Power Internet of Things data analysis method, system and device

Abstract

The present invention provides a method, system and device for analyzing data of an electric power Internet of Things, wherein the method comprises obtaining data of electric power equipment within an analysis period; calculating the hourly energy consumption data of the electric power equipment according to the data of the electric power equipment; inputting the hourly energy consumption data into a state prediction model to obtain a prediction result of the operation state of the electric power equipment; the state prediction model is obtained by training with samples of the operation state of the electric power equipment. The present invention calculates the hourly energy consumption data by analyzing the data of the electric power equipment within the analysis period, and then predicts the operation state of the electric power equipment, which can detect abnormal operation of the equipment in advance and enhance the stability and reliability of the operation of the power system.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a method, system and device for analyzing data of an electric power Internet of Things. Background Art

[0002] As a new generation of technological revolution, the Internet of Things and cloud computing have been widely used in environmental protection, manufacturing and other fields. With the development of the power industry, it is imperative to integrate the information level of the power system through the integration of communication infrastructure and power system infrastructure resources, and then integrate the Internet of Things and cloud computing technologies into the power industry. Under this premise, the power Internet of Things data analysis method has also emerged.

[0003] Power Internet of Things devices and storage media can quickly and comprehensively collect sensor data from the power system, and at the same time process data services, form decisions, and support specific power services. At present, the way to realize the power Internet of Things is to use the collection device + server + platform method, through the publish / subscribe message mode, the collection device reports the data to the server, and the server forwards it to the platform.

[0004] However, in the prior art, IoT data analysis methods based on real-time processing can only judge the current status of the device and cannot achieve preventive device data analysis.

[0005] Therefore, it is of great practical value and significance to provide a delayed data analysis method that is compatible with the existing power Internet of Things system to provide predictive analysis of equipment operating status. Summary of the invention

[0006] The present invention provides a power Internet of Things data analysis method, system and device to solve the defect of the prior art that only real-time processing and analysis of equipment data is performed, and to achieve predictive analysis of the equipment operating status that is compatible with the existing power Internet of Things system.

[0007] The present invention provides a method for analyzing data of an electric power Internet of Things, comprising:

[0008] Obtaining power equipment data within the analysis period;

[0009] Calculating the hourly energy consumption data of the power equipment according to the power equipment data;

[0010] Inputting the hourly energy consumption data into a state prediction model to obtain an operating state prediction result of the power equipment;

[0011] The state prediction model is obtained by training with power equipment operating state samples.

[0012] According to a power Internet of Things data analysis method provided by the present invention, the step of calculating the hourly energy consumption data of the power equipment according to the power equipment data comprises:

[0013] According to the power equipment data in the sub-period, the energy consumption data of the power equipment in the sub-period is obtained, which is recorded as the energy consumption of the sub-period;

[0014] The sub-period is a subset of the analysis period;

[0015] The hourly energy consumption data of the electric power equipment is a collection of one or more sub-period data pairs; the sub-period data pairs are one-to-one corresponding sub-periods and sub-period energy consumption.

[0016] According to a method for analyzing data of an electric power Internet of Things provided by the present invention, the step of obtaining energy consumption data of electric power equipment in a sub-period based on the data of electric power equipment in a sub-period, recorded as energy consumption in a sub-period, comprises:

[0017] Divide the sub-period into multiple computing time units, and establish a data extraction task for each computing time unit and distribute it to different computing nodes;

[0018] Add the unit energy consumption of the operation time unit returned by the operation node to obtain the energy consumption of the sub-period;

[0019] The data extraction task refers to extracting unit data pairs based on the power equipment data within the operation time unit; the unit data pairs are a mapping of unit parameters to unit energy consumption; the unit parameters include any one or any combination of the phase voltage, phase current, phase angle and power of the power equipment.

[0020] According to a power Internet of Things data analysis method provided by the present invention, the step of adding up the unit energy consumption of the computing time unit returned by the computing node to obtain the sub-period energy consumption includes:

[0021] Set the weight of the i-th computing time unit ;

[0022] Calculate the intermediate energy consumption of the first i computing time units :

[0023]

[0024] In the formula, is the unit energy consumption of the i-th operation time unit, is the set value;

[0025] Calculate energy usage in sub-periods :

[0026]

[0027] Where A is the number of computing units.

[0028] According to a power Internet of Things data analysis method provided by the present invention, the step of obtaining power equipment data within the analysis period includes:

[0029] Read the power equipment data in the HBase cluster during the analysis period;

[0030] The power equipment data within the analysis period in the HBase cluster refers to: the HBase cluster reads the real-time power equipment data cached in the Kafka cluster, and analyzes the power equipment data within the analysis period in the power equipment historical data obtained after performing data persistence operation on the cached real-time power equipment data.

[0031] According to a power Internet of Things data analysis method provided by the present invention, the real-time power equipment data refers to: under the load balancing of the reverse proxy server Nginx, the data information generated by the power equipment in real time is connected to the server through address mapping, parsed by the MQTT server, and cached in the Kafka cluster to obtain the real-time power equipment data.

[0032] The present invention also provides a power Internet of Things data analysis system, including a Kafka cluster, an HBase cluster, a real-time data processing cluster and a state prediction cluster; the state prediction cluster includes a MapReduce cluster and a prediction model cluster;

[0033] The kafka cluster can cache power equipment data;

[0034] The real-time data processing cluster can obtain the power equipment data cached by the kafka cluster and compare it with the set first data set to obtain the real-time operating status of the power equipment;

[0035] The HBase cluster can obtain the power equipment data cached by the Kafka cluster and persist the power equipment data;

[0036] The MapReduce cluster can:

[0037] Obtaining power equipment data within the analysis period in the HBase cluster;

[0038] Calculating the hourly energy consumption data of the power equipment according to the power equipment data;

[0039] The prediction model cluster can compare the hourly energy consumption data with a set second data set to obtain a prediction result of the operating state of the power equipment; or input the hourly energy consumption data into a state prediction model to obtain a prediction result of the operating state of the power equipment;

[0040] The state prediction model is obtained by training with power equipment operating state samples.

[0041] The present invention also provides a power Internet of Things data analysis device, comprising an acquisition module, a calculation module and a prediction module;

[0042] The acquisition module is capable of acquiring the power equipment data within the analysis period;

[0043] The calculation module can calculate the hourly energy consumption data of the power equipment according to the power equipment data;

[0044] The prediction module can input the hourly energy consumption data into a state prediction model to obtain a prediction result of the operating state of the power equipment;

[0045] The state prediction model is obtained by training with power equipment operating state samples.

[0046] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-described methods for analyzing data of the electric power Internet of Things are implemented.

[0047] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the power Internet of Things data analysis method as described in any one of the above are implemented.

[0048] The electric power Internet of Things data analysis method, system and device provided by the present invention calculate the hourly energy consumption data by analyzing the electric power equipment data within a time period, and then predict the operating status of the electric power equipment. This can detect equipment operating abnormalities in advance and enhance the stability and reliability of the power system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 It is a flow chart of the electric power Internet of Things data analysis method provided by the present invention;

[0051] Figure 2 It is a structural schematic diagram of the power Internet of Things data analysis system provided by the present invention;

[0052] Figure 3It is a structural schematic diagram of the power Internet of Things data analysis device provided by the present invention;

[0053] Figure 4 It is a schematic diagram of the structure of the electric power Internet of Things system provided by an embodiment of the present invention;

[0054] Figure 5 is a schematic diagram of a device registration process provided by an embodiment of the present invention;

[0055] Figure 6 is a schematic diagram of a flow chart of device configuration provided by an embodiment of the present invention;

[0056] Figure 7 It is a schematic diagram of the process of processing the collected data reported by the device according to an embodiment of the present invention;

[0057] Figure 8 is a schematic diagram of the process of offline data processing provided by an embodiment of the present invention;

[0058] Fig. 9 It is a structural schematic diagram of the electronic device provided by the present invention.

[0059] Reference numerals:

[0060] 10: Kafka cluster; 20: HBase cluster; 30: real-time data processing cluster;

[0061] 40: state prediction cluster; 42: prediction model cluster; 41: MapReduce cluster;

[0062] 1: Acquisition module; 2: Operation module; 3: Prediction module;

[0063] 910: processor; 920: communication interface; 930: memory;

[0064] 940: Communication bus. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Combine the following Figure 1 Describe the power Internet of Things data analysis method of the present invention;

[0067] like Figure 1 As shown, an embodiment of the present invention provides a method for analyzing power Internet of Things data, including:

[0068] Step 100, obtaining power equipment data within the analysis period;

[0069] Step 200, calculating and obtaining hourly energy consumption data of the power equipment according to the power equipment data;

[0070] Step 300, inputting the hourly energy consumption data into a state prediction model to obtain an operating state prediction result of the power equipment;

[0071] The state prediction model is obtained by training with power equipment operating state samples.

[0072] This embodiment can be specifically implemented through the state prediction cluster 40 in the power Internet of Things system. The state prediction cluster 40 can be deployed in an existing power Internet of Things system, such as a power Internet of Things system based on an MQTT server; in the system, the state prediction cluster 40 is connected to a data persistence cluster, such as an Hbase cluster; the data persistence cluster is connected to a data cache cluster, such as a kafka cluster 10;

[0073] Since the data cache cluster is a necessary cluster of the power Internet of Things system, the method of this embodiment is compatible with the existing power Internet of Things system.

[0074] In this embodiment, the state prediction model can be a mathematical model trained based on power equipment operating status samples, or a neural network model trained based on power equipment operating status samples (or samples and labels), or a comparison model based on an expert database.

[0075] The beneficial effects of this embodiment are:

[0076] By analyzing the power equipment data within a period of time, the hourly energy consumption data can be calculated, and then the operating status of the power equipment can be predicted. This can detect equipment operating abnormalities in advance and enhance the stability and reliability of the power system operation.

[0077] According to the above embodiment, in this embodiment:

[0078] The step of calculating the hourly energy consumption data of the power equipment according to the power equipment data comprises:

[0079] According to the power equipment data in the sub-period, the energy consumption data of the power equipment in the sub-period is obtained, which is recorded as the energy consumption of the sub-period;

[0080] The sub-period is a subset of the analysis period;

[0081] The hourly energy consumption data of the electric power equipment is a collection of one or more sub-period data pairs; the sub-period data pairs are one-to-one corresponding sub-periods and sub-period energy consumption.

[0082] The step of obtaining the energy consumption data of the electric equipment in the sub-period according to the electric equipment data in the sub-period, recorded as the energy consumption of the sub-period, comprises:

[0083] Divide the sub-period into multiple computing time units, and establish a data extraction task for each computing time unit and distribute it to different computing nodes;

[0084] Add the unit energy consumption of the operation time unit returned by the operation node to obtain the energy consumption of the sub-period;

[0085] The data extraction task refers to extracting unit data pairs based on the power equipment data within the operation time unit; the unit data pairs are a mapping of unit parameters to unit energy consumption; the unit parameters include any one or any combination of the phase voltage, phase current, phase angle and power of the power equipment.

[0086] The execution subject of this embodiment may be the MapReduce cluster 41 in the state prediction cluster 40;

[0087] The execution subject of step 300 may be the prediction model cluster 42 in the state prediction cluster 40 .

[0088] The beneficial effects of this embodiment are:

[0089] This embodiment provides a distributed computing method for hourly energy consumption data. For the electric power Internet of Things system, the amount of data of the devices involved is relatively large. Using a distributed data computing method to obtain hourly energy consumption data is conducive to achieving high-concurrency computing, and provides a basis for the stable operation of the Internet of Things system in a large-scale data processing environment.

[0090] According to the above embodiment, in this embodiment:

[0091] The step of adding the unit energy consumption of the computing time unit returned by the computing node to obtain the sub-period energy consumption includes:

[0092] Set the weight of the i-th computing time unit ;

[0093] Calculate the intermediate energy consumption of the first i computing time units :

[0094]

[0095] In the formula, is the unit energy consumption of the i-th operation time unit, is the set value;

[0096] Calculate energy usage in sub-periods :

[0097]

[0098] Where A is the number of computing units.

[0099] In this embodiment, the weight The setting can be based on the time span of the operation time unit and the overall energy consumption within the time span. For example, 3-4 am is the energy consumption valley, so the operation time unit at 3-4 am can be set with a lower weight.

[0100] The beneficial effects of this embodiment are:

[0101] By introducing weights, the hourly energy consumption data can reflect the operating pressure of the power equipment to a certain extent, thereby providing a more accurate data basis for the subsequent prediction of the operating status of the power equipment and improving the accuracy of the prediction.

[0102] According to any of the above embodiments, in this embodiment:

[0103] The step of obtaining the power equipment data within the analysis period includes:

[0104] Read the power equipment data within the analysis period in the HBase cluster 20;

[0105] The power equipment data within the analysis period in the HBase cluster 20 refers to: the HBase cluster 20 reads the real-time power equipment data cached in the Kafka cluster 10, and analyzes the power equipment data within the analysis period in the power equipment historical data obtained after performing data persistence operation on the cached real-time power equipment data.

[0106] The real-time power equipment data refers to: under the load balancing of the reverse proxy server Nginx, the data information generated by the power equipment in real time is connected to the server through address mapping, parsed by the MQTT server, and cached in the kafka cluster 10 to obtain the real-time power equipment data.

[0107] This embodiment provides a specific data acquisition method, that is, using the power Internet of Things system including an MQTT server, an Nginx server, a kafka cluster 10, and an HBase cluster 20 to achieve the acquisition of power equipment data within the analysis period.

[0108] The beneficial effects of this embodiment are:

[0109] Since the data cache cluster, such as the kafka cluster 10, is a necessary cluster of the power Internet of Things system, the method of this embodiment is compatible with the existing power Internet of Things system, and on the basis of the existing Internet of Things system, provides an operating status prediction service for power equipment, which can detect equipment operation abnormalities in advance and enhance the stability and reliability of the power system operation.

[0110] The power Internet of Things data analysis system and device provided by the present invention are described below. The power Internet of Things data analysis system and device described below and the power Internet of Things data analysis method described above can be referenced to each other.

[0111] like Figure 2 As shown, the embodiment of the present invention further provides a power Internet of Things data analysis system, including a Kafka cluster 10, an HBase cluster 20, a real-time data processing cluster 30, and a state prediction cluster 40; the state prediction cluster 40 includes a MapReduce cluster 41 and a prediction model cluster 42;

[0112] The kafka cluster 10 is capable of caching power equipment data;

[0113] The real-time data processing cluster 30 can obtain the power equipment data cached by the kafka cluster 10, and compare it with the set first data set to obtain the real-time operating status of the power equipment;

[0114] The HBase cluster 20 can obtain the power equipment data cached by the Kafka cluster 10 and persist the power equipment data;

[0115] The MapReduce cluster 41 is capable of:

[0116] Obtaining power equipment data within the analysis period in the HBase cluster 20;

[0117] Calculating the hourly energy consumption data of the power equipment according to the power equipment data;

[0118] The prediction model cluster 42 can compare the hourly energy consumption data with the set second data set to obtain the operation state prediction result of the power equipment; or input the hourly energy consumption data into the state prediction model to obtain the operation state prediction result of the power equipment;

[0119] The state prediction model is obtained by training with power equipment operating state samples.

[0120] The beneficial effects of this embodiment are:

[0121] The system of this embodiment calculates the hourly energy consumption data by analyzing the power equipment data within a time period, and then predicts the operating status of the power equipment, which can detect equipment operating abnormalities in advance and enhance the stability and reliability of the power system operation.

[0122] like Figure 3 As shown, an embodiment of the present invention further provides a power Internet of Things data analysis device, including an acquisition module 1, a calculation module 2 and a prediction module 3;

[0123] The acquisition module 1 is capable of acquiring the power equipment data within the analysis period;

[0124] The calculation module 2 can calculate the hourly energy consumption data of the power equipment according to the power equipment data;

[0125] The prediction module 3 can input the hourly energy consumption data into a state prediction model to obtain a prediction result of the operation state of the power equipment;

[0126] The state prediction model is obtained by training with power equipment operating state samples.

[0127] The beneficial effects of this embodiment are:

[0128] The device of this embodiment calculates the hourly energy consumption data by analyzing the power equipment data within the time period, and then predicts the operating status of the power equipment, which can detect equipment operation abnormalities in advance and enhance the stability and reliability of the power system operation.

[0129] like Figure 4 As shown, this embodiment provides a power Internet of Things data analysis system based on the MQTT protocol, including:

[0130] A server that uses the MQTT protocol as the communication protocol is used as the message middleware;

[0131] Nginx server, used for reverse proxy and load balancing;

[0132] WEB server, used for collection equipment management such as registration, configuration and command issuance;

[0133] One or more combinations of relational databases such as MySQL and Oracle, used to store data such as device registration, configuration, and command issuance;

[0134] Redis non-relational data, used to store device online, configuration, command issuance and other status;

[0135] Kafka cluster 10, used to cache data reported by devices;

[0136] An HBase cluster 20 is used to persist data reported by devices; it includes a MapReduce cluster 41, which is used to delay processing of data reported by devices and provide support for data enabling;

[0137] The real-time data processing cluster 30 is used to consume data from the Kafka cluster 10 in real time and process data in real time, and also provides support for data enablement.

[0138] The MQTT server uses a separate node to deploy the Apache Apollo service. Each device, as a client of MQTT, needs to be authenticated for access to the platform. The authentication method is one machine and one password, and the device reports data and the control service issues commands using the SSL / TLS protocol asymmetric encryption method.

[0139] The Nginx server acts as a load balancing service between the MQTT server and the device and control service to balance the MQTT server publish / subscribe messages.

[0140] like Figure 7 As shown, when the client performs a subscription or publishing operation, the wss protocol is used to effectively hide the address of the backend service through the Nginx reverse proxy, and then the MQTT parses the message sent by the client after connecting to the server through address mapping, and stores the message in the kafka cluster 10. After the data is stored in the kafka cluster 10, the Hbase cluster consumes data from the kafka cluster 10, persists the data reported by the device, and then the MapReduce cluster 41 obtains the data reported by the device from Hbase regularly for processing, providing support for data enablement. After the data is stored in the kafka cluster 10, the real-time data service cluster consumes data from the kafka cluster 10 in real time and processes the data, which also provides support for data enablement.

[0141] like Figure 8 As shown, the offline data processing flow of the MapReduce cluster 41 is as follows.

[0142] The Map task of the MapReduce model takes the historical data of each device over a period of time as input, and generates a data pair that maps the phase voltage, phase current or one or more combinations of each device with the energy consumption data after data screening and verification.<key,value> , which means <phase voltage, phase current, energy consumption, weight>, that is, energy consumption is used as value, phase voltage, phase current, and weight are used as keys. After all Map tasks are completed, the system will generate several Reduce tasks. Reduce tasks are merged and processed to generate processing results, which are compared and analyzed with the expert database to obtain prediction results.

[0143] The WEB server communicates with one or more combinations of relational databases such as MySQL and Oracle, and communicates with Redis non-relational data to provide data storage services; it provides services to clients and third-party applications through a Restful-style API data interface based on the HTTP protocol.

[0144] like Figure 5 As shown, after the device reports the registration message, the registration message is processed, the device registration data is stored in the MySQL database, the device status is stored in the Redis database, and the registration message is replied to the device;

[0145] like Figure 6 As shown in the figure, when the client and the third-party platform configure the device, the configuration and command data are stored in the MySQL database through the configuration and command of the Nginx reverse proxy, the configuration and command status are stored in the Redis database, and the configuration and command are sent to the device. When the client and the third-party platform request the device to register, configure, and send command data, it is obtained from the MySQL database. When the client and the third-party platform request the device to register, configure, and send command status, it is obtained from the Redis database.

[0146] The beneficial effects of this embodiment are:

[0147] It provides a method for analyzing the data collected by the device through the device and storage media. It is suitable for high concurrency, supports millions of transmission terminals, ensures the real-time and storage of collected data, and performs real-time and delayed data processing respectively, providing support for data enabling. It has strong practicality, a wide range of applications, and has great promotion and application value.

[0148] Fig. 9 An example of a physical structure diagram of an electronic device is shown in FIG. Fig. 9 As shown, the electronic device may include: a processor 910, a communication interface 920, a memory 930 and a communication bus 940, wherein the processor 910, the communication interface 920 and the memory 930 communicate with each other through the communication bus 940. The processor 910 may call the logic instructions in the memory 930 to execute the power Internet of Things data analysis method, which includes: obtaining power equipment data within the analysis period; calculating the hourly energy consumption data of the power equipment according to the power equipment data; inputting the hourly energy consumption data into the state prediction model to obtain the operation state prediction result of the power equipment; the state prediction model is obtained by training the power equipment operation state sample.

[0149] In addition, the logic instructions in the above-mentioned memory 930 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0150] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the power Internet of Things data analysis method provided by the above methods, and the method includes: obtaining power equipment data within an analysis period; calculating the hourly energy consumption data of the power equipment based on the power equipment data; inputting the hourly energy consumption data into a state prediction model to obtain an operating state prediction result of the power equipment; the state prediction model is obtained by training with power equipment operating state samples.

[0151] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned power Internet of Things data analysis methods, the methods comprising: acquiring power equipment data within an analysis period; calculating the hourly energy consumption data of the power equipment based on the power equipment data; inputting the hourly energy consumption data into a state prediction model to obtain an operating state prediction result of the power equipment; the state prediction model is obtained by training with power equipment operating state samples.

[0152] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0153] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0154] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing power Internet of Things data, characterized in that: The method is applied to a MapReduce cluster, and includes: Obtaining power equipment data within the analysis period; Calculating the hourly energy consumption data of the power equipment according to the power equipment data; Input the hourly energy consumption data into the state prediction model to obtain the operation state prediction result of the power equipment; or compare the hourly energy consumption data with a set data set through a prediction model cluster to obtain the operation state prediction result of the power equipment; The state prediction model is obtained by training with power equipment operation state samples; The step of obtaining the power equipment data within the analysis period includes: Read the power equipment data within the analysis period in the HBase cluster; the power equipment data within the analysis period in the HBase cluster refers to: the HBase cluster reads the real-time power equipment data cached in the Kafka cluster, and analyzes the power equipment data within the analysis period in the power equipment historical data obtained after performing data persistence operation on the cached real-time power equipment data.

2. The electric power Internet of Things data analysis method according to claim 1 is characterized in that: The step of calculating the hourly energy consumption data of the power equipment according to the power equipment data comprises: According to the power equipment data in the sub-period, the energy consumption data of the power equipment in the sub-period is obtained, which is recorded as the energy consumption of the sub-period; The sub-period is a subset of the analysis period; The hourly energy consumption data of the electric power equipment is a collection of one or more sub-period data pairs; the sub-period data pairs are one-to-one corresponding sub-periods and sub-period energy consumption.

3. The electric power Internet of Things data analysis method according to claim 2 is characterized in that: The step of obtaining the energy consumption data of the electric equipment in the sub-period according to the electric equipment data in the sub-period, recorded as the energy consumption of the sub-period, comprises: Divide the sub-period into multiple computing time units, and establish a data extraction task for each computing time unit and distribute it to different computing nodes; Add the unit energy consumption of the operation time unit returned by the operation node to obtain the energy consumption of the sub-period; The data extraction task refers to extracting unit data pairs based on the power equipment data within the operation time unit; the unit data pairs are a mapping of unit parameters to unit energy consumption; the unit parameters include any one or any combination of the phase voltage, phase current, phase angle and power of the power equipment.

4. The electric power Internet of Things data analysis method according to claim 3 is characterized in that: The step of adding the unit energy consumption of the computing time unit returned by the computing node to obtain the sub-period energy consumption includes: Set the weight n of the i-th computing time unit i ; Calculate the intermediate energy P of the first i computing time units i ′ : Where P i is the unit energy consumption of the i-th operation time unit, P0 ′ is the set value; Calculate the energy consumption P of the sub-period: P=P A ′ Where A is the number of computing units.

5. The electric power Internet of Things data analysis method according to claim 1 is characterized in that: The real-time power equipment data refers to: under the load balancing of the reverse proxy server Nginx, the data information generated by the power equipment in real time is connected to the server through address mapping, parsed by the MQTT server, and cached in the kafka cluster to obtain the real-time power equipment data.

6. A power Internet of Things data analysis system, characterized in that: It includes a Kafka cluster, an HBase cluster, a real-time data processing cluster and a state prediction cluster; the state prediction cluster includes a MapReduce cluster and a prediction model cluster; The kafka cluster can cache power equipment data; The real-time data processing cluster can obtain the power equipment data cached by the kafka cluster and compare it with the set first data set to obtain the real-time operating status of the power equipment; The HBase cluster can obtain the power equipment data cached by the Kafka cluster and persist the power equipment data; The MapReduce cluster is capable of: Obtaining power equipment data within the analysis period in the HBase cluster; Calculating the hourly energy consumption data of the power equipment according to the power equipment data; The prediction model cluster can compare the hourly energy consumption data with a set second data set to obtain a prediction result of the operating state of the power equipment; or input the hourly energy consumption data into a state prediction model to obtain a prediction result of the operating state of the power equipment; The state prediction model is obtained by training with power equipment operating state samples.

7. A power Internet of Things data analysis device, characterized in that: Applied to MapReduce cluster, including acquisition module, operation module and prediction module; The acquisition module is capable of acquiring the power equipment data within the analysis period; The calculation module can calculate the hourly energy consumption data of the power equipment according to the power equipment data; The prediction module can input the hourly energy consumption data into the state prediction model to obtain the operation state prediction result of the power equipment; or compare the hourly energy consumption data with a set data set through a prediction model cluster to obtain the operation state prediction result of the power equipment; The state prediction model is obtained by training with power equipment operation state samples; Among them, the acquisition module can specifically read the power equipment data within the analysis period in the HBase cluster; the power equipment data within the analysis period in the HBase cluster refers to: the HBase cluster reads the real-time power equipment data cached in the kafka cluster, and performs data persistence operation on the cached real-time power equipment data to obtain the power equipment data within the analysis period in the power equipment historical data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the power Internet of Things data analysis method as described in any one of claims 1 to 5 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power Internet of Things data analysis method as described in any one of claims 1 to 5 are implemented.

Images