monitoring results include a repair plan and / or adjustment plan that matches the fault condition and / or estimated loss condition of each group of photovoltaic components;
[0009] Based on the monitoring results corresponding to each group of photovoltaic components, each group of photovoltaic components is controlled to perform self-repair and / or automatic adjustment.
[0010] In a technical solution of the above-mentioned online monitoring method for photovoltaic new energy storage system, each group of photovoltaic components includes a plurality of different types of photovoltaic modules, the types of the different types of photovoltaic modules include energy storage, input conversion and output conversion, each photovoltaic module includes a plurality of different types of photovoltaic elements, and before responding to the monitoring instruction and obtaining the energy storage data of each group of photovoltaic components matching the monitoring instruction and the environmental data of each group of photovoltaic components, the method further includes:
[0011] Updating a monitoring scheme for each group of photovoltaic assemblies, wherein the monitoring scheme includes a plurality of monitoring time points for each photovoltaic module of the photovoltaic assembly and monitoring types for different types of photovoltaic elements in each photovoltaic module;
[0012] If the monitoring time point of any photovoltaic module in any group of photovoltaic components is reached, the control sends a monitoring instruction matching the photovoltaic components.
[0013] In a technical solution of the above-mentioned online monitoring method for photovoltaic new energy storage system, the step of obtaining the energy storage data of each group of photovoltaic components matching the monitoring instruction and the environmental data of each group of photovoltaic components in response to the monitoring instruction includes:
[0014] In response to a monitoring instruction of any group of photovoltaic assemblies, obtaining operation data of each photovoltaic module of the photovoltaic assembly matching the monitoring instruction;
[0015] Determine the current operating state of the energy storage photovoltaic module in the photovoltaic assembly based on the operating data of each photovoltaic module of the photovoltaic assembly, wherein the current operating state is one of a storage state, a transfer state or a partial transfer state;
[0016] Based on the operation data of each photovoltaic module of the photovoltaic assembly, different types of monitoring data of the energy storage photovoltaic module in the photovoltaic assembly are obtained, wherein the different types include storage and / or transfer;
[0017] The energy storage data of the photovoltaic assembly is formed by using different types of monitoring data of the energy storage photovoltaic modules in the photovoltaic assembly and the current operating status of the energy storage photovoltaic modules in the photovoltaic assembly;
[0018] And obtain environmental data of the photovoltaic module.
[0019] In a technical solution of the above-mentioned online monitoring method for photovoltaic new energy storage system, the obtaining of environmental data of the photovoltaic module includes:
[0020] Acquire current collected data and online collected data of the photovoltaic module;
[0021] Based on the current collected data and online collected data of the photovoltaic assembly, different types of current environmental data of the photovoltaic assembly are obtained;
[0022] Acquire the current time, geographical location and a historical environment database of the geographical location of the photovoltaic module;
[0023] Based on the current environmental data of the photovoltaic component, the current time and geographical location of the photovoltaic component and a historical environmental database of the geographical location, different types of estimated environmental data of the photovoltaic component within a preset time period are obtained.
[0024] In a technical solution of the above-mentioned online monitoring method for photovoltaic new energy storage system, the online monitoring device also stores a historical energy storage database and a historical environment database, and the photovoltaic monitoring model stores a preset self-repair parameter comparison table. Before substituting the energy storage data and environmental data of each group of photovoltaic components into the photovoltaic monitoring model, the method further trains the photovoltaic monitoring model through the following steps:
[0025] Randomly select different photovoltaic modules as training sample groups, and construct multiple training sample data sets corresponding to each training sample group based on a historical energy storage database and a historical environment database, wherein the training sample data sets include a set of energy storage data and a set of environment data corresponding to the training sample group;
[0026] Based on the energy storage data in each group of training sample data sets, each group of training sample data sets is selectively labeled;
[0027] Based on the energy storage data in each group of training sample data sets and the current environment data in the environment data, it is determined whether the training sample group corresponding to the training sample data set has a fault, and the fault type of the training sample group is determined:
[0028] If it is determined that the training sample group has a fault, a repair solution matching the fault condition of the training sample data set is obtained based on the data information matching the fault type and a preset self-repair parameter comparison table;
[0029] If it is determined that the training sample group does not have a fault, selectively determining an adjustment scheme for the current operating state of the energy storage photovoltaic modules in the training sample group based on the energy storage data in the training sample data set and the estimated environmental data in the environmental data;
[0030] Based on the repair schemes or adjustment schemes corresponding to the various training sample data sets and the marking conditions of each group of training sample data sets, it is determined whether the photovoltaic monitoring model is successfully trained.
[0031] In a technical solution of the above-mentioned online monitoring method for photovoltaic new energy storage system, the historical energy storage database stores multiple groups of energy storage data of each group of photovoltaic components acquired historically, and the historical environment database stores historical environment data corresponding to each group of photovoltaic components. The randomly selected different photovoltaic components are used as training sample groups, and based on the historical energy storage database and the historical environment database, multiple groups of training sample data sets corresponding to each group of training sample groups are constructed, including:
[0032] Randomly select different photovoltaic components as training sample groups, and use each photovoltaic module in each photovoltaic component group as a training sample;
[0033] Based on the historical energy storage database and the historical environment database, multiple groups of energy storage data and multiple groups of environment data corresponding to each group of training sample groups are randomly selected;
[0034] The multiple sets of energy storage data and multiple sets of environmental data corresponding to each training sample group are randomly allocated to construct multiple sets of training sample data sets corresponding to each training sample group, wherein the training sample data sets include a set of energy storage data and a set of environmental data corresponding to the training sample group.
[0035] In a technical solution of the above-mentioned online monitoring method for photovoltaic new energy storage system, based on the energy storage data in each group of training sample data sets and the current environmental data in the environmental data, judging whether the training sample group corresponding to the training sample data set has a fault, and determining the fault type of the training sample group includes:
[0036] Based on the energy storage data in the training sample data set, determining whether a training sample group corresponding to the training sample data set has an energy storage fault:
[0037] If the judgment is yes, determining that the fault type of the training sample group is an energy storage fault;
[0038] If the judgment is no, determining the current energy storage loss of the training sample data set based on the current environmental data in the environmental data in the training sample data set and the energy storage data in the training sample data set;
[0039] Based on the current energy storage loss of the training sample data set, determine whether a training sample group corresponding to the training sample data set has a loss fault:
[0040] If the judgment is yes, determining that the fault type of the training sample group is a loss fault;
[0041] If the judgment is no, it is determined that there is no fault in the training sample group corresponding to the training sample data set.
[0042] In a technical solution of the above-mentioned online monitoring method for photovoltaic new energy storage system, the preset self-repair parameter comparison table stores different self-repair combination parameters, multiple groups of energy storage data corresponding to each group of self-repair combination parameters, current loss and estimated loss data range, and the repair solution matching the fault condition of the training sample data set based on the data information matching the fault type and the preset self-repair parameter comparison table includes:
[0043] If the fault type of the training sample group is an energy storage fault, determining the self-repair combination parameters corresponding to the energy storage data in the training sample data set based on the energy storage data in the training sample data set and a preset self-repair parameter comparison table;
[0044] Using the self-repair combination parameters corresponding to the energy storage data in the training sample data set as the repair solution that matches the fault condition of the training sample data set;
[0045] Alternatively, if the fault type of the training sample group is a loss fault, then based on the current energy storage loss of the training sample group and a preset self-repair parameter comparison table, the self-repair combination parameter corresponding to the current energy storage loss of the training sample group is determined;
[0046] The self-repair combination parameter corresponding to the current energy storage loss of the training sample group is used as the repair solution that matches the fault condition of the training sample data set.
[0047] In a technical solution of the above-mentioned online monitoring method for photovoltaic new energy storage system, the photovoltaic monitoring model also stores a preset adjustment scheme reference library, and the preset adjustment scheme reference library stores multiple adjustment schemes and an estimated adjustment index corresponding to each adjustment scheme. The adjustment scheme for selectively determining the current operating state of the energy storage photovoltaic module in the training sample group based on the energy storage data in the training sample data set and the estimated environmental data in the environmental data includes:
[0048] Based on the energy storage data in the training sample data set and the estimated environmental data in the environmental data, obtaining an estimated loss curve of the training sample group;
[0049] Based on the estimated loss curve of the training sample group, determine whether the current operating state of the energy storage photovoltaic module in the training sample group needs to be adjusted:
[0050] If it is determined that adjustment is required, then based on the estimated loss curve of the training sample group and a preset adjustment scheme reference library, an adjustment scheme for the current operating state of the energy storage photovoltaic module in the training sample group is determined;
[0051] If it is determined that no adjustment is needed, the situation that the training sample group does not need adjustment and does not have any faults is used as the monitoring result corresponding to the training sample group.
[0052] In a second aspect, the present invention provides an online monitoring device for a photovoltaic new energy storage system, wherein the online monitoring device is communicatively connected to the photovoltaic new energy storage system, wherein the photovoltaic new energy storage system includes multiple groups of photovoltaic components, and the online monitoring device includes a photovoltaic monitoring model and a control module, wherein the control module includes a processor and a memory, wherein the memory is suitable for storing multiple program codes, and wherein the program code is suitable for being loaded and run by the processor to execute the online monitoring method for a photovoltaic new energy storage system described in any one of the technical solutions for the online monitoring method for a photovoltaic new energy storage system.
[0053] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:
[0054] By responding to the monitoring instruction, the energy storage data and environmental data of each group of photovoltaic components matching the monitoring instruction are obtained, so that the data information of the photovoltaic components can be automatically obtained, and the monitoring efficiency is improved. Then, the acquired energy storage data and environmental data are substituted into the photovoltaic monitoring model to obtain the monitoring results corresponding to each group of photovoltaic components, wherein the monitoring results include the repair plan and / or adjustment plan that matches the fault condition and / or estimated loss condition of the group of photovoltaic components, so that the automatic monitoring and diagnosis of the fault condition of the photovoltaic components is realized, and the corresponding repair or adjustment plan is given according to the monitoring condition, and each group of photovoltaic components is controlled according to the monitoring results. The photovoltaic components are grouped to perform self-repair and / or automatic adjustment, ensuring that the photovoltaic components can operate continuously and stably, so as to realize automatic repair of faults of each photovoltaic component and / or optimization of the loss of each photovoltaic component, thereby realizing efficient, accurate and intelligent online monitoring of the photovoltaic new energy storage system, avoiding the technical problem that the monitoring method of the existing technology can only send fault alarms to management personnel according to the fault of the energy storage system, and because the distribution range of the energy storage system is generally large, the management personnel cannot perform multi-location operation and maintenance synchronously after receiving multiple fault instructions of the energy storage system, which leads to untimely maintenance of the energy storage system and even causes property loss.
[0055] In the technical solution of the present invention, different types of current environmental data of the photovoltaic module are obtained by acquiring the current collected data and the online collected data, thereby realizing the comprehensive acquisition of the environmental data of the photovoltaic module and improving the accuracy of the current environmental data of the photovoltaic module. Then, the current time, geographical location, historical environmental database and current environmental data of the photovoltaic module are combined to obtain different types of estimated environmental data within a preset time period of the photovoltaic module, so as to selectively determine the adjustment plan of the photovoltaic module according to the estimated environmental data, thereby realizing that the online monitoring device accurately estimates the future operating status of the photovoltaic module in the photovoltaic energy storage system, so as to adjust and optimize the photovoltaic module in advance.
[0056] In the technical solution of the present invention, in model training, multiple groups of training sample data sets corresponding to each randomly selected training sample group are constructed through a historical energy storage database and a historical environment database, thereby improving the training ability of the photovoltaic monitoring model. Then, according to the energy storage data of each group of training sample data sets, the training sample data sets are selectively marked to facilitate verification of the training results. Then, through the energy storage data in the training sample data sets and the current environment data, it is determined whether the training sample group corresponding to the training sample data set has a fault, and the fault type of the training sample group is determined, thereby achieving self-inspection and accurate diagnosis of the faults of the training sample group, so as to obtain a repair plan or adjustment plan that matches the fault condition of the training sample group, thereby achieving intelligent analysis and processing of the data of the training sample group, and then judging the training results of the model through the monitoring results and marking conditions of each training sample data set, thereby achieving automatic verification of the model training and improving the intelligent ability of the photovoltaic monitoring model. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] The disclosure of the present invention will become more easily understood with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In addition, similar numbers in the figures are used to represent similar components, among which:
[0058] Figure 1 It is a schematic flow chart of the main steps of a method for online monitoring of a photovoltaic new energy storage system according to an embodiment of the present invention;
[0059] Figure 2 is a schematic flow chart of the main steps of training a photovoltaic monitoring model according to an embodiment of the present invention;
[0060] Figure 3 It is a schematic diagram of the main structure block diagram of an online monitoring device according to an embodiment of the present invention.
[0061] The reference numerals are as follows:
[0062] 300: online monitoring device; 301: control module; 3011: processor; 3012: memory; 3013: program code; 302: photovoltaic monitoring model; 3021: self-repair parameter comparison table; 3022: adjustment plan comparison library; 303: historical energy storage database; 304: historical environment database. DETAILED DESCRIPTION
[0063] Some embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.
[0064] In the description of the present invention, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, and memories, and may also include software parts, such as program codes, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware, or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store program codes, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and the like. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B", and may include only A, only B, or A and B. The singular terms "one" and "the" may also include plural forms.
[0065] See attached Figure 1 , Figure 1 1 is a schematic flow chart of the main steps of a method for online monitoring of a photovoltaic new energy storage system according to an embodiment of the present invention. Figure 1 As shown, the online monitoring method for a photovoltaic new energy storage system in an embodiment of the present invention is applied to an online monitoring device of a photovoltaic new energy storage system, the photovoltaic new energy storage system includes at least a plurality of photovoltaic components, the photovoltaic new energy storage system is communicatively connected to the online monitoring device, and the method mainly includes the following steps S101-S103.
[0066] Step S101: In response to a monitoring instruction, energy storage data of each group of photovoltaic components matching the monitoring instruction and environmental data of each group of photovoltaic components are obtained, wherein the energy storage data includes different types of monitoring data of energy storage photovoltaic modules in the photovoltaic components and the current operating status of the energy storage photovoltaic modules, and the environmental data includes different types of environmental data of the photovoltaic components at present and within a preset time period;
[0067] Specifically, in some embodiments, the types of different types of monitoring data include at least current input, current output, voltage input, voltage output, stored power, module temperature, module humidity and module status. The selection of different types of monitoring data here is only an exemplary description. In actual testing, technical personnel in this field can make a selection according to actual needs, which will not be repeated here.
[0068] Specifically, in some embodiments, the different types of environmental data include at least temperature, humidity, light intensity and effective lighting time. The selection of different types of environmental data here is only an exemplary description. In actual testing, technical personnel in this field can make a selection according to actual needs, which will not be repeated here.
[0069] Further, in some embodiments, each group of photovoltaic components includes a plurality of different types of photovoltaic modules, the types of the different types of photovoltaic modules include energy storage, input conversion and output conversion, each photovoltaic module includes a plurality of different types of photovoltaic elements, and before responding to the monitoring instruction and obtaining the energy storage data of each group of photovoltaic components matching the monitoring instruction and the environmental data of each group of photovoltaic components, the method further includes:
[0070] Updating a monitoring scheme for each group of photovoltaic assemblies, wherein the monitoring scheme includes a plurality of monitoring time points for each photovoltaic module of the photovoltaic assembly and monitoring types for different types of photovoltaic elements in each photovoltaic module;
[0071] If the monitoring time point of any photovoltaic module in any group of photovoltaic components is reached, the control sends a monitoring instruction matching the photovoltaic components.
[0072] Specifically, in some embodiments, in response to the monitoring instruction, obtaining the energy storage data of each group of photovoltaic components matching the monitoring instruction and the environmental data of each group of photovoltaic components includes:
[0073] In response to a monitoring instruction of any group of photovoltaic assemblies, obtaining operation data of each photovoltaic module of the photovoltaic assembly matching the monitoring instruction;
[0074] Determine the current operating state of the energy storage photovoltaic module in the photovoltaic assembly based on the operating data of each photovoltaic module of the photovoltaic assembly, wherein the current operating state is one of a storage state, a transfer state or a partial transfer state;
[0075] Based on the operation data of each photovoltaic module of the photovoltaic assembly, different types of monitoring data of the energy storage photovoltaic module in the photovoltaic assembly are obtained, wherein the different types include storage and / or transfer;
[0076] The energy storage data of the photovoltaic assembly is formed by using different types of monitoring data of the energy storage photovoltaic modules in the photovoltaic assembly and the current operating status of the energy storage photovoltaic modules in the photovoltaic assembly;
[0077] And obtain environmental data of the photovoltaic module.
[0078] Specifically, in some embodiments, obtaining the environmental data of the photovoltaic assembly includes:
[0079] Acquire current collected data and online collected data of the photovoltaic module;
[0080] Based on the current collected data and online collected data of the photovoltaic assembly, different types of current environmental data of the photovoltaic assembly are obtained;
[0081] Acquire the current time, geographical location and a historical environment database of the geographical location of the photovoltaic module;
[0082] Based on the current environmental data of the photovoltaic component, the current time and geographical location of the photovoltaic component and a historical environmental database of the geographical location, different types of estimated environmental data of the photovoltaic component within a preset time period are obtained.
[0083] Specifically, in some embodiments, the different types of environmental data include temperature, humidity, light intensity, and effective light time.
[0084] Specifically, in some embodiments, the currently collected data of the photovoltaic component can be collected by different types of sensors installed around the photovoltaic component that match the type of environmental data, and the online collected data of the photovoltaic component can be obtained by remotely acquiring different types of online environmental data from a weather platform. The selection of the current collected data of the photovoltaic component and the collection method of the online collected data here is only an exemplary description. In actual testing, those skilled in the art can make a selection based on actual needs, which will not be repeated here.
[0085] Specifically, in some embodiments, obtaining different types of current environmental data of the photovoltaic component based on the current collected data and online collected data of the photovoltaic component includes:
[0086] The current environmental data of any type of the photovoltaic module = the current collected data corresponding to the type * the collection comprehensive weight value matching the current collected data corresponding to the type + the online collected data corresponding to the type * the online comprehensive weight value matching the online collected data corresponding to the type, and the sum of the collection comprehensive weight value and the online comprehensive weight value corresponding to the same type is 1;
[0087] The setting of the formula for obtaining different types of current environmental data of photovoltaic components here is only an exemplary description. In actual testing, technical personnel in this field can make settings according to actual needs. As long as the different types of current environmental data of the photovoltaic components can be obtained through the current collected data and online collected data of the photovoltaic components, they will not be repeated here.
[0088] Specifically, in some embodiments, the preset time period may be 1 month or 15 days. The setting of the preset time period here is only an exemplary description. In actual testing, those skilled in the art may set it according to actual needs, which will not be elaborated here.
[0089] In the above embodiment, different types of current environmental data of the photovoltaic module are obtained by acquiring the current collected data and the online collected data, thereby realizing the comprehensive acquisition of the environmental data of the photovoltaic module and improving the accuracy of the current environmental data of the photovoltaic module. Then, in combination with the current time, geographical location, historical environmental database and current environmental data of the photovoltaic module, different types of estimated environmental data within a preset time period of the photovoltaic module are obtained, so that the adjustment plan of the photovoltaic module can be selectively determined according to the estimated environmental data, and the online monitoring device can accurately estimate the future operating status of the photovoltaic module in the photovoltaic energy storage system, so as to adjust and optimize the photovoltaic module in advance.
[0090] Step S102: Substituting the energy storage data and environmental data of each group of photovoltaic components into the photovoltaic monitoring model, so that based on the energy storage data and environmental data of each group of photovoltaic components, the fault condition and / or estimated loss condition of each group of photovoltaic components are obtained, and then the monitoring results corresponding to each group of photovoltaic components are obtained, wherein the monitoring results include a repair plan and / or adjustment plan that matches the fault condition and / or estimated loss condition of each group of photovoltaic components;
[0091] like Figure 2 As shown, further, in some embodiments, the online monitoring device also stores a historical energy storage database and a historical environment database, and the photovoltaic monitoring model stores a preset self-repair parameter comparison table. Before substituting the energy storage data and environmental data of each group of photovoltaic components into the photovoltaic monitoring model, the method further trains the photovoltaic monitoring model through the following steps:
[0092] Randomly select different photovoltaic modules as training sample groups, and construct multiple training sample data sets corresponding to each training sample group based on a historical energy storage database and a historical environment database, wherein the training sample data sets include a set of energy storage data and a set of environment data corresponding to the training sample group;
[0093] Based on the energy storage data in each group of training sample data sets, each group of training sample data sets is selectively labeled;
[0094] Based on the energy storage data in each group of training sample data sets and the current environment data in the environment data, it is determined whether the training sample group corresponding to the training sample data set has a fault, and the fault type of the training sample group is determined:
[0095] If it is determined that the training sample group has a fault, a repair solution matching the fault condition of the training sample data set is obtained based on the data information matching the fault type and a preset self-repair parameter comparison table;
[0096] If it is determined that the training sample group does not have a fault, selectively determining an adjustment scheme for the current operating state of the energy storage photovoltaic modules in the training sample group based on the energy storage data in the training sample data set and the estimated environmental data in the environmental data;
[0097] Based on the repair schemes or adjustment schemes corresponding to the various training sample data sets and the marking conditions of each group of training sample data sets, it is determined whether the photovoltaic monitoring model is successfully trained.
[0098] Specifically, in some embodiments, the historical energy storage database stores multiple groups of energy storage data of each group of photovoltaic components historically acquired, the historical environment database stores historical environment data corresponding to each group of photovoltaic components, and the randomly selecting different photovoltaic components as training sample groups, and constructing multiple groups of training sample data sets corresponding to each group of training sample groups based on the historical energy storage database and the historical environment database includes:
[0099] Randomly select different photovoltaic components as training sample groups, and use each photovoltaic module in each photovoltaic component group as a training sample;
[0100] Based on the historical energy storage database and the historical environment database, multiple groups of energy storage data and multiple groups of environment data corresponding to each group of training sample groups are randomly selected;
[0101] The multiple sets of energy storage data and multiple sets of environmental data corresponding to each training sample group are randomly allocated to construct multiple sets of training sample data sets corresponding to each training sample group, wherein the training sample data sets include a set of energy storage data and a set of environmental data corresponding to the training sample group.
[0102] Specifically, selectively marking each set of training sample data sets based on the energy storage data in each set of training sample data sets includes:
[0103] Based on the energy storage data in each set of training sample data sets, determine whether the training sample group corresponding to each set of training sample data sets has an energy storage fault:
[0104] If the training sample group corresponding to the training sample data set has an energy storage fault, the training sample data set is marked; otherwise, the training sample data set is not marked.
[0105] Specifically, in some embodiments, judging whether a training sample group corresponding to the training sample data set has a fault based on the energy storage data in each group of training sample data sets and the current environment data in the environment data, and determining the fault type of the training sample group includes:
[0106] Based on the energy storage data in the training sample data set, determining whether a training sample group corresponding to the training sample data set has an energy storage fault:
[0107] If the judgment is yes, determining that the fault type of the training sample group is an energy storage fault;
[0108] If the judgment is no, determining the current energy storage loss of the training sample data set based on the current environmental data in the environmental data in the training sample data set and the energy storage data in the training sample data set;
[0109] Based on the current energy storage loss of the training sample data set, determine whether a training sample group corresponding to the training sample data set has a loss fault:
[0110] If the judgment is yes, determining that the fault type of the training sample group is a loss fault;
[0111] If the judgment is no, it is determined that there is no fault in the training sample group corresponding to the training sample data set.
[0112] Specifically, in some embodiments, judging whether a training sample group corresponding to the training sample data set has a loss fault based on the current energy storage loss of the training sample data set includes:
[0113] If the current energy storage loss of the training sample data set exceeds a preset energy storage loss threshold, it is determined that a loss fault exists in the training sample group corresponding to the training sample data set;
[0114] Otherwise, it is determined that the training sample group corresponding to the training sample data set does not have a loss fault.
[0115] Specifically, in some embodiments, the preset self-repair parameter comparison table stores different self-repair combination parameters, multiple groups of energy storage data corresponding to each group of self-repair combination parameters, current loss and estimated loss data range, and the repair solution matching the fault condition of the training sample data set based on the data information matching the fault type and the preset self-repair parameter comparison table includes:
[0116] If the fault type of the training sample group is an energy storage fault, determining the self-repair combination parameters corresponding to the energy storage data in the training sample data set based on the energy storage data in the training sample data set and a preset self-repair parameter comparison table;
[0117] Using the self-repair combination parameters corresponding to the energy storage data in the training sample data set as the repair solution that matches the fault condition of the training sample data set;
[0118] Alternatively, if the fault type of the training sample group is a loss fault, then based on the current energy storage loss of the training sample group and a preset self-repair parameter comparison table, the self-repair combination parameter corresponding to the current energy storage loss of the training sample group is determined;
[0119] The self-repair combination parameter corresponding to the current energy storage loss of the training sample group is used as the repair solution that matches the fault condition of the training sample data set.
[0120] Specifically, in some embodiments, the photovoltaic monitoring model further stores a preset adjustment scheme reference library, wherein the preset adjustment scheme reference library stores a plurality of adjustment schemes and an estimated adjustment index corresponding to each adjustment scheme, and the adjustment scheme for selectively determining the current operating state of the energy storage photovoltaic module in the training sample group based on the energy storage data in the training sample data set and the estimated environmental data in the environmental data includes:
[0121] Based on the energy storage data in the training sample data set and the estimated environmental data in the environmental data, obtaining an estimated loss curve of the training sample group;
[0122] Based on the estimated loss curve of the training sample group, determine whether the current operating state of the energy storage photovoltaic module in the training sample group needs to be adjusted:
[0123] If it is determined that adjustment is required, then based on the estimated loss curve of the training sample group and a preset adjustment scheme reference library, an adjustment scheme for the current operating state of the energy storage photovoltaic module in the training sample group is determined;
[0124] If it is determined that no adjustment is needed, the situation that the training sample group does not need adjustment and does not have any faults is used as the monitoring result corresponding to the training sample group.
[0125] Specifically, in some embodiments, obtaining the estimated loss curve of the training sample group based on the energy storage data in the training sample data set and the estimated environmental data in the environmental data includes:
[0126] Constructing a scene estimation model for a training sample group corresponding to the training sample data set according to the energy storage data in the training sample data set and the estimated environmental data in the environmental data;
[0127] Substituting the preset time period corresponding to the training sample data set and the estimated environmental data in the environmental data in the training sample data set into the scene estimation model for execution, to obtain the estimated loss data of the training sample group within the preset time period;
[0128] An estimated loss curve of the training sample group is constructed based on the preset time period and the estimated loss data of the training sample group within the preset time period.
[0129] Specifically, in some embodiments, the scene prediction model can be a model of a simulation scene constructed by a neural network through deep learning in the prior art. The setting of the scene prediction model here is only an exemplary description. In actual testing, technical personnel in this field can choose according to actual needs. As long as it can be achieved by constructing a corresponding simulation scene based on the energy storage data in the training sample data set and the estimated environmental data in the environmental data, so as to obtain the estimated loss data of the training sample group within the preset time period according to the preset time period corresponding to the training sample data set and the estimated environmental data in the environmental data in the training sample data set, it will not be repeated here.
[0130] Specifically, in some embodiments, judging whether the photovoltaic monitoring model is successfully trained based on the repair scheme or adjustment scheme corresponding to each training sample data set and the marking of each group of training sample data sets includes:
[0131] Based on the repair scheme or adjustment scheme corresponding to each training sample data set and the marking status of each group of training sample data sets, determine the monitoring accuracy of all marked training sample data sets;
[0132] If the monitoring accuracy of all the marked training sample data sets reaches a preset accuracy threshold, all the unmarked training sample data sets and the monitoring results corresponding to each training sample data set are selected for simulation to obtain simulation adjustment results of each training sample data set, wherein the simulation adjustment results include fault repair results and / or adjustment results;
[0133] Based on the simulation adjustment results of each training sample data set, obtaining the adjustment success rate of all unlabeled training sample data sets;
[0134] If the adjustment success rate of all the unlabeled training sample data sets reaches a preset success rate threshold, it is determined that the photovoltaic monitoring model training is successful;
[0135] Otherwise, it is determined that the photovoltaic monitoring model training has failed, and the photovoltaic monitoring model is retrained.
[0136] Specifically, in some embodiments, the simulation method of all the unlabeled training sample data sets and the monitoring results corresponding to each training sample data set is generated by using a trained neural network model in the prior art, and the neural network model is trained according to the environmental data, energy storage data and corresponding monitoring results of different groups of photovoltaic components. The choice of simulation method here is only an exemplary description. In actual testing, those skilled in the art can make a choice according to actual needs, as long as it is possible to obtain the simulation adjustment results of each training sample data set based on the training sample data set and the monitoring results corresponding to each training sample data set, it will not be repeated here.
[0137] Specifically, in some embodiments, obtaining the adjustment success rate of all unlabeled training sample data sets based on the simulation adjustment results of each training sample data set includes:
[0138] Based on the simulation adjustment results of each training sample data set, determining the adjustment result of each training sample data set, wherein the adjustment result is one of success or failure;
[0139] Based on the adjustment result of each training sample data set, the adjustment success rate of all unlabeled training sample data sets is obtained.
[0140] Specifically, in some embodiments, the preset accuracy threshold may be 95% or 98%, and the preset success rate threshold may be 93% or 95%. The settings of the preset accuracy threshold and the preset success rate threshold here are only exemplary. In actual tests, those skilled in the art may set them according to actual needs, which will not be elaborated here.
[0141] In the above embodiment, in model training, multiple groups of training sample data sets corresponding to each randomly selected training sample group are constructed through the historical energy storage database and the historical environment database, thereby improving the training ability of the photovoltaic monitoring model. Then, according to the energy storage data of each group of training sample data sets, the training sample data sets are selectively marked to facilitate verification of the training results. Then, through the energy storage data and the current environment data in the training sample data sets, it is determined whether the training sample group corresponding to the training sample data set has a fault, and the fault type of the training sample group is determined, thereby realizing self-inspection and accurate diagnosis of the faults of the training sample group, so as to obtain a repair plan or adjustment plan that matches the fault condition of the training sample group, realizing intelligent analysis and processing of the data of the training sample group, and then judging the training results of the model through the monitoring results and marking conditions of each training sample data set, realizing automatic verification of model training, and improving the intelligent ability of the photovoltaic monitoring model.
[0142] Step S103: Based on the monitoring results corresponding to each group of photovoltaic components, each group of photovoltaic components is controlled to perform self-repair and / or automatic adjustment.
[0143] Specifically, in some embodiments, controlling each group of photovoltaic components to perform self-repair and / or automatic adjustment based on the monitoring results corresponding to each group of photovoltaic components includes:
[0144] Based on the repair scheme and / or adjustment scheme in the monitoring result corresponding to the photovoltaic assembly, the photovoltaic assembly is controlled to be executed to achieve self-repair and / or automatic adjustment of the photovoltaic assembly.
[0145] Based on the above steps S101 to S103, by responding to the monitoring instruction, the energy storage data and environmental data of each group of photovoltaic components matching the monitoring instruction are obtained, so that the data information of the photovoltaic components can be automatically obtained, and the monitoring efficiency is improved. Then, the acquired energy storage data and environmental data are substituted into the photovoltaic monitoring model to obtain the monitoring results corresponding to each group of photovoltaic components, wherein the monitoring results include the repair plan and / or adjustment plan that matches the fault condition and / or estimated loss condition of the group of photovoltaic components, so that the automatic monitoring and diagnosis of the fault condition of the photovoltaic components is realized, and the corresponding repair or adjustment plan is given according to the monitoring condition, and the fault condition of each group of photovoltaic components is automatically monitored and diagnosed. Based on the monitoring results, each group of photovoltaic components is controlled to perform self-repair and / or automatic adjustment, ensuring that the photovoltaic components can operate continuously and stably, so as to realize automatic repair of the faults of each photovoltaic component and / or optimize the loss of each photovoltaic component, thereby realizing efficient, accurate and intelligent online monitoring of the photovoltaic new energy storage system, avoiding the technical problem that the monitoring method of the existing technology can only send fault alarms to management personnel according to the faults of the energy storage system, and because the distribution range of the energy storage system is generally large, the management personnel cannot perform multi-location operation and maintenance synchronously after receiving multiple fault instructions of the energy storage system, which leads to untimely maintenance of the energy storage system and even causes property loss.
[0146] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order, and they can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.
[0147] Furthermore, the present invention also provides an online monitoring device for a photovoltaic new energy storage system.
[0148] See attached Figure 3 , Figure 3 1 is a main structural block diagram of an online monitoring device for a photovoltaic new energy storage system according to an embodiment of the present invention. Figure 3 As shown, the online monitoring device 300 of the photovoltaic new energy storage system in the embodiment of the present invention is connected to the photovoltaic new energy storage system in communication, and the photovoltaic new energy storage system includes multiple groups of photovoltaic components. The online monitoring device 300 mainly includes a photovoltaic monitoring model 302 and a control module 301. The control module 301 includes a processor 3011 and a memory 3012. The memory 3012 can be configured to store a program code 3013 for the online monitoring method of the photovoltaic new energy storage system for executing the above method embodiment. The processor 3011 can be configured to execute the program code 3013 in the memory 3012, and the program code 3013 includes but is not limited to executing the program code 3013 for the online monitoring method of the photovoltaic new energy storage system for executing the above method embodiment. For ease of explanation, only the part related to the embodiment of the present invention is shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The control module 301 can be a control module 301 device formed by various electronic devices. In one embodiment, the description of the specific implementation function can refer to the description of steps S101-step S103.
[0149] Specifically, in some embodiments, the online monitoring device 300 also stores a historical energy storage database 303 and a historical environment database 304. The historical energy storage database 303 stores multiple groups of energy storage data of each group of photovoltaic components historically acquired, and the historical environment database 304 stores historical environment data corresponding to each group of photovoltaic components.
[0150] Specifically, in some embodiments, each group of photovoltaic components includes a plurality of photovoltaic modules of different types, where the types of the photovoltaic modules of different types include energy storage, input conversion, and output conversion, and each photovoltaic module includes a plurality of photovoltaic elements of different types.
[0151] Specifically, in some embodiments, the photovoltaic monitoring model 302 stores a preset self-repair parameter comparison table 3021 and a preset adjustment scheme comparison library 3022. The preset self-repair parameter comparison table 3021 stores different self-repair combination parameters, multiple groups of energy storage data corresponding to each group of self-repair combination parameters, current losses, and estimated loss data ranges. The preset adjustment scheme comparison library 3022 stores multiple adjustment schemes and an estimated adjustment index corresponding to each adjustment scheme.
[0152] The online monitoring device 300 of the photovoltaic new energy storage system is used to perform Figure 1The embodiment of the online monitoring method for photovoltaic new energy storage system shown in the figure has similar technical principles, technical problems solved and technical effects produced. Technicians in this technical field can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the online monitoring device 300 of the photovoltaic new energy storage system can refer to the contents described in the embodiment of the online monitoring method for photovoltaic new energy storage system, which will not be repeated here.
[0153] It is understood by those skilled in the art that the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor 3011, the steps of each of the above method embodiments can be implemented. Among them, the computer program includes a computer program code 3013, and the computer program code 3013 can be in the form of source code, object code, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory 3012, read-only memory 3012, random access memory 3012, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code 3013. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electric carrier signal and telecommunication signal.
[0154] Furthermore, the online monitoring device 300 of the photovoltaic new energy storage system of the present invention also includes a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium can be configured to store a program for executing the above-mentioned method embodiment for the online monitoring method of the photovoltaic new energy storage system, and the program can be loaded and run by the processor 3011 to implement the above-mentioned online monitoring method for the photovoltaic new energy storage system. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium can be a memory 3012 device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.
[0155] Further, it should be understood that since the setting of each module is only for illustrating the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor 3011 itself, or a part of the software, a part of the hardware, or a part of the combination of software and hardware in the processor 3011. Therefore, the number of each module in the figure is only schematic.
[0156] It is understood by those skilled in the art that the modules in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principle of the present invention, and therefore, the technical solutions after splitting or merging will fall within the protection scope of the present invention.
[0157] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.
Claims
1. A method for online monitoring of photovoltaic new energy storage system, characterized in that: The method is applied to an online monitoring device of a photovoltaic new energy storage system, wherein the photovoltaic new energy storage system comprises at least a plurality of photovoltaic components, wherein the photovoltaic new energy storage system is communicatively connected to an online monitoring device, wherein each photovoltaic component comprises a plurality of different types of photovoltaic modules, wherein the types of the different types of photovoltaic modules include energy storage, input conversion and output conversion, and each photovoltaic module comprises a plurality of different types of photovoltaic elements, wherein the method comprises the following steps: Updating a monitoring scheme for each group of photovoltaic assemblies, wherein the monitoring scheme includes a plurality of monitoring time points for each photovoltaic module of the photovoltaic assembly and monitoring types for different types of photovoltaic elements in each photovoltaic module; If the monitoring time point of any photovoltaic module in any group of photovoltaic components is reached, the control sends a monitoring instruction matching the photovoltaic component; In response to a monitoring instruction, energy storage data of each group of photovoltaic components matching the monitoring instruction and environmental data of each group of photovoltaic components are acquired, wherein the energy storage data includes different types of monitoring data of energy storage photovoltaic modules in the photovoltaic components and the current operating status of the energy storage photovoltaic modules, and the environmental data includes different types of environmental data of the photovoltaic components at present and within a preset time period; Substituting the energy storage data and environmental data of each group of photovoltaic components into the photovoltaic monitoring model, so that based on the energy storage data and environmental data of each group of photovoltaic components, the fault condition and / or estimated loss condition of each group of photovoltaic components are obtained, and then the monitoring results corresponding to each group of photovoltaic components are obtained, wherein the monitoring results include a repair plan and / or adjustment plan that matches the fault condition and / or estimated loss condition of each group of photovoltaic components; Based on the monitoring results corresponding to each group of photovoltaic components, control each group of photovoltaic components to perform self-repair and / or automatic adjustment; The obtaining of the environmental data of the photovoltaic assembly comprises: Acquire current collected data and online collected data of the photovoltaic module; Based on the current collected data and online collected data of the photovoltaic assembly, different types of current environmental data of the photovoltaic assembly are obtained; Acquire the current time, geographical location and a historical environment database of the geographical location of the photovoltaic module; Based on the current environmental data of the photovoltaic component, the current time and geographical location of the photovoltaic component, and a historical environmental database of the geographical location, different types of estimated environmental data of the photovoltaic component within a preset time period are obtained; The online monitoring device also stores a historical energy storage database and a historical environment database, and the photovoltaic monitoring model stores a preset self-repair parameter comparison table. Before substituting the energy storage data and environment data of each group of photovoltaic components into the photovoltaic monitoring model, the method further trains the photovoltaic monitoring model through the following steps: Randomly select different photovoltaic modules as training sample groups, and construct multiple training sample data sets corresponding to each training sample group based on a historical energy storage database and a historical environment database, wherein the training sample data sets include a set of energy storage data and a set of environment data corresponding to the training sample group; Based on the energy storage data in each group of training sample data sets, each group of training sample data sets is selectively labeled; Based on the energy storage data in each group of training sample data sets and the current environment data in the environment data, it is determined whether the training sample group corresponding to the training sample data set has a fault, and the fault type of the training sample group is determined: If it is determined that the training sample group has a fault, a repair solution matching the fault condition of the training sample data set is obtained based on the data information matching the fault type and a preset self-repair parameter comparison table; If it is determined that the training sample group does not have a fault, selectively determining an adjustment scheme for the current operating state of the energy storage photovoltaic modules in the training sample group based on the energy storage data in the training sample data set and the estimated environmental data in the environmental data; Based on the repair scheme or adjustment scheme corresponding to each training sample data set and the marking of each group of training sample data sets, determining whether the photovoltaic monitoring model is successfully trained; The determining, based on the energy storage data in each group of training sample data sets and the current environment data in the environment data, whether a training sample group corresponding to the training sample data sets has a fault, and determining the fault type of the training sample group includes: Based on the energy storage data in the training sample data set, determining whether a training sample group corresponding to the training sample data set has an energy storage fault: If the judgment is yes, determining that the fault type of the training sample group is an energy storage fault; If the judgment is no, determining the current energy storage loss of the training sample data set based on the current environmental data in the environmental data in the training sample data set and the energy storage data in the training sample data set; Based on the current energy storage loss of the training sample data set, determine whether a training sample group corresponding to the training sample data set has a loss fault: If the judgment is yes, determining that the fault type of the training sample group is a loss fault; If the judgment is no, then it is judged that there is no fault in the training sample group corresponding to the training sample data set; The preset self-repair parameter comparison table stores different self-repair combination parameters, multiple groups of energy storage data corresponding to each group of self-repair combination parameters, current loss and estimated loss data range. The repair scheme matching the fault condition of the training sample data set based on the data information matching the fault type and the preset self-repair parameter comparison table includes: If the fault type of the training sample group is an energy storage fault, determining the self-repair combination parameters corresponding to the energy storage data in the training sample data set based on the energy storage data in the training sample data set and a preset self-repair parameter comparison table; Using the self-repair combination parameters corresponding to the energy storage data in the training sample data set as the repair solution that matches the fault condition of the training sample data set; Alternatively, if the fault type of the training sample group is a loss fault, then based on the current energy storage loss of the training sample group and a preset self-repair parameter comparison table, the self-repair combination parameter corresponding to the current energy storage loss of the training sample group is determined; The self-repair combination parameter corresponding to the current energy storage loss of the training sample group is used as the repair solution that matches the fault condition of the training sample data set.
2. The online monitoring method for photovoltaic new energy storage system according to claim 1, characterized in that: The step of obtaining, in response to the monitoring instruction, the energy storage data of each group of photovoltaic components matching the monitoring instruction and the environmental data of each group of photovoltaic components comprises: In response to a monitoring instruction of any group of photovoltaic assemblies, obtaining operation data of each photovoltaic module of the photovoltaic assembly matching the monitoring instruction; Determine the current operating state of the energy storage photovoltaic module in the photovoltaic assembly based on the operating data of each photovoltaic module of the photovoltaic assembly, wherein the current operating state is one of a storage state, a transfer state or a partial transfer state; Based on the operation data of each photovoltaic module of the photovoltaic assembly, different types of monitoring data of the energy storage photovoltaic module in the photovoltaic assembly are obtained, wherein the different types include storage and / or transfer; The energy storage data of the photovoltaic assembly is formed by using different types of monitoring data of the energy storage photovoltaic modules in the photovoltaic assembly and the current operating status of the energy storage photovoltaic modules in the photovoltaic assembly; And obtain environmental data of the photovoltaic module.
3. The online monitoring method for photovoltaic new energy storage system according to claim 2 is characterized in that: The historical energy storage database stores multiple sets of energy storage data of each group of photovoltaic components acquired historically, and the historical environment database stores historical environment data corresponding to each group of photovoltaic components. The randomly selected different photovoltaic components are used as training sample groups, and based on the historical energy storage database and the historical environment database, multiple sets of training sample data sets corresponding to each training sample group are constructed, including: Randomly select different photovoltaic components as training sample groups, and use each photovoltaic module in each photovoltaic component group as a training sample; Based on the historical energy storage database and the historical environment database, multiple groups of energy storage data and multiple groups of environment data corresponding to each group of training sample groups are randomly selected; The multiple sets of energy storage data and multiple sets of environmental data corresponding to each training sample group are randomly allocated to construct multiple sets of training sample data sets corresponding to each training sample group, wherein the training sample data sets include a set of energy storage data and a set of environmental data corresponding to the training sample group.
4. The online monitoring method for photovoltaic new energy storage system according to claim 3 is characterized in that: The photovoltaic monitoring model also stores a preset adjustment scheme reference library, wherein the preset adjustment scheme reference library stores a plurality of adjustment schemes and an estimated adjustment index corresponding to each adjustment scheme. The adjustment scheme for selectively determining the current operating state of the energy storage photovoltaic module in the training sample group based on the energy storage data in the training sample data set and the estimated environmental data in the environmental data includes: Based on the energy storage data in the training sample data set and the estimated environmental data in the environmental data, obtaining an estimated loss curve of the training sample group; Based on the estimated loss curve of the training sample group, determine whether the current operating state of the energy storage photovoltaic module in the training sample group needs to be adjusted: If it is determined that adjustment is required, then based on the estimated loss curve of the training sample group and a preset adjustment scheme reference library, an adjustment scheme for the current operating state of the energy storage photovoltaic module in the training sample group is determined; If it is determined that no adjustment is needed, the situation that the training sample group does not need adjustment and does not have any faults is used as the monitoring result corresponding to the training sample group.
5. An online monitoring device for a photovoltaic new energy storage system, characterized in that: The online monitoring device is communicatively connected to the photovoltaic new energy storage system, the photovoltaic new energy storage system includes multiple groups of photovoltaic components, the online monitoring device includes a photovoltaic monitoring model and a control module, the control module includes a processor and a memory, the memory is suitable for storing multiple program codes, and the program code is suitable for being loaded and run by the processor to execute the online monitoring method for photovoltaic new energy storage system described in any one of claims 1 to 4.
Citation Information
Patent Citations
Photovoltaic panel fault detection method and device, storage medium and electronic equipment
CN117118355A
Intelligent operation and maintenance management method and system of photovoltaic power station based on big data
CN117277958A
Distributed photovoltaic power distribution network fault self-healing control and evaluation method
CN117674249A
