Over-the-air upgrading method and device for optical storage equipment and optical storage equipment

Abstract

The invention discloses an over-the-air upgrading method and device for optical storage equipment and the optical storage equipment, and belongs to the technical field of computers. The method comprises the steps of obtaining a first feature vector of a target optical storage device in a current time period; the first feature vector comprises a first element used for indicating an operation feature and a second element used for indicating a network communication feature; inputting the first feature vector into an execution time prediction model to obtain target time; the execution time prediction model is obtained by training by taking a first feature vector of each historical time period of the sample optical storage equipment as a training sample and taking sample time as a label corresponding to the training sample; the influence of the sample optical storage device executing the over-the-air upgrade operation at the sample time on the load side is smaller than a first threshold value; and controlling the target optical storage device to execute an over-the-air upgrade operation at the target time. According to the over-the-air upgrading method for the optical storage device, the purpose of reducing the adverse effect of OTA upgrading of the optical storage device on the load side can be achieved.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and in particular, relates to an over-the-air download upgrade method and device for optical storage equipment, and an optical storage equipment. Background Art

[0002] Photovoltaic storage equipment is a device that combines energy storage, energy conversion and charging functions. It is generally used to supply energy to the user's load equipment through new energy power generation methods such as solar photovoltaic power generation and wind power generation. In actual situations, in order for the photovoltaic storage equipment to operate better, the software program on the photovoltaic storage equipment needs to be updated or upgraded, such as performing an over-the-air (OTA) upgrade of the photovoltaic storage equipment.

[0003] However, in general, after the OTA upgrade of the optical storage device, the optical storage device needs to be restarted to run the OTA upgraded software program normally. The restart of the optical storage device after the OTA upgrade will have certain adverse effects on the user, such as causing the user's load device to lose power, causing the user to be unable to use the load device normally. Therefore, the OTA upgrade of the optical storage device will have certain adverse effects on the load side. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes an over-the-air download upgrade method, device and optical storage device for optical storage equipment to reduce the adverse effects of the OTA upgrade of the optical storage equipment on the load side.

[0005] In a first aspect, the present application provides an over-the-air download upgrade method for an optical storage device, the method comprising:

[0006] Acquire a first feature vector of the current time period of the target optical storage device; the first feature vector includes a first element for indicating an operation feature and a second element for indicating a network communication feature;

[0007] The first feature vector is input into an execution time prediction model to obtain a target time; the execution time prediction model is obtained by training with the first feature vector of each historical time period of the sample optical storage device as a training sample and the sample time as a label corresponding to the training sample; the impact of the over-the-air upgrade operation performed by the sample optical storage device at the sample time on the load side is less than a first threshold;

[0008] The target optical storage device is controlled to perform an over-the-air upgrade operation at the target time.

[0009] According to the over-the-air upgrade method for photovoltaic storage devices of the present application, a target time for a target photovoltaic storage device to perform an over-the-air upgrade operation is obtained by inputting a first feature vector of each historical time period of a sample photovoltaic storage device as a training sample and training the model using the sample time as a label corresponding to the training sample, wherein the impact of the sample photovoltaic storage device performing an over-the-air upgrade operation at the sample time on the load side is less than a first threshold value, so that the target time obtained by inputting the first feature vector into the execution time prediction model can reduce the adverse impact of the target photovoltaic storage device performing an over-the-air upgrade operation on the load side at the target time, so as to achieve the purpose of reducing the adverse impact on the load side when the target photovoltaic storage device performs an over-the-air upgrade operation at the target time.

[0010] According to an embodiment of the present application, inputting the first feature vector into an execution time prediction model to obtain a target time includes:

[0011] Replacing the second element in the first eigenvector with a constant to obtain a second eigenvector;

[0012] The target time is acquired by processing the first feature vector and the second feature vector based on the differential data obtained by the execution time prediction model.

[0013] According to one embodiment of the present application, the execution time prediction model includes a plurality of repetitive units based on a long short-term memory network; each of the repetitive units includes a forget gate, an input gate, and an output gate;

[0014] The step of obtaining the target time by processing the first feature vector and the second feature vector based on the execution time prediction model to obtain differential data includes:

[0015] For each of the repeating units, inputting a first input vector and a second input vector into a forget gate in the repeating unit respectively to obtain a first output and a second output; the first input vector is obtained based on the first feature vector; the second input vector is obtained based on the second feature vector;

[0016] Performing differential processing on the first output and the second output to obtain a differential result; the differential data includes the differential result;

[0017] Based on the difference result, a target input vector is input into an input gate and an output gate in the repeating unit to obtain the target time; the target input vector is the first feature vector or the second feature vector.

[0018] According to an embodiment of the present application, inputting the target input vector into the input gate and the output gate in the repeating unit based on the differential result includes:

[0019] When the difference result is less than a second threshold, determining the first input vector as the target input vector and inputting the first input vector into an input gate and an output gate in the repeating unit;

[0020] When the difference result is greater than a second threshold, the second input vector is determined as the target input vector and input into an input gate and an output gate in the repeating unit.

[0021] According to an embodiment of the present application, after controlling the target optical storage device to perform an over-the-air upgrade operation at the target time, the method further includes:

[0022] Obtaining feedback data for the target time;

[0023] Based on the feedback data, the execution time prediction model is updated.

[0024] According to an embodiment of the present application, updating the execution time prediction model based on the feedback data includes:

[0025] Taking the first feature vector of the current time period of the target optical storage device as a new training sample, and obtaining a new sample time based on the feedback data as a label corresponding to the new training sample;

[0026] Based on the new training samples and the labels corresponding to the new training samples, the execution time prediction model is updated.

[0027] According to an embodiment of the present application, before obtaining the first feature vector of the current time period of the target optical storage device, the method further includes:

[0028] Obtaining operation characteristic data and network communication characteristic data of the sample optical storage device in each historical time period;

[0029] The operation characteristic data and the network communication characteristic data of each historical time period are preprocessed to obtain a first characteristic vector of each historical time period.

[0030] According to one embodiment of the present application, the operating characteristic data includes at least one of load power, energy storage charging / discharging power, light intensity, photovoltaic input power, grid output power, grid voltage, grid frequency, and user usage status data;

[0031] The network communication characteristic data includes at least one of network speed and bandwidth.

[0032] According to an embodiment of the present application, the preprocessing of the operation characteristic data and the network communication characteristic data of each historical time period to obtain the first characteristic vector of each historical time period includes:

[0033] Performing data cleaning processing on the operation characteristic data and network communication characteristic data of each historical time period;

[0034] Performing feature engineering processing on the operation feature data and the network communication feature data of each historical time period after data cleaning processing to obtain a third feature vector of each historical time period;

[0035] The third eigenvector of each historical time period is numerically converted to obtain the first eigenvector of each historical time period.

[0036] In a second aspect, the present application provides an over-the-air download upgrade device for an optical storage device, the device comprising:

[0037] An acquisition module, used to acquire a first feature vector of a current time period of a target optical storage device; the first feature vector includes a first element for indicating an operation feature and a second element for indicating a network communication feature;

[0038] A prediction module is used to input the first feature vector into an execution time prediction model to obtain a target time; the time prediction model is obtained by training with the first feature vector of each historical time period of the sample optical storage device as a training sample and the sample time as a label corresponding to the training sample; the impact of the over-the-air upgrade operation performed by the sample optical storage device at the sample time on the load side is less than a first threshold;

[0039] The control module is used to control the target optical storage device to perform an over-the-air download upgrade operation at the target time.

[0040] According to the over-the-air upgrade device for optical storage devices of the present application, a target time for a target optical storage device to perform an over-the-air upgrade operation is obtained by inputting a first feature vector of each historical time period of a sample optical storage device as a training sample and training the model using the sample time as a label corresponding to the training sample, wherein the impact of the over-the-air upgrade operation performed by the sample optical storage device at the sample time on the load side is less than a first threshold value, so that the target time obtained by inputting the first feature vector into the execution time prediction model can reduce the adverse impact on the load side when the target optical storage device performs an over-the-air upgrade operation at the target time, so as to achieve the purpose of reducing the adverse impact on the load side when the target optical storage device performs an over-the-air upgrade operation at the target time.

[0041] In a third aspect, the present application provides an optical storage device, which includes the over-the-air download upgrade device of the optical storage device as described in the second aspect.

[0042] According to the optical storage device of the present application, the target time for the target optical storage device to perform the over-the-air upgrade operation is obtained by inputting the first feature vector of each historical time period of the sample optical storage device as a training sample and training the model with the sample time as the label corresponding to the training sample, wherein the impact of the sample optical storage device performing the over-the-air upgrade operation at the sample time on the load side is less than the first threshold value, so that the target time obtained by inputting the first feature vector into the execution time prediction model can make the target optical storage device perform the over-the-air upgrade operation at the target time with lower adverse impact on the load side, so as to achieve the purpose of lower adverse impact on the load side when the target optical storage device performs the over-the-air upgrade operation at the target time.

[0043] In a fourth aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the over-the-air download upgrade method for an optical storage device as described in the first aspect above is implemented.

[0044] In a fifth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the over-the-air download upgrade method for an optical storage device as described in the first aspect above is implemented.

[0045] In a sixth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the over-the-air download upgrade method for an optical storage device as described in the first aspect above.

[0046] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0048] Figure 1 It is a flow chart of an over-the-air download upgrade method for an optical storage device provided in an embodiment of the present application;

[0049] Figure 2 It is a flow chart of another over-the-air download upgrade method for an optical storage device provided in an embodiment of the present application;

[0050] Figure 3It is a structural schematic diagram of an over-the-air download upgrade device for an optical storage device provided in an embodiment of the present application;

[0051] Figure 4 is a schematic diagram of the structure of an optical storage device provided in an embodiment of the present application;

[0052] Figure 5 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0054] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0055] In conjunction with the accompanying drawings, the over-the-air upgrade method for an optical storage device, the over-the-air upgrade device for an optical storage device, the electronic device and the readable storage medium provided in the embodiments of the present application are described in detail below through specific embodiments and their application scenarios.

[0056] The over-the-air download upgrade method of the optical storage device can be applied to a terminal, and can be specifically executed by hardware or software in the terminal.

[0057] The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet computer with a touch-sensitive surface (e.g., a touch screen display and / or a touch pad). It should also be understood that in some embodiments, the terminal may not be a portable communication device, but a desktop computer with a touch-sensitive surface (e.g., a touch screen display and / or a touch pad).

[0058] In the following various embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse and a joystick.

[0059] The over-the-air upgrade method for an optical storage device provided in an embodiment of the present application may be executed by an electronic device or a functional module or functional entity in the electronic device that can implement the over-the-air upgrade method for an optical storage device. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras, and wearable devices. The over-the-air upgrade method for an optical storage device provided in an embodiment of the present application is described below using an electronic device as an example of the execution subject.

[0060] like Figure 1 As shown, the over-the-air download upgrade method of the optical storage device includes: step 110, step 120 and step 130.

[0061] After the optical storage device is upgraded over the air (Over-The-Air, OTA) based on the upgrade requirements of the optical storage device, the optical storage device usually needs to be restarted to run the software program after the OTA upgrade normally. However, during the restart of the optical storage device, it has a certain adverse effect on the load side. For example, the restart of the optical storage device causes the load-side device to lose power or stop running, resulting in a poor user experience on the load side. Therefore, this application provides an over-the-air download upgrade method for optical storage devices, and the specific steps are as follows:

[0062] Step 110: Obtain a first feature vector of the current time period of the target optical storage device; the first feature vector includes a first element for indicating an operation feature and a second element for indicating a network communication feature.

[0063] In actual execution, the time period can be any time period of the target optical storage device, such as ten minutes or half an hour. The current time period can be any time in 24 hours, such as 1:10 am to 1:20 am or 2:00 pm to 2:30 pm.

[0064] In actual execution, the first feature vector of the current time period of the target optical storage device can be obtained based on the operation feature data and the network communication feature data of the current time period of the target optical storage device.

[0065] The operation characteristic data may be characteristic data extracted by characterizing the operation data of the target photovoltaic storage device, and the operation characteristic data may be characteristic data characterizing the operation characteristics of the target photovoltaic storage device. The operation data of the target photovoltaic storage device may include at least one of load power (units may be W, etc.), energy storage charge / discharge power (units may be W, etc.), light intensity (units may be lm, etc.), photovoltaic input power (units may be W, etc.), grid output power (units may be W, etc.), grid voltage (units may be V, etc.), grid frequency (units may be Hz, etc.), and user usage status data.

[0066] The network communication characteristic data may be characteristic data extracted from the network communication data in the network communication environment where the target optical storage device is located, and the network communication characteristic data may be characteristic data characterizing the network communication characteristics in the network communication environment where the target optical storage device is located. The network communication data in the network communication environment where the target optical storage device is located may include at least one of the network speed (in units such as bps), the network delay (in units such as s), and the bandwidth (in units such as bps).

[0067] In actual execution, based on at least one type of data in the operating characteristic data, the first element in the first characteristic vector of the current time period of the target optical storage device for indicating the operating characteristic can be obtained. Correspondingly, based on at least one type of data in the network communication characteristic data, the second element in the first characteristic vector of the current time period of the target optical storage device for indicating the network communication characteristic can be obtained.

[0068] In some embodiments, the operating characteristic data and network communication characteristic data of the target optical storage device in the historical time period can be obtained, and the acquired operating characteristic data and network communication characteristic data of the previous time period can be preprocessed to obtain the first characteristic vector of the current time period of the target optical storage device.

[0069] Step 120, input the first feature vector into the execution time prediction model to obtain the target time; the execution time prediction model is obtained after training with the first feature vector of each historical time period of the sample optical storage device as the training sample and the sample time as the label corresponding to the training sample; the impact of the over-the-air download upgrade operation performed by the sample optical storage device at the sample time on the load side is less than the first threshold.

[0070] In actual execution, the execution time prediction model can be a prediction model constructed based on the first feature vector of each historical time period of the sample optical storage device and the sample time. In some embodiments, the first feature vector of each historical time period of the sample optical storage device can be used as a training sample, the sample time can be used as a label corresponding to the training sample, and the sample optical storage device can be trained with the impact of the air-download upgrade operation performed at the sample time on the load side being less than the first threshold as the training purpose, and the execution time prediction model is obtained through training. The target time obtained by inputting the first feature vector into the execution time prediction model satisfies the condition of reducing the adverse impact on the load side when the target optical storage device performs the air-download upgrade operation at the target time.

[0071] In some embodiments, the execution time prediction model may be a long short-term memory (LSTM) neural network model, or a recurrent neural network (RNN) model or a generative adversarial network (GAN) model. The execution time prediction model may be a neural network model based on a differential algorithm, such as an LSTM model based on a differential algorithm, or a neural network model based on a particle swarm optimization algorithm, such as an LSTM model based on a particle swarm optimization algorithm.

[0072] In some embodiments, the first feature vector may be input into the execution time prediction model based on a differential algorithm to obtain the target time. For example, the second feature vector may be obtained based on the first feature vector, and then the target time may be obtained by processing the first feature vector and the second feature vector based on the differential data obtained by the execution time prediction model.

[0073] Step 130: Control the target optical storage device to perform an over-the-air upgrade operation at a target time.

[0074] In actual execution, after obtaining the target time through the execution time prediction model, the target optical storage device can be controlled to perform the over-the-air upgrade operation at the target time, so that even if the target device restarts due to the over-the-air upgrade operation, the adverse impact on the load side is relatively small.

[0075] According to the over-the-air upgrade device for optical storage devices of the present application, a target time for a target optical storage device to perform an over-the-air upgrade operation is obtained by inputting a first feature vector of each historical time period of a sample optical storage device as a training sample and training the model using the sample time as a label corresponding to the training sample, wherein the impact of the over-the-air upgrade operation performed by the sample optical storage device at the sample time on the load side is less than a first threshold value, so that the target time obtained by inputting the first feature vector into the execution time prediction model can reduce the adverse impact on the load side when the target optical storage device performs an over-the-air upgrade operation at the target time, so as to achieve the purpose of reducing the adverse impact on the load side when the target optical storage device performs an over-the-air upgrade operation at the target time.

[0076] In some embodiments, in step 120, the first feature vector is input into the execution time prediction model to obtain the target time. The second element in the first feature vector can be replaced with a constant to obtain the second feature vector, and then the first feature vector and the second feature vector are processed based on the execution time prediction model to obtain differential data to obtain the target time.

[0077] In actual execution, after obtaining a first feature vector including a first element for indicating an operating characteristic and a second element for indicating a network communication characteristic, the second element for indicating the network communication characteristic in the first feature vector can be replaced with a constant to obtain a second feature vector to eliminate the impact caused by unstable changes in the network communication characteristic.

[0078] In actual execution, after obtaining the first eigenvector and the second eigenvector, a differential process may be performed on the first eigenvector and the second eigenvector based on a differential algorithm to obtain differential data.

[0079] In actual execution, the first eigenvector and the second eigenvector can be input into the execution time prediction model to obtain the first output and the second output, and then the first output and the second output are differentially processed to obtain the differential result; finally, based on the differential result, the target input vector is determined from the first eigenvector and the second eigenvector, and the target time is obtained based on the target input vector.

[0080] According to the over-the-air upgrade method for a photovoltaic storage device of the present application, the second element in the first feature vector indicating the network communication characteristics is replaced with a constant to obtain a second feature vector, the first feature vector and the second feature vector are processed based on an execution time prediction model to obtain differential data, and the influence caused by the unstable changes in the network communication characteristics is eliminated based on the idea of ​​a differential algorithm, so that the association relationship can be captured from the second element indicating the network communication characteristics in time sequence to obtain the target time after eliminating the influence, thereby achieving the purpose of having a lower adverse impact on the load side when the target photovoltaic storage device performs an over-the-air upgrade operation at the target time obtained by the execution time prediction model.

[0081] In some embodiments, the target time may be obtained by processing the first feature vector and the second feature vector based on the differential data obtained by the execution time prediction model, wherein the execution time prediction model may be a long short-term memory neural network model.

[0082] In actual execution, the execution time prediction model may include multiple repeating units based on the long short-term memory network; each repeating unit includes a forget gate, an input gate, and an output gate. The target time can be obtained by processing the first eigenvector and the second eigenvector through the forget gate, input gate, and output gate in each repeating unit, and obtaining differential data.

[0083] In actual execution, for each of the multiple repeating units of the long short-term memory network, the first input vector obtained based on the first eigenvector and the second input vector obtained based on the second eigenvector can be respectively input into the forget gate in the repeating unit to obtain the first output and the second output, and then the first output and the second output are differentially processed to obtain the differential result; finally, based on the differential result, the target input vector is determined from the first eigenvector and the second eigenvector, and the target input vector is input into the input gate and the output gate in the repeating unit to obtain the target time. The differential data includes the differential result.

[0084] In some embodiments, after performing differential processing on the first output and the second output obtained by the forget gate and obtaining the differential result, a target input vector can also be determined from the first input vector and the second input vector based on the differential result, and the target input vector is input into the input gate and the output gate in the repeating unit to obtain the target time. In some embodiments, after obtaining the differential result, if the differential result is less than the second threshold, the first input vector is determined as the target input vector and is input into the input gate and the output gate in the repeating unit; if the differential result is greater than the second threshold, the second input vector is determined as the target input vector and is input into the input gate and the output gate in the repeating unit to obtain the target time.

[0085] In actual execution, the first output and the second output obtained by the forget gate can be differentially processed to obtain a differential vector, and the element at the target position in the differential vector represents the differential result.

[0086] In some embodiments, after executing step 130 to control the target optical storage device to perform the over-the-air upgrade operation at the target time, feedback data for the target time is obtained, and the execution time prediction model is updated based on the feedback data.

[0087] In actual implementation, a feedback channel can be set up. After controlling the target optical storage device to perform the over-the-air download upgrade operation at the target time, feedback data can be obtained through the feedback channel. The feedback channel can include optical storage device indicator data acquisition interface, mini-programs, and web questionnaires.

[0088] In some embodiments, the feedback data at the target time may include load-side user satisfaction data and photovoltaic storage device index data. The load-side user satisfaction data may include a user satisfaction score. The photovoltaic storage device index data may represent an objective evaluation of various operating indicators of the target photovoltaic storage device after performing an over-the-air download upgrade operation.

[0089] In actual execution, after obtaining feedback data for the target time, the feedback data can be used as new training data to update the execution time prediction model.

[0090] According to the over-the-air upgrade method for optical storage devices of the present application, after controlling the target optical storage device to perform the over-the-air upgrade operation at the target time, feedback data on the target optical storage device performing the over-the-air upgrade operation at the target time can be obtained, and the execution time prediction model can be updated based on the feedback data. Through continuous updating and training, the accuracy of the execution time prediction model can be improved.

[0091] In some embodiments, the first feature vector of the current time period of the target optical storage device can be used as a new training sample. Based on the feedback data, a new sample time is obtained as the label corresponding to the new training sample. Based on the new training sample and the label corresponding to the new training sample, the execution time prediction model is updated, where the sample time may include the target time.

[0092] In some embodiments, before obtaining the first feature vector of the current time period of the target optical storage device in step 110, the operating feature data and network communication feature data of each historical time period of the sample optical storage device can be obtained, and the operating feature data and network communication feature data of each historical time period can be preprocessed to obtain the first feature vector of each historical time period.

[0093] In actual implementation, the sample optical storage device and the target optical storage device may be the same optical storage device or different optical storage devices. Each historical time period may be any time period before the above current time period.

[0094] In actual implementation, the operating characteristic data of the sample photovoltaic storage device in each historical time period may include load power (units may be W, etc.), energy storage charging / discharging power (units may be W, etc.), light intensity (units may be lm, etc.), photovoltaic input power (units may be W, etc.), grid output power (units may be W, etc.), grid voltage (units may be V, etc.), grid frequency (units may be Hz, etc.) and at least one of user usage status data.

[0095] The network communication characteristic data may include at least one of network speed (unit may be bps, etc.), network delay (unit may be s, etc.) and bandwidth (unit may be bps, etc.).

[0096] In actual execution, the operation characteristic data and network communication characteristic data of each historical time period can be preprocessed respectively, and then the first characteristic vector of each historical time period is obtained based on the preprocessed operation characteristic data and network communication characteristic data. The preprocessing can include at least one of data cleaning processing, feature engineering processing and numerical conversion processing.

[0097] According to the over-the-air upgrade method for photovoltaic storage devices of the present application, the operation characteristic data and network communication characteristic data of each historical time period of the sample photovoltaic storage device are obtained and preprocessed to obtain the first characteristic vector of each historical time period, so that the first characteristic vector of each historical time period of the sample photovoltaic storage device is used as a training sample, the sample time is used as the label corresponding to the training sample, and training is carried out with the impact of the sample photovoltaic storage device performing an over-the-air upgrade operation at the sample time on the load side being less than a first threshold as the training purpose, so as to obtain an execution time prediction model, and then the first characteristic vector of the current time period is input into the execution time prediction model to obtain the target time for the target photovoltaic storage device to perform the over-the-air upgrade operation, so as to achieve the purpose of having a lower adverse impact on the load side when the target photovoltaic storage device performs the over-the-air upgrade operation at the target time obtained by the execution time prediction model.

[0098] In some embodiments, data cleaning processing may be performed on the operation characteristic data and network communication characteristic data of each historical time period; feature engineering processing may be performed on the operation characteristic data and network communication characteristic data of each historical time period after data cleaning processing to obtain the third characteristic vector of each historical time period; and numerical conversion processing may be performed on the third characteristic vector of each historical time period to obtain the first characteristic vector of each historical time period.

[0099] In order to better understand the over-the-air download upgrade method for an optical storage device provided in an embodiment of the present application, further explanation is given below. It should be understood that the discussion below is only exemplary.

[0100] The present application provides an over-the-air download upgrade method for an optical storage device. The specific steps can be as follows: Figure 2 As shown:

[0101] Step 1: Obtain the operation characteristic data and network communication characteristic data of the sample optical storage equipment in each historical time period.

[0102] In actual implementation, the historical time period can be any time interval as a period, such as 1 minute. Operation characteristic data may include load power, energy storage charge / discharge power, light intensity, photovoltaic input power, grid output power, grid voltage, grid frequency and user usage status data. The network communication characteristic data of each historical time period of the sample photovoltaic storage device may include network communication characteristic data including network speed, network delay and bandwidth.

[0103] Step 2: pre-process the operation characteristic data and network communication characteristic data of each historical time period to obtain the first characteristic vector of each historical time period.

[0104] In actual execution, data cleaning processing may be performed on the operation characteristic data and network communication characteristic data of each historical time period, and the data cleaning processing may include outlier cleaning.

[0105] In actual implementation, in the process of outlier cleaning, outliers in the operation characteristic data and network communication characteristic data of each historical time period can be detected based on the box plot. Since the operation characteristic data and network communication characteristic data of each historical time period obtained are time-series, the detected outliers can be corrected to eliminate the anomalies. For example, if the anomaly is missing or an obviously wrong value, then the average value of the corresponding position elements of the adjacent 4 groups (two groups before and after) of data is used to replace the abnormal position element. If the anomaly is a sudden increase or decrease in the value by a certain order of magnitude, and it is reasonable after scaling / expanding, then the abnormal value is replaced with a reasonable value after scaling / expanding.

[0106] In some embodiments, the correlation between various types of data in the operation characteristic data and the network communication characteristic data of each historical time period can be calculated, and the data with high correlation can be eliminated to reduce unnecessary calculations. In some embodiments, the correlation between the elements can be measured based on the mutual information (MI) correlation coefficient. For any two random variables X and Y, the process of calculating the MI correlation coefficient between X and Y can be described as:

[0107]

[0108] Among them, I(X;Y) is the MI correlation coefficient between variables X and Y, p(x,y) is the joint probability distribution function, which indicates the probability of X and Y appearing at the same time, and p(x) and p(y) are the marginal probability distribution functions of X and Y respectively. When I(X;Y) is 0, it means that there is no correlation between the two variables X and Y; when I(X;Y) is not 0, the larger the I(X;Y), the stronger the correlation. After calculating the MI correlation coefficient between each element, all elements with MI correlation coefficient greater than the preset value can be eliminated.

[0109] In some embodiments, feature engineering processing can be performed on the operation characteristic data and network communication characteristic data of each historical time period after data cleaning processing to obtain the third characteristic vector of each historical time period, and the third characteristic vector of each historical time period can be numerically converted to obtain the first characteristic vector of each historical time period.

[0110] In actual execution, since the order of magnitude of the operating characteristic data and the network communication characteristic data of each historical time period is quite different, in order to balance the impact of this gap on the subsequent execution time prediction model training, the third eigenvector of each historical time period can be numerically converted. For example, a unified dimensionality reduction process can be performed based on the ln logarithmic transformation method to obtain the first eigenvector of each historical time period.

[0111] Step 3: Based on the first eigenvector of each historical time period, build an execution time prediction model.

[0112] In actual execution, the LSTM algorithm can be used to build an execution time prediction model based on the first eigenvector of each historical time period.

[0113] In actual execution, the first feature vector of each historical time period can be used as a training set, and iterative training can be performed through the LSTM algorithm to build an execution time prediction model. The execution time prediction model can be an LSTM neural network model, and the execution time prediction model can include multiple repeating units based on a long short-term memory network; each of the repeating units includes a forget gate, an input gate, and an output gate.

[0114] Step 4: Obtain a first feature vector of the current time period of the target optical storage device, wherein the first feature vector includes a first element for indicating an operation feature and a second element for indicating a network communication feature.

[0115] In actual implementation, the operating characteristics may be characteristic data extracted by characterizing the operating data of the target photovoltaic storage device, and the operating data of the target photovoltaic storage device may include at least one of load power, energy storage charging / discharging power, light intensity, photovoltaic input power, grid output power, grid voltage, grid frequency and user usage status data.

[0116] In actual implementation, after obtaining the first feature vector of each historical time period, the first feature vector of each historical time period can be divided into n vectors X according to the time period. n (n is a positive integer), vector X t ={x 1 ,x 2 ,...,x m} represents the first eigenvector of the tth time period. Each element x in the first eigenvector j Represents a type of feature data. Based on the first feature vector of each historical time period, obtain the first feature vector of the current time period of the target optical storage device, for example, X te .

[0117] Step 5: The first feature vector is input into the execution time prediction model to obtain the target time.

[0118] In actual execution, the second element in the first feature vector can be replaced with a constant to obtain a second feature vector. The first input vector and the second input vector obtained based on the second feature vector can be respectively input into the execution time prediction model, and the first output and the second output are differentially processed to obtain a differential result, and the target time is obtained based on the differential result.

[0119] In actual implementation, the first feature vector of the current time period of the target optical storage device obtained includes a second element for indicating network communication characteristics. The second element for indicating network communication characteristics is different from the first element, which changes more stably. It is difficult to capture the correlation relationship from the time sequence. Therefore, the second element in the first feature vector can be replaced with a constant to eliminate the unstable effect caused by the second element. For example, for the first feature vector X of the current time period te ={x 1 ,x 2 ,...,x m}, the first eigenvector X te The mth element representing the network communication capability, that is, the second element is replaced by a constant to obtain the second eigenvector X tn ={x 1 ,x 2 ,...,x m-1 ,1}.

[0120] In actual execution, a first input vector obtained based on the first feature vector and a second input vector obtained based on the second feature vector may be respectively input into a forget gate in the repeating unit to obtain a first output and a second output.

[0121] In actual execution, the execution time prediction model may include multiple repeating units based on the long short-term memory network; each repeating unit includes a forget gate, an input gate, and an output gate. te ={x 1 ,x 2 ,...,x m} and the second eigenvector X tn ={x 1 ,x 2 ,...,x m-1 ,1} respectively input the forget gate in the repeating unit to obtain the first output F te and the second output F tn .

[0122] In actual execution, the forget gate decides which information to discard for the current input X tn and X te , the hidden state of a time period can be recorded as H t-1 , respectively X tn and H t-1 , X te and H t-1 As the input of the forget gate, the forget gate output is obtained through a fully connected layer and a sigmoid activation function. The process can be described as:

[0123] F t =σ(Wf [H t-1 ,X t ]+b f )

[0124] Where W f is the weight matrix, σ is the sigmoid activation function, b f It is a bias term. The bias term is an important definition in many artificial intelligence algorithms. It is similar to the intercept of a straight line on the y-axis. The bias term allows the model output to be unaffected by the input feature value and adjusted. If there is no bias term, the output of the model will always pass through the origin (that is, the output must be 0 when the input is 0). Therefore, after adding the bias term, the model can better adapt to different data distributions and reduce the risk of overfitting.

[0125] In actual implementation, the first output F obtained by the forget gate is te and the second output F tn Based on the first output F te and the second output F tn Perform differential operation to obtain the differential result ΔF t :

[0126] ΔF t =F tn -F te ={Δx 1 ,Δx 2 ,...,Δx m}

[0127] Based on the difference result, a target input vector is determined from the first eigenvector and the second eigenvector, and the target input vector is input into an input gate and an output gate in the repeating unit to obtain a target time.

[0128] After obtaining the differential result ΔF t After that, the Δx in the difference result m If it exceeds the expected threshold α, then F te As the output of the forget gate F t , in order to filter out the noise generated by network jitter; on the contrary, in Δx m If the expected threshold α is not exceeded, F tn As the output of the forget gate F t .

[0129] Based on the difference result, a target input vector X can be determined from the first feature vector and the second feature vector, and the target input vector is input into the output gate to obtain the target time. In some embodiments, based on the difference result, a target input vector X is determined from the first feature vector and the second feature vector. t , and the target input vector X tInput and output gates, the output gates determine what information should be output based on the current cell state. You can use the target input vector X t and the hidden state H of the previous time period t-1 As input, after passing through a linear layer, the Sigmoid activation function is input to obtain the output of the output gate O t The process can be described as:

[0130] O t =σ(W o [H t-1 ,X t ]+b o ).

[0131] Where W o is the weight matrix, σ is the sigmoid activation function, b o is the bias term. Based on the output O of the output gate t Get the target time.

[0132] In actual execution, the input gate determines what information should be updated to the cell state. The input gate can calculate the output i of the input gate. t and candidate state c′ t The process can be described as follows:

[0133] i t =σ(W i [H t-1 ,X t ]+b i );

[0134] c′ t =σ(W c [H t-1 ,X t ]+b c ).

[0135] Where W i is the weight matrix of the input gate, W c is the weight matrix of the candidate unit state, b i and b c is the corresponding bias term.

[0136] In actual execution, the cell state C can be calculated based on the output of the forget gate and the input gate. t , the process can be described as:

[0137]

[0138] Among them, ○ represents the element-by-element multiplication operation, C t-1 is the unit state at the previous moment, i t is the output of the input gate, c′t It is a candidate state.

[0139] In actual implementation, the output gate O t and cell status C t , calculate the hidden state H t , the process can be described as:

[0140] H t =O t tanh(C t ).

[0141] And H t As input to the next time period to better capture long-term dependencies in the sequence data and improve the prediction accuracy of the model.

[0142] Step 6: Control the target optical storage device to perform the over-the-air download upgrade operation at the target time.

[0143] In actual execution, after obtaining the target time through the execution time prediction model, the target optical storage device can be controlled to perform the over-the-air upgrade operation at the target time. In this way, even if the target device restarts due to the over-the-air upgrade operation, the adverse impact on the load side is relatively small.

[0144] Step 7: Obtain feedback data on the over-the-air upgrade operation performed on the target optical storage device at the target time, so as to update the execution time prediction model through the feedback data.

[0145] In actual implementation, the feedback data at the target time may include user satisfaction data on the load side, such as user satisfaction scores. A feedback channel may be set, and after the target optical storage device is controlled to perform an over-the-air upgrade operation at the target time, feedback data may be obtained through the feedback channel, wherein the feedback channel may include mini-programs, webpage questionnaires, and the like.

[0146] In actual execution, after obtaining feedback data for the target time, the execution time prediction model can be updated according to the feedback data. In some embodiments, the first feature vector of the current time period of the target optical storage device can be used as a new training sample, and based on the feedback data, a new sample time is obtained as a label corresponding to the new training sample, and based on the new training sample and the label corresponding to the new training sample, the execution time prediction model is updated, where the sample time may include the target time.

[0147] The embodiment of the present application also provides an over-the-air download upgrade device for an optical storage device.

[0148] like Figure 3As shown, the over-the-air download upgrade device 300 of the optical storage device includes: a first acquisition module 310 , a prediction module 320 and a control module 330 .

[0149] A first acquisition module 310 is used to acquire a first feature vector of a current time period of a target optical storage device; the first feature vector includes a first element for indicating an operation feature and a second element for indicating a network communication feature;

[0150] The prediction module 320 is used to input the first feature vector into the execution time prediction model to obtain the target time; the time prediction model is obtained by training with the first feature vector of each historical time period of the sample optical storage device as a training sample and the sample time as the label corresponding to the training sample; the impact of the over-the-air upgrade operation performed by the sample optical storage device at the sample time on the load side is less than the first threshold;

[0151] The control module 330 is used to control the target optical storage device to perform an over-the-air download upgrade operation at a target time.

[0152] According to the over-the-air upgrade device for optical storage devices of the present application, the first feature vector is input into the first feature vector of each historical time period of the sample optical storage device as a training sample, and the execution time prediction model is obtained after training with the sample time as the label corresponding to the training sample, so as to obtain the target time for the target optical storage device to execute the over-the-air upgrade operation, wherein the impact of the sample optical storage device executing the over-the-air upgrade operation at the sample time on the load side is less than the first threshold, so as to achieve that when the target optical storage device executes the over-the-air upgrade operation at the target time obtained by the execution time prediction model, the adverse impact on the load side is low.

[0153] In some embodiments, the prediction module 320 may include:

[0154] A first acquisition unit, used for replacing the second element in the first eigenvector with a constant to acquire a second eigenvector;

[0155] The second acquisition unit is used to acquire the target time by processing the first feature vector and the second feature vector based on the execution time prediction model to obtain the differential data.

[0156] In some embodiments, the execution time prediction model includes a plurality of repetitive units based on a long short-term memory network; each repetitive unit includes a forget gate, an input gate, and an output gate; and the second acquisition unit may include:

[0157] A first input unit is used to input the first input vector and the second input vector into the forget gate in the repeating unit for each repeating unit, respectively, to obtain the first output and the second output; the first input vector is obtained based on the first feature vector; the second input vector is obtained based on the second feature vector;

[0158] A processing unit, configured to perform differential processing on the first output and the second output to obtain a differential result; the differential data includes the differential result;

[0159] The second input unit is used to input the target input vector into the input gate and the output gate in the repeating unit based on the difference result to obtain the target time; the target input vector is the first eigenvector or the second eigenvector.

[0160] In some embodiments, the second input unit may include:

[0161] A first determining unit, configured to determine the first input vector as a target input vector and input the first input vector into an input gate and an output gate in a repeating unit when the difference result is less than a second threshold value;

[0162] The second determining unit is used to determine the second input vector as the target input vector and input the second input vector into the input gate and the output gate in the repeating unit when the difference result is greater than the second threshold.

[0163] In some embodiments, the over-the-air upgrade device 300 of the optical storage device may further include:

[0164] A second acquisition module is used to acquire feedback data for the target time;

[0165] The update module is used to update the execution time prediction model based on the feedback data.

[0166] In some embodiments, the update module may include:

[0167] A third acquisition unit is used to use the first feature vector of the current time period of the target optical storage device as a new training sample, and based on the feedback data, acquire a new sample time as a label corresponding to the new training sample;

[0168] The updating unit is used to update the execution time prediction model based on the new training samples and the labels corresponding to the new training samples.

[0169] In some embodiments, the over-the-air upgrade device 300 of the optical storage device may further include:

[0170] A third acquisition module is used to obtain the operation characteristic data and network communication characteristic data of the sample optical storage device in each historical time period;

[0171] The processing module is used to pre-process the operation characteristic data and network communication characteristic data of each historical time period to obtain the first characteristic vector of each historical time period.

[0172] In some embodiments, the operating characteristic data includes at least one of load power, energy storage charge / discharge power, light intensity, photovoltaic input power, grid output power, grid voltage, grid frequency, and user usage status data;

[0173] The network communication characteristic data includes at least one of network speed and bandwidth.

[0174] In some embodiments, the processing module may include:

[0175] A first processing unit is used to perform data cleaning processing on the operation characteristic data and network communication characteristic data of each historical time period;

[0176] A second processing unit is used to perform feature engineering processing on the operation feature data and the network communication feature data of each historical time period after the data cleaning processing, and obtain a third feature vector of each historical time period;

[0177] The third processing unit is used to perform numerical conversion processing on the third eigenvector of each historical time period to obtain the first eigenvector of each historical time period.

[0178] The over-the-air download upgrade device of the optical storage device in the embodiment of the present application can be an electronic device or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices other than a terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc. It can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0179] The over-the-air download upgrade device of the optical storage device in the embodiment of the present application may be a device having an operating system. The operating system may be a Microsoft (Windows) operating system, an Android (Android) operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0180] The air download upgrade device 300 of the optical storage device provided in the embodiment of the present application can achieve Figure 1 to Figure 2 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0181] In some embodiments, Figure 4 As shown, an embodiment of the present application further provides an optical storage device 400, and the optical storage device 400 includes an over-the-air download upgrade device of the optical storage device.

[0182] In some embodiments, Figure 5 As shown, an embodiment of the present application also provides an electronic device 500, including a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501. When the program is executed by the processor 501, each process of the above-mentioned over-the-air download upgrade method embodiment of the optical storage device is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0183] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0184] An embodiment of the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned over-the-air download upgrade method embodiment of the optical storage device are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0185] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0186] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the over-the-air download upgrade method for the above-mentioned optical storage device.

[0187] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0188] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned over-the-air download upgrade method embodiment of the optical storage device, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0189] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0190] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0191] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0192] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0193] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0194] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. An over-the-air download upgrade method for an optical storage device, characterized in that: include: Acquire a first feature vector of the current time period of the target optical storage device; the first feature vector includes a first element for indicating an operation feature and a second element for indicating a network communication feature; The first feature vector is input into an execution time prediction model to obtain a target time; the execution time prediction model is obtained by training with the first feature vector of each historical time period of the sample optical storage device as a training sample and the sample time as a label corresponding to the training sample; the impact of the over-the-air upgrade operation performed by the sample optical storage device at the sample time on the load side is less than a first threshold; The target optical storage device is controlled to perform an over-the-air upgrade operation at the target time.

2. The over-the-air download upgrade method for optical storage equipment according to claim 1, characterized in that: Inputting the first feature vector into the execution time prediction model to obtain the target time includes: Replacing the second element in the first eigenvector with a constant to obtain a second eigenvector; The target time is acquired by processing the first feature vector and the second feature vector based on the differential data obtained by the execution time prediction model.

3. The over-the-air download upgrade method for optical storage equipment according to claim 2, characterized in that: The execution time prediction model includes a plurality of repetitive units based on a long short-term memory network; each of the repetitive units includes a forget gate, an input gate and an output gate; The step of obtaining the target time by processing the first feature vector and the second feature vector based on the execution time prediction model to obtain differential data includes: For each of the repeating units, inputting a first input vector and a second input vector into a forget gate in the repeating unit respectively to obtain a first output and a second output; the first input vector is obtained based on the first feature vector; the second input vector is obtained based on the second feature vector; Performing differential processing on the first output and the second output to obtain a differential result; the differential data includes the differential result; Based on the difference result, a target input vector is input into an input gate and an output gate in the repeating unit to obtain the target time; the target input vector is the first feature vector or the second feature vector.

4. The over-the-air download upgrade method for optical storage equipment according to claim 3, characterized in that: The step of inputting the target input vector into the input gate and the output gate in the repeating unit based on the differential result comprises: When the difference result is less than a second threshold, determining the first input vector as the target input vector and inputting the first input vector into an input gate and an output gate in the repeating unit; When the difference result is greater than a second threshold, the second input vector is determined as the target input vector and input into an input gate and an output gate in the repeating unit.

5. The over-the-air download upgrade method for optical storage equipment according to claim 1, characterized in that: After controlling the target optical storage device to perform an over-the-air upgrade operation at the target time, the method further includes: Obtaining feedback data for the target time; Based on the feedback data, the execution time prediction model is updated.

6. The over-the-air download upgrade method for optical storage equipment according to claim 5, characterized in that: The updating of the execution time prediction model based on the feedback data includes: Taking the first feature vector of the current time period of the target optical storage device as a new training sample, and obtaining a new sample time based on the feedback data as a label corresponding to the new training sample; Based on the new training samples and the labels corresponding to the new training samples, the execution time prediction model is updated.

7. The over-the-air download upgrade method for optical storage equipment according to any one of claims 1 to 6, characterized in that: Before obtaining the first feature vector of the current time period of the target optical storage device, the method further includes: Obtaining operation characteristic data and network communication characteristic data of the sample optical storage device in each historical time period; The operation characteristic data and the network communication characteristic data of each historical time period are preprocessed to obtain a first characteristic vector of each historical time period.

8. The over-the-air download upgrade method for optical storage equipment according to claim 7, characterized in that: The operation characteristic data includes at least one of load power, energy storage charging / discharging power, light intensity, photovoltaic input power, grid output power, grid voltage, grid frequency and user usage status data; The network communication characteristic data includes at least one of network speed and bandwidth.

9. The over-the-air download upgrade method for optical storage equipment according to claim 7, characterized in that: The preprocessing of the operation characteristic data and the network communication characteristic data of each historical time period to obtain the first characteristic vector of each historical time period includes: Performing data cleaning processing on the operation characteristic data and network communication characteristic data of each historical time period; Performing feature engineering processing on the operation feature data and the network communication feature data of each historical time period after data cleaning processing to obtain a third feature vector of each historical time period; The third eigenvector of each historical time period is numerically converted to obtain the first eigenvector of each historical time period.

10. An over-the-air download upgrade device for optical storage equipment, characterized in that: include: A first acquisition module, used to acquire a first feature vector of a current time period of a target optical storage device; the first feature vector includes a first element for indicating an operation feature and a second element for indicating a network communication feature; A prediction module is used to input the first feature vector into an execution time prediction model to obtain a target time; the time prediction model is obtained by training with the first feature vector of each historical time period of the sample optical storage device as a training sample and the sample time as a label corresponding to the training sample; the impact of the over-the-air upgrade operation performed by the sample optical storage device at the sample time on the load side is less than a first threshold; The control module is used to control the target optical storage device to perform an over-the-air download upgrade operation at the target time.

11. A light storage device, characterized in that: The optical storage device has the over-the-air download upgrade device for optical storage devices as claimed in claim 10.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the over-the-air download upgrade method for the optical storage device as described in any one of claims 1-9 is implemented.

13. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the over-the-air download upgrade method for an optical storage device as described in any one of claims 1 to 9 is implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the over-the-air download upgrade method for an optical storage device as described in any one of claims 1-9 is implemented.

Images