Internet of Things energy data capitalization processing method and system and electronic equipment
Through IoT technology, energy data is comprehensively collected and used asset-based models for processing, the problems of incomplete data collection, low fault processing efficiency, and inaccurate load regulation are solved, and the intelligent management and operation efficiency of the energy system are improved.
Patent Information
- Application Number
- CN202411798992.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-09
- Publication Date
- 2025-03-28
AI Technical Summary
Traditional energy management methods have problems such as incomplete data collection, low fault processing efficiency, and inaccurate load regulation, resulting in unstable operation of energy systems and low management efficiency.
Through IoT technology, data is collected comprehensively in all links of the energy network, and the asset model is used to predict the data, identify the fault and output the operation strategy, and adjust the energy network based on the identified faults and output operation strategies.
It has achieved accurate control of the operating conditions of the energy system, efficient handling and prevention of faults, and reasonable control of loads, and overall improved the intelligent management level of the energy system.
Smart Images
Figure CN119721473A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and specifically to a method, system and electronic equipment for processing energy data assets in the Internet of Things. Background Art
[0002] With the widespread application of Internet of Things technology in the energy field, intelligent management of energy systems has become a research hotspot. The inventors found the following problems in their research on existing energy management methods:
[0003] In terms of energy data acquisition, traditional methods often rely on manual inspections and limited fixed monitoring points, making it difficult to achieve comprehensive and real-time data collection at all stages of the energy network, resulting in inaccurate and in-time understanding of the operating conditions of the energy system. For example, there are a lot of missing data on the impact of changes in indoor and outdoor environments on the load of energy consumption terminals, which cannot provide sufficient basis for load forecasting.
[0004] There is a lack of effective automated identification and response mechanisms for energy system fault handling. Usually, after a fault occurs, the fault is located through manual troubleshooting and empirical judgment, which is inefficient and prone to misjudgment. Moreover, it is difficult for traditional methods to quickly formulate and implement targeted operation strategies based on fault characteristics, and it is impossible to isolate the fault area and enable backup resources in time, resulting in an expansion of the fault impact range and an increased risk of energy supply interruption.
[0005] In terms of load control, since it is impossible to accurately predict load changes and dynamically adjust the operating power of energy consumption terminals according to real-time conditions, it is easy to cause energy waste or insufficient supply, affecting the stability and economy of the energy system.
[0006] In summary, a new technical solution for IoT energy data asset processing is urgently needed to improve the intelligent management level and operation efficiency of the energy network. Summary of the invention
[0007] The purpose of this application is to provide a method, system and electronic device for processing energy data assets in the Internet of Things to solve the technical problems raised in the above-mentioned background technology.
[0008] To achieve the above objectives, this application discloses the following technical solutions:
[0009] In a first aspect, the present application discloses a method for processing IoT energy data assets, the method comprising:
[0010] S1: using the preset Internet of Things to collect data at various links of the energy network to generate energy data; wherein the energy data is used to characterize the operating status of the energy system;
[0011] S2: running a preset assetization model to assetize the energy data; wherein the assetization includes load forecasting, fault identification and operation strategy output;
[0012] S3: Make corresponding adjustments to the energy network based on the identified faults and / or output operation strategies.
[0013] Preferably, the process of generating the energy data includes:
[0014] Determine the key monitoring nodes in the energy network, install energy consumption monitoring devices and operation status monitoring devices at indoor energy consumption terminals, install indoor environmental status monitoring devices in indoor working environments, and install outdoor environmental status monitoring devices outdoors corresponding to the working environment;
[0015] Use the Internet of Things communication protocol to aggregate the data collected by each key monitoring node to the corresponding preset data gateway;
[0016] Perform preliminary data cleaning in the data gateway to remove obvious outliers and erroneous data based on the preset normal data range and logical rules;
[0017] By using data fusion technology, the data from different data sources and in different formats are unified in data structure and encoding method to generate the energy data.
[0018] Preferably, the preset process of the assetization model includes:
[0019] Obtain historical energy data and corresponding historical operation strategies;
[0020] The load feature extraction and fault feature extraction are performed using historical energy data; the load feature extraction is specifically: extracting the impact of the outdoor environment on the load generated by the energy consumption terminal in the indoor environment based on the time series, and obtaining the corresponding load feature; the fault feature extraction is specifically: extracting the data generated by the energy consumption terminal at the time of the fault based on the time series, and obtaining the corresponding fault feature;
[0021] Establishing a first correspondence between the load characteristic and the corresponding operation strategy and a second correspondence between the fault characteristic and the corresponding operation strategy;
[0022] The load characteristics, the fault characteristics, the operation strategy, the first corresponding relationship and the second corresponding relationship are stored in an assetized learning model pre-built using machine learning technology, and the assetized learning model is trained to execute the corresponding operation strategy generated based on energy data. The assetized learning model that meets a preset model accuracy threshold is defined as the assetized model and output.
[0023] Preferably, the load forecast is specifically as follows:
[0024] Acquire and analyze real-time energy data to obtain real-time energy consumption data, real-time indoor environment data, and real-time outdoor environment data;
[0025] Extracting the real-time load characteristics of the real-time outdoor environment data and the real-time indoor environment data to the real-time energy consumption data of the energy consumption terminal based on the time series;
[0026] The real-time load feature is matched with the load features for similarity, and a load feature that meets a preset load similarity threshold is output.
[0027] Preferably, the fault identification is specifically:
[0028] Acquire and analyze real-time energy data to obtain real-time operation data of energy consumption terminals;
[0029] Extracting real-time operation features of the real-time operation data based on the time series;
[0030] The real-time operation feature is matched with the fault feature for similarity, and the fault feature that meets a preset fault similarity threshold is output.
[0031] Preferably, the operation strategy output is specifically:
[0032] Acquiring the matched load characteristics and the fault characteristics;
[0033] Based on the load characteristics, the first corresponding relationship is retrieved, and based on the first corresponding relationship, the corresponding operation strategy is retrieved, each operation strategy is simulated and run, and the simulated energy consumption generated during the operation is compared, and the operation strategy corresponding to the minimum value of the simulated energy consumption is output to obtain a real-time load strategy;
[0034] The second corresponding relationship is retrieved based on the fault feature, and the corresponding operation strategy is retrieved based on the second corresponding relationship. Each operation strategy is simulated and the simulated interference generated during the operation is compared. The operation strategy corresponding to the minimum range of the simulated interference is output to obtain a real-time fault strategy.
[0035] Preferably, the energy network is adjusted accordingly based on the identified fault, specifically:
[0036] Based on the acquired real-time fault strategy, the relevant equipment or system parameters in the energy network are adjusted for faults. The specific fault adjustments are as follows:
[0037] Switching the operation mode of the energy consumption terminal based on the real-time fault strategy, isolating the corresponding fault area, and calling the backup energy consumption terminal corresponding to the fault area;
[0038] During the adjustment process, the frequency of extracting the real-time fault features is increased, and the corresponding real-time fault strategy is updated until the fault is resolved.
[0039] As a preference, the energy network is adjusted accordingly based on the output operation strategy, specifically:
[0040] Based on the acquired real-time load strategy, load adjustment is performed on relevant equipment or system parameters in the energy network. The load adjustment is specifically as follows:
[0041] Performing operating power switching of energy consumption terminals based on the real-time load strategy;
[0042] During the adjustment process, the frequency of extracting the real-time load characteristics is increased, and the corresponding real-time load strategy is updated.
[0043] In a second aspect, the present application discloses an IoT energy data asset processing system, which is applicable to the IoT energy data asset processing method as described above, and the system includes:
[0044] An energy data generation module, wherein the energy data generation module is configured to: utilize a preset Internet of Things to collect data at various links of the energy network to generate energy data; wherein the energy data is used to characterize the operating status of the energy system;
[0045] An assetization module, wherein the assetization module is configured to: run a preset assetization model to assetize the energy data; wherein the assetization includes load forecasting, fault identification, and operation strategy output;
[0046] An adjustment module, wherein the adjustment module is configured to make corresponding adjustments to the energy network based on the identified faults and / or output operation strategies.
[0047] In a third aspect, the present application discloses an electronic device, comprising: at least one processor and at least one memory, wherein the memory is communicatively connected to the processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, the IoT energy data assetization processing method as described above is implemented.
[0048] Beneficial effects: The IoT energy data asset processing method, system and electronic equipment of the present application utilize the preset IoT to comprehensively collect data in all aspects of the energy network to generate energy data, and assetize the energy data in combination with the operation of the preset assetization model, as well as make targeted adjustments to the energy network based on the identified faults and output operation strategies, thereby achieving precise control of the operating status of the energy system, efficient handling and prevention of faults, and reasonable regulation of loads, thereby improving the overall intelligent management level of the energy system, and effectively solving the problems of incomplete data collection, low fault handling efficiency, and inaccurate load regulation in traditional energy management methods. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.
[0050] Figure 1 A flowchart of the method for processing IoT energy data assets provided in the embodiment of the present application;
[0051] Figure 2 This is a structural block diagram of the IoT energy data asset processing system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0052] The technical solutions in the embodiments of the present application are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.
[0053] In this article, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprising..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0054] The first aspect of this embodiment discloses Figure 1 A method for processing IoT energy data assets is shown, the method comprising:
[0055] S1: Use the preset Internet of Things to collect data at various links of the energy network to generate energy data; the energy data is used to characterize the operating status of the energy system;
[0056] S2: Run the preset assetization model to assetize energy data; assetization includes load forecasting, fault identification and operation strategy output;
[0057] S3: Make corresponding adjustments to the energy network based on the identified faults and / or output operation strategies.
[0058] It should be noted that this embodiment utilizes the existing Internet of Things technology to realize data collection on the energy network. In a specific example, the energy network of this embodiment is an indoor terminal air-conditioning system.
[0059] Based on the above, this embodiment utilizes the preset Internet of Things to comprehensively collect data in all aspects of the energy network to generate energy data, combines the operation of the preset assetization model to assetize the energy data, and makes targeted adjustments to the energy network based on the identified faults and output operation strategies, thereby achieving precise control of the operating status of the energy system, efficient handling and prevention of faults, and reasonable regulation of loads, thereby improving the overall level of intelligent management of the energy system, and effectively solving the problems of incomplete data collection, low fault handling efficiency, and inaccurate load regulation in traditional energy management methods.
[0060] Specifically, the process of generating energy data includes:
[0061] Determine the key monitoring nodes in the energy network, install energy consumption monitoring devices and operation status monitoring devices at indoor energy consumption terminals, install indoor environmental status monitoring devices in indoor working environments, and install outdoor environmental status monitoring devices outdoors corresponding to the working environment;
[0062] Use the Internet of Things communication protocol to aggregate the data collected by each key monitoring node to the corresponding preset data gateway;
[0063] Perform preliminary data cleaning in the data gateway to remove obvious outliers and erroneous data based on the preset normal data range and logical rules;
[0064] By using data fusion technology, the data structure and encoding method of different data sources and data in different formats are unified to generate energy data.
[0065] In a simple example, the indoor energy consumption terminal of this embodiment is equipped with an energy consumption monitoring device and an operation status monitoring device to collect the equipment status of air conditioner cabinets, fan coil units, and fresh air fans. An indoor environment status monitoring device is set in the indoor working environment to monitor indoor temperature, humidity and other environmental data. An outdoor environment status monitoring device is set outdoors corresponding to the working environment to collect wet-bulb temperature and light intensity data, etc.
[0066] It should be noted that this embodiment utilizes any existing Internet of Things communication protocol to aggregate data, and processes the original data based on any existing data cleaning and data fusion technology to obtain energy data.
[0067] Based on the above, this embodiment utilizes the determination of key monitoring nodes of the energy network and the setting of multiple monitoring devices, combined with the Internet of Things communication protocol to transmit data, and performs cleaning and data fusion technology at the data gateway, to achieve comprehensive, real-time and accurate collection of data from all links of the energy network, solving the problem of incomplete and untimely data collection by traditional means, and providing a reliable data foundation for subsequent energy data asset processing.
[0068] Specifically, the preset process of the assetization model includes:
[0069] Obtain historical energy data and corresponding historical operation strategies;
[0070] Use historical energy data to extract load characteristics and fault characteristics; load characteristic extraction is specifically: extract the impact of the outdoor environment on the load generated by the energy consumption terminal in the indoor environment based on the time series, and obtain the corresponding load characteristics; fault characteristic extraction is specifically: extract the data generated by the energy consumption terminal at the time of the fault based on the time series, and obtain the corresponding fault characteristics;
[0071] Establishing a first correspondence between a load characteristic and a corresponding operation strategy and a second correspondence between a fault characteristic and a corresponding operation strategy;
[0072] The load characteristics, fault characteristics, operation strategies, first corresponding relationships and second corresponding relationships are stored in an assetized learning model pre-built using machine learning technology, and the assetized learning model is trained to execute the corresponding operation strategies generated based on energy data. The assetized learning model that meets the preset model accuracy threshold is defined as an assetized model and output.
[0073] As a preferred implementation of this embodiment, the load characteristics obtained in this embodiment can be calculated using a load characteristic formula, wherein the load characteristic formula is specifically:
[0074]
[0075] in, is the function of the load on the time series obtained by fitting, i is the response time required for load adjustment by the combination of different energy consumption terminals obtained by statistics, is a function of the time series based on the combination of different energy consumption terminals using the optimized load i, j is the number of the outdoor environmental factor, Q j () is the fitting influence factor of outdoor environmental factor numbered j on load, It represents the sum of the influencing factors of all q existing outdoor environmental factors on the load, t is the current moment, k is the duration required for prediction. It can be understood that this embodiment takes into account the response time required for load adjustment in different combinations of energy consumption terminals, and locates the predicted moment to t+ki, so as to improve the prediction accuracy (based on this design, when formulating the predicted duration, just add the corresponding i in k, that is, k=k0-i, where k0 is the predicted duration with the corresponding i added), LV(t+ki) is the calculated load characteristic at the moment t+ki. In a simple example, the load can be but is not limited to the energy consumption value at the moment t+ki.
[0076] As a preferred implementation of this embodiment, the fault characteristics obtained in this embodiment will be based on the data of the time series when the energy consumption terminal generates a fault to fix the fault mode, thereby obtaining the corresponding fault characteristics. Furthermore, the fault identification method adopted in this embodiment can be, but is not limited to, analyzing the thermal imaging spectrum of the equipment and analyzing the vibration spectrum of the equipment.
[0077] It should be noted that this embodiment uses existing machine learning technology to realize the construction of assetization model, for example, such as deep learning model, wherein any existing feature extraction technology is used to realize load feature extraction and fault feature extraction. It can be understood that the purpose of constructing assetization model in this embodiment is to realize autonomous processing of energy data by using assetization model, obtain corresponding load features and fault features, thereby providing a basis for the generation of memory operation strategy, and further autonomously generate operation strategy and optimize it for execution, so as to realize the assetization of energy data through optimized control of energy consumption.
[0078] Based on the above, this embodiment uses historical energy data and corresponding operating strategies to extract load characteristics and fault characteristics and establish relevant corresponding relationships, store and train assetized learning models, and realize accurate generation of corresponding operating strategies based on energy data. It overcomes the defect that traditional methods are difficult to quickly formulate effective operating strategies based on energy data, and improves the ability of the energy system to cope with different situations.
[0079] Specifically, load forecasting is as follows:
[0080] Acquire and analyze real-time energy data to obtain real-time energy consumption data, real-time indoor environment data, and real-time outdoor environment data;
[0081] Extracting real-time outdoor environment data and real-time indoor environment data based on time series to measure the real-time load characteristics of real-time energy consumption data of energy consumption terminals;
[0082] The real-time load characteristics are matched with the load characteristics to output the load characteristics that meet the preset load similarity threshold.
[0083] It should be noted that after obtaining the real-time energy consumption data, this embodiment uses the existing feature extraction technology to extract load features from the real-time energy consumption data, and performs similarity matching between the extracted features and the load features stored in the assetization model based on the existing similarity analysis technology, wherein the preset load similarity threshold is an empirical value formulated based on the experience known to those skilled in the art, and all load states that meet the load similarity threshold are output, providing a data basis for the subsequent screening of real-time load strategies.
[0084] Based on the above, this embodiment utilizes the acquisition and analysis of real-time energy data, extracts real-time load characteristics based on time series and performs similarity matching, thereby realizing accurate load prediction of real-time energy consumption data of energy consumption terminals, changing the situation where traditional methods are difficult to accurately predict load changes, and providing a basis for reasonably regulating the operating power of energy consumption terminals.
[0085] Specifically, fault identification is as follows:
[0086] Acquire and analyze real-time energy data to obtain real-time operation data of energy consumption terminals;
[0087] Extract real-time operation features of real-time operation data based on time series;
[0088] The real-time operation features are matched with the fault features for similarity, and the fault features that meet the preset fault similarity threshold are output.
[0089] It should be noted that, after obtaining the real-time energy consumption data, this embodiment uses the existing feature extraction technology to extract fault features from the real-time energy consumption data, and performs similarity matching between the extracted features and the fault features stored in the assetization model based on the existing similarity analysis technology, wherein the preset fault similarity threshold is an empirical value formulated based on the experience known to those skilled in the art, and all load states that meet the fault similarity threshold are output, providing a data basis for the subsequent screening of real-time fault strategies.
[0090] Based on the above, this embodiment utilizes the acquisition and analysis of real-time energy data, extracts real-time operation characteristics and performs similarity matching with fault characteristics, thereby achieving rapid and accurate identification of energy consumption terminal faults, solving the problem of low efficiency and easy misjudgment of traditional manual troubleshooting, and facilitating timely response measures to ensure the normal operation of the energy system.
[0091] Specifically, the operation strategy output is as follows:
[0092] Obtaining matched load characteristics and fault characteristics;
[0093] Based on the load characteristics, the corresponding first corresponding relationship is retrieved, and based on the first corresponding relationship, the corresponding operation strategy is retrieved, each operation strategy is simulated and run, and the simulated energy consumption generated during the operation is compared, and the operation strategy corresponding to the minimum value of the simulated energy consumption is output to obtain the real-time load strategy;
[0094] Based on the fault characteristics, the corresponding second corresponding relationship is retrieved, and based on the second corresponding relationship, the corresponding operation strategy is retrieved, each operation strategy is simulated and the simulated interference generated during the operation is compared, and the operation strategy corresponding to the minimum range of the simulated interference is output to obtain a real-time fault strategy.
[0095] It should be noted that this embodiment uses existing simulation operation technology to perform corresponding simulation operations. The minimum value of the simulated energy consumption obtained in this embodiment is the summed energy consumption data obtained when the energy consumption terminal is simulated. The minimum range of the simulated interference obtained in this embodiment is obtained by integrating the range obtained based on the records of the impact of historical faults.
[0096] Based on the above, this embodiment utilizes the corresponding relationship obtained by obtaining matching load characteristics and fault characteristics, simulates the operation strategy and compares the simulated energy consumption and simulated interference, and realizes the output of a real-time load strategy that can minimize the simulated energy consumption and a real-time fault strategy that can minimize the scope of simulated interference, optimizes the operating power adjustment method of the energy consumption terminal, and avoids the energy waste or insufficient supply caused by the inability to dynamically adjust power in the traditional method.
[0097] Specifically, the energy network is adjusted accordingly based on the identified faults, specifically:
[0098] Based on the acquired real-time fault strategy, the relevant equipment or system parameters in the energy network are adjusted for faults. The specific fault adjustments are as follows:
[0099] Switch the operation mode of the energy consumption terminal based on the real-time fault strategy, isolate the corresponding fault area, and call the backup energy consumption terminal corresponding to the fault area;
[0100] During the adjustment process, the frequency of extracting real-time fault features is increased, and the corresponding real-time fault strategy is updated until the fault is resolved.
[0101] Based on the above, this embodiment uses the acquired real-time fault strategy to switch the operation mode of the energy consumption terminal, isolate the fault area and call the backup terminal, while improving the fault feature extraction frequency update strategy, thereby achieving rapid response when a fault occurs and effectively controlling the scope of the fault impact, solving the problem of untimely fault handling and ineffective isolation of the fault area in the traditional way, and ensuring the stability of the energy system.
[0102] Specifically, the energy network is adjusted accordingly based on the output operation strategy, specifically:
[0103] Based on the acquired real-time load strategy, load adjustment is performed on relevant equipment or system parameters in the energy network. The load adjustment is specifically as follows:
[0104] Switch the operating power of energy consumption terminals based on real-time load strategies;
[0105] During the adjustment process, the frequency of extracting real-time load characteristics is increased, and the corresponding real-time load strategy is updated.
[0106] Based on the above, this embodiment uses the acquired real-time load strategy to switch the operating power of the energy consumption terminal, and at the same time improves the load feature extraction frequency update strategy, thereby realizing dynamic adjustment of the operating power of the energy consumption terminal according to the real-time situation, overcoming the disadvantage that the traditional method cannot flexibly adjust the power according to the real-time situation, and ensuring the energy supply balance and efficient operation of the energy system.
[0107] The second aspect of this embodiment discloses Figure 2 The system for processing energy data assets of the Internet of Things is shown, and the system is applicable to the above-mentioned method for processing energy data assets of the Internet of Things, and the system includes:
[0108] The energy data generation module is configured to: use the preset Internet of Things to collect data at various links of the energy network to generate energy data; wherein the energy data is used to characterize the operating status of the energy system;
[0109] The assetization module is configured to: run a preset assetization model to assetize energy data; wherein assetization includes load forecasting, fault identification, and operation strategy output;
[0110] An adjustment module, the adjustment module is configured to: make corresponding adjustments to the energy network based on the identified faults and / or output operation strategies.
[0111] It should be noted that the IoT energy data assetization processing system of the present embodiment corresponds to the aforementioned IoT energy data assetization processing method. Therefore, the contents not specifically described in the IoT energy data assetization processing system of the present embodiment may include but are not limited to the functional definition, working principle and technical effects, etc., which may refer to the records of the aforementioned IoT energy data assetization processing method and will not be elaborated in this text.
[0112] The third aspect of this embodiment discloses an electronic device, including: at least one processor and at least one memory, the memory is communicatively connected to the processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, the IoT energy data assetization processing method as described above is implemented.
[0113] Similarly, it should be noted that the electronic device of this embodiment corresponds to the aforementioned IoT energy data assetization processing method. Therefore, the contents not specifically described in the electronic device of this embodiment may include but are not limited to the function definition, working principle and technical effect, etc., which can all refer to the records of the aforementioned IoT energy data assetization processing method, and this text will not elaborate on them here.
[0114] In summary, the IoT energy data asset processing method, system and electronic equipment of this embodiment utilize the preset IoT to comprehensively collect data in all aspects of the energy network to generate energy data, and assetize the energy data in combination with the operation of the preset assetization model, as well as make targeted adjustments to the energy network based on the identified faults and output operation strategies, thereby achieving precise control of the operating status of the energy system, efficient handling and prevention of faults, and reasonable regulation of loads, thereby improving the overall intelligent management level of the energy system, and effectively solving the problems of incomplete data collection, low fault handling efficiency, and inaccurate load regulation in traditional energy management methods.
[0115] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein or their combination. For software implementation, part or all of the flow of the embodiment can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a computer can access. The computer-readable storage medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer.
[0116] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.
Claims
1. A method for processing energy data assets of the Internet of Things, characterized in that: The method includes: S1: using the preset Internet of Things to collect data at various links of the energy network to generate energy data; wherein the energy data is used to characterize the operating status of the energy system; S2: running a preset assetization model to assetize the energy data; wherein the assetization includes load forecasting, fault identification and operation strategy output; S3: Make corresponding adjustments to the energy network based on the identified faults and / or output operation strategies.
2. The method for processing IoT energy data assets according to claim 1 is characterized in that: The generation process of the energy data includes: Determine the key monitoring nodes in the energy network, install energy consumption monitoring devices and operation status monitoring devices at indoor energy consumption terminals, install indoor environmental status monitoring devices in indoor working environments, and install outdoor environmental status monitoring devices outdoors corresponding to the working environment; Use the Internet of Things communication protocol to aggregate the data collected by each key monitoring node to the corresponding preset data gateway; Perform preliminary data cleaning in the data gateway to remove obvious outliers and erroneous data based on the preset normal data range and logical rules; By using data fusion technology, the data from different data sources and in different formats are unified in data structure and encoding method to generate the energy data.
3. The method for processing IoT energy data assets according to claim 1 is characterized in that: The preset process of the assetization model includes: Obtain historical energy data and corresponding historical operation strategies; The load feature extraction and fault feature extraction are performed using historical energy data; the load feature extraction is specifically: extracting the impact of the outdoor environment on the load generated by the energy consumption terminal in the indoor environment based on the time series, and obtaining the corresponding load feature; the fault feature extraction is specifically: extracting the data generated by the energy consumption terminal at the time of the fault based on the time series, and obtaining the corresponding fault feature; Establishing a first correspondence between the load characteristic and the corresponding operation strategy and a second correspondence between the fault characteristic and the corresponding operation strategy; The load characteristics, the fault characteristics, the operation strategy, the first corresponding relationship and the second corresponding relationship are stored in an assetized learning model pre-built using machine learning technology, and the assetized learning model is trained to execute the corresponding operation strategy generated based on energy data. The assetized learning model that meets a preset model accuracy threshold is defined as the assetized model and output.
4. The method for processing IoT energy data assets according to claim 3 is characterized in that: The load forecast is specifically: Acquire and analyze real-time energy data to obtain real-time energy consumption data, real-time indoor environment data, and real-time outdoor environment data; Extracting the real-time load characteristics of the real-time outdoor environment data and the real-time indoor environment data to the real-time energy consumption data of the energy consumption terminal based on the time series; The real-time load feature is matched with the load features for similarity, and a load feature that meets a preset load similarity threshold is output.
5. The method for processing IoT energy data assets according to claim 4 is characterized in that: The fault identification is specifically: Acquire and analyze real-time energy data to obtain real-time operation data of energy consumption terminals; Extracting real-time operation features of the real-time operation data based on the time series; The real-time operation feature is matched with the fault feature for similarity, and the fault feature that meets a preset fault similarity threshold is output.
6. The method for processing IoT energy data assets according to claim 5 is characterized in that: The operation strategy output is specifically: Acquiring the matched load characteristics and the fault characteristics; Based on the load characteristics, the first corresponding relationship is retrieved, and based on the first corresponding relationship, the corresponding operation strategy is retrieved, each operation strategy is simulated and run, and the simulated energy consumption generated during the operation is compared, and the operation strategy corresponding to the minimum value of the simulated energy consumption is output to obtain a real-time load strategy; The second corresponding relationship is retrieved based on the fault feature, and the corresponding operation strategy is retrieved based on the second corresponding relationship. Each operation strategy is simulated and the simulated interference generated during the operation is compared. The operation strategy corresponding to the minimum range of the simulated interference is output to obtain a real-time fault strategy.
7. The method for processing IoT energy data assets according to claim 5 is characterized in that: Based on the identified faults, the energy network is adjusted accordingly, specifically: Based on the acquired real-time fault strategy, the relevant equipment or system parameters in the energy network are adjusted for faults. The specific fault adjustments are as follows: Switching the operation mode of the energy consumption terminal based on the real-time fault strategy, isolating the corresponding fault area, and calling the backup energy consumption terminal corresponding to the fault area; During the adjustment process, the frequency of extracting the real-time fault features is increased, and the corresponding real-time fault strategy is updated until the fault is resolved.
8. The method for processing IoT energy data assets according to claim 6 is characterized in that: The energy network is adjusted accordingly based on the output operation strategy, specifically: Based on the acquired real-time load strategy, load adjustment is performed on relevant equipment or system parameters in the energy network. The load adjustment is specifically as follows: Performing operating power switching of energy consumption terminals based on the real-time load strategy; During the adjustment process, the frequency of extracting the real-time load characteristics is increased, and the corresponding real-time load strategy is updated.
9. An IoT energy data asset processing system, the system is applicable to the IoT energy data asset processing method according to any one of claims 1 to 8, characterized in that: The system includes: An energy data generation module, wherein the energy data generation module is configured to: utilize a preset Internet of Things to collect data at various links of the energy network to generate energy data; wherein the energy data is used to characterize the operating status of the energy system; An assetization module, wherein the assetization module is configured to: run a preset assetization model to assetize the energy data; wherein the assetization includes load forecasting, fault identification, and operation strategy output; An adjustment module, wherein the adjustment module is configured to make corresponding adjustments to the energy network based on the identified faults and / or output operation strategies.
10. An electronic device, characterized in that: include: At least one processor and at least one memory, the memory being communicatively connected to the processor; the memory storing a computer program executable by the processor, and when the computer program is executed by the processor, the method for assetization of energy data of the Internet of Things as described in any one of claims 1 to 8 is implemented.