A distributed photovoltaic computer computing power control method and system

Abstract

The application relates to a distributed photovoltaic computer computing power control method and system, wherein the method comprises the following steps: acquiring photovoltaic power generation output power data and computer CPU computing power demand data, and performing pretreatment; establishing a photovoltaic power generation output power data and computer CPU computing power demand correlation model; constructing computer CPU utilization and computer CPU power consumption functions; according to the photovoltaic power generation output power data and computer CPU computing power demand correlation model and the computer CPU utilization and computer CPU power consumption functions, regulating and controlling computer CPU computing power; and according to photovoltaic power generation output power data, computer CPU power consumption and computer CPU resource utilization in the running process, optimizing the photovoltaic power generation output power data and computer CPU computing power demand correlation model. The application provides a distributed photovoltaic computer computing power control method and system, which can maximize the use of new energy and reduce the energy consumption of a computing system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer computing power regulation, and particularly relates to a computer computing power control method and system for distributed photovoltaics. BACKGROUND

[0002] With the transformation of global energy structure and the promotion of sustainable development goals, as well as the growth of energy demand and the emphasis on clean energy, the application prospect of photovoltaic power generation is wide, which can reduce the dependence on traditional fossil fuels and reduce greenhouse gas emissions. Distributed photovoltaics have been widely developed as a method of photovoltaic power generation. Distributed photovoltaic systems can generate electricity near the user end, reducing power transmission losses and other problems. However, distributed photovoltaic power generation devices have volatility and instability, which can greatly affect the stability of the power grid and the difficulty of scheduling.

[0003] In the prior art, a battery energy storage system is usually used for relay storage of electric energy, thereby reducing the volatility of the distributed photovoltaic power generation device. In addition, different types of photovoltaic components exhibit different performance characteristics under different light and temperature conditions. By combining multiple photovoltaic components, the entire photovoltaic power generation system can maintain relatively stable output under a wider range of environmental conditions.

[0004] However, in the above technical solution, the use of a battery energy storage system for relay storage of electric energy requires the construction and maintenance of a battery energy storage station, thereby increasing the cost of power generation. In addition, the use of different types of photovoltaic components requires special design according to different environments, thereby increasing the construction cost and design difficulty of the photovoltaic power generation system.

[0005] Therefore, it is necessary to improve one or more problems in the above related technical solutions.

[0006] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] The purpose of the embodiments of the present disclosure is to provide a computer computing power control method and system for distributed photovoltaics, thereby at least partially overcoming one or more problems caused by the limitations and defects of the related art.

[0008] In a first aspect, the present application provides a computer computing power control method for distributed photovoltaics, comprising:

[0009] Obtaining photovoltaic power generation output power data and computer CPU computing power demand data and preprocessing; the computer CPU computing power demand data includes computer CPU usage, task queue length and memory usage;

[0010] According to the processed photovoltaic power output data and the computer CPU computing power demand data, a photovoltaic power output data and computer CPU computing power demand correlation model is established;

[0011] The computer CPU usage rate and the computer CPU power consumption function are constructed;

[0012] According to the photovoltaic power output data and computer CPU computing power demand correlation model and the computer CPU usage rate and the computer CPU power consumption function, the computer CPU computing power is regulated;

[0013] According to the photovoltaic power output data, computer CPU computing power demand data and computer CPU power consumption during operation, the photovoltaic power output data and computer CPU computing power demand correlation model and the computer CPU usage rate and the computer CPU power consumption function are optimized.

[0014] In a possible implementation, the step of obtaining photovoltaic power output data and computer CPU computing power demand data and preprocessing includes:

[0015] The output voltage and output current are collected by the sensor arranged in the photovoltaic module to obtain the photovoltaic power output data;

[0016] The computer CPU computing power demand data is obtained by the computer task manager;

[0017] The photovoltaic power output data and the computer CPU computing power demand data are preprocessed to obtain a processed data set.

[0018] In a possible implementation, the step of preprocessing the photovoltaic power output data and the computer CPU computing power demand data to obtain a processed data set includes:

[0019] The missing values and abnormal values of the photovoltaic power output data and the computer CPU computing power demand data are processed;

[0020] The photovoltaic power output data and the computer CPU computing power demand data are fused to obtain a first data set;

[0021] The ratio of the photovoltaic power output data and the computer CPU usage rate is calculated to obtain a resource utilization rate, and a time feature is generated according to a timestamp to obtain a second data set;

[0022] The second data set is processed by a time series processing method to obtain a processed data set.

[0023] In a possible implementation, the step of establishing a photovoltaic power output data and computer CPU computing power demand correlation model according to the processed photovoltaic power output data and the computer CPU computing power demand data includes:

[0024] The processed photovoltaic power output data and the computer CPU computing power demand data are divided into a training set and a test set.

[0025] A three-layer long short-term memory network LSTM time series model is constructed, and the three-layer long short-term memory network LSTM time series model includes an input layer, an LSTM layer, and an output layer.

[0026] The three-layer long short-term memory network LSTM time series model is trained through the training set, and a trained three-layer long short-term memory network LSTM time series model is obtained.

[0027] The trained three-layer long short-term memory network LSTM time series model is tested and adjusted through the test set, and the photovoltaic power output data and computer CPU computing power demand correlation model is obtained.

[0028] In a possible implementation, the step of testing and adjusting the trained three-layer long short-term memory network LSTM time series model through the test set to obtain the photovoltaic power output data and computer CPU computing power demand correlation model includes:

[0029] The test set is input into the trained three-layer long short-term memory network LSTM time series model to obtain a prediction result.

[0030] The model performance of the trained three-layer long short-term memory network LSTM time series model is evaluated through an index mean square error.

[0031] When the model performance is normal, a photovoltaic power output data and computer CPU computing power demand correlation model is obtained.

[0032] When the model performance is abnormal, a photovoltaic power output data and computer CPU computing power demand correlation model is obtained by increasing the number of LSTM layers and introducing more features to increase the model input dimension.

[0033] In a possible implementation, the computer CPU usage rate and the computer CPU power consumption function are a first formula, and the first formula is:

[0034]

[0035] Wherein, P is the computer CPU power consumption, f is the computer CPU usage rate, P0 is the initial value of CPU power consumption.

[0036] In a possible implementation, the step of regulating the computer CPU computing power according to the photovoltaic power generation output power data and computer CPU computing power demand correlation model and the computer CPU usage rate and computer CPU power consumption function comprises:

[0037] According to the photovoltaic power generation output power data and computer CPU computing power demand correlation model, the computer CPU usage rate prediction value is obtained;

[0038] According to the computer CPU usage rate and the computer CPU power consumption function, the CPU usage rate target value is obtained;

[0039] The CPU usage rate prediction value is smoothly adjusted so that the CPU usage rate prediction value gradually approaches the CPU usage rate target value.

[0040] In a possible implementation, the step of optimizing the photovoltaic power generation output power data and computer CPU computing power demand correlation model and the computer CPU usage rate and computer CPU power consumption function according to the photovoltaic power generation output power data, computer CPU computing power demand data and computer CPU power consumption in the running process comprises:

[0041] The real-time computer CPU computing power demand data and photovoltaic power generation output power data are input into the photovoltaic power generation output power data and computer CPU computing power demand correlation model to continuously optimize the model;

[0042] The computer CPU usage rate and computer CPU power consumption function are continuously optimized through the real-time computer CPU usage rate and computer CPU power consumption.

[0043] In a possible implementation, the method for smoothly adjusting the computer CPU usage rate prediction value is to smoothly adjust the computer CPU usage rate through a PID controller, and the specific method is as follows:

[0044] PID input, the deviation between the current computer CPU power consumption and the target computer CPU power consumption is calculated through a second formula; wherein the second formula is Δe=P 目标 -P, Δe is the deviation, P 目标 is the target computer CPU power consumption, and P is the current computer CPU power consumption;

[0045] PID output, a computer CPU usage rate adjustment value is output by using a PID controller to adjust the current computer CPU usage rate to approach the target computer CPU usage rate.

[0046] In a second aspect, the present application provides a distributed photovoltaic computer computing power control system, which is used to execute the distributed photovoltaic computer computing power control method, and comprises:

[0047] A data processing module is configured to acquire photovoltaic power generation output power data and computer CPU computing power demand data, and perform preprocessing; the computer CPU computing power demand data comprises computer CPU usage rate, task queue length, and memory usage;

[0048] A model establishing module is configured to establish a photovoltaic power generation output power data and computer CPU computing power demand correlation model according to the processed photovoltaic power generation output power data and computer CPU computing power demand data;

[0049] A function establishing module is configured to construct the computer CPU usage rate and the computer CPU power consumption function;

[0050] A computing power regulation module is configured to regulate computer CPU computing power according to the photovoltaic power generation output power data and computer CPU computing power demand correlation model and the computer CPU usage rate and the computer CPU power consumption function;

[0051] A model optimization module is configured to optimize the photovoltaic power generation output power data and computer CPU computing power demand correlation model according to photovoltaic power generation output power data, computer CPU power consumption, and computer CPU resource usage in a running process.

[0052] The technical scheme provided by the present application can include the following beneficial effects:

[0053] Through the distributed photovoltaic computer computing power control method and system, the correlation model between photovoltaic power generation output power data and computer CPU computing power demand can be established, the functional relationship between CPU usage rate and power consumption can be constructed, the computer computing power allocation strategy can be adjusted according to real-time monitoring of photovoltaic power generation power and computer computing power demand and in combination with a prediction algorithm, and the CPU usage rate of the computer and the scheduling of computing tasks can be further dynamically adjusted, so as to maximize the use of new energy and reduce the energy consumption of the computing system.

[0054] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0055] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, further serve to explain the principles of the disclosure. It is to be understood that the drawings are designed solely for purposes of illustration to be used in conjunction with the description insofar as specifically described herein. Changes in design or structure can be made in the embodiments described herein, without departing from the spirit or scope of the present disclosure, which can be practiced or carried out in various ways.

[0056] Figure 1 A flow chart of the computer computing power control method of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown.

[0057] Figure 2 A detailed flow chart of step S100 of the computer computing power control method of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown.

[0058] Figure 3 A detailed flow chart of step S130 of the computer computing power control method of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown.

[0059] Figure 4 A detailed flow chart of step S200 of the computer computing power control method of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown.

[0060] Figure 5 A detailed flow chart of step S240 of the computer computing power control method of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown.

[0061] Figure 6 A detailed flow chart of step S400 of the computer computing power control method of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown.

[0062] Figure 7 A detailed flow chart of step S500 of the computer computing power control method of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown.

[0063] Figure 8 A LSTM mapping relationship diagram of photovoltaic power generation output power data and computer CPU computing power demand data in the computer computing power control method of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown.

[0064] Figure 9 A comparison diagram of the prior art method and the algorithm control computer computing power demand data of the present application in the computer computing power control method of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown.

[0065] Figure 10 A relationship diagram of computer CPU usage and computer CPU power consumption in the computer computing power control method of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown.

[0066] Figure 11A cluster analysis fitting diagram of computer CPU usage rate and computer CPU power consumption of a computer power control method of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown.

[0067] Figure 12 A structure diagram of a computer power control system of distributed photovoltaics in an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0068] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations can be implemented in any

[0069] In addition, the accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the present disclosure and serve to explain the principles of the present disclosure. The same reference numbers in different drawings represent the same or similar elements.

[0070] In the present example implementation, a computer power control method of distributed photovoltaics is first provided, which can be applied to a terminal device, such as a mobile terminal, e.g., a mobile phone, a desktop computer, a personal digital assistant, a notebook computer, a tablet computer, a smart watch, etc. Referring to FIG. 1, the method can include the following steps: Figure 1

[0071] Step S100: Obtain photovoltaic power generation output power data and computer CPU power demand data, and perform preprocessing; the computer CPU power demand data includes computer CPU usage rate, task queue length, and memory usage.

[0072] Step S200: According to the processed photovoltaic power generation output power data and computer CPU power demand data, establish a photovoltaic power generation output power data and computer CPU power demand correlation model.

[0073] Step S300: Construct the computer CPU usage rate and the computer CPU power consumption function.

[0074] ​Step S400: According to the photovoltaic power output power data and the computer CPU power demand association model and the computer CPU usage and the computer CPU power consumption function, the computer CPU power is regulated.

[0075] Step S500: According to the photovoltaic power output power data, the computer CPU power consumption and the computer CPU resource usage in the running process, the photovoltaic power output power data and the computer CPU power demand association model are optimized.

[0076] Through the above method, the photovoltaic power output power can be obtained through the sensor and the external interface, the real-time process of the computer power demand is obtained by using the computer task manager, the photovoltaic power output power and the computer power demand information are given to the central processor for data preprocessing, the association model between the distributed photovoltaic output and the computer CPU power demand is established, the function relationship of the CPU usage and the power consumption is constructed, the computer power is controlled according to the function relationship and the association model, and the CPU power consumption parameters and the computer CPU resource usage are monitored, and the actual situation is fed back to the association model for optimization.

[0077] In the following, the above-mentioned method in the present example embodiment will be described in more detail with reference to the accompanying drawings. Figures 1 to 7 The above-mentioned method in the present example embodiment will be described in more detail with reference to the accompanying drawings.

[0078] In step S100, photovoltaic power output power data and computer CPU power demand data are obtained and preprocessed; the computer CPU power demand data includes computer CPU usage, task queue length and memory usage.

[0079] Optionally, the photovoltaic power output power is obtained through the sensor and the peripheral interface, and the sensor is connected to the peripheral interface of the computer for data transmission.

[0080] It should be noted that the measurement of photovoltaic output power: the output voltage and the output current of the photovoltaic module are monitored to calculate. The output voltage is measured by the voltage sensor INA219 and the data is output through the I2C interface, the output current is measured by the Hall effect current sensor ACS712, the sensor converts the collected analog signal into digital signal through the analog converter ADC, and the processor reads it. The combination of the two can obtain the instantaneous power of the photovoltaic output, which can be expressed as:

[0081] P(t)=V(t)×I(t)

[0082] Where V(t) is the output voltage, I(t) is the output current, and P(t) is the instantaneous output power.

[0083] In one embodiment, step S100 can include the following sub-steps:

[0084] In step S110, the output voltage and output current are collected by the sensor arranged in the photovoltaic module to obtain the photovoltaic power generation output power data.

[0085] It should be noted that the collected power data is transmitted to the cloud server by wireless transmission and stored in the local database in real time for subsequent analysis and decision-making of the control algorithm.

[0086] Optionally, the sampling frequency of the collected data is set to be collected once every second, and the data read by the sensor after processing may have errors. The voltage and current data are calibrated, and the calibration formula is as follows:

[0087] V 校准 = V 测量 × K voitaged

[0088] I 校准 = I 测量 × K current

[0089] Wherein, K voitaged is the voltage calibration coefficient, and K current is the current calibration coefficient.

[0090] In step S120, the computer CPU computing power requirement data is obtained by the computer task manager.

[0091] It should be noted that in the Linux system, the psutil.cpu_percent() function is called to return the current CPU usage, the interval parameter is set to automatically collect the CPU usage every second; the psutil.virtual_memory() is called to obtain the system memory usage; the psutil.process_iter() is called to traverse all processes in the current system, and the PID, name, CPU usage and memory usage of each process are extracted. The collected computer computing power requirement data is stored in the database SQLite for subsequent analysis.

[0092] In step 130, the photovoltaic power generation output power data and the computer CPU computing power requirement data are preprocessed to obtain a processing data set.

[0093] It should be noted that the distributed photovoltaic output power data preprocessing in the data preprocessing includes data cleaning, feature selection and the like, and the preprocessing of the computer CPU computing power requirement data includes data standardization processing.

[0094] Further, step S130 can include the following sub-steps:

[0095] In step S131, missing values and abnormal values of the photovoltaic power generation output power data and the computer CPU computing power demand data are processed.

[0096] It should be noted that the transmission of data is performed by transmitting the photovoltaic output power stored on the remote server and the computer computing power demand data stored in the database to the central processor for processing using the requests library of Python. An interface is set in the central processor to obtain data from each data source. Step S131 is a data cleaning step, in which linear interpolation is used to process missing data points in the collection process, and box plot method is used to identify and process abnormal values within a reasonable range.

[0097] In step S132, the photovoltaic power generation output power data and the computer CPU computing power demand data are fused to obtain a first data set.

[0098] It can be understood that the photovoltaic output power and the CPU computing power data are fused by the data fusion method to generate a unified data structure containing all relevant information.

[0099] In step S133, the ratio of the photovoltaic power generation output power data and the computer CPU utilization rate is calculated to obtain the resource utilization rate, and the time feature is generated according to the time stamp to obtain a second data set.

[0100] It can be understood that the above method extracts data feature values and generates time features according to time stamps to perform periodic analysis.

[0101] In step S134, the second data set is processed by a lag term introduction method to obtain a processed data set.

[0102] It should be noted that the preprocessed data is stored in the central processor in the form of a CSV file in a standardized format and is transmitted to the upper algorithm for further processing and analysis; and the processed data is monitored and visualized using Matplotlib and Seaborn libraries.

[0103] In step S200, a photovoltaic power generation output power data and computer CPU computing power demand correlation model is established according to the processed photovoltaic power generation output power data and computer CPU computing power demand data.

[0104] It should be noted that, wherein the correlation model is constructed by using a time series model, including data collection, data preprocessing, model selection and training, and model application, data collection and data preprocessing are the method of step S100, after data preprocessing, data normalization is used Z-score standardization, the data is scaled to [0, 1], and the influence between different dimensions of photovoltaic power generation and computer power demand is eliminated.

[0105] In one embodiment, step S200 can include the following sub-steps:

[0106] In step S210, the processed photovoltaic power output data and the computer CPU power demand data are divided into training set and test set.

[0107] Exemplarily, the collected data is divided into training set and test set according to the ratio of 7:3; the data is adjusted to the three-dimensional structure of LSTM input, that is, [sample number, time step, feature number].

[0108] In step S220, a three-layer long short-term memory network LSTM time series model is constructed, which includes an input layer, an LSTM layer and an output layer.

[0109] Exemplarily, the Keras library of Python is used to construct the LSTM model, including an input layer, an LSTM layer and an output layer, wherein the first layer returns a sequence, the second layer does not return a sequence, and the output layer predicts the CPU power demand and the photovoltaic output power, the number of units of each LSTM layer is set to 50, the input dimension is determined as (60, 2) according to the number of features, the time step is set to 60, and the mapping relationship diagram is as shown in Figure 8 .

[0110] In step S230, the three-layer long short-term memory network LSTM time series model is trained by using the training set, and the trained three-layer long short-term memory network LSTM time series model is obtained.

[0111] Exemplarily, the LSTM model is trained by using the training set, and the iteration round is set to 100 and the batch size is set to 64; at the same time, the training loss and the validation loss are monitored during the training process to determine whether overfitting phenomenon occurs.

[0112] In step S240, the trained three-layer long short-term memory network LSTM time series model is tested and adjusted by using the test set, and the photovoltaic power output power data and computer CPU power demand correlation model are obtained.

[0113] It should be noted that, for example, the prediction is made by using the test set, the prediction result is normalized back to the original data range, the model performance is evaluated using the index mean square error (MSE), and finally the comparison between the predicted value and the true value is plotted to intuitively analyze the effect of the model. If the model performance is not ideal, the model input dimension can be increased by adjusting the parameters, increasing the number of LSTM layers, and introducing more features; after training, the model is saved and deployed to the production environment, and real-time photovoltaic power output data is input into the LSTM model to predict the CPU computing power demand and distributed photovoltaic output power in real time and adjust the CPU usage.

[0114] Further, step S240 can include the following sub-steps:

[0115] In step S241, the test set is input into the trained three-layer long short-term memory network LSTM time series model to obtain a prediction result.

[0116] In step S242, the model performance of the trained three-layer long short-term memory network LSTM time series model is evaluated by the index mean square error.

[0117] In step S243, when the model performance is normal, a photovoltaic power output power data and computer CPU computing power demand correlation model is obtained.

[0118] In step S244, when the model performance is abnormal, a photovoltaic power output power data and computer CPU computing power demand correlation model is obtained by increasing the number of LSTM layers and introducing more features to increase the model input dimension.

[0119] It should be noted that, as shown in Figure 9 The prediction of distributed photovoltaic output power by the LSTM model aims to better adjust the computer CPU computing power demand to achieve efficient use of energy, that is, to increase the computing load and improve the computing capacity when the photovoltaic power generation is sufficient, and to reduce the computing power demand and reduce energy waste when the photovoltaic power generation is insufficient. At the same time, by predicting photovoltaic power generation and computer demand in real time, dynamic scheduling and load management can be realized, computer resources can be reasonably allocated, and the overall performance and response speed of the system can be improved.

[0120] In step S300, the computer CPU usage rate and the computer CPU power consumption function are constructed.

[0121] It can be understood that the functional relationship between CPU usage rate and computer CPU power consumption is constructed, and the computer computing power demand is regulated according to the LSTM model and the functional relationship.

[0122] In one embodiment, as shown in Figures 10-11As shown, the computer CPU usage rate and the computer CPU power consumption function are a first formula; the first formula is:

[0123]

[0124] Wherein, P is the computer CPU power consumption, f is the computer CPU usage rate, P0 is the CPU power consumption initial value.

[0125] Further, the future photovoltaic output and computing power demand are predicted according to the LSTM model, and the power consumption control strategy is established combining the function relationship between CPU frequency and power consumption:

[0126] A power consumption target value based on photovoltaic output is set to ensure that the photovoltaic output matches the power consumption demand. In actual operation, the CPU power consumption is monitored in real time, the actual power consumption is compared with the target power consumption value, and the frequency f is inversely solved by using the function relationship between CPU frequency and power consumption, so that the power consumption is close to the target power consumption. The frequency formula can be expressed as:

[0127]

[0128] Wherein, P target must be greater than P0 to be solved, and the solved f target is the CPU frequency to meet the target power consumption.

[0129] In step S400, the computer CPU computing power is regulated according to the photovoltaic power generation output power data and computer CPU computing power demand correlation model and the computer CPU usage rate and computer CPU power consumption function.

[0130] In one embodiment, step S400 can include the following sub-steps:

[0131] In step S410, the computer CPU usage rate prediction value is obtained according to the photovoltaic power generation output power data and computer CPU computing power demand correlation model.

[0132] In step S420, the CPU usage rate target value is obtained according to the computer CPU usage rate and the computer CPU power consumption function.

[0133] In step S430, the CPU usage rate prediction value is smoothly adjusted so that the CPU usage rate prediction value gradually approaches the CPU usage rate target value.

[0134] For example, the CPU usage rate adjustment may cause system instability due to direct jump of CPU usage rate. The PID controller is used to smoothly adjust the CPU usage rate so that it gradually approaches f target . The adjustment method is as follows:

[0135] PID input: calculate the deviation of current computer CPU power consumption P and P target target P;

[0136] PID output: use the PID controller to output a CPU usage adjustment value Af to adjust the current CPU usage to the target CPU usage.

[0137] It should be noted that the power consumption control strategy uses a trained LSTM time series model, inputs the current photovoltaic power output and CPU computing power demand data, and the model outputs the prediction of future computing power demand. Based on the prediction results of the correlation model, combined with the CPU frequency and power consumption function relationship, the CPU frequency and computing task priority of the system are dynamically adjusted according to the photovoltaic output and the computing power demand of the computer.

[0138] When the system runs multiple tasks, the computer tasks are prioritized, and the computer task priority is set by the task manager to divide the computer tasks into high, medium and low priority tasks. Among them, the high priority task represents the key task, which must be run, even if the photovoltaic power is low, it must be run; the medium priority task represents the normal task, which is run when the power is sufficient; the low priority task represents the non-key task, which is executed when the power is sufficient; the present application adopts a multi-level feedback queue scheduling algorithm combined with task priority scheduling;

[0139] High priority task guarantee: when the photovoltaic output is insufficient, the high priority CPU usage is guaranteed first, and the low priority CPU usage is reduced.

[0140] Low priority task absorbs photovoltaic: when the photovoltaic output is high, the low priority CPU usage is increased to achieve higher power consumption, thereby better absorbing photovoltaic energy.

[0141] In step S500, according to the photovoltaic power output data, computer CPU computing power demand data and computer CPU power consumption in the running process, the photovoltaic power output data and computer CPU computing power demand correlation model are optimized with the computer CPU usage and the computer CPU power consumption function.

[0142] In one embodiment, step S500 can include the following sub-steps:

[0143] In step S510, the real-time computer CPU computing power demand data and photovoltaic power output data are input into the photovoltaic power output data and computer CPU computing power demand correlation model, and the model is continuously optimized.

[0144] ​It can be understood that during the regulation process, the distributed photovoltaic output and the running state of the computer system are continuously monitored, and the actual running result is fed back to the correlation model; according to the feedback information, the correlation model is optimized and adjusted to improve the accuracy and effectiveness of the regulation.

[0145] In step S520, the computer CPU usage rate and the computer CPU power consumption function are continuously optimized by the real-time computer CPU usage rate and the computer CPU power consumption.

[0146] It should be noted that the dynamic feedback control establishes a feedback closed loop, continuously monitors the actual power consumption and dynamically adjusts the frequency according to the deviation:

[0147] Power consumption feedback: the actual power consumption P of the system is obtained in real time, and compared with P 目标 ;

[0148] Frequency fine-tuning: fine-tune the frequency according to the power consumption deviation in f 目标 Nearby, ensure that the system is always close to the target power consumption.

[0149] Further, in the example embodiment, a computer power control system for distributed photovoltaic is also provided. Referring to Figure 12 , the system can include:

[0150] A data processing module is configured to obtain photovoltaic power generation output power data and computer CPU power demand data, and to preprocess the data; the computer CPU power demand data includes computer CPU usage rate, task queue length and memory usage;

[0151] A model establishing module is configured to establish a photovoltaic power generation output power data and computer CPU power demand correlation model according to the processed photovoltaic power generation output power data and computer CPU power demand data;

[0152] A function establishing module is configured to construct the computer CPU usage rate and the computer CPU power consumption function;

[0153] A power regulation module is configured to regulate computer CPU power according to the photovoltaic power generation output power data and computer CPU power demand correlation model and the computer CPU usage rate and the computer CPU power consumption function;

[0154] A model optimization module is configured to optimize the photovoltaic power generation output power data and computer CPU power demand correlation model according to the photovoltaic power generation output power data, computer CPU power consumption and computer CPU resource usage during operation.

[0155] As to the apparatus in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and thus will not be described in detail here.

[0156] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, such division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into several modules or units for embodiment. The components shown as modules or units can or can not be physical units, i.e., can be located in one place or can be distributed on multiple network units. Some or all of the modules can be selected to achieve the purpose of the present disclosure according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0157] In an exemplary embodiment of the present disclosure, an electronic device is also provided, which can include a processor, and a memory for storing executable instructions of the processor. Wherein the processor is configured to perform the steps of the computer power control method of distributed photovoltaics in any one of the above embodiments via execution of the executable instructions.

[0158] Those skilled in the art can understand that each aspect of the present disclosure can be implemented as a system, a method or a program product. Therefore, each aspect of the present disclosure can be embodied in a form of entirely hardware, entirely software (including firmware, microcode, etc.), or a combination of hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system" herein.

[0159] From the above description of the embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to make a computing device (which can be a personal computer, a server, or a network device, etc.) execute the above-mentioned computer power control method of distributed photovoltaics according to the embodiments of the present disclosure.

[0160] In an exemplary embodiment of the present disclosure, a computer storage medium is also provided, which stores a computer program that, when executed by a processor, can implement the steps of the computer power control method of distributed photovoltaics in any one of the above embodiments.

[0161] In some possible implementation manners, each aspect of the present application can also be implemented in the form of a computer program product, which includes computer programs or instructions, when the computer program product runs on a terminal device, the computer program code or instructions are used to make the terminal device execute the steps described in the above computer algorithm control method part of distributed photovoltaic according to various exemplary embodiments of the present application.

[0162] The program product described above can be written in any combination of one or more programming languages to perform the operations of the present application, including object-oriented programming languages such as Java, C++, and conventional procedural programming languages such as "C" programming language or similar programming languages. Program code can be executed entirely on a user computing device, partially on a user device, as an independent software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case involving a remote computing device, the remote computing device can be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, connected through the Internet by using an Internet service provider).

[0163] The computer software product can be stored in a computer storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disk storage, magnetic disk storage, magnetic tape storage, or any other medium that can be used to carry or store data readable by a computer.

[0164] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A computer power control method for distributed photovoltaics, characterized in that, The method comprises the following steps: Obtain photovoltaic power output power data and computer CPU computing power requirement data, and preprocess the data; the computer CPU computing power requirement data includes computer CPU usage rate, task queue length, and memory usage; According to the processed photovoltaic power output power data and computer CPU computing power requirement data, establish a photovoltaic power output power data and computer CPU computing power requirement correlation model, which comprises the following steps: divide the processed photovoltaic power output power data and computer CPU computing power requirement data into a training set and a test set; construct a three-layer long short-term memory network (LSTM) time series model, which comprises an input layer, an LSTM layer, and an output layer; train the three-layer long short-term memory network (LSTM) time series model through the training set to obtain a trained three-layer long short-term memory network (LSTM) time series model; test and adjust the trained three-layer long short-term memory network (LSTM) time series model through the test set to obtain the photovoltaic power output power data and computer CPU computing power requirement correlation model; Construct the computer CPU usage rate and computer CPU power consumption function, which comprises the following steps: acquire output voltage and output current through sensors arranged in photovoltaic modules to obtain the photovoltaic power output power data; acquire computer CPU computing power requirement data through a computer task manager; preprocess the photovoltaic power output power data and computer CPU computing power requirement data to obtain a processed data set, which comprises the following steps: process missing values and abnormal values of the photovoltaic power output power data and computer CPU computing power requirement data; fuse the photovoltaic power output power data and computer CPU computing power requirement data to obtain a first data set; calculate the ratio of the photovoltaic power output power data to the computer CPU usage rate to obtain resource utilization rate, and generate time features according to timestamps to obtain a second data set; process the second data set through a lag term introduction method to obtain a processed data set; According to the photovoltaic power output power data and computer CPU computing power requirement correlation model and the computer CPU usage rate and computer CPU power consumption function, regulate and control computer CPU computing power, which comprises the following steps: obtain computer CPU usage rate prediction values according to the photovoltaic power output power data and computer CPU computing power requirement correlation model; obtain CPU usage rate target values according to the computer CPU usage rate and computer CPU power consumption function; smoothly adjust the CPU usage rate prediction values so that the CPU usage rate prediction values gradually approach the CPU usage rate target values; According to photovoltaic power output power data, computer CPU computing power requirement data, and computer CPU power consumption during operation, optimize the photovoltaic power output power data and computer CPU computing power requirement correlation model and the computer CPU usage rate and computer CPU power consumption function.

2. The computer computing power control method of distributed photovoltaics according to claim 1, characterized in that, The step of testing and adjusting the trained three-layer long short-term memory network LSTM time series model through the test set to obtain the photovoltaic power generation output power data and computer CPU computing power demand association model comprises: Input the test set into the trained three-layer long short-term memory network LSTM time series model to obtain a prediction result; Evaluate the model performance of the trained three-layer long short-term memory network LSTM time series model through an index mean square error; When the model performance is normal, obtain a photovoltaic power generation output power data and computer CPU computing power demand association model; When the model performance is abnormal, increase the number of LSTM layers and introduce more features to increase the input dimension of the model to obtain a photovoltaic power generation output power data and computer CPU computing power demand association model.

3. The computer computing power control method of distributed photovoltaics according to claim 1, characterized in that, The computer CPU usage rate and the computer CPU power consumption function are a first formula; the first formula is: wherein, is the computer CPU power consumption, is the computer CPU usage, is the CPU power consumption initial value.

4. The computer computing power control method of distributed photovoltaics according to claim 1, characterized in that, The step of optimizing the photovoltaic power generation output power data and computer CPU computing power demand association model and the computer CPU usage rate and the computer CPU power consumption function according to the photovoltaic power generation output power data, computer CPU computing power demand data and computer CPU power consumption during the running process comprises: Input real-time computer CPU computing power demand data and photovoltaic power generation output power data into the photovoltaic power generation output power data and computer CPU computing power demand association model to continuously optimize the model; Continuously optimize the computer CPU usage rate and the computer CPU power consumption function through real-time computer CPU usage rate and computer CPU power consumption.

5. The computer computing power control method of distributed photovoltaic according to claim 1, characterized in that, The method for smoothly adjusting the computer CPU usage rate prediction value is to smoothly adjust the computer CPU usage rate through a PID controller, and the specific method is as follows: The PID input calculates the deviation between the current computer CPU power consumption and the target computer CPU power consumption through a second formula; wherein the second formula is , is the deviation, is the target computer CPU power consumption, and P is the current computer CPU power consumption. PID output, a computer CPU usage rate adjustment value is output by the PID controller to adjust the current computer CPU usage rate to approach the target computer CPU usage rate.

6. A distributed photovoltaic computer computing power control system, characterized in that, The system is used to perform the distributed photovoltaic computer computing power control method according to any one of claims 1-5, and the system comprises: A data processing module is used to acquire photovoltaic power generation output power data and computer CPU computing power demand data and perform preprocessing; the computer CPU computing power demand data comprises computer CPU usage rate, task queue length and memory usage; The model establishing module is configured to establish a photovoltaic power generation output power data and computer CPU computing power demand correlation model according to the processed photovoltaic power generation output power data and the computer CPU computing power demand data, including: dividing the processed photovoltaic power generation output power data and the computer CPU computing power demand data into a training set and a test set; constructing a three-layer long short-term memory network (LSTM) time sequence model, which includes an input layer, an LSTM layer and an output layer; training the three-layer LSTM time sequence model through the training set to obtain a trained three-layer LSTM time sequence model; and testing and adjusting the trained three-layer LSTM time sequence model through the test set to obtain the photovoltaic power generation output power data and computer CPU computing power demand correlation model; The function establishing module is configured to construct the computer CPU usage rate and the computer CPU power consumption function, including: acquiring output voltage and output current through sensors arranged in photovoltaic modules to obtain the photovoltaic power generation output power data; obtaining computer CPU computing power demand data through a computer task manager; preprocessing the photovoltaic power generation output power data and the computer CPU computing power demand data to obtain a processing data set, including: processing missing values and abnormal values of the photovoltaic power generation output power data and the computer CPU computing power demand data; fusing the photovoltaic power generation output power data and the computer CPU computing power demand data to obtain a first data set; calculating the ratio of the photovoltaic power generation output power data and the computer CPU usage rate to obtain resource utilization rate, and generating time characteristics according to a time stamp to obtain a second data set; and processing the second data set through a lag item introduction method to obtain a processing data set; The computing power regulation module is configured to regulate computer CPU computing power according to the photovoltaic power generation output power data and computer CPU computing power demand correlation model and the computer CPU usage rate and the computer CPU power consumption function, including: obtaining a computer CPU usage rate prediction value according to the photovoltaic power generation output power data and computer CPU computing power demand correlation model; obtaining a CPU usage rate target value according to the computer CPU usage rate and the computer CPU power consumption function; and smoothing the CPU usage rate prediction value to gradually approach the CPU usage rate target value; The model optimization module is configured to optimize the photovoltaic power generation output power data and computer CPU computing power demand correlation model and the computer CPU usage rate and the computer CPU power consumption function according to photovoltaic power generation output power data, computer CPU computing power demand data and computer CPU power consumption in a running process.

Images