Intelligent power supply adjustment method and system based on voltage, and storage medium

Abstract

The invention discloses an intelligent power supply adjusting method and system based on voltage and a storage medium. The method comprises the following steps: acquiring related data of voltage fluctuation; training a voltage fluctuation prediction model by using the related data of the voltage fluctuation so as to analyze the mode and trend of the voltage fluctuation; inputting real-time monitoring data by using the voltage fluctuation prediction model to obtain a prediction result of voltage fluctuation; dynamically adjusting the working state of the power supply through a self-adaptive control strategy according to the prediction result of the voltage fluctuation; wherein the self-adaptive control strategy comprises the step of automatically adjusting the output voltage and current of the power supply module through an energy storage and release system according to the change of a voltage wave bottom. Through the trained voltage fluctuation prediction model, the mode and trend of the voltage fluctuation are analyzed by using a multi-feature factor analysis method, so that the voltage fluctuation can be predicted more comprehensively and accurately. By dynamically adjusting the output voltage and current of the power supply module, stable power output is maintained.

Description

Technical Field

[0001] The present invention generally relates to the field of artificial intelligence technology. More specifically, the present invention relates to a voltage-based intelligent power supply adjustment method, system and storage medium. Background Art

[0002] In the field of modern power applications, the power module is undoubtedly the key hub to maintain the normal operation of the entire power system. From precision machinery on industrial production lines to various electronic devices in the home, from life support systems in the medical field to core base stations of communication networks, power modules are everywhere, and their stability is directly related to whether these systems can operate reliably. Therefore, the stability of the power module plays a vital role in the reliable operation of the entire power system.

[0003] However, the reality is that frequent fluctuations and abnormal changes in voltage can cause serious damage to the power module itself. Just like a ship sailing in a rough sea, the power module is under the impact of unstable voltage, and the internal electronic components are under additional pressure, and their aging and loss rate is significantly accelerated. The power module that was originally expected to work stably for a long time may end its service life prematurely due to being in an unstable voltage environment for a long time. This not only means that the power module needs to be replaced more frequently, increasing equipment maintenance costs and downtime, but may also cause serious safety hazards in some key application scenarios.

[0004] On the other hand, for those electrical devices that rely on power modules for power supply, the impact of unstable voltage is even more multifaceted and far-reaching. Taking common computer systems as an example, unstable voltage may cause the performance of the central processing unit (CPU) to decline. When the voltage is lower than the normal level, the CPU may not be able to run at the rated frequency, the computing speed is greatly reduced, and the data tasks that could be processed quickly become slow, seriously affecting work efficiency. In terms of data transmission, unstable voltage may interfere with the signal integrity of the data bus, causing data errors during transmission. These errors may manifest as data loss, data tampering, or transmission interruption. For some applications that require extremely high data accuracy, such as financial trading systems and scientific research data acquisition systems, even a tiny data error may lead to catastrophic consequences. More seriously, long-term voltage instability may also directly damage the hardware of electrical equipment. For example, excessively high voltage may break through the insulation layer of electronic components, causing the components to short-circuit and burn; while too low voltage may prevent equipment such as motors from starting normally, and they will be in a stalled state for a long time, and then overheat and damage. Similar problems also exist in other fields. For example, in some continuous production industrial processes, equipment failures caused by voltage problems may even cause the entire production line to stop production, resulting in huge economic losses. In the medical field, many medical devices such as electrocardiographs, monitors, surgical instruments, etc. have extremely high requirements for power supply stability. Even slight fluctuations in voltage may affect the measurement accuracy of medical equipment, leading to misjudgment of the patient's condition, and even endangering the patient's life safety.

[0005] In view of this, there is an urgent need to provide a voltage-based intelligent power adjustment method to effectively control the stable output of the power supply. Summary of the invention

[0006] In order to at least solve one or more of the technical problems mentioned above, the present invention proposes a voltage-based intelligent power supply adjustment solution in multiple aspects.

[0007] In the first aspect, the present invention provides a voltage-based intelligent power supply adjustment method, comprising: obtaining relevant data of voltage fluctuations; using the relevant data of voltage fluctuations to train a voltage fluctuation prediction model to analyze the pattern and trend of voltage fluctuations; using the voltage fluctuation prediction model to input real-time monitoring data to obtain prediction results of voltage fluctuations; dynamically adjusting the working state of the power supply through an adaptive control strategy based on the prediction results of the voltage fluctuations; wherein the adaptive control strategy includes automatically adjusting the output voltage and current of the power supply module through an energy storage and release system according to changes in the voltage wave bottom; storing energy when the voltage wave bottom is lower than a set threshold of a reference voltage, and releasing energy when the voltage wave bottom is higher than a set threshold of the reference voltage, so as to smooth voltage fluctuations.

[0008] In some embodiments, the voltage fluctuation prediction model is trained using the relevant data of the voltage fluctuation to analyze the pattern and trend of the voltage fluctuation, including the following data preparation stages: processing the missing or abnormal data in the relevant data of the voltage fluctuation to obtain the original training data; transforming or combining the feature data in the original training data to generate effective training data containing the transformed or combined new features, wherein the new features include frequency features extracted using Fourier transform; normalizing the effective training data to eliminate the dimensional difference between different features; analyzing the correlation between different features in the effective training data and the voltage fluctuation, and adding features whose influence coefficient on the prediction result exceeds a threshold to the effective training data; wherein the analysis of the correlation between different features in the effective training data and the voltage fluctuation includes: extracting static features and time series features in the effective training data, and fusing the two features using a context feature fusion network;

[0009] In some embodiments, the training voltage fluctuation prediction model includes: dividing the valid training data into a training set, a validation set and a test set; using the training set data to train the voltage fluctuation prediction model according to a time series prediction model to analyze the pattern and trend of voltage fluctuations; using the validation set data to verify the trained voltage fluctuation prediction model to obtain a verification result; based on the verification result, adjusting the voltage fluctuation prediction model to optimize the voltage fluctuation prediction model; the adjustment of the voltage fluctuation prediction model includes adjusting model parameters, feature combinations or model structures; using the test set data to evaluate the prediction result indicators of the optimized voltage fluctuation prediction model to obtain an evaluation result.

[0010] In some embodiments, the time series prediction model includes: normalizing all input training set data to the range of [-1,1]; constructing a multi-layer long short-term memory network, the long short-term memory network includes at least one layer for capturing short-term dependencies and one layer for capturing long-term dependencies; wherein, an added attention mechanism is also included before or after each layer of the long short-term memory network to weight the input features, and dynamically adjust the attention weights of different time steps according to the current input and context vector; using the long short-term memory network, inputting a multidimensional feature vector at time point t, the multidimensional feature vector containing at least one or more of the following features: voltage value, temperature, humidity, load change; according to the multidimensional feature vector, capturing the long-term and short-term dependencies in the time series data to obtain a voltage fluctuation prediction result.

[0011] In some embodiments, the extraction of static features and temporal features from the effective training data and the fusion of the two features using a context feature fusion network include: extracting original static features from the effective training data; the original static features include the rated power, voltage range, and environmental indicators of the smart power supply; using a statistical analysis algorithm to calculate the context features of the original static features in the effective training data to obtain a static feature context vector; using an Embedding layer in a deep learning model to process the original static features to obtain an original static feature vector; and combining the original static feature vector and the static feature context vector. Weighted splicing to obtain a fused static feature vector; extracting time series features from the effective training data through a time series analysis algorithm; the time series features include historical data of voltage and current; processing the time series features using the LSTM layer in the deep learning model to obtain a time series feature vector; calculating the context features of the time series features in the effective training data using a statistical analysis algorithm to obtain a time series feature context vector; weighted splicing of the time series feature vector and the time series feature context vector to obtain a fused time series feature vector; weighted splicing and fusion of the fused static feature vector and the fused time series feature vector to obtain a fused feature vector.

[0012] In some embodiments, the working state of the power supply is dynamically adjusted according to the predicted results of voltage fluctuations through an adaptive control strategy, including: judging the change of the voltage wave bottom according to the predicted results of voltage fluctuations to automatically adjust the output voltage and current of the power module; the automatic adjustment includes adjusting the output current and voltage of the inverter in the power module, and controlling the charging and discharging process of the energy storage system of the power module.

[0013] In a second aspect, the present invention provides a voltage-based intelligent power supply adjustment system, comprising: a data acquisition module: used to obtain relevant data of voltage fluctuations; a prediction model training module: used to use the relevant data of voltage fluctuations to train a voltage fluctuation prediction model to analyze the pattern and trend of voltage fluctuations; a real-time prediction module: used to use the voltage fluctuation prediction model to input real-time monitoring data to obtain the prediction result of voltage fluctuations; a power supply adjustment module: used to dynamically adjust the working state of the power supply through an adaptive control strategy according to the prediction result of voltage fluctuations; wherein the adaptive control strategy includes automatically adjusting the output voltage and current of the power supply module through an energy storage and release system according to the change of the voltage wave bottom; storing energy when the voltage wave bottom is lower than the set threshold of the reference voltage, and releasing energy when the voltage wave bottom is higher than the set threshold of the reference voltage, so as to smooth the voltage fluctuations.

[0014] In a second aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the voltage-based intelligent power supply adjustment method as described in any one of the embodiments described in the first aspect is implemented.

[0015] Through a voltage-based intelligent voltage adjustment method as provided above, the embodiment of the present invention can ensure the accuracy of intelligent power supply adjustment by preprocessing and analyzing the acquired voltage fluctuation related data. By adding an attention mechanism before or after each layer of the long short-term memory network to weight the input features, and then using these weights to construct a context vector, the feature weights of different time steps are dynamically adjusted. This mechanism enables the model to focus on key information more flexibly and improve the accuracy of prediction. According to the input multidimensional feature vector, the long-term and short-term dependencies in the time series data are captured to obtain the voltage fluctuation prediction results. Through training, the model can learn the patterns and trends of voltage fluctuations, improve the accuracy and response speed of voltage bottom prediction, and thus dynamically adjust the working state of the power supply to adapt to voltage fluctuations.

[0016] Furthermore, in some embodiments, by real-time monitoring and prediction of the voltage bottom, the power module can be adaptively adjusted to improve the stability and efficiency of the power system. By integrating the energy storage and release system, energy storage and release can be achieved, voltage fluctuations can be effectively smoothed, and the reliability of the power system can be improved.

[0017] Therefore, the voltage-based intelligent voltage adjustment method provided by the present invention can accurately monitor the real-time changes of voltage, quickly analyze the causes and trends of voltage instability, and take effective adjustment measures in time to ensure that the power output is always stable within a safe and reliable range. This ensures the stable operation of various power systems in the field of modern power applications, avoids many risks and losses caused by power problems, and provides a solid power guarantee foundation for scientific and technological progress and social development. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0019] Figure 1 An exemplary flow chart of a voltage-based intelligent voltage adjustment method according to an embodiment of the present invention is shown;

[0020] Figure 2 An exemplary structural block diagram of a voltage-based intelligent voltage adjustment system according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present invention indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or their collections. It should also be further understood that the terms "and / or" used in the specification and claims of the present invention refer to any combination of one or more of the associated listed items and all possible combinations, and include these combinations.

[0023] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0024] Figure 1 FIG. 1 shows an exemplary flow chart of a voltage-based intelligent voltage adjustment method 100 according to an embodiment of the present invention.

[0025] like Figure 1 As shown, in step S101 of method 100: obtain data related to voltage fluctuation. The data collected for voltage fluctuation mainly includes: 1) historical data, which is achieved by collecting past voltage fluctuation data, including input / output voltage, current, temperature, etc. 2) real-time monitoring data: real-time monitoring of current voltage, current, temperature and other data through sensors.

[0026] In one embodiment, the voltage fluctuation related data includes: historical data and real-time monitoring data including at least one of the following characteristics: input voltage, output voltage, current, temperature, and load.

[0027] By collecting historical data and real-time monitoring data, including input / output voltage, current, temperature, load changes, etc., this is the basis for predicting voltage fluctuations. Through these data, the current status and historical performance of the power module can be analyzed to provide training data for subsequent prediction models.

[0028] Further, in step S102: using the voltage fluctuation related data, a voltage fluctuation prediction model is trained to analyze the pattern and trend of the voltage fluctuation.

[0029] In one embodiment, the voltage fluctuation prediction model is trained using the voltage fluctuation related data to analyze the pattern and trend of the voltage fluctuation, including the following data preparation stages:

[0030] First, data cleaning is performed. Missing or abnormal data in the voltage fluctuation related data is processed, and abnormal values ​​and missing values ​​in historical data and real-time monitoring data are removed to obtain original training data. Features that are helpful for prediction are extracted from the original data, such as statistical features such as the mean, standard deviation, maximum and minimum values ​​of the voltage.

[0031] Secondly, feature selection is performed to select some features that affect the prediction results. Based on the selected features and correlations, the feature data in the original training data are transformed or combined to generate effective training data containing the transformed or combined new features, wherein the new features include frequency features extracted using Fourier transform. If the number of features is too large, methods such as principal component analysis (PCA) can be used for dimensionality reduction to reduce the complexity of the model.

[0032] Then, the effective training data is normalized to eliminate the dimension difference between different features. By normalizing the features, they have the same dimension, which is convenient for model processing.

[0033] Finally, according to the correlation between different features in the effective training data and the voltage fluctuation, feature fusion is performed to obtain fused features, and the fused features whose influence coefficient on the prediction result exceeds a threshold are added to the effective training data; wherein, according to the correlation between different features in the effective training data and the voltage fluctuation, feature fusion includes: extracting static features and time series features in the effective training data, and fusing the two features using a context feature fusion network.

[0034] Specifically, in one embodiment, extracting static features and temporal features from the effective training data and fusing the two features using a context feature fusion network includes:

[0035] Extract original static features from the valid training data; the original static features are features that do not change over time, including, for example, the rated power, voltage range, environmental indicators, etc. of the power module. These features can be converted into continuous vector representations through the Embedding layer.

[0036] The context features of the original static features in the valid training data are calculated using a statistical analysis algorithm to obtain a static feature context vector. In non-image data, global context features generally refer to features that can provide overall environmental or background information. For static features, global context features may refer to global statistical information related to the static features, or their relationship with other static features.

[0037] The original static features are processed by the Embedding layer in the deep learning model to obtain the original static feature vector. The original static feature vector and the static feature context vector are then weighted concatenated to obtain a fused static feature vector. Concatenation is to connect two feature vectors on the same dimension. By analyzing the relationship between static features, or calculating the statistical features of static features in the entire data set, and concatenating this information with the static feature vector output by the Embedding layer.

[0038] For the static eigenvector, let S be the static eigenvector, G S is the global context feature vector of the static feature, and the weighted concatenation operation can be expressed as:

[0039] Fusion static feature vector F S =αS+βG S +λ SG S⊙G s , where α, β are learnable weight coefficients that can be optimized through the training process. SG is the weight of the interaction term between the static feature vector and the context feature vector, which can also be optimized through the training process. ⊙ represents the element-wise product of the vectors (Hadamard product).

[0040] Compared with extracting static features, time series features can be extracted from the effective training data through a time series analysis algorithm. The time series features refer to features that change over time, including historical data of voltage and current, etc. These features can be processed through an LSTM layer to extract long-term dependencies in time series data.

[0041] The time series features are processed using the LSTM layer in the deep learning model to obtain a time series feature vector.

[0042] Utilizing a statistical analysis algorithm, context features of the time series features in the effective training data are calculated to obtain a time series feature context vector.

[0043] The time series feature vector and the time series feature context vector are weightedly concatenated to obtain a fused time series feature vector. For time series data, the global context feature can be a statistical feature of the entire time series, such as the average value, standard deviation, maximum value, and minimum value.

[0044] For the time series feature vector, T is the time series feature vector obtained by processing the LSTM layer, G T is the global context feature vector of the time series feature, including the overall statistical features of the time series, etc. Weighted fusion can be performed using the following formula:

[0045] Fusion time series feature vector F T =γT+δG T +λ TG T⊙G T , where F T is the fused time series feature vector, which includes the time series features and their global context features. γ,δ are learnable weight coefficients that can be optimized through the training process. TG is the weight of the interaction term between the time series feature vector and the context feature vector.

[0046] Then, the fused static feature vector and the fused temporal feature vector are weightedly spliced ​​and fused to obtain a fused feature vector. The fused feature vector contains information of the fused static feature vector and the fused temporal feature vector, and can be specifically weighted fused by the following formula:

[0047] F=òF S +ζF T , where F is the final fusion feature vector, which is F S and F T ∈ and ζ are the weights of the fused static feature vector and the fused temporal feature vector, which are used to adjust the importance of the two in the final fused feature vector.

[0048] The final fused feature vector will at least include: the original static feature vector, the temporal feature vector, and the corresponding global context feature. In this way, the model can not only capture the information of static features and temporal features, but also understand the contextual relationship of these features in the entire data set.

[0049] The above algorithm provided by the present invention not only includes static features and time series features and their corresponding global context features, but also adds interaction terms between features, so that the model can capture the interaction between different features. Those skilled in the art can understand that the global context features provide additional information for the model, so that the information in the input data can be more fully utilized to improve the performance and prediction accuracy of the model.

[0050] In one embodiment, the step of training the voltage fluctuation prediction model may include:

[0051] First, the effective training data is divided into a training set, a validation set, and a test set. A new sequence feature data set is constructed using historical data. Given a data set with a total length of L, the data set is divided into a training set, a validation set, and a test set according to a certain ratio. When sampling the training set, first select the first sliding window at the head of the training set, with an input window time step of T and an output prediction time step of τ. Then slide the first window backward τ steps, select the second window, and so on, until the boundary of the divided training set and validation set is reached.

[0052] Secondly, the training set data is used to train a voltage fluctuation prediction model according to a time series prediction model to analyze the pattern and trend of voltage fluctuation.

[0053] In one embodiment, the time series prediction model includes: normalizing all input training set data to the range of [-1, 1]. The following formula can be used:

[0054]

[0055] Among them, x normalized is the normalized standard data, x min and x max are the minimum and maximum values ​​of the original data x, respectively.

[0056] According to the enlightenment of the embodiments provided by the present invention, those skilled in the art should understand that in some cases, linearly mapping data to the range of [-1,1] is not unique, and the normalized range needs to be adjusted according to the distribution of the data and the performance feedback of the model. For example, if the distribution of the data is mainly concentrated in the interval [0,1], it may be more appropriate to use [0,1] as the normalized range. Similarly, if the model is more sensitive to a specific range of values ​​during training, the normalization strategy can be adjusted to adapt to this sensitivity.

[0057] Further, a multi-layer long short-term memory network is constructed. The long short-term memory network includes at least one layer for capturing short-term dependencies and one layer for capturing long-term dependencies. An additional attention mechanism is included before or after each layer of the long short-term memory network to weight the input features and dynamically adjust the attention weights of different time steps according to the current input and context vector.

[0058] Specifically, in one embodiment scenario of building a multi-layer long short-term memory network, in order to increase the multiple factors and weights that reflect the influencing dependencies, in addition to considering characteristic factors such as voltage value, temperature, humidity and load changes, in order to more comprehensively reflect all influencing factors of voltage fluctuations, more relevant features can be added, such as time factors (such as time periods of the day), holiday information, or other environmental factors.

[0059] Assuming that time feature t (such as hours) and holiday flag Holiday are added as new features, the new feature vector can be expressed as: X t =[V t ,T t ,H t ,L t ,t,Holiday], where V t is the voltage, T t is the temperature, H t is the humidity, L t is the load change.

[0060] Through the above new feature vector X t , the long short-term memory network can capture the impact of different time periods and holidays on voltage fluctuations.

[0061] The input layer of the LSTM network receives the enhanced multidimensional feature vector X at time t t After that, specifically, the state formula at the first layer is:

[0062] f t =σ(W f ·[h t-1 ,x t ]+b f ),i t =σ(W i ·[h t-1 ,x t ]+b i ), o t =σ(W o ·[h t-1 ,x t ]+b o ), h t =o t *tanh(C t ),

[0063] Among them, f t is the activation vector of the forget gate at time t to determine the information to be retained or forgotten in the cell state; i tis the activation vector of the input gate at time t to determine the information stored in the cell state; is the candidate value of the cell state at time t, used to update the cell state; C t is the cell state at time t, which is used to store the information in the sequence and pass it to the next time step; o t is the activation vector of the output gate at time t, which is used to determine the amount of information in the cell state that is output to the hidden state; h t is the hidden state at time t, based on the output gate o t and cell status C t The weighted sum of is used as the input or output of the output layer for the next time step.

[0064] W f ,W i ,W C ,W o : They are the weight matrices of the forget gate, input gate, unit state, and output gate, respectively, which are used to respond to the input and the previous hidden state. Assume that the input multidimensional feature vector X t If it is 6-dimensional, the weight matrix is ​​a 6*128 matrix, where 128 is the number of LSTM units.

[0065] b f ,b i ,b C ,b o : They are the bias vectors of the forget gate, input gate, unit state, and output gate, respectively, providing a baseline value for the calculation of the corresponding gate.

[0066] σ is the activation function used for the forget gate, input gate, and output gate. Its output range is between 0 and 1, indicating the degree of the gate opening. Tanh is the hyperbolic tangent activation function used for candidate memory units. Its output range is between -1 and 1, indicating the strength of the new information. t-1 ,x t ] is the hidden state h of the previous time step t-1 and the input x at the current time step t * is an element-by-element multiplication operation used to calculate the update of the unit state. t-1 is the hidden state at time t-1, which contains the information of the previous time step. t-1 is the cell state at time t-1, which contains information from the previous time steps in the sequence.

[0067] Each of the above gates has its own weight matrix and bias vector. The parameters can be learned through the training process to adapt to the specific data and task. The size of the weight matrix depends on the dimension of the input and the number of units in the hidden layer.

[0068] In order to allow the model to automatically learn which features are more important at the current time step during training, the input features can be weighted by adding an attention mechanism. This allows the model to not only rely on a fixed hidden state at each step, but also adaptively adjust the attention weights for different time steps based on the current input and previous context, so that the model can automatically learn which features are more important at the current time step during training.

[0069] Specifically, the attention weight α t It is calculated through an additional fully connected layer, and its formula can be expressed as:

[0070] α t =softmax(W a ·[h t ;h t-1 ;...;h 1 ]+b a ),

[0071] Among them, W a is the weight matrix of the attention layer, b a is the bias vector. The vector α t Each element of corresponds to the weight of the hidden state at the previous time step.

[0072] Through the description of the above embodiments, those skilled in the art can understand that the output h of the LSTM layer t Afterwards, an attention vector α can be introduced t , weighting the hidden state so that the model can focus on important information at different time steps. Further, through the attention weight α t and the hidden state h t , construct a context vector c t , which contains the historical information that the model considers important at the current time step.

[0073] Specifically, in one embodiment, assuming that an attention layer is added after the second LSTM layer, the specific steps are as follows:

[0074] Calculate attention weight: α t =softmax(W a ·[h t (2) ,x t ]+b a ),in, is the hidden state of the second layer of LSTM.

[0075] Then, the formula for constructing the context vector includes:

[0076]

[0077] Among them, the context vector c t is the weighted sum of all previous hidden states, with weights determined by α t Decide.

[0078] Further, the context vector is combined with the current hidden state: c t Directly as input for subsequent processing, or with After splicing, it is used as the new input:

[0079]

[0080] Finally, the weighted feature vector can be It can be passed to the third LSTM layer, or used directly in the output layer for prediction.

[0081] By introducing an additional fully connected layer to calculate the attention weights, and then using these weights to build the context vector, the feature weights at different time steps can be dynamically adjusted. This mechanism enables the model to focus on key information more flexibly and improve the accuracy of prediction.

[0082] Furthermore, in one embodiment, a Dropout layer may be added after the third LSTM layer, and the dropout rate may be preset to 0.2. The formula may include:

[0083]

[0084] Furthermore, in one embodiment, the output layer can output the prediction result through a fully connected layer. Formulas can include:

[0085]

[0086] Finally, the mean square error can be used as the loss function and the Adam optimizer can be used for model training. In addition, during the training process, early stopping can be used to prevent overfitting.

[0087] After training is completed, you can use the trained model to make predictions:

[0088] In one embodiment scenario, the long short-term memory network can be used to input a multidimensional feature vector X at time point t. t, the multidimensional feature vector contains at least one or more of the following features: voltage value, temperature, humidity, load change, time point (such as time, day / night, etc.), and other external factors (such as holidays). According to the input multidimensional feature vector, the long-term and short-term dependencies in the time series data are captured to obtain the voltage fluctuation prediction results. Through training, the model can learn the patterns and trends of voltage fluctuations, thereby predicting future voltage changes.

[0089] Then, the trained voltage fluctuation prediction model is further verified using the verification set data to obtain a verification result. According to the verification result, the voltage fluctuation prediction model can be adjusted to optimize the voltage fluctuation prediction model; the adjustment of the voltage fluctuation prediction model includes adjusting model parameters, feature combinations or model structures, etc.

[0090] Finally, the test set data is used to evaluate the prediction result indicators of the optimized voltage fluctuation prediction model to obtain an evaluation result.

[0091] Further, in step S103: using the voltage fluctuation prediction model, inputting real-time monitoring data to obtain a prediction result of voltage fluctuation;

[0092] By inputting real-time monitoring data into the trained voltage fluctuation prediction model, the voltage fluctuation prediction results can be obtained, which can provide decision support for the adaptive control strategy and is the prerequisite for dynamic adjustment.

[0093] Further, in step S104: according to the predicted result of the voltage fluctuation, the working state of the power supply is dynamically adjusted through an adaptive control strategy; wherein the adaptive control strategy includes automatically adjusting the output voltage and current of the power module through an energy storage and release system according to the change of the voltage wave bottom; storing energy when the voltage wave bottom is lower than the set threshold of the reference voltage, and releasing energy when the voltage wave bottom is higher than the set threshold of the reference voltage, so as to smooth the voltage fluctuation.

[0094] Dynamically adjust the working state of the power supply: Based on the voltage fluctuation prediction result obtained in step S103, dynamically adjust the working state of the power supply module through an adaptive control strategy. This step is the core of realizing intelligent power management, which enables the power supply module to adapt to voltage fluctuations and maintain stable output.

[0095] In one embodiment, dynamically adjusting the working state of the power supply through an adaptive control strategy according to the prediction result of the voltage fluctuation includes:

[0096] According to the predicted results of voltage fluctuations, the change of the voltage wave bottom is judged to automatically adjust the output voltage and current of the power module; the automatic adjustment includes adjusting the output current and voltage of the inverter in the power module, and controlling the charging and discharging process of the power module energy storage system.

[0097] The adaptive control strategy includes automatically adjusting the output voltage and current of the power module through the energy storage and release system according to the changes in the voltage wave bottom. This strategy can effectively smooth out voltage fluctuations and improve the stability and efficiency of the power system.

[0098] In one embodiment, first, one or more reference voltage levels are set, which are based on the standard operating voltage and historical voltage data of the power grid. The reference voltage level can be the average voltage of the power grid or a voltage range defined by the power system operator. Then, by monitoring the voltage level of the power grid in real time, the voltage fluctuation can be captured. These data can be used to determine whether the current voltage is at the bottom of the wave. The voltage level monitored in real time is compared with the reference voltage. If the real-time voltage is lower than a certain threshold of the reference voltage, it can be considered that the voltage bottom is low; if it is higher than another threshold, it is considered that the voltage bottom is high.

[0099] The threshold of the reference voltage is set dynamically based on the power grid conditions and historical data. For example, during peak power consumption periods, the reference voltage may be different and needs to be determined based on specific grid conditions and safety standards. In this way, the energy storage and release of the power supply can be effectively managed to respond to voltage fluctuations and ensure the stability and reliability of the power output.

[0100] Furthermore, in some embodiments, a fault analysis model is also included. By using the voltage prediction model to input real-time monitoring data, in addition to obtaining voltage fluctuation prediction results, the fault cause and location of the power module are obtained through the fault analysis model, thereby improving the reliability and maintenance efficiency of the intelligent power supply.

[0101] In summary, by real-time monitoring of grid voltage and load changes, the necessary input data is provided to the power module. The constructed voltage prediction model is used to predict the trend and pattern of voltage fluctuations, so that the output voltage and current of the power module can be dynamically adjusted according to the predicted results of voltage fluctuations to maintain stable power output. Then, by maintaining a stable voltage output, the adverse effects on connected devices are reduced and the service life of the equipment is extended.

[0102] Figure 2 FIG. 2 shows an exemplary structural block diagram of a voltage-based intelligent voltage adjustment system 200 according to an embodiment of the present invention.

[0103] like Figure 2As shown, a voltage-based intelligent power adjustment system is provided in system 200, including:

[0104] Data acquisition module 201: used to obtain voltage fluctuation related data.

[0105] The prediction model training module 202 is used to train a voltage fluctuation prediction model using the voltage fluctuation related data to analyze the pattern and trend of the voltage fluctuation.

[0106] The real-time prediction module 203 is used to utilize the voltage fluctuation prediction model and input the real-time monitoring data to obtain the prediction result of the voltage fluctuation.

[0107] Power supply adjustment module 204: used to dynamically adjust the working state of the power supply through an adaptive control strategy according to the predicted results of voltage fluctuations; wherein the adaptive control strategy includes automatically adjusting the output voltage and current of the power supply module through an energy storage and release system according to the changes in the voltage wave bottom; storing energy when the voltage wave bottom is lower than the set threshold of the reference voltage, and releasing energy when the voltage wave bottom is higher than the set threshold of the reference voltage, so as to smooth the voltage fluctuations.

[0108] It can be understood that the system 200 is a specific implementation of the method 100, so the above text is combined with Figure 1 The features described can analogously apply here.

[0109] Based on the above, the present invention further discloses a computer-readable storage medium, which contains computer program instructions storing a voltage-based intelligent power supply adjustment method. When the computer program instructions are executed by a processor, the method described in the above multiple embodiments or implementation methods is implemented.

[0110] In some implementation scenarios, the computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium. Any such computer storage medium may be part of a device or apparatus, or may be accessible or connectable to a device or apparatus. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0111] In summary, the embodiment scheme provided by the present invention trains a voltage fluctuation prediction model by combining historical data and real-time monitoring data (input / output voltage, current, temperature, etc.) to analyze the mode and trend of voltage fluctuation. This multi-feature factor analysis method can provide a more comprehensive and accurate voltage fluctuation prediction, which can better adapt to the complex and changeable power grid environment compared to the traditional single-feature prediction model. In addition, the scheme of the present invention not only considers the change of the voltage wave bottom through the designed adaptive control strategy according to the prediction result of voltage fluctuation, but also automatically adjusts the output voltage and current of the power module through the energy storage and release system. This integrated solution can more effectively smooth voltage fluctuations and improve the stability and efficiency of the power supply system. Therefore, through the real-time monitoring and adjustment of the power supply operation state of the present invention, more stable and reliable digital intelligent power management can be achieved. And through the integration of adaptive control strategy and energy storage and release system, it is also possible to achieve high power density and miniaturization of power modules based on high frequency, magnetic integration, packaging, modularization and other technologies, and improve the packaging technology of power modules.

[0112] Although multiple embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art may conceive of many changes, modifications, and alternatives without departing from the thought and spirit of the present invention. It should be understood that in the process of practicing the present invention, various alternatives to the embodiments of the present invention described herein may be adopted. The appended claims are intended to define the scope of protection of the present invention, and therefore cover equivalents or alternatives within the scope of these claims.

Claims

1. A voltage-based intelligent power supply adjustment method, characterized in that: include: Obtain data related to voltage fluctuations; Using the voltage fluctuation related data, training a voltage fluctuation prediction model to analyze the pattern and trend of voltage fluctuation; Using the voltage fluctuation prediction model, inputting real-time monitoring data to obtain a prediction result of voltage fluctuation; According to the predicted result of the voltage fluctuation, the working state of the power supply is dynamically adjusted through an adaptive control strategy; wherein the adaptive control strategy includes automatically adjusting the output voltage and current of the power module through an energy storage and release system according to the change of the voltage wave bottom; storing energy when the voltage wave bottom is lower than the set threshold of the reference voltage, and releasing energy when the voltage wave bottom is higher than the set threshold of the reference voltage, so as to smooth the voltage fluctuation.

2. The intelligent power supply adjustment method according to claim 1, characterized in that: The voltage fluctuation related data include: historical data and real-time monitoring data including at least one of the following characteristics: input voltage, output voltage, current, temperature, and load.

3. The intelligent power supply adjustment method according to claim 1, characterized in that: Using the relevant data of voltage fluctuation, the voltage fluctuation prediction model is trained to analyze the pattern and trend of voltage fluctuation, including the following data preparation stages: Processing missing or abnormal data in the voltage fluctuation related data to obtain original training data; Transform or combine the feature data in the original training data to generate effective training data containing the transformed or combined new features, wherein the new features include frequency features extracted using Fourier transform; Normalizing the effective training data to eliminate dimensional differences between different features; According to the correlation between different features in the effective training data and the voltage fluctuation, feature fusion is performed to obtain fused features, and the fused features whose influence coefficient on the prediction result exceeds a threshold are added to the effective training data; wherein, according to the correlation between different features in the effective training data and the voltage fluctuation, feature fusion includes: extracting static features and time series features in the effective training data, and fusing the two features using a context feature fusion network.

4. The intelligent power supply adjustment method according to claim 3, characterized in that: The step of extracting static features and temporal features from the effective training data and fusing the two features using a context feature fusion network includes: Extracting original static features from the valid training data; the original static features include the rated power, voltage range, and environmental indicators of the smart power supply; Calculate the context features of the original static features in the valid training data using a statistical analysis algorithm to obtain a static feature context vector; Processing the original static features using an Embedding layer in a deep learning model to obtain an original static feature vector; Performing weighted concatenation of the original static feature vector and the static feature context vector to obtain a fused static feature vector; Extracting time series features from the effective training data by using a time series analysis algorithm; the time series features include historical data of voltage and current; Processing the time series features using the LSTM layer in the deep learning model to obtain a time series feature vector; Calculate the context features of the time series features in the valid training data using a statistical analysis algorithm to obtain a time series feature context vector; Performing weighted concatenation of the temporal feature vector and the temporal feature context vector to obtain a fused temporal feature vector; The fused static feature vector and the fused temporal feature vector are weightedly concatenated and fused to obtain a fused feature vector.

5. The intelligent power supply adjustment method according to claim 3, characterized in that: The training voltage fluctuation prediction model comprises: Dividing the effective training data into a training set, a validation set and a test set; Using the training set data, according to the time series prediction model, a voltage fluctuation prediction model is trained to analyze the pattern and trend of voltage fluctuation; Using the validation set data to validate the trained voltage fluctuation prediction model to obtain a validation result; According to the verification result, the voltage fluctuation prediction model is adjusted to optimize the voltage fluctuation prediction model; the adjustment of the voltage fluctuation prediction model includes adjusting model parameters, feature combinations or model structures; The test set data is used to evaluate the prediction result index of the optimized voltage fluctuation prediction model to obtain an evaluation result.

6. The intelligent power supply adjustment method according to claim 5, characterized in that: The time series prediction model includes: Normalize all input training set data to the range of [-1, 1]; Constructing a multi-layer long short-term memory network, the long short-term memory network includes at least one layer for capturing short-term dependencies and one layer for capturing long-term dependencies; wherein an additional attention mechanism is included before or after each layer of the long short-term memory network to weight the input features and dynamically adjust the attention weights at different time steps according to the current input and context vector; Using the long short-term memory network, a multidimensional feature vector is input at a time point t, wherein the multidimensional feature vector includes at least one or more of the following features: voltage value, temperature, humidity, and load change; According to the multi-dimensional feature vector, the long-term and short-term dependencies in the time series data are captured to obtain the voltage fluctuation prediction result.

7. The intelligent power supply adjustment method according to claim 1, characterized in that: The method of dynamically adjusting the working state of the power supply through an adaptive control strategy according to the prediction result of the voltage fluctuation includes: According to the predicted results of voltage fluctuations, the change of the voltage wave bottom is judged to automatically adjust the output voltage and current of the power module; the automatic adjustment includes adjusting the output current and voltage of the inverter in the power module, and controlling the charging and discharging process of the power module energy storage system.

8. The intelligent power supply adjustment method according to claim 1, characterized in that: The setting threshold of the reference voltage is dynamically set according to the power grid conditions and historical data of the power source.

9. A voltage-based intelligent power adjustment system, characterized in that: include: Data acquisition module: used to obtain relevant data of voltage fluctuation; Prediction model training module: used to train a voltage fluctuation prediction model using the voltage fluctuation related data to analyze the pattern and trend of voltage fluctuation; Real-time prediction module: used to use the voltage fluctuation prediction model and input real-time monitoring data to obtain the prediction result of voltage fluctuation; Power supply adjustment module: used to dynamically adjust the working state of the power supply through an adaptive control strategy according to the predicted results of voltage fluctuations; wherein the adaptive control strategy includes automatically adjusting the output voltage and current of the power supply module through an energy storage and release system according to the changes in the voltage wave bottom; storing energy when the voltage wave bottom is lower than the set threshold of the reference voltage, and releasing energy when the voltage wave bottom is higher than the set threshold of the reference voltage, so as to smooth the voltage fluctuations.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the voltage-based intelligent power supply adjustment method according to any one of claims 1 to 8 is implemented.

Images