96 results about "Utilization behavior" patented technology

The invention discloses power utilization mode classification and control method based on user behavior characteristics. With an improved secondary clustering model built by use of a secondary clustering method, the load point of each day of the same user in one year in an industrial park is taken as a characteristic vector, the daily power utilization characteristics of the user can be concluded from a clustering result, and a plurality of typical power utilization modes of the enterprise user can be provided, and therefore, basis can be provided for load prediction, fault diagnosis, electricity pricing and the like in the industrial park; furthermore, the optimal plane power utilization mode in demand side management can be selected by virtue of optimization function modeling on load data; the model is advantageous for a power supply company to reduce the loss of electricity selling profit as much as possible under the premise of guaranteeing power supply; at last, a user power utilization behavior mode library in the industrial park built on the basis is capable of comparing a new settling enterprise inconvenient to model with the modelled typical user mode and obtaining the load characteristics of the new settling enterprise by virtue of analogizing, and therefore, the planning efficiency of the park can be improved.

The invention discloses a non-intrusive load identification method and a non-intrusive load identification device. The non-intrusive load identification method comprises steps that electricity utilization behavior habits of users are counted to acquire first data; an electricity utilization load standard characteristic database is established; a voltage discrete signal and a current discrete signal sampled on a power supply entrance are acquired; the acquired voltage discrete signal and the acquired current discrete signal are preprocessed; load characteristics are calculated according to the transient voltages corresponding to various sampling points in the voltage discrete signal of the power supply entrance and the transient currents corresponding to the various sampling points in the current discrete signal of the power supply entrance; the load identification is carried out according to the load characteristics, and second data is acquired; the weighting of the first data and the second data is carried out, and the type of the load is identified. The technical problem of the prior art of the low accuracy of the load identification during non-intrusive load monitoring is solved.

The invention discloses a system and method for managing line loss of a power grid in real time. The system comprises an automatic data management server, a center database, a real-time line loss management module and a plurality of work stations. The output end of the automatic data management server is connected with the input end of the centre database through a network; the center database and the real-time line loss management module are communicated with each other; and the output end of the real-time line loss management module is connected with each work station through a network. By using an SG186 system data and remote meter reading data as bases, the refined management of the line loss can be realized, the problems existing in the existing line loss management are effectively solved, and various metering faults and illegal power utilization behaviors can be found out in time, so that measures can be adopted in time. Therefore, the purpose of reducing the line loss is achieved.

The invention discloses a power consumer electricity stealing behavior analysis method based on big data and machine learning. The method comprises the following steps: 1, extracting a large amount ofuser electricity consumption data, and establishing an electricity consumption behavior pattern map by using a clustering algorithm; 2, analyzing a clustering result, and obtaining a normal electricity utilization behavior mode and a behavior mode to which an electricity stealing user belongs in combination with business experience and actual data; 3, on the basis of the behavior pattern to whichthe electricity larceny user belongs, extracting electricity consumption behavior characteristics of the user in the mode, and establishing an algorithm analysis model; 4, training and evaluating themodel by using the test data set and the training data set to obtain an optimal model; 5, monitoring the abnormal action of the user by combining line loss, metering abnormity and the like of the transformer area; and 6, tracking and monitoring the highly suspected electricity stealing user or generating an on-site patrol work order and a processing system. The invention discloses a correspondinganalysis processing system.

The invention discloses an intelligent building microgrid power utilization behavior identification method. The intelligent building microgrid power utilization behavior identification method is characterized in that power utilization big data is obtained through an intelligent building microgrid power utilization data acquisition terminal and monitoring of each environment sensor; then the obtained data is subjected to pretreatments (data integration, data filling and feature normalization); the load feature parameter of each powered device is extracted from a pretreated data sample by means of a kernel principal component analysis method; the environment factor of each power utilization behavior feature of the user and the contribution rates of different powered devices, i.e., the feature weight of each influence factor of fuzzy C-mean value clustering are determined by means of a multi-variable multi-scale sample entropy weight method; finally the obtained feature data set is subjected to cluster analysis through the fuzzy C-mean value clustering method and the user power utilization behavior identification accuracy and rapidity can be improved. According to the invention, the building microgrid user power utilization behavior can be effectively identified, and a basis and reference can be provided for scheduling of the building microgrid power utilization load by the power grid, and furthermore the fact that the user saves power in life, and power wasting behaviors are reduced is promoted.

The invention relates to a regional power utilization intelligent management system. By building a regional energy utilization monitoring system which is automatic, intelligent and networked, has complete functions and is wide in measurement range and high in adaptability, real-time power utilization energy consumption information of various power utilization equipment (electrical appliances) in a region is measured, power utilization behavior is recorded, stored and analyzed, a user power utilization mode optimization scheme is formed by machine learning, an optimization algorithm is developed, an automatic response strategy of a demand side is combined, load management (dispatching control) is performed on a power utilization terminal through access of a controller of the power utilization equipment by an intelligent gateway, reasonable and orderly power utilization, terminal energy use efficiency improvement and power utilization behavior optimization are finally realized, and the purposes of energy saving and efficiency increase are achieved.

The invention discloses a typical daily load characteristic-based power load forecasting method, including: collecting power load data of users in a set industry in a set area, and performing preprocessing on the data; obtaining typical daily load curves of the users and an industry overall load curve; obtaining a correlation coefficient of the typical daily load curves of the users; classifying the users according to a power utilization laws of the users; and selecting a user whose power load change trend has the highest consistency with an industry overall load change, and forecasting power load data of an overall industry through the power utilization behavior laws of the user. The typical daily load characteristic-based power load forecasting method provided by the invention has the beneficial effects of being capable of deriving a forecast of an abnormality of a specific industry and even a whole society power load abnormality from an abnormality of a certain user power load, improving accuracy of a power load forecasting result, and providing a power guarantee for reasonable economic dispatching of an electric power system, reduction of production cost, and prevention of a large-area power failure of a power grid or a power grid breakdown.

The invention provides an attribute association based load prediction system in the energy Internet environment. The system is characterized by comprising a data collection and a database management module, an electric quantity supply and demand balance real-time monitoring module, a data analysis and processing module, a data storage module and an electric quantity query module. The invention also provides an attribute association based load prediction method in the energy Internet environment, and the method includes an excavation algorithm for short-term load prediction on the basis of a graph theory. The system takes attributes influencing the load into consideration, and power utilization rules of users can be mastered in a more complete manner. The prediction method mainly aims at association factors related to load change, influential factors and chain reaction links of high association degree are found, power utilization behaviors of users and power utilization association modes of user groups are excavated, and a new solution ideal is provided for real-time load prediction method after large-scale intermittent new-energy grid connection.

The invention discloses a power customer credit evaluating method based on large data credit investigation. The method comprises the steps of constructing a power customer credit evaluating indicatorsystem, wherein the power customer credit evaluating indicator system comprises multiple pieces of power user information, and the power user information comprises but are not limited to customer basic information, arrearage information, power utilization behaviors, contract breaking records and demand-side factors; obtaining information corresponding to the power customer credit evaluating indicator system, and preprocessing the obtained power user information to sift out qualified and accurate information; constructing a dynamic power customer credit evaluating model, and inputting the sifted qualified and accurate information to the customer credit evaluating model to correspondingly obtain the level of each power user; adopting corresponding processing measures according to different levels to achieve risk prevention of electric charge. Individualized marketing and service strategies are customized for users with different power utilization types, different industries and differentpower utilization scales, the operation risk is avoided, and the economic benefit of power supply enterprises is improved.

The invention discloses a behavior recognition method based on an action subspace and weight behavior recognition model. The behavior recognition method includes the following steps: A1, inputting a behavior video sequence to be tested, using a dynamic background detection method or a static background detection method for detecting background images, and using a background reduction method for obtaining foreground images; A2, extracting an outline of a moving object, and expressing outline characteristics correspondingly; A3, using a kernel principal component analysis (KPCA) algorithm for achieving nonlinear dimensionality reduction on high-dimensional characteristics in kernel guide subspace, and mapping behavior track in a low-dimensional space; and A4, using the behavior recognition model namely a world cancer research fund (WCRF) module for performing behavior recognition. An experimental result shows that a provided framework can recognize human behavior of personnel changes inside and outside an area along the time accurately and is strong in robustness of noise and other influencing factors.

The invention discloses a user portrait construction method for a power industry. The method comprises the steps of generating basic attribute tags of a user according to fields in a database, wherein basic attributes of the user include an area, a voltage grade, an industry, a power utilization type, a network access duration, whether energy consumption is high or not, and whether the user is a third-party user or not; and / or, generating basic behavior tags of the user based on a power utilization behavior, a paying behavior and an interactive behavior respectively. According to the user portrait construction method for the power industry, provided by an embodiment of the invention, the frequency, degree and recent prediction of the user behaviors of the power industry are combined and behavior characteristics of power utilization customers of different attributes can be described multi-dimensionally, thereby effectively assisting business personnel of power companies to provide differential value-added services according to states of the power utilization customers.

The invention discloses an intelligent electricity stealing checking method based on non-invasive load monitoring, which mainly comprises the following steps of: (1) judging whether an electricity user is a suspected electricity stealing user; (2) dividing the electric equipment of the user into electric equipment, the operation state of which can reflect a whole-day electricity utilization behavior of the user and is suitable for analyzing the behavior of intermittent meter throwing and electric equipment, the monitoring result of the operation state of which is not influenced by the behaviorof less metering and electricity stealing; secondly, calculating an evaluation index of the electricity stealing behavior; (3) judging the electricity stealing behavior of the user; (4) estimating the electricity stealing quantity of the user by utilizing the relation between the accumulated electricity consumption of the same type of electric equipment and the total electricity quantity of the user under the normal condition and the judgment result of the electricity stealing behavior of the user. According to the invention, the non-invasive load monitoring technology is utilized to acquirethe power utilization detail data, so that the defects that the prior method is difficult to utilize at a household and evidence is difficult to obtain are overcome, and the accuracy and reliability of the inspection of the two electricity stealing behaviors are improved.

The invention discloses a distribution network fault information comprehensive collection and management platform which comprises a fault information collection system, a fault high-incidence section early-warning system, a fault information processing and pushing system, a fault information database analysis system and a client database analysis system.Fault information collected by an automatic fault service information collecting module comprises user fault service information, switch displacement fault information and distribution transform and user fault information.A distribution network emergency repair command worker carries out power grid topology analysis according to the fault information, obtains detailed power failure user information, manages power failure management service data in real time, carries out real-time fault information screen pushing and real-time fault searching, labels a fault position on a geographic map in real time, displays a fault influence range, perfects a client database, carries out monitoring and analysis according to client power utilization behaviors, and provides diversified power supply services.

The invention discloses an intelligent and online area monitoring system and an implementation method thereof. The system comprises a master distribution automation station, a plurality of intelligent area monitoring substations connected with the master distribution automation station, servers connected with the intelligent area monitoring substations, a plurality of communication terminals capable of realizing information transmission with the servers through wireless communication networks as well as an intelligent and online area monitoring terminal connected with the communication terminals, wherein the intelligent and online area monitoring terminal is connected into electric wires and monitors a whole grid. The system can provide timely and reliable operation data for management automation and power utilization standardization of electric power sectors and can monitor states such as undervoltage, overvoltage, overcurrents, overloads, open circuits / short circuits and the like of distribution areas and users in real time, so that abnormal power utilization behaviors of the users as well as fault states of the areas and all circuits can be discovered timely, the power supply quality is improved, the service level of the electric power sectors is increased, and the safe operation of a power supply system is guaranteed.

The invention discloses a method and device for analyzing a power utilization behavior of a user. The invention aims to provide a power utilization behavior analysis method and device which adopt a distributed database, are high in computation speed and can monitor in real time. The method comprises: acquiring power utilization information of a user in a set duration in advance; according to a preset rule, processing the power utilization information, and generating a user behavior label, wherein the user behavior label is used for setting a safety power utilization range of the user; establishing a distributed label database, and storing the user behavior label in the distributed label database; acquiring power utilization behavior data of the user in real time; comparing the power utilization behavior data with the user behavior label stored in the distributed label database; according to a comparison result, determining whether the power utilization behavior data exceeds the safety power utilization range of the user or not.

The invention provides a log mining method based on a Petri network behavior profile, and belongs to the field of process mining. The method aims to improve a business progress model by means of implementation of a mining technology, so that procedure operation efficiency and service quality are improved. The method includes the steps that firstly, log sequences are extracted from a track generated in program running and pre-processing is carried out; the behavior relation between two adjacent actions is analyzed, the behavior profile is built, and an initial model is built according to direct dependency; then the log sequence with the largest occurrence frequency is replayed, and two procedure models superior to the initial model are found according to indexes; the consistency degrees of the two models and the initial model are respectively compared by means of behavior profile consistency so as to choose the more superior model; the last two steps are repeated until log replay is finished so as to obtain the optimal business procedure model. The log mining method can guarantee that the business procedure meets the requirement of functionality, enables procedure behaviors to be concise, and shortens program running time.

The invention relates to an intelligent power distribution big data application system which comprises a data acquisition module, a data integration cleaning module, a public service module, a data analysis application module and an application display module. The data acquisition module is used for providing a standardized data interface and performing standardized access of multi-source and heterogeneous data sources. The data integration cleaning module is used for combining, associating, de-weighting and transposing data accessed to the data acquisition module in lines. The public service module uses the data processed by the data integration cleaning module. The data analysis application module builds an analysis algorithm library, analyzes power utilization behaviors of a user, builds an application model and an algorithm library and builds a power-saving application, a power utilization forecasting application, a power grid optimization application and a peak-alternation regulation application. The application display module displays data of results of the data analysis application module. Compared with the prior art, the system has the advantages that the data are cleaned, migrated on a distributed platform and integrated in a standardized manner, a user behavior analysis and power utilization forecasting application module is developed, intelligent power distribution and utilization level is improved and the like.

The invention belongs to the technical field of electric power detection, particularly relates to the technical field of electric power electricity stealing detection, and particularly relates to a method for detecting electricity stealing on the basis of electricity utilization behavior patterns of electric energy users and application. The method and the application have the advantages that themethod starts from electricity utilization behavior characteristics of the users, factors such as behavior habit, climate and seasons are considered according to electricity utilization energy consumption characteristics of the different electric power users, and different user energy consumption time-sharing models are built; the problem of incapability of accurately determining electricity stealing behavior of users under the consideration of reasonable electricity utilization behavior change of the electric energy users after the anomaly of electric energy measurement data of the users is detected on the basis of K-means clustering algorithms and LOF (local outlier factor) algorithms can be solved by the aid of the method and the application; the method is combined with electricity utilization information acquisition systems for measuring electric energy loss, the electricity stealing probability is introduced according to energy consumption formulas in districts, the electric energy electricity stealing probability can be computed, and accordingly different types of electricity stealing behavior of the electric energy users can be reliably monitored.

The invention relates to a power consumer clustering power utilization behavior characteristic analysis method based on load decomposition. According to the method, considering that the proportion ofmeteorological sensitive loads such as temperature in the total power load becomes larger and larger, in order to analyze the load of a power consumer more finely, the total power load is decomposed into a basic-level load and a seasonal load, and then a fuzzy C-means algorithm is used for performing clustering analysis on the two levels of loads respectively; the method has the following steps: selecting typical users for each cluster, comprehensively considering a plurality of common screening methods, and finally selecting each type of typical users by adopting a grey correlation degree method; and finally, calculating important characteristic indexes of each type of typical users to analyze the magnitude of the load regulation and control potential of the typical users, and further classifying the power users according to the magnitude of the regulation and control potential of the typical users so as to finally formulate more detailed demand side regulation and control measures.

The invention discloses a distributed detection system for an illegal power utilization behavior of a smart power grid, and a detection method. The distributed detection system comprises a smart electricity meter data acquisition module, a smart electricity meter data transmission module, a smart electricity meter data storage module, a smart electricity meter data security authentication module and a smart electricity meter core computation module. According to the detection system and the detection method, global coverage of the smart power grid is realized; illegal power utilization detection is finished by a smart electricity meter; after system deployment is finished, compared with an original centralized detection system, the coverage range of the system is greatly expanded, emergency situations can be well dealt with, and the precision of computation and detection is relatively high.

The invention discloses a power utilization behavior electricity theft prevention diagnosis method and device based on dynamic grid outliers. The method comprises the steps: obtaining the sampling information of three-phase voltage values (a, b, c) at a current moment from a metering device of a power utilization information collection system, building a data observation matrix based on the sampling information, and calculating the sampling information, an information variance actual measurement value, and an information variance theoretical value; building a first examination function based on residual examination and a second examination function based on the information variance examination according to the sampling information, the information variance actual measurement value and the information variance theoretical value, and respectively calculating a first detection value and a second detection value; and determining a power utilization abnormality of a user when the first detection value is greater than a first preset threshold value and the second detection value is greater than a second preset threshold value. The method solves technical problems in the prior art that the real-time performance is poor and the field inspection efficiency is low, which are caused by a method that a power monitoring department determines a suspected user with the electricity stealing behavior through the changes of a monthly power utilization quantity or the statistics of station line loss.

The invention discloses a block chain stimulation type energy saving method for electricity transaction in the energy internet and belongs to the technical field of energy internet and information security. The power margin of a user is taken as a transaction object, the maximum power margin ratio of the user is taken as the interest certificate of account keeping right, and the power utilization behavior of the user is stimulated with economic means to develop towards the direction beneficial to resource saving. Besides, the safe operation of the system is guaranteed due to the characteristics of openness, transparence and non-distortion of block chains.

The invention discloses a clustering algorithm-based power user load measurement and calculation method, and belongs to the technical field of power system measurement. The method comprises the following steps of collecting historical power utilization data of a user; converting the historical data into a formatted machine learning sample library through a data preprocessing technology; training apower user clustering model by applying a clustering algorithm, and testing a clustering effect; according to a clustering result, determining a class typical user as a real-time measurement apparatus installation point; and reading power load data of the typical user in real time, and calculating total power consumption of the class user and power consumption of all users. The power load quick measurement method for the users with similar power utilization behaviors is given by taking load measurement speed and precision into account through applying the clustering algorithm based on the historical data; the measurement apparatus installation expense is reduced; and reference information is provided for power system control.

The invention provides an electricity larceny prevention early warning method based on multi-source data fusion. The electricity larceny prevention early warning method is used for realizing an analysis and early warning system for electricity larceny and abnormal electricity utilization behaviors of a user in the electricity utilization process. According to the method, multi-source composite information is utilized to improve the system monitoring and prediction early warning diagnosis capability of power utilization behaviors, and the support technology of power utilization mass data application is adopted; a multi-layer perception system is established, and multi-source integration, deep extraction and omnidirectional application of the power utilization information system are promoted; Meanwhile, a monitoring and sensing method based on user power utilization analysis is provided, and optimal configuration of relevant resources such as power utilization types, power utilization strategies and power utilization behavior specifications is improved; the identification method for the electricity consumption behavior attribute of the user is provided, and technical support is provided for power grid safety and electric quantity maintenance marketing.

The invention discloses a package recommendation method for a power user in the Internet environment. The method comprises the following steps that (1) a user package model is established; (2) power utilization behavior features and Internet behavior features of the user are analyzed to obtain power utilization preference and efficacy management attention degree of the user; and (3) according to the power utilization preference and efficacy management attention degree of the user, optimization is carried out by making the difference between the practical power utilization amount and a package minimal, the user package model is combined in use, and the power utilization package is recommended for the user. According to the invention, the most proper power utilization package can be recommended for the user, a power seller can be helped to realize accurate marketing, and the efficacy of the user is improved.

The invention provides a method for predicting the power utilization mode of a new user of grid under the internet environment. The method includes the following steps: constructing a relation network between an existing internet user and the labels thereof; separately computing the number W of same labels between each existing user and a new user, then arranging the order of the existing users which correspond to elements in the number W in the descending order, cancelling the number M of existing users to form a user group A, computing the number Nij of the same labels between any two users in the user group A and the power utilization behavior similarity Sij of the users represented by the two nodes, then computing the mutual relation weight between the two nodes; computing the average value of daily load curves of users in a user group B and taking the average value as the prediction value of the power utilization mode of the new grid user. According to the invention, the method can predict the power utilization mode of the new grid user through the attribute labels of the user in combination of the analysis of similar user group when there is no historic load of the user, so that the method can help power entities to provide personalized power utilization service recommendation to the new grid user.

The invention discloses a power consumer classification method based on self-adaptive particle swarm clustering. The method comprises the following steps: A, carrying out standardization processing onoriginal load curve data; B, removing data noise, namely an interference load curve, through a density-based data screening method; C, clustering the residual load curve data by using an adaptive particle swarm algorithm; D, clustering the clusters through a fuzzy clustering algorithm; And E, re-classifying the interference load curve based on a pattern recognition principle to obtain a clustering result. According to the invention, classification of power consumers based on the load curve can be realized; The method is suitable for user power utilization behavior analysis in the field of demand response, can effectively remove data noise and reduce the sensitivity to the clustering number by fusing the DBSCAN algorithm and the fuzzy mathematics theory, and meanwhile, the self-adaptive particle swarm algorithm is less affected by an initial value, fast in convergence and not easy to fall into local optimum, so that the clustering precision is improved.

The invention relates to a low-voltage area network user electric load characteristic analysis method. The method comprises the following specific steps: (1) determining electric load characteristic indexes of the users in the low-voltage area network; (2) according to the determined user power consumption load characteristic index, carrying out standardization processing on the low-voltage area network user power consumption information; (3) performing clustering analysis on the standardized power consumption information of the users in the low-voltage area network; (4) analyzing different types of low-voltage area network user power consumption data obtained after clustering analysis; and (5) formulating load management measures according to an analysis result. According to the method, the influence of factors such as temperature, holidays and climate on the power utilization characteristics of the low-voltage area network users is analyzed, the power utilization behaviors of the users are analyzed, then reasonable and effective load management measures are formulated, the economical efficiency of system operation is improved, the power utilization efficiency of the terminal is improved, and energy conservation and emission reduction work is deeply promoted.

The invention discloses a low-voltage user loop impedance estimation method based on a unitary model, and belongs to the technical field of electric management. The method is characterized by defininga user loop impedance ZL on the basis of time series data for acquiring voltage and current through a user intelligent electric meter, and deducing and building a unitary linear model of a low-voltage user loop impedance by utilizing a KVL loop voltage equation. The loop impedance estimation method comprises the steps of firstly selecting a data acquisition time interval on the basis of a peak valley ordinary time frame statistics division at the area, observing a current step moment of a user at an interval of 5min within the time frame, and freezing voltage-current data before and after thestep; and then adopting one-day data as a sample, carrying out linear-regression analysis, and estimating the user loop impedance ZL, wherein the loop impedance value can be used for estimating and judging a health ageing degree of a low-voltage distributing network circuit and a user abnormal power utilization behavior.

The invention relates to a reminding method and device based on electricity consumption. The method comprises the steps that electricity consumption of each hour within the specified time period is obtained; the current total electricity price corresponding to the electricity consumption of each hour within the specified time period is calculated according to the corresponding relation of time and the electricity price; the target time period with the time length identical to that of the specified time period is determined according to a preset conversion condition; the target total electricity price corresponding to the electricity consumption of each hour within the target time period is calculated according to the corresponding relation of the time and the electricity price; when the target total electricity price is smaller than the current total electricity price, reminding information for converting the specified time period into the target time period is output. Due to the fact that the electricity prices within different time periods are different, whether the current electricity utilization behavior of a user is reasonable or not is analyzed by comparing the current total electricity price of the specified time period with the current total electricity price of the target time period. Therefore, according to the scheme, the electricity utilization advice capable of saving the electricity charge can be analyzed according to the electricity consumption condition of the user, and is pushed to the user.