Energy data processing method and device, computer device and storage medium

Abstract

The application relates to an energy data processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining original energy data based on space division multiplexing transmission energy data; sequentially performing denoising processing and data quality evaluation processing on the original energy data to obtain denoised energy data and a quality evaluation result of the denoised energy data; performing denoising processing on the denoised energy data again according to the quality evaluation result to obtain target energy data; and inputting the target energy data into a trained energy scheduling processing model to obtain target scheduling information of the target energy data. The method can improve the energy data processing efficiency, utilize the target scheduling information to improve the scheduling effect of energy equipment, and realize intelligent management of the energy equipment.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular to an energy data processing method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] Energy monitoring, as an effective technology for achieving the goal of "energy conservation and emission reduction", mainly utilizes modern computer, communication network, real-time database, data analysis and other technologies to provide reliable data support for enterprises to carry out centralized, flat dynamic monitoring and digital management of the production, transmission and consumption of energy media such as "water, electricity, gas, heat, wind and oil" and the status of energy supply and consumption equipment.

[0003] However, the energy data involved in energy monitoring scenarios is often large in scale, so the time consumed in data collection and processing is also long, resulting in low energy data processing efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide an energy data processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the efficiency of energy data processing in response to the above-mentioned technical problems.

[0005] Firstly, this application provides an energy data processing method. The method includes:

[0006] Energy data is transmitted using space division multiplexing to obtain raw energy data.

[0007] The original energy data is sequentially subjected to denoising and data quality assessment to obtain denoised energy data and the quality assessment results of the denoised energy data.

[0008] Based on the quality assessment results, the denoised energy data is denoised again to obtain the target energy data;

[0009] The target energy data is input into the trained energy scheduling processing model to obtain the target scheduling information of the target energy data.

[0010] In one embodiment, raw energy data is obtained based on spatially multiplexed transmission source data, including:

[0011] The data acquisition device acquires multiple energy data points from the energy equipment collected by the sensors.

[0012] The space of the transmission medium to which the data acquisition device is connected is divided into multiple spatial channels;

[0013] From the multiple space channels, determine the target space channel corresponding to each energy data, so as to perform spatial multiplexing transmission of each energy data through the target space channel;

[0014] At the receiving end of the target space channel, the received energy data is demultiplexed to obtain the original energy data.

[0015] In one embodiment, the original energy data is sequentially subjected to denoising processing and data quality assessment processing to obtain denoised energy data and the quality assessment result of the denoised energy data, including:

[0016] The original energy data is sequentially calibrated and denoised to obtain the denoised energy data.

[0017] Determine the data error between the denoised energy data and the original energy data, and the change in signal-to-noise ratio between the denoised energy data and the original energy data;

[0018] Based on the data error and the change in signal-to-noise ratio, the quality assessment result of the denoised energy data is obtained.

[0019] In one embodiment, the original energy data is sequentially calibrated and denoised to obtain the denoised energy data, including:

[0020] Based on the data format and data range of the original energy data, the original energy data is calibrated to obtain calibrated energy data;

[0021] Based on the noise characteristics of the calibrated energy data, the calibrated energy data is filtered to obtain the denoised energy data.

[0022] In one embodiment, the target energy data is input into a trained energy scheduling processing model to obtain target scheduling information for the target energy data, including:

[0023] The trained energy scheduling processing model determines multiple initial scheduling information corresponding to the target energy data and the fitness of each initial scheduling information; the fitness is used to measure the quality of each initial scheduling information.

[0024] Based on each fitness level, candidate scheduling information is selected from the multiple initial scheduling information;

[0025] The candidate scheduling information is paired and then processed by the crossover operator in the energy scheduling processing model to generate information from the candidate scheduling information, resulting in processed scheduling information.

[0026] The processed scheduling information is updated to obtain updated scheduling information;

[0027] Based on the updated scheduling information, the energy scheduling processing model outputs the target scheduling information.

[0028] In one embodiment, after obtaining the target energy data, the method further includes:

[0029] Obtain the alarm threshold corresponding to the target energy data;

[0030] If the target energy data reaches the alarm threshold, a preset alarm operation will be executed.

[0031] Secondly, this application also provides an energy data processing device. The device includes:

[0032] The data acquisition module is used to transmit energy data based on space division multiplexing to obtain raw energy data;

[0033] The data evaluation module is used to sequentially perform denoising and data quality evaluation on the original energy data to obtain denoised energy data and the quality evaluation result of the denoised energy data.

[0034] The data denoising module is used to perform denoising processing on the denoised energy data again based on the quality assessment results to obtain the target energy data;

[0035] The scheduling prediction module is used to input the target energy data into the trained energy scheduling processing model to obtain the target scheduling information of the target energy data.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0037] Energy data is transmitted using space division multiplexing to obtain raw energy data.

[0038] The original energy data is sequentially subjected to denoising and data quality assessment to obtain denoised energy data and the quality assessment results of the denoised energy data.

[0039] Based on the quality assessment results, the denoised energy data is denoised again to obtain the target energy data;

[0040] The target energy data is input into the trained energy scheduling processing model to obtain the target scheduling information of the target energy data.

[0041] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0042] Energy data is transmitted using space division multiplexing to obtain raw energy data.

[0043] The original energy data is sequentially subjected to denoising and data quality assessment to obtain denoised energy data and the quality assessment results of the denoised energy data.

[0044] Based on the quality assessment results, the denoised energy data is denoised again to obtain the target energy data;

[0045] The target energy data is input into the trained energy scheduling processing model to obtain the target scheduling information of the target energy data.

[0046] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0047] Energy data is transmitted using space division multiplexing to obtain raw energy data.

[0048] The original energy data is sequentially subjected to denoising and data quality assessment to obtain denoised energy data and the quality assessment results of the denoised energy data.

[0049] Based on the quality assessment results, the denoised energy data is denoised again to obtain the target energy data;

[0050] The target energy data is input into the trained energy scheduling processing model to obtain the target scheduling information of the target energy data.

[0051] The aforementioned energy data processing method, apparatus, computer equipment, storage medium, and computer program product transmit energy data based on space division multiplexing to obtain raw energy data. The raw energy data is then subjected to denoising and data quality assessment processes sequentially to obtain denoised energy data and its quality assessment results. Based on the quality assessment results, the denoised energy data is further denoised to obtain target energy data. This target energy data is then input into a trained energy dispatching model to obtain target dispatching information. This method improves data transmission speed through space division multiplexing technology and enhances the quality of target energy data through denoising and data quality assessment processes. This improves the accuracy of the target dispatching information output by the energy dispatching model, thereby increasing energy data processing efficiency and enhancing the dispatching effect of energy equipment using target dispatching information, thus achieving intelligent management of energy equipment. Attached Figure Description

[0052] Figure 1 This is an application environment diagram of an energy data processing method in one embodiment;

[0053] Figure 2 This is a flowchart illustrating an energy data processing method in one embodiment;

[0054] Figure 3 This is a flowchart illustrating the steps of transmitting energy data based on space division multiplexing in one embodiment;

[0055] Figure 4 This is a flowchart illustrating the energy data processing method in another embodiment;

[0056] Figure 5 This is a flowchart illustrating the energy data processing method in yet another embodiment;

[0057] Figure 6 This is a structural block diagram of an energy data processing device in one embodiment;

[0058] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0061] The energy data processing method provided in this application embodiment can be applied to, for example... Figure 1 The application environment is shown. Energy device 101 is connected to sensor 102, and both are connected to energy monitoring system 103 via transmission media. A data storage system can store the data that energy monitoring system 103 needs to process. The data storage system can be integrated into energy monitoring system 103 or placed in the cloud or on other network servers. Energy device 101 refers to energy-producing equipment in the energy sector. Sensor 102 is used to collect energy data from the energy device. Energy monitoring system 103 is used to acquire, monitor, and schedule the energy output of energy device 101; energy monitoring system 103 can be deployed on terminals (such as personal computers, laptops, smartphones, tablets, portable wearable devices, etc.) or servers (such as cloud servers, server clusters, etc.). Energy monitoring system 103 can also be connected to controller 104, which is also connected to the energy device, allowing energy monitoring system 103 to control energy device 101 through controller 104. Controller 104 includes switch controllers, regulation controllers, etc.

[0062] In one embodiment, such as Figure 2 As shown, an energy data processing method is provided, which can be applied to... Figure 1 Taking the energy monitoring system in China as an example, the following steps are included:

[0063] Step S201: Based on the spatial division multiplexing transmission of energy data, the original energy data is obtained.

[0064] Energy data refers to data collected by monitoring the energy output of energy equipment. For example, energy data includes electricity consumption, power, voltage, current, equipment operating time, switch status, operating mode, operating duration, energy consumption, temperature, humidity, and light intensity. Raw energy data refers to the data obtained after energy data transmission and processing.

[0065] Specifically, sensors can be installed on or near energy equipment to collect various energy data. Then, Space Division Multiplexing (SDM) communication technology divides the transmission channel into multiple spatial channels, enabling energy data transmission between multiple devices through these independent channels, thereby improving transmission capacity and efficiency. To further enhance data transmission efficiency and security, the energy data can be encrypted and compressed sequentially to obtain compressed energy data. This compressed energy data is then transmitted via SDM. Compared to transmitting raw energy data directly, transmitting compressed energy data reduces network bandwidth usage and data storage space, thus improving data transmission efficiency. After receiving the compressed energy data, the energy monitoring system must further decompress and decrypt it to obtain the original energy data.

[0066] Step S202: The original energy data is subjected to denoising and data quality assessment in sequence to obtain denoised energy data and the quality assessment results of the denoised energy data.

[0067] Among them, the quality assessment results are used to measure the data quality of the energy data after noise reduction.

[0068] Specifically, the energy monitoring system uses a filter with pre-set parameters to denoise the raw energy data, removing electrical noise, electromagnetic interference, and other noise from the original data to obtain denoised energy data. Then, based on quality assessment indicators, the energy monitoring system performs a data quality assessment on the denoised energy data, ultimately obtaining the quality assessment result of the denoised energy data.

[0069] Step S203: Based on the quality assessment results, the denoised energy data is denoised again to obtain the target energy data.

[0070] Specifically, based on the quality assessment results, the energy monitoring system adjusts the filter parameters of the filter in step S202 to obtain an adjusted filter; the adjusted filter is then used to denoise the denoised energy data again to obtain processed energy data; the processed energy data undergoes a data quality assessment to obtain a quality assessment result; if the quality assessment result of the processed energy data is better than that of the denoised energy data, the processed energy data is set as the target energy data; if the quality assessment result of the processed energy data is worse than that of the denoised energy data, the system jumps to the step of adjusting the filter parameters to obtain an adjusted filter, which is then used to denoise the denoised energy data again to obtain processed energy data, until the number of denoising rounds reaches a preset maximum number of rounds, or the quality assessment result of the processed energy data is better than that of the denoised energy data. Finally, the energy monitoring system stores the processed target energy data in a relational database or data warehouse.

[0071] Step S204: Input the target energy data into the trained energy scheduling processing model to obtain the target scheduling information of the target energy data.

[0072] The energy dispatching processing model is used to reason about and optimize the energy monitoring system's dispatching strategies for energy equipment. Target dispatching information refers to information describing strategies for the use, storage, dispatching, and planning of energy equipment resources.

[0073] Specifically, the energy monitoring system uses machine learning algorithms to construct and train an energy dispatching and processing model; for example, the model can be built based on a genetic algorithm. The system inputs target energy data into the trained model, which then infers a dispatching plan for energy equipment based on the target energy data. The model then outputs target dispatching information for the target energy data. Furthermore, the system can use a controller to manage the operation of energy equipment according to this target dispatching information, achieving adaptive adjustment of energy equipment operation and improving the utilization efficiency of energy produced by the equipment.

[0074] In the aforementioned energy data processing method, energy data is transmitted using spatial division multiplexing to obtain raw energy data. The raw energy data is then subjected to denoising and data quality assessment processes to obtain denoised energy data and its quality assessment results. Based on the quality assessment results, the denoised energy data is further denoised to obtain target energy data. This target energy data is then input into a trained energy dispatching model to obtain target dispatching information. This method improves data transmission speed through spatial division multiplexing, significantly accelerating energy data transmission. Furthermore, denoising and data quality assessment processes enhance the quality of the target energy data, thereby improving the accuracy of the target dispatching information output by the energy dispatching model. This not only improves energy data processing efficiency but also enhances the dispatching effect of energy equipment using target dispatching information, achieving intelligent management of energy equipment.

[0075] In one embodiment, such as Figure 3 As shown, step S201 above, based on space division multiplexing to transmit energy data, obtains the original energy data, specifically including the following:

[0076] Step S301: Acquire multiple energy data from the energy equipment collected by the sensor through the data acquisition device.

[0077] Specifically, the energy monitoring system uses sensors to collect multiple energy data from energy devices and uses a data acquisition unit to receive the data collected by the sensors.

[0078] Step S302: Divide the space of the transmission medium connected to the data acquisition device into multiple spatial channels.

[0079] Specifically, data acquisition devices can transmit energy data through wireless transmission technology or fiber optic communication technology. If fiber optic communication is used, multi-core or multi-mode optical fibers can be deployed in new energy power plants or smart grids to enable data transmission and communication between multiple sensors, energy devices, and energy monitoring systems. The energy monitoring system uses spatial division multiplexing technology to divide the transmission space of the optical fiber into multiple independent spatial channels.

[0080] Step S303: Determine the target spatial channel corresponding to each energy data from multiple spatial channels, so as to perform spatial multiplexing transmission of each energy data through the target spatial channel.

[0081] Specifically, the energy monitoring system allocates spatial channels for the transmission of each energy data point, that is, it determines the target spatial channel corresponding to each energy data point, so that each energy data point can be sent simultaneously through multiple target control channels. This not only improves data transmission efficiency, but also reduces data transmission loss and improves data transmission quality.

[0082] Step S304: At the receiving end of the target space channel, the received energy data is demultiplexed to obtain the original energy data.

[0083] The receiving end refers to the communication port of the energy monitoring system used to receive energy data.

[0084] Specifically, data transmission incurs some transmission loss. Therefore, the energy monitoring system performs data processing at the receiving end to compensate for this loss. This can be achieved by using an optical amplifier to amplify the received energy data, resulting in amplified energy data. Since multiplexing mixes the energy data, the energy monitoring system also demultiplexes the amplified energy data to separate (or restore) the mixed energy data into the original, independent data. The energy monitoring system then obtains the original energy data.

[0085] In this embodiment, multiple energy data from energy devices collected by sensors are acquired by a data acquisition device, and then the target spatial channel corresponding to each energy data is used to perform spatial multiplexing transmission of each energy data, which effectively improves the data transmission efficiency of energy data; at the receiving end of the target spatial channel, the received energy data is demultiplexed, which effectively improves the data quality of the restored original energy data.

[0086] In one embodiment, step S202 above, which involves sequentially performing denoising and data quality assessment on the original energy data to obtain denoised energy data and a quality assessment result of the denoised energy data, specifically includes the following: sequentially performing calibration and denoising on the original energy data to obtain denoised energy data; determining the data error between the denoised energy data and the original energy data, as well as the change in signal-to-noise ratio between the denoised energy data and the original energy data; and obtaining the quality assessment result of the denoised energy data based on the data error and the change in signal-to-noise ratio.

[0087] The signal-to-noise ratio (SNR) change refers to a metric describing how the SNR changes. The SNR change includes both increases and decreases in SNR.

[0088] Specifically, the energy monitoring system performs data calibration on the raw energy data, which may include calibrating the data format, range, integrity, and logical consistency to obtain calibrated energy data. Then, it filters and denoises the calibrated energy data to obtain denoised energy data. The system then calculates the data error between the denoised energy data and the original energy data, as well as the first signal-to-noise ratio (SNR) of the denoised energy data and the second SNR of the original energy data. The difference between the first and second SNRs is defined as the SNR change. The system can also calculate the error distribution and filtering gain of the denoised energy data. Based on these factors, the system comprehensively determines the quality assessment result of the denoised energy data. This can be achieved by separately determining the weights for each factor, and then weighting and summing them to obtain the final quality assessment result of the denoised energy data.

[0089] The filter gain is used to evaluate the filtering effect of the filter on data (such as raw energy data). The filter gain can be achieved through metrics such as signal-to-noise ratio, mean square error, peak signal-to-noise ratio, and structural similarity index.

[0090] In this embodiment, by calibrating the original energy data, the data quality of the calibrated energy data can be improved. Then, by denoising, the data quality of the denoised energy data can be further improved. Based on the data error and the change in signal-to-noise ratio, the quality assessment result of the denoised energy data is determined to analyze the gain of the denoising process on the calibrated energy data, which helps to improve the data quality and thus improve the scheduling and analysis effect of the energy dispatching processing model.

[0091] In one embodiment, the original energy data is sequentially calibrated and denoised to obtain denoised energy data. Specifically, this includes: calibrating the original energy data according to its data format and range to obtain calibrated energy data; and filtering the calibrated energy data according to its noise characteristics to obtain denoised energy data.

[0092] Specifically, the energy monitoring system can check whether the raw energy data conforms to a specified format (e.g., date format, telephone number format); whether it falls within a specified data range; whether it is unique within the dataset; the completeness of the data (e.g., missing or null values); the logical relationships (e.g., start date should be earlier than end date); the legality of the data (compliance with relevant laws, regulations, and business rules, such as privacy and financial regulations); and the consistency of the data (consistency of related fields across different systems or tables). Finally, the energy monitoring system processes the data to obtain calibrated energy data.

[0093] Furthermore, the energy monitoring system calculates the power spectral density of the calibrated energy data and sets the power spectral density as the noise characteristic of the calibrated energy data; then, based on the noise characteristic, it sets the initial parameters of the filter to obtain the set filter; and uses the set filter to filter the calibrated energy data to obtain the denoised energy data.

[0094] In this embodiment, the original energy data is calibrated according to its data format and range to improve the data quality of the calibrated energy data. Based on the noise characteristics of the calibrated energy data, it is filtered to remove noise signals and greatly improve the data quality of the denoised energy data.

[0095] In one embodiment, step S204 above, which involves inputting the target energy data into a trained energy dispatch processing model to obtain target dispatch information for the target energy data, specifically includes the following: determining multiple initial dispatch information corresponding to the target energy data and the fitness of each initial dispatch information through the trained energy dispatch processing model; the fitness is used to measure the quality of each initial dispatch information; based on each fitness, candidate dispatch information is selected from the multiple initial dispatch information; the candidate dispatch information is paired, and the crossover operator in the energy dispatch processing model is used to generate information from the candidate dispatch information to obtain processed dispatch information; the processed dispatch information is updated to obtain updated dispatch information; and the energy dispatch processing model outputs target dispatch information based on the updated dispatch information.

[0096] Specifically, the energy monitoring model pre-sets the parameters of the evolutionary generation counter of the trained energy dispatching and processing model, i.e., sets the maximum evolutionary generation. Then, based on the target energy data, the trained energy dispatching and processing model randomly generates multiple dispatching information for energy devices and sets them as initial dispatching information. The trained energy dispatching and processing model calculates the fitness of each initial dispatching information based on its quality. From the initial dispatching information, multiple initial dispatching information with relatively high fitness are selected and set as candidate dispatching information. The candidate dispatching information is paired to obtain paired dispatching information. Then, the crossover operator in the energy dispatching and processing model is used to generate new dispatching information from the paired dispatching information, and the newly generated dispatching information is set as the processed dispatching information. The local dispatching information in the processed dispatching information is randomly adjusted to enhance the diversity of dispatching information, thereby obtaining updated dispatching information, and the evolutionary generation is incremented by one. If the current evolutionary generation reaches the maximum evolutionary generation, or other termination conditions are met, the optimal solution is selected from the updated dispatching information and output, and the output result is set as the target dispatching information.

[0097] In practical applications, target scheduling information mainly achieves the following aspects:

[0098] (1) Power generation regulation: Based on real-time energy data such as wind and solar power output, power generation is regulated to meet grid demand. Regulation parameters include: new energy power generation, grid load demand, energy storage status, and forecast data.

[0099] (2) Energy storage management: Intelligent scheduling of energy equipment charging and discharging operations based on grid load changes and energy data such as new energy power generation. Adjustment parameters include: energy storage capacity, charging and discharging efficiency, grid demand forecast, electricity price information, etc.

[0100] (3) Grid optimization configuration: Through target scheduling information, optimize the power flow in the grid, improve transmission efficiency, and reduce losses. Adjustment parameters include: transmission line capacity, line loss, node voltage, power flow, etc.

[0101] (4) Demand-side management: Adjusting electricity demand on the user side, such as adjusting industrial load or incentivizing household users to change their electricity consumption patterns. Adjustment parameters include: user electricity consumption data, demand response capability, electricity price signals, incentive mechanisms, etc.

[0102] (5) Electricity market transactions: Optimize electricity purchase and sales strategies. Adjustment parameters include: market price, trading rules, forecasting algorithms, cost-benefit analysis, etc.

[0103] (6) Fault detection and recovery: Perform recovery operations on faulty energy equipment based on target scheduling information. Adjustment parameters include: fault type, scope of impact, backup plan, recovery priority, etc.

[0104] (7) Prediction and Simulation: Based on the current target scheduling information, predict the operating status of the power grid in the future time period and simulate different regulation strategies in the future time period. Regulation parameters include: historical operating data, meteorological conditions, algorithm model, simulation results, etc.

[0105] (8) Communication and Coordination: Adjusting the communication parameters of various control units and equipment in the power grid to ensure smooth communication. Adjustment parameters include: communication protocol, data synchronization, control signals, response time, etc.

[0106] In this embodiment, the potential operating patterns of energy equipment are mined from the target energy data through the trained energy scheduling processing model, providing a reliable processing basis for iteratively optimizing the scheduling information of energy equipment. Finally, the target scheduling information of energy equipment is output, realizing the adaptive adjustment of energy equipment scheduling and operation, which is conducive to improving the utilization efficiency of energy produced by energy equipment.

[0107] In one embodiment, after obtaining the target energy data in step S203, the method further includes: obtaining the alarm threshold corresponding to the target energy data; if the target energy data reaches the alarm threshold, then executing a preset alarm operation.

[0108] Specifically, after obtaining target energy data, the energy monitoring system can also acquire the corresponding alarm thresholds. If the target energy data reaches the alarm threshold, a preset alarm operation is executed. These alarm thresholds can be multifaceted, such as energy consumption alarm thresholds or equipment failure alarm thresholds. Different alarm levels can also be set based on the anomaly level of the target energy data to allow for timely response measures. Alarm operations can include audible alarms, SMS notifications, and email alerts to ensure relevant personnel receive alarm information promptly. The energy monitoring system can also designate recipients of alarm information, including responsible personnel and managers, to ensure timely response and handling of alarm information. Furthermore, the energy monitoring system can set more detailed operational procedures for alarm operations, including alarm information confirmation, processing, and feedback, ensuring timely handling and tracking of abnormal situations.

[0109] Furthermore, to facilitate relevant personnel in viewing and analyzing target energy data, the target energy data can be visualized in various forms such as line charts, bar charts, and tables; the format and template of the reports can be customized, and the target energy data can be imported into the report template to form report data. The report data can be exported to Excel or other formats for further processing and analysis; the report data can also be compared and analyzed with historical target energy data.

[0110] In this embodiment, by using alarm thresholds and visualization processing of target energy data, alarms can be issued in a timely manner and corresponding measures can be taken when energy equipment malfunctions, thereby improving the operational safety of energy equipment.

[0111] In one embodiment, such as Figure 4 As shown, another energy data processing method is provided, which can be applied to... Figure 1 Taking the energy monitoring system in China as an example, the following steps are included:

[0112] Step S401: Acquire multiple energy data from the energy equipment collected by the sensor through the data acquisition device.

[0113] Step S402: Divide the space of the transmission medium connected to the data acquisition device into multiple spatial channels.

[0114] Step S403: Determine the target spatial channel corresponding to each energy data from multiple spatial channels, so as to perform spatial multiplexing transmission of each energy data through the target spatial channel.

[0115] Step S404: At the receiving end of the target space channel, the received energy data is demultiplexed to obtain the original energy data.

[0116] Step S405: The original energy data is calibrated and denoised sequentially to obtain denoised energy data.

[0117] Step S406: Determine the data error between the denoised energy data and the original energy data, as well as the change in signal-to-noise ratio between the denoised energy data and the original energy data.

[0118] Step S407: Based on the data error and the change in signal-to-noise ratio, obtain the quality assessment result of the denoised energy data.

[0119] Step S408: Based on the quality assessment results, the denoised energy data is denoised again to obtain the target energy data.

[0120] Step S409: Input the target energy data into the trained energy scheduling processing model to obtain the target scheduling information of the target energy data.

[0121] The above-mentioned energy data processing method can achieve the following beneficial effects: by improving the data transmission method through spatial division multiplexing technology, the transmission speed of energy data is significantly accelerated. Furthermore, by denoising and data quality assessment, the data quality of the target energy data is improved, thereby enhancing the accuracy of the target scheduling information output by the energy scheduling processing model. While improving the efficiency of energy data processing, the target scheduling information can also be used to improve the scheduling effect of energy equipment, realizing intelligent management of energy equipment.

[0122] To more clearly illustrate the energy data processing method provided in this disclosure, a specific embodiment will be used to describe the above-mentioned energy data processing method in detail below. For example... Figure 5 As shown, another energy data processing method is provided, which can be applied to... Figure 1 The energy monitoring system in China specifically includes the following components:

[0123] (1) Data acquisition: Accurate and comprehensive acquisition of energy data from energy equipment.

[0124] (2) Data transmission: By deploying multi-core optical fibers or multi-mode optical fibers in new energy power plants or smart grids, the transmission of energy data is realized in optical fiber communication systems using space division multiplexing technology.

[0125] (3) Data processing: The received energy data is calibrated and filtered.

[0126] (4) Data storage: Store the energy data obtained in step (3) into a relational database or data warehouse.

[0127] (5) Data analysis: The energy data obtained in step (3) is analyzed by genetic algorithm to optimize the storage management of energy equipment, energy network planning and control strategies.

[0128] (6) Data monitoring and alarm mechanism: Real-time monitoring of whether the energy data obtained in step (3) exceeds the alarm threshold. If it does, the corresponding alarm action is executed according to the preset alarm method.

[0129] (7) Report data and data display: Convert the energy data obtained in step (3) into report data and perform data visualization processing to facilitate user viewing and analysis.

[0130] In this embodiment, spatial multiplexing technology is used to improve the data transmission method, which significantly accelerates the transmission speed of energy data. Furthermore, noise reduction and data quality assessment are used to improve the data quality of the target energy data, thereby enhancing the accuracy of the target scheduling information output by the energy scheduling processing model. While improving the efficiency of energy data processing, the target scheduling information can also be used to improve the scheduling effect of energy equipment, realizing intelligent management of energy equipment.

[0131] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0132] Based on the same inventive concept, this application also provides an energy data processing apparatus for implementing the energy data processing method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more energy data processing apparatus embodiments provided below can be found in the limitations of the energy data processing method described above, and will not be repeated here.

[0133] In one embodiment, such as Figure 6 As shown, an energy data processing device 600 is provided, including: a data acquisition module 601, a data evaluation module 602, a data denoising module 603, and a scheduling prediction module 604, wherein:

[0134] The data acquisition module 601 is used to transmit energy data based on space division multiplexing to obtain raw energy data.

[0135] The data evaluation module 602 is used to perform denoising and data quality evaluation on the raw energy data in sequence, so as to obtain the denoised energy data and the quality evaluation results of the denoised energy data.

[0136] The data denoising module 603 is used to further denoise the denoised energy data based on the quality assessment results to obtain the target energy data.

[0137] The scheduling prediction module 604 is used to input the target energy data into the trained energy scheduling processing model to obtain the target scheduling information of the target energy data.

[0138] In one embodiment, the data acquisition module 601 is further configured to acquire multiple energy data from energy devices collected by sensors via a data acquisition device; divide the space of the transmission medium connected to the data acquisition device into multiple spatial channels; determine the target spatial channel corresponding to each energy data from the multiple spatial channels, so as to perform spatial multiplexing transmission of each energy data through the target spatial channel; and at the receiving end of the target spatial channel, perform demultiplexing processing on the received energy data to obtain the original energy data.

[0139] In one embodiment, the data evaluation module 602 is further configured to perform calibration and denoising processing on the original energy data in sequence to obtain denoised energy data; determine the data error between the denoised energy data and the original energy data, as well as the change in signal-to-noise ratio between the denoised energy data and the original energy data; and obtain the quality evaluation result of the denoised energy data based on the data error and the change in signal-to-noise ratio.

[0140] In one embodiment, the energy data processing device 600 further includes a data calibration module, which is used to calibrate the original energy data according to the data format and data range of the original energy data to obtain calibrated energy data; and to filter the calibrated energy data according to the noise characteristics of the calibrated energy data to obtain denoised energy data.

[0141] In one embodiment, the scheduling prediction module 604 is used to determine multiple initial scheduling information corresponding to the target energy data and the fitness of each initial scheduling information through a trained energy scheduling processing model; the fitness is used to measure the quality of each initial scheduling information; based on each fitness, candidate scheduling information is selected from the multiple initial scheduling information; the candidate scheduling information is paired and processed by the cross operator in the energy scheduling processing model to obtain processed scheduling information; the processed scheduling information is updated to obtain updated scheduling information; and the energy scheduling processing model outputs the target scheduling information based on the updated scheduling information.

[0142] In one embodiment, the energy data processing device 600 further includes an alarm processing module for obtaining an alarm threshold corresponding to the target energy data; if the target energy data reaches the alarm threshold, a preset alarm operation is executed.

[0143] Each module in the aforementioned energy data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0144] In one embodiment, a computer device is provided, which may be a terminal, and the terminal is equipped with an energy detection system. The internal structure diagram of the terminal may be as follows: Figure 7 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an energy data processing method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0145] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0146] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0147] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0148] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0149] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0150] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0151] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An energy data processing method, characterized in that, The method includes: Energy data is transmitted using space division multiplexing to obtain raw energy data. The original energy data is calibrated to obtain calibrated energy data; the calibration process includes at least one of detecting the uniqueness of the original energy data in the dataset and detecting the consistency of related fields of the original energy data in different systems or data tables. Obtain the power spectral density of the calibrated energy data, and set the power spectral density as the noise characteristic of the calibrated energy data; set the initial parameters of the filter according to the noise characteristic to obtain the set filter; use the set filter to filter the calibrated energy data to obtain denoised energy data. The denoised energy data is subjected to data quality assessment processing to obtain the quality assessment result of the denoised energy data. Based on the quality assessment results, the filtering parameters of the set filter are adjusted to obtain the adjusted filter; the adjusted filter is then used to denoise the denoised energy data again to obtain the processed energy data. The processed energy data is subjected to a data quality assessment process to obtain the quality assessment result of the processed energy data. If the quality assessment result of the processed energy data is better than the quality assessment result of the denoised energy data, then the processed energy data is set as the target energy data; otherwise, proceed to the step of adjusting the filtering parameters of the set filter according to the quality assessment result to obtain an adjusted filter; use the adjusted filter to denoise the denoised energy data again to update the obtained processed energy data; stop when the number of denoising rounds reaches the preset maximum number of rounds, or when the quality assessment result of the processed energy data is better than the quality assessment result of the denoised energy data. The target energy data is input into the trained energy scheduling processing model to obtain the target scheduling information of the target energy data.

2. The method according to claim 1, characterized in that, The energy data obtained by transmitting energy data based on space division multiplexing includes: The data acquisition device acquires multiple energy data points from the energy equipment collected by the sensors. The space of the transmission medium to which the data acquisition device is connected is divided into multiple spatial channels; From the plurality of said spatial channels, determine the target spatial channel corresponding to each of said energy data, so as to perform spatial multiplexing transmission of each of said energy data through said target spatial channel; At the receiving end of the target space channel, the received energy data is demultiplexed to obtain the original energy data.

3. The method according to claim 1, characterized in that, The process of sequentially performing denoising and data quality assessment on the original energy data to obtain denoised energy data and the quality assessment results of the denoised energy data includes: The original energy data is sequentially calibrated and denoised to obtain the denoised energy data. Determine the data error between the denoised energy data and the original energy data, as well as the change in signal-to-noise ratio between the denoised energy data and the original energy data; Based on the data error and the change in signal-to-noise ratio, the quality assessment result of the denoised energy data is obtained.

4. The method according to claim 3, characterized in that, The process of sequentially calibrating and denoising the original energy data to obtain the denoised energy data includes: Based on the data format and data range of the original energy data, the original energy data is calibrated to obtain calibrated energy data; Based on the noise characteristics of the calibrated energy data, the calibrated energy data is filtered to obtain the denoised energy data.

5. The method according to claim 1, characterized in that, The step of inputting the target energy data into the trained energy scheduling processing model to obtain the target scheduling information of the target energy data includes: The trained energy scheduling processing model determines multiple initial scheduling information corresponding to the target energy data and the fitness of each initial scheduling information; the fitness is used to measure the quality of each initial scheduling information. Based on each fitness level, candidate scheduling information is selected from the multiple initial scheduling information; The candidate scheduling information is paired and then processed by the crossover operator in the energy scheduling processing model to generate information from the candidate scheduling information, resulting in processed scheduling information. The processed scheduling information is updated to obtain updated scheduling information; Based on the updated scheduling information, the energy scheduling processing model outputs the target scheduling information.

6. The method according to claim 1, characterized in that, After obtaining the target energy data, the following is also included: Obtain the alarm threshold corresponding to the target energy data; If the target energy data reaches the alarm threshold, a preset alarm operation will be executed.

7. An energy data processing device, characterized in that, The device includes: The data acquisition module is used to transmit energy data based on space division multiplexing to obtain raw energy data; A data evaluation module is used to calibrate the original energy data to obtain calibrated energy data. The calibration process includes at least one of detecting the uniqueness of the original energy data within the dataset and detecting the consistency of related fields in different systems or data tables. The module also obtains the power spectral density of the calibrated energy data and sets it as the noise characteristic of the calibrated energy data. Based on the noise characteristic, it sets the initial parameters of a filter to obtain a set filter. The set filter is then used to filter the calibrated energy data to obtain denoised energy data. Finally, the module performs a data quality evaluation on the denoised energy data to obtain a quality evaluation result for the denoised energy data. The data denoising module is used to adjust the filtering parameters of the set filter according to the quality assessment result to obtain an adjusted filter; use the adjusted filter to denoise the denoised energy data again to obtain processed energy data; perform data quality assessment on the processed energy data to obtain a quality assessment result; if the quality assessment result of the processed energy data is better than the quality assessment result of the denoised energy data, then the processed energy data is set as the target energy data; otherwise, it jumps to the step of adjusting the filtering parameters of the set filter according to the quality assessment result to obtain an adjusted filter; and using the adjusted filter to denoise the denoised energy data again to update the obtained processed energy data; the process continues until the number of denoising rounds reaches a preset maximum number of rounds, or the quality assessment result of the processed energy data is better than the quality assessment result of the denoised energy data. The scheduling prediction module is used to input the target energy data into the trained energy scheduling processing model to obtain the target scheduling information of the target energy data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images