CN111091240A - Public institution electric power energy efficiency monitoring system and service method - Google Patents
Public institution electric power energy efficiency monitoring system and service method Download PDFInfo
- Publication number
- CN111091240A CN111091240A CN201911255736.2A CN201911255736A CN111091240A CN 111091240 A CN111091240 A CN 111091240A CN 201911255736 A CN201911255736 A CN 201911255736A CN 111091240 A CN111091240 A CN 111091240A
- Authority
- CN
- China
- Prior art keywords
- data
- analysis
- data acquisition
- protocol
- end processor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C19/00—Electric signal transmission systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/04—Protocols for data compression, e.g. ROHC
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/18—Multiprotocol handlers, e.g. single devices capable of handling multiple protocols
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/22—Parsing or analysis of headers
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a public institution electric power energy efficiency monitoring system and a service method, which comprises a data acquisition module, a data exchange interface, a data reading module, a front-end processor, a data analysis library and a display and display module, wherein the data acquisition module sends acquired information to the data reading module through the data exchange interface; the method has the advantages that the large data are analyzed by means of remote monitoring in different items, modern network technology, data warehouses, data models, data mining and other technical means are fully utilized, monitoring, analysis, diagnosis, publicity and reporting of energy consumption are achieved, and the energy supervision level is improved.
Description
Technical Field
The invention relates to the technical field of public institution energy efficiency monitoring, in particular to a public institution electric energy efficiency monitoring system and a service method.
Background
The application of energy management and analysis in various industries is a new requirement which is provided on the premise that the whole energy monitoring automation is continuously developed, and along with the continuous improvement of the automation degree, a large amount of energy data can be acquired, so that the problem of data analysis and utilization is solved. Through the verification test of the energy monitoring system, the real-time data of the data acquisition system can be better utilized, data basis is provided for energy management, the problem of energy use is found through the application of the real-time data, and management personnel are helped to make a decision to adjust measures for energy use. In view of the fact that in the energy efficiency management industry, a system integrating power distribution and power utilization also belongs to a new subject, the energy system needs to be managed and analyzed by combining the currently international leading scientific and technological technology, particularly the software technology, through a system verification test means, an effective analysis platform combining the domestic management characteristics is formed, and the problem of energy consumption is pointed out for managers.
The existing power utilization information acquisition system cannot meet the requirements of acquisition, management and analysis of various energy sources, only single energy source data are realized, the number of the accessed sensing devices is not enough, the acquired data volume is increased by geometric progression along with the improvement of data types and data acquisition frequency, and the existing data analysis technology cannot meet the requirements. However, the system and the physical architecture system can meet the requirements of acquisition, management and analysis of various types of energy of the current market demand, so that in order to quickly solve the market demand and quickly develop products for solving the low energy utilization rate condition of users, an energy supervision system can be researched on the basis of an electricity utilization information acquisition system, various energy consumption can be uniformly acquired, and the system and the method can be quickly applied.
Disclosure of Invention
The invention aims to provide a public institution electric power energy efficiency monitoring system and a service method, which can perform item-by-item remote monitoring, fully utilize technical means such as modern network technology, data warehouse, data model and data mining to perform big data analysis, realize monitoring, analysis, diagnosis, public indication and report of energy consumption, and improve the energy supervision level.
The technical scheme adopted by the invention is as follows:
the invention comprises a data acquisition module, a data exchange interface, a data reading module, a front-end processor, a data analysis library and a display and display module, wherein the data acquisition module sends acquired information to the data reading module through the data exchange interface, the data reading module reads data through a system protocol and then sends the read information to the front-end processor, the front-end processor simply analyzes the information and finally sends the data to the data analysis library, meanwhile, the original data is directly sent to the data analysis library by the data reading module for storage, and the data is displayed and displayed in real time after being analyzed by the data analysis library.
The data acquisition module adopts a data acquisition terminal to realize the access of devices such as a pressure sensor, a temperature and humidity sensor, an illumination sensor, an infrared detector and the like, and the communication mode mainly comprises an M _ BUS mode and an RS485 mode.
The data exchange interface realizes a large amount of socket access through a small amount of threads, and ensures that large-scale terminal access occupies less system resources.
The data reading module realizes simple filtering and analysis of data in a protocol adaptation mode, and data of different protocol types are sent to different data processing channels. And the data analysis loads a corresponding protocol library according to the protocol type, and calls a data analysis interface to realize the uniform analysis output of the data.
The front-end processor compresses and transmits the analyzed original value through a Snappy compression technology, and performs decompression processing after business processing acquires data.
The data analysis library realizes mass data storage and high-speed processing of the energy supervision data acquisition system through a cloud storage and cloud computing technology, improves the reliability and data capacity of the computing and storage system, and reduces the investment and operation cost of a computing center.
A service method of a public institution electric energy efficiency monitoring system comprises the following steps:
a: arranging a data acquisition module in a public environment to be monitored;
the data acquisition module needs to satisfy:
(1) data acquisition
a. The data acquisition terminal supports two data acquisition modes of acquisition according to a data center command and active timing acquisition, and the timing acquisition period can be configured from 10 minutes/time to 1 hour/time;
b. one data acquisition terminal supports data acquisition on not less than 128 metering device devices;
c. a data acquisition terminal should support data acquisition of metering devices of different energy types, including electric energy meters (including single-phase electric energy meters, three-phase electric energy meters, multifunctional electric energy meters), water meters, gas meters, heat (cold) meters and the like;
(2) data processing
a. The data acquisition terminal supports the analysis of the energy consumption data of the metering device;
b. adding additional information such as energy consumption type, time, building codes and the like into the data packet according to the format of the remote transmission data packet, and packaging the data;
(3) data storage
The data acquisition terminal is configured with a storage space not less than 16MB to support the storage of the energy consumption data for more than 7 days;
(4) data remote transmission
a. The data acquisition terminal is used for carrying out timed remote transmission on the acquired energy consumption data, generally, the uploading period of the itemized energy consumption data is regulated to be 10 minutes/time, and the uploading period of the non-itemized energy consumption data is regulated to be 1 hour/time;
b. the data acquisition terminal encrypts the data packet before remote transmission;
c. if the data cannot be transmitted at regular time due to the failure of the transmission network and the like, the data acquisition terminal performs breakpoint transmission by using the stored data after the transmission network recovers to be normal;
d. the data acquisition terminal supports concurrent data transmission to a plurality of data centers (servers);
b: the data acquisition module sends acquired information to the data reading module through the data exchange interface;
c: the data reading module reads data through a system protocol and then sends the read information to the front-end processor;
the system front-end processor adopts a port completion technology, realizes a large amount of socket access through a small amount of threads, and ensures that large-scale terminal access occupies less system resources; the front-end processor realizes simple filtering and analysis of data in a protocol adaptation mode, and data of different protocol types are sent to different data processing channels. The data analysis loads a corresponding protocol library according to the protocol type, and calls a data analysis interface to realize unified analysis output of the data; aiming at the analyzed data, the data is rapidly distributed and transmitted in a message bus encryption transmission mode; compressing and transmitting the analyzed original value through a Snappy compression technology, and decompressing after business processing acquires data;
d: the front-end processor simply analyzes the information and finally sends the data to a data analysis database;
the data analysis base realizes the mass data storage and high-speed processing of the energy supervision data acquisition system through a cloud storage and cloud computing technology, improves the reliability and data capacity of a computing and storage system, and reduces the investment operation cost of a computing center;
(1) establishing a decision tree: and (3) generating a decision tree: a process of generating a decision tree from a training sample set;
the training sample data set is a data set which has history according to actual needs and a certain comprehensive degree and is used for data analysis and processing;
(2) pruning of the decision tree: the pruning of the decision tree is the process of checking, correcting and repairing the decision tree generated at the last stage, and mainly comprises the steps of checking a preliminary rule generated in the process of generating the decision tree by using data in a new sample data set, and pruning branches influencing the accuracy of pre-balance;
(3) and (3) load prediction:
1. the establishment basis of the data model is not single, the load situation is predicted by a machine learning method aiming at load prediction, and a load situation prediction model based on an FOA-SVR algorithm is formed, the method combines the excellent nonlinear fitting capability of the SVR (vector regression) algorithm and the good global optimization capability of the FOA (fruit fly optimization algorithm), and the FOA is used for optimizing the load situation parameters, so that the blindness of parameter selection is avoided, and the scientificity of a load situation prediction preliminary model is improved;
2. the weight is determined by adopting a Delphi method for calculation and comprehensively evaluating and determining the weight by combining an industry experience case;
3. an RBF (radial basis function) neural network and a PSO-SVR algorithm (PSO: particle swarm optimization algorithm) are established through experiments for comparative analysis, and the excellent characteristics of the FOA-SVR algorithm are proved;
4. after weighted combination based on a basic algorithm, combining with the experience discussion of an expert group to finally form an initial load situation prediction model;
5. according to the operation of experiments and real data, the comparison and analysis are carried out through machine learning, the model parameters are continuously optimized by combining the optimization algorithm, and the accuracy of the prediction model is improved.
The invention comprises a data acquisition module, a data exchange interface, a data reading module, a front-end processor, a data analysis library and a display and display module, wherein the data acquisition module sends acquired information to the data reading module through the data exchange interface, the data reading module reads data through a system protocol and then sends the read information to the front-end processor, the front-end processor simply analyzes the information and finally sends the data to the data analysis library, meanwhile, the original data is directly sent to the data analysis library by the data reading module for storage, and the data is displayed and displayed in real time after being analyzed by the data analysis library.
The unified access technology of the multi-type metering sensing equipment is researched, and the self-adaptive access and unified management of the multi-type metering sensing equipment are realized; the communication networking technology of multi-protocol multi-channel metering sensing equipment is researched, and the ad hoc network and the self modeling of the metering sensing equipment are realized; the data acquisition and processing mode of the data acquisition terminal is researched, a standard, unified and open access standard of the metering sensing equipment is established, the friendly access of the metering sensing equipment is realized, and the configuration is simplified.
The energy supervision system acquisition platform based on the power consumption information acquisition system acquires multi-type data of the electric meter, and has the advantages of numerous data items, high data frequency and large data volume. Therefore, the high-speed reliable mass data transmission technology is researched, and the requirement of the energy supervision data acquisition platform on mass data transmission is met. The storage and processing technology of the mass data is researched, and the requirement of the energy supervision data acquisition platform on the mass data processing is met. The research realizes the mass data storage and high-speed processing of the energy supervision data acquisition system through the cloud storage and cloud computing technology, improves the reliability and data capacity of the computing and storage system, and reduces the investment operation cost of a computing center.
Drawings
FIG. 1 is a functional block diagram of the present invention;
FIG. 2 is a schematic block diagram of the load budget of the present invention;
FIG. 3 is a diagram of a weighting operation model according to the present invention.
Detailed Description
As shown in fig. 1, the data analysis system comprises a data acquisition module, a data exchange interface, a data reading module, a front-end processor, a data analysis library and a display and display module, wherein the data acquisition module sends acquired information to the data reading module through the data exchange interface, the data reading module reads data through a system protocol and then sends the read information to the front-end processor, the front-end processor simply analyzes the information and finally sends the data to the data analysis library, meanwhile, the original data is directly sent to the data analysis library by the data reading module for storage, and the data is displayed and displayed in real time after being analyzed by the data analysis library.
The data acquisition module adopts a data acquisition terminal to realize the access of devices such as a pressure sensor, a temperature and humidity sensor, an illumination sensor, an infrared detector and the like, and the communication mode mainly comprises an M _ BUS mode and an RS485 mode.
The data exchange interface realizes a large amount of socket access through a small amount of threads, and ensures that large-scale terminal access occupies less system resources.
The data reading module realizes simple filtering and analysis of data in a protocol adaptation mode, and data of different protocol types are sent to different data processing channels. And the data analysis loads a corresponding protocol library according to the protocol type, and calls a data analysis interface to realize the uniform analysis output of the data.
The front-end processor compresses and transmits the analyzed original value through a Snappy compression technology, and performs decompression processing after business processing acquires data.
The data analysis library realizes mass data storage and high-speed processing of the energy supervision data acquisition system through a cloud storage and cloud computing technology, improves the reliability and data capacity of the computing and storage system, and reduces the investment and operation cost of a computing center.
A service method of a public institution electric energy efficiency monitoring system comprises the following steps:
a: arranging a data acquisition module in a public environment to be monitored;
the data acquisition module needs to satisfy:
(1) data acquisition
a. The data acquisition terminal supports two data acquisition modes of acquisition according to a data center command and active timing acquisition, and the timing acquisition period can be configured from 10 minutes/time to 1 hour/time;
b. one data acquisition terminal supports data acquisition on not less than 128 metering device devices;
c. a data acquisition terminal should support data acquisition of metering devices of different energy types, including electric energy meters (including single-phase electric energy meters, three-phase electric energy meters, multifunctional electric energy meters), water meters, gas meters, heat (cold) meters and the like;
(2) data processing
a. The data acquisition terminal supports the analysis of the energy consumption data of the metering device;
b. adding additional information such as energy consumption type, time, building codes and the like into the data packet according to the format of the remote transmission data packet, and packaging the data;
(3) data storage
The data acquisition terminal is configured with a storage space not less than 16MB to support the storage of the energy consumption data for more than 7 days;
(4) data remote transmission
a. The data acquisition terminal is used for carrying out timed remote transmission on the acquired energy consumption data, generally, the uploading period of the itemized energy consumption data is regulated to be 10 minutes/time, and the uploading period of the non-itemized energy consumption data is regulated to be 1 hour/time;
b. the data acquisition terminal encrypts the data packet before remote transmission;
c. if the data cannot be transmitted at regular time due to the failure of the transmission network and the like, the data acquisition terminal performs breakpoint transmission by using the stored data after the transmission network recovers to be normal;
d. the data acquisition terminal supports concurrent data transmission to a plurality of data centers (servers);
b: the data acquisition module sends acquired information to the data reading module through the data exchange interface;
c: the data reading module reads data through a system protocol and then sends the read information to the front-end processor;
the system front-end processor adopts a port completion technology, realizes a large amount of socket access through a small amount of threads, and ensures that large-scale terminal access occupies less system resources; the front-end processor realizes simple filtering and analysis of data in a protocol adaptation mode, and data of different protocol types are sent to different data processing channels. The data analysis loads a corresponding protocol library according to the protocol type, and calls a data analysis interface to realize unified analysis output of the data; aiming at the analyzed data, the data is rapidly distributed and transmitted in a message bus encryption transmission mode; compressing and transmitting the analyzed original value through a Snappy compression technology, and decompressing after business processing acquires data;
d: the front-end processor simply analyzes the information and finally sends the data to a data analysis database;
the data analysis base realizes the mass data storage and high-speed processing of the energy supervision data acquisition system through a cloud storage and cloud computing technology, improves the reliability and data capacity of a computing and storage system, and reduces the investment operation cost of a computing center;
(1) establishing a decision tree: and (3) generating a decision tree: a process of generating a decision tree from a training sample set;
the training sample data set is a data set which has history according to actual needs and a certain comprehensive degree and is used for data analysis and processing;
(2) pruning of the decision tree: the pruning of the decision tree is the process of checking, correcting and repairing the decision tree generated at the last stage, and mainly comprises the steps of checking a preliminary rule generated in the process of generating the decision tree by using data in a new sample data set, and pruning branches influencing the accuracy of pre-balance;
(3) and (3) load prediction:
as shown in fig. 2, 1, the basis for establishing a data model is not single, and for load prediction, a load situation is predicted by using a machine learning method to form a load situation prediction model based on an FOA-SVR algorithm, the load situation parameter is optimized by using FOA in combination with the excellent nonlinear fitting capability of the SVR (vector regression) algorithm and the good global optimization capability of the FOA (drosophila optimization algorithm), so that the blindness of parameter selection is avoided, and the scientificity of a load situation prediction preliminary model is improved;
2. the weight is determined by adopting a Delphi method for calculation and comprehensively evaluating and determining the weight by combining an industry experience case;
3. an RBF (radial basis function) neural network and a PSO-SVR algorithm (PSO: particle swarm optimization algorithm) are established through experiments for comparative analysis, and the excellent characteristics of the FOA-SVR algorithm are proved;
as shown in fig. 3, 4, after the weighted combination based on the basic algorithm, combining with the experience study of the expert group, finally forming an initial load situation prediction model;
5. according to the operation of experiments and real data, the comparison and analysis are carried out through machine learning, the model parameters are continuously optimized by combining the optimization algorithm, and the accuracy of the prediction model is improved.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The access specification of the metering sensing equipment is opened, the friendly access of the metering sensing equipment is realized, and the configuration is simplified.
The terminal organically integrates functions of metering, centralized meter reading, environment monitoring and the like by using a power electronic technology, an automatic control technology and a digital signal processing technology to form integrated platform equipment with functions of resource sharing, data sharing, equipment metering, comprehensive management and the like.
A data acquisition terminal is developed to realize the access of various water, electricity, gas, heat meters and the like, and the communication modes comprise RS485, M _ BUS, micropower wireless and other modes; the realization is to the access of equipment such as various environmental data equipment, pressure sensor, temperature and humidity sensor, illuminance sensor, infrared detector, and the communication mode mainly has two kinds of M _ BUS and RS 485. The data acquisition terminal also has the following main functional performances:
data acquisition
a. The data acquisition terminal supports two data acquisition modes of acquisition according to a data center command and active timing acquisition, and the timing acquisition period can be configured from 10 minutes/time to 1 hour/time.
b. One data acquisition terminal should support data acquisition on not less than 128 metering device devices.
c. A data acquisition terminal supports data acquisition of metering devices with different energy types, including electric energy meters (including single-phase electric energy meters, three-phase electric energy meters and multifunctional electric energy meters), water meters, gas meters, heat (cold) meters and the like.
Data processing
a. The data acquisition terminal should support the analysis of the energy consumption data of the metering device.
b. And adding additional information such as energy consumption type, time, building codes and the like into the data packet according to the format of the remote transmission data packet, and packaging the data.
Data storage
The data acquisition terminal should be configured with a storage space not less than 16MB to support the storage of the energy consumption data for more than 7 days.
Data remote transmission
a. The data acquisition terminal is used for carrying out timing remote transmission on the acquired energy consumption data, and generally, the uploading period of the itemized energy consumption data is regulated to be 10 minutes/time, and the uploading period of the non-itemized energy consumption data is regulated to be 1 hour/time.
b. And the data acquisition terminal encrypts the data packet before remote transmission.
c. If the data cannot be transmitted at regular time due to the transmission network fault and other reasons, the data acquisition terminal should use the stored data to perform breakpoint transmission after the transmission network recovers to normal.
d. The data acquisition terminal should support the concurrent transmission of data to multiple data centers (servers).
Configuration and maintenance
a. The data acquisition terminal should have local configuration and management functions.
b. The data acquisition terminal should support receiving commands such as inquiry, time correction and the like from a system data center.
c. The data acquisition terminal should support the positioning and diagnosis of the fault of the data acquisition subsystem and support the reporting of fault information to the sub-platform data center.
d. The replacement of the fault metering device cannot affect the normal work of other parts of the data acquisition terminal.
e. The data acquisition terminal has an automatic recovery function, and can recover a normal working state from a fault under the unattended condition.
Others
a. The data acquisition terminal is required to meet the relevant electromagnetic compatibility standard requirements of the country and the industry.
b. The Mean Time Between Failures (MTBF) of the data collection terminal should be no less than 3 ten thousand hours.
c. The data acquisition terminal should use a low-power embedded system, the power should be less than 20W, and a PC-based system should not be used.
2. Large-scale measurement data access technology
A large-scale terminal unified access technology; multi-type, multi-protocol data parsing techniques; a data security transmission technology; the large-scale measurement data compression technology reduces the network transmission pressure.
The system front-end processor adopts a port completion technology, realizes a large amount of socket access through a small amount of threads, and ensures that large-scale terminal access occupies less system resources.
The front-end processor realizes simple filtering and analysis of data in a protocol adaptation mode, and data of different protocol types are sent to different data processing channels. And the data analysis loads a corresponding protocol library according to the protocol type, and calls a data analysis interface to realize the uniform analysis output of the data.
And aiming at the analyzed data, the data is rapidly distributed and transmitted in a message bus encryption transmission mode.
And compressing and transmitting the analyzed original value through a Snappy compression technology, and decompressing after business processing acquires data.
3. Measurement data processing technology based on cloud computing
The energy supervision system acquisition platform based on the power utilization information acquisition system acquires various types of data such as water, electricity, gas, heat, environment and the like, and has numerous data items, high data frequency and large data volume. Therefore, the high-speed reliable mass data transmission technology is researched, and the requirement of the energy supervision data acquisition platform on mass data transmission is met. The storage and processing technology of the mass data is researched, and the requirement of the energy supervision data acquisition platform on the mass data processing is met. The research realizes the mass data storage and high-speed processing of the energy supervision data acquisition system through the cloud storage and cloud computing technology, improves the reliability and data capacity of the computing and storage system, and reduces the investment operation cost of a computing center.
Decision tree
A decision tree algorithm is a method of approximating discrete function values. It is a typical classification method that first processes the data, generates readable rules and decision trees using a generalisation algorithm, and then uses the decisions to analyze the new data. In essence, a decision tree is a process of classifying data through a series of rules.
How to construct a decision tree with high precision and small scale is the core content of the decision tree algorithm. Decision tree construction can be performed in two steps. First, generation of a decision tree: a process of generating a decision tree from a training sample set. In general, a training sample data set is a data set which has a history according to actual needs and a certain degree of integration and is used for data analysis processing. Step two, pruning the decision tree: the pruning of the decision tree is a process of checking, correcting and repairing the decision tree generated at the previous stage, and is mainly to use data in a new sample data set (called a test data set) to check a preliminary rule generated in the process of generating the decision tree and prune branches influencing the accuracy of pre-balance.
Second, load prediction
There are 5 steps:
1. the establishment basis of the data model is not single, the load situation is predicted by a machine learning method aiming at load prediction, and a load situation prediction model based on an FOA-SVR algorithm is formed.
2. The weight is determined by calculating by using a Delphi method and comprehensively evaluating and determining the weight by combining with an industry experience case.
3. The excellent characteristics of the FOA-SVR algorithm are proved by establishing an RBF (radial basis function) neural network and a PSO-SVR algorithm (PSO: particle swarm optimization algorithm) through experiments for comparative analysis.
4. And after the weighted combination based on the basic algorithm is combined, an initial load situation prediction model is finally formed by combining the experience study of expert groups.
5. According to the operation of experiments and real data, the comparison and analysis are carried out through machine learning, the model parameters are continuously optimized by combining the optimization algorithm, and the accuracy of the prediction model is improved.
4. Power quality monitoring
The power quality detection is actually a data processing system. The power quality detection system analyzes and processes the acquired data and transmits the result to the core control room to provide a basis for unit workers to perform the next processing.
The power quality detection system uses the monitoring point as the data unit. There is consistency in the data format at each watch point, and each watch point has independence and integrity. And an HBase is adopted in the system to store the acquired data, the number of the monitoring point is used as a row key in a table, and a MopRobuee task is used for processing data of each monitoring point, so that the working efficiency of the system is improved.
The system is built on a PC server cluster of virtualization technology. The system does not directly store the data in the HDFS, but stores the data in the HBase to manage mass detection data. And the HIDFS is used at the bottom layer of the HBase to complete the data storage task, so that the data is acquired and processed according to the monitoring point number, and finally the analysis result of the data is stored in the SQLServen database. And the platform distributes a MopReduce operation for each power quality index, and the data of each monitoring point is taken as a sub-operation of the operation in each operation. The entire job is completed after each sub-job is completed. And in order to ensure the orderly operation, a work map of MapReduce is constructed according to the dependency relationship of each power quality index analysis process.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A utility power efficiency monitoring system, its characterized in that: the data analysis system comprises a data acquisition module, a data exchange interface, a data reading module, a front-end processor, a data analysis library and a display and display module, wherein the data acquisition module sends acquired information to the data reading module through the data exchange interface, the data reading module reads data through a system protocol and sends the read information to the front-end processor, the front-end processor simply analyzes the information, the data are finally sent to the data analysis library, meanwhile, the original data are directly sent to the data analysis library by the data reading module to be stored, and the data are displayed and displayed in real time after being analyzed by the data analysis library.
2. The utility power efficiency monitoring system of claim 1, wherein: the data acquisition module adopts a data acquisition terminal to realize the access of devices such as a pressure sensor, a temperature and humidity sensor, an illumination sensor, an infrared detector and the like, and the communication mode mainly comprises an M _ BUS mode and an RS485 mode.
3. The utility power efficiency monitoring system of claim 2, wherein: the data exchange interface realizes a large amount of socket access through a small amount of threads, and ensures that large-scale terminal access occupies less system resources.
4. The utility power efficiency monitoring system of claim 3, wherein: the data reading module realizes simple filtering and analysis of data in a protocol adaptation mode, and different protocol types of data are sent to different data processing channels; and the data analysis loads a corresponding protocol library according to the protocol type, and calls a data analysis interface to realize the uniform analysis output of the data.
5. The utility power efficiency monitoring system of claim 2, wherein: the front-end processor compresses and transmits the analyzed original value through a Snappy compression technology, and performs decompression processing after business processing acquires data.
6. The utility power efficiency monitoring system of claim 2, wherein: the data analysis library realizes mass data storage and high-speed processing of the energy supervision data acquisition system through a cloud storage and cloud computing technology, improves the reliability and data capacity of the computing and storage system, and reduces the investment and operation cost of a computing center.
7. The service method of the utility power energy efficiency monitoring system according to claim 1, characterized in that: the method comprises the following steps:
a: arranging a data acquisition module in a public environment to be monitored;
the data acquisition module needs to satisfy:
(1) data acquisition
a. The data acquisition terminal supports two data acquisition modes of acquisition according to a data center command and active timing acquisition, and the timing acquisition period can be configured from 10 minutes/time to 1 hour/time;
b. one data acquisition terminal supports data acquisition on not less than 128 metering device devices;
c. a data acquisition terminal should support data acquisition of metering devices of different energy types, including electric energy meters (including single-phase electric energy meters, three-phase electric energy meters, multifunctional electric energy meters), water meters, gas meters, heat (cold) meters and the like;
(2) data processing
a. The data acquisition terminal supports the analysis of the energy consumption data of the metering device;
b. adding additional information such as energy consumption type, time, building codes and the like into the data packet according to the format of the remote transmission data packet, and packaging the data;
(3) data storage
The data acquisition terminal is configured with a storage space not less than 16MB to support the storage of the energy consumption data for more than 7 days;
(4) data remote transmission
a. The data acquisition terminal is used for carrying out timed remote transmission on the acquired energy consumption data, generally, the uploading period of the itemized energy consumption data is regulated to be 10 minutes/time, and the uploading period of the non-itemized energy consumption data is regulated to be 1 hour/time;
b. the data acquisition terminal encrypts the data packet before remote transmission;
c. if the data cannot be transmitted at regular time due to the failure of the transmission network and the like, the data acquisition terminal performs breakpoint transmission by using the stored data after the transmission network recovers to be normal;
d. the data acquisition terminal supports concurrent data transmission to a plurality of data centers (servers);
b: the data acquisition module sends acquired information to the data reading module through the data exchange interface;
c: the data reading module reads data through a system protocol and then sends the read information to the front-end processor;
the system front-end processor adopts a port completion technology, realizes a large amount of socket access through a small amount of threads, and ensures that large-scale terminal access occupies less system resources; the front-end processor realizes simple filtering and analysis of data in a protocol adaptation mode, and data of different protocol types are sent to different data processing channels; the data analysis loads a corresponding protocol library according to the protocol type, and calls a data analysis interface to realize unified analysis output of the data; aiming at the analyzed data, the data is rapidly distributed and transmitted in a message bus encryption transmission mode; compressing and transmitting the analyzed original value through a Snappy compression technology, and decompressing after business processing acquires data;
d: the front-end processor simply analyzes the information and finally sends the data to a data analysis database;
the data analysis base realizes the mass data storage and high-speed processing of the energy supervision data acquisition system through a cloud storage and cloud computing technology, improves the reliability and data capacity of a computing and storage system, and reduces the investment operation cost of a computing center;
establishing a decision tree: and (3) generating a decision tree: a process of generating a decision tree from a training sample set;
the training sample data set is a data set which has history according to actual needs and a certain comprehensive degree and is used for data analysis and processing;
pruning of the decision tree: the pruning of the decision tree is the process of checking, correcting and repairing the decision tree generated at the last stage, and mainly comprises the steps of checking a preliminary rule generated in the process of generating the decision tree by using data in a new sample data set, and pruning branches influencing the accuracy of pre-balance;
and (3) load prediction:
①, the establishment basis of the data model is not single, and the load situation is predicted by a machine learning method aiming at load prediction to form a load situation prediction model based on an FOA-SVR algorithm, the method combines the excellent nonlinear fitting capability of the SVR (vector regression) algorithm and the good global optimization capability of the FOA (fruit fly optimization algorithm), and the FOA is used for optimizing the load situation parameters, thereby avoiding the blindness of parameter selection and improving the scientificity of the load situation prediction preliminary model;
②, calculating by using a Delphi method, and comprehensively evaluating and determining the weight by combining with an industry experience case;
③, establishing an RBF (radial basis function) neural network and a PSO-SVR algorithm (PSO: particle swarm optimization algorithm) through experiments to carry out comparative analysis, and proving the excellent characteristics of the FOA-SVR algorithm;
④, after weighted combination based on basic algorithm, combining with experience study of expert group, finally forming initial load situation prediction model;
⑤ according to the operation of experiment and real data, the comparison analysis is carried out by machine learning, the model parameters are continuously optimized by combining the optimization algorithm, and the accuracy of the prediction model is improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911255736.2A CN111091240A (en) | 2019-12-10 | 2019-12-10 | Public institution electric power energy efficiency monitoring system and service method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911255736.2A CN111091240A (en) | 2019-12-10 | 2019-12-10 | Public institution electric power energy efficiency monitoring system and service method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111091240A true CN111091240A (en) | 2020-05-01 |
Family
ID=70394857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911255736.2A Pending CN111091240A (en) | 2019-12-10 | 2019-12-10 | Public institution electric power energy efficiency monitoring system and service method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111091240A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112231039A (en) * | 2020-10-23 | 2021-01-15 | 岭东核电有限公司 | Work order information statistical method and device, computer equipment and storage medium |
| CN112394222A (en) * | 2020-11-19 | 2021-02-23 | 国网山西省电力公司临汾供电公司 | Load comparison method and system for line loss monitoring |
| CN113064942A (en) * | 2020-11-03 | 2021-07-02 | 国网浙江省电力有限公司绍兴供电公司 | Environment-friendly monitoring system and method based on electric power big data analysis |
| CN113689112A (en) * | 2021-08-20 | 2021-11-23 | 国网湖南省电力有限公司节能管理分公司 | Smart energy station energy efficiency evaluation method and system using cloud computing to improve analytic hierarchy process |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651633A (en) * | 2016-10-09 | 2017-05-10 | 国网浙江省电力公司信息通信分公司 | Power utilization information acquisition system and method based on big data technology |
-
2019
- 2019-12-10 CN CN201911255736.2A patent/CN111091240A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651633A (en) * | 2016-10-09 | 2017-05-10 | 国网浙江省电力公司信息通信分公司 | Power utilization information acquisition system and method based on big data technology |
Non-Patent Citations (4)
| Title |
|---|
| 占勇,程浩忠,丁屹峰,吕干云,孙毅斌,张帆,张昊: "电能质量监测分析系统的设计与开发" * |
| 李冬辉;尹海燕;郑博文;: "基于MFOA-GRNN模型的年电力负荷预测" * |
| 陈梅;张永坚;牛祺飞;: "公共建筑能耗监测系统研究" * |
| 韩朝;张东宁;吴彦文;程康婴;张红兵;: "企业用电设备能效监测信息系统的设计与实现" * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112231039A (en) * | 2020-10-23 | 2021-01-15 | 岭东核电有限公司 | Work order information statistical method and device, computer equipment and storage medium |
| CN112231039B (en) * | 2020-10-23 | 2023-09-19 | 岭东核电有限公司 | Work order information statistical method, device, computer equipment and storage medium |
| CN113064942A (en) * | 2020-11-03 | 2021-07-02 | 国网浙江省电力有限公司绍兴供电公司 | Environment-friendly monitoring system and method based on electric power big data analysis |
| CN112394222A (en) * | 2020-11-19 | 2021-02-23 | 国网山西省电力公司临汾供电公司 | Load comparison method and system for line loss monitoring |
| CN113689112A (en) * | 2021-08-20 | 2021-11-23 | 国网湖南省电力有限公司节能管理分公司 | Smart energy station energy efficiency evaluation method and system using cloud computing to improve analytic hierarchy process |
| CN113689112B (en) * | 2021-08-20 | 2023-06-13 | 国网湖南省电力有限公司节能管理分公司 | Intelligent energy station energy efficiency evaluation method and system by utilizing cloud computing improved analytic hierarchy process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111783846B (en) | Intelligent energy consumption service cooperative control system and method | |
| CN111091240A (en) | Public institution electric power energy efficiency monitoring system and service method | |
| CN105608758B (en) | A kind of big data analysis platform device and method calculated based on algorithm configuration and distributed stream | |
| CN112488558A (en) | Energy consumption monitoring and analyzing system based on industrial internet | |
| JP5616330B2 (en) | Method and system for managing a power grid | |
| CN107330056B (en) | Wind power plant SCADA system based on big data cloud computing platform and operation method thereof | |
| CN109151072A (en) | A kind of edge calculations system based on mist node | |
| CN102955977A (en) | Energy efficiency service method and energy efficiency service platform adopting same on basis of cloud technology | |
| CN107909300A (en) | Intelligent plant management platform and method | |
| CN102855525B (en) | A kind of resident's load prediction analytic system and method | |
| CN101763598A (en) | Electrical energy management system | |
| CN114493500A (en) | Energy equipment management method and device based on digital twin technology | |
| CN113240289A (en) | Power grid dispatching control system operation state evaluation method and system | |
| CN102931625B (en) | Online state maintenance intelligent decision analysis device used for relay protection device, and signal processing method and application thereof | |
| CN101673363A (en) | Method and system for evaluating energy-consuming efficiency | |
| CN102929827A (en) | Wireless sensor data acquisition cluster for industrial-and-mining-enterprise-oriented safety production cloud service platform | |
| CN114169570A (en) | Smart energy management platform based on Internet of things and cloud computing technology | |
| CN113516331A (en) | Building data processing method and device | |
| CN116933952B (en) | Park low-carbon energy scheduling system based on visualization of Internet of things | |
| CN114297290A (en) | Electric power marketing data sharing application platform | |
| CN113723684A (en) | Device and method for load prediction and energy management of enterprise power users | |
| CN115730749B (en) | Power dispatching risk early warning method and device based on fusion power data | |
| CN116522746A (en) | Power distribution hosting method for high-energy-consumption enterprises | |
| CN114997574A (en) | Power distribution station area elastic resource management method and device based on service middling station | |
| CN205176932U (en) | Data collection and transmission system for intelligence measurement platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |