CN115296424A - Distributed power supply comprehensive monitoring system and method based on fusion terminal - Google Patents
Distributed power supply comprehensive monitoring system and method based on fusion terminal Download PDFInfo
- Publication number
- CN115296424A CN115296424A CN202211230968.4A CN202211230968A CN115296424A CN 115296424 A CN115296424 A CN 115296424A CN 202211230968 A CN202211230968 A CN 202211230968A CN 115296424 A CN115296424 A CN 115296424A
- Authority
- CN
- China
- Prior art keywords
- data
- building
- power supply
- power
- new area
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Human Computer Interaction (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a distributed power supply comprehensive monitoring system and method based on a fusion terminal, and belongs to the technical field of distributed power supply monitoring. The system comprises an electric power utilization data processing module, a new region prediction module, a threshold analysis module and a distributed power supply monitoring module; the output end of the power usage data processing module is connected with the input end of the new region prediction module; the output end of the new region prediction module is connected with the input end of the threshold analysis module; and the output end of the threshold analysis module is connected with the input end of the distributed power supply monitoring module. The invention also provides a comprehensive monitoring method of the distributed power supply based on the fusion terminal, which can accurately detect the power use data in the development of a new region, reduce the urban power grid pressure through a mechanism of the distributed power supply, provide time early warning analysis of the power use data under the condition that buildings are continuously added in the new region, and improve the power dispatching level.
Description
Technical Field
The invention relates to the technical field of distributed power supply monitoring, in particular to a distributed power supply comprehensive monitoring system and method based on a fusion terminal.
Background
The intelligent integrated terminal is a user terminal on the periphery of a computer network, and in the prior art, the intelligent integrated terminal has the functions of information acquisition, internet of things agent and edge calculation, and supports marketing, power distribution and emerging services. The intelligent integration terminal device integrates the functions of power supply and power information acquisition of a power distribution station area, data collection of each acquisition terminal or electric energy meter, equipment state monitoring and communication networking, local analysis decision, cooperative calculation and the like. The system is generally deployed at the cloud, online management and remote operation and maintenance of various types of edge Internet of things agents and intelligent terminals are achieved, various types of acquisition terminals are managed in a unified mode, various types of acquisition sensing data are gathered according to a unified Internet of things information model, and model conversion and data preprocessing are conducted. By constructing the power distribution internet of things, the topology of the power supply relation at the low-voltage 0.4kV side can be monitored on line, and the branch switch, the line state, the metering box and the electric energy meter can be monitored comprehensively; by sensing the Internet of things of the transformer area, meter reading, line loss calculation, power quality management, topology identification, fault first-aid repair and the like can be realized; meanwhile, the power supply reliability and the high-quality service level can be improved, the marketing and distribution service fusion is realized, and the visual management of 'full networking', 'full online' and 'full monitoring' of the distribution network assets is achieved.
The distributed power supply is distributed at a user end and is connected with a power grid with a voltage level of 35kV or below so as to be consumed on site. The energy-saving power generation system comprises solar energy, natural gas, biomass energy, wind energy, water energy, hydrogen energy, geothermal energy, ocean energy, resource comprehensive utilization power generation (including coal mine gas power generation), energy storage and the like. These power sources are owned by the power department, the power consumer, or the 3 rd party to meet power system and consumer specific requirements. Such as peak regulation, power supply for remote users or commercial districts and residential districts, power transmission and transformation investment saving, power supply reliability improvement and the like.
Nowadays, the application of distributed power supplies in development areas is emerging, the development areas are generally in the uncovered areas of urban power grids, the power transmission and transformation investment can be greatly reduced and the power supply reliability can be controlled by using the distributed power supplies, however, the load of the distributed power supplies is continuously increased due to the continuous development of the development areas, and no effective supervision means exists at present.
Disclosure of Invention
The invention aims to provide a distributed power supply comprehensive monitoring system and method based on a fusion terminal, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a distributed power supply comprehensive monitoring method based on a fusion terminal comprises the following steps:
the method includes the steps that S1, electric power use data collected by a new area are obtained from a fusion terminal according to preset collection frequency, the new area refers to a development area in a city, the development area refers to various development areas which are approved by state couriers, provinces, autonomous regions, and national government of the direct municipality to set up in a city planning area and carry out national specific preferential policies, such as economic technology development areas, bonded areas, high and new technology industry development areas, national tourism and vacation areas, the development areas are special mechanisms set by local governments for promoting regional economy to rapidly develop, the development areas refer to undeveloped places, and the places have economic or human environment potential. The connotation of a development area mainly comprises two layers: first, a newly reclaimed land resource area; and secondly, excavating and discovering areas with economic potential. Generally refers to a new area which has not exerted resources and economic advantages and needs to be artificially developed so as to achieve the purpose that the social limited resources generate the maximum social benefit through reasonable allocation. The power usage data comprises distributed power supply power data and urban power grid power data;
s2, classifying the collected power utilization data according to the type of the power utilization data, wherein the type of the power utilization data comprises industrial production power consumption of each building in the new area and commercial life power consumption of each building in the new area, and power utilization information of each building in the new area is obtained; the buildings comprise office buildings, shopping malls, factories and the like, wherein the power utilization of the factories is recorded as industrial production power utilization; the electricity consumption of business life is recorded in office buildings, shopping malls and the like;
s3, constructing a first building prediction model of the new area, generating the time and the type of newly added buildings in the new area in a preset period, constructing a second building prediction model of the new area, and generating predicted power use data changes of buildings in the new area in the preset period;
and S4, acquiring threshold information of the power utilization data according to output results of the first building prediction model and the second building prediction model, generating time early warning information when the predicted power utilization data in the new area exceed the threshold, and outputting the time early warning information to an administrator port.
According to the technical scheme, the distributed power supply power data refer to power use data provided for each building by a distributed power supply in a new region; the urban power grid power data refers to power utilization data provided by the urban power grid for each building in the new area. Under the current technical means, four to six can be achieved generally, namely, the distributed power supply can provide 40% of electric quantity, and the rest 60% is provided by a city power grid.
According to the above technical solution, the first building prediction model includes:
constructing an initial training set, and acquiring the time of the same newly added building in a new area, wherein the newly added buildings comprise two buildings, one is a building using industrial production electricity, and the other is a building using commercial life electricity;
establishing an initial training set according to historical time data of the same newly added building;
setting the mean square error function as the loss function, notedWhereinWhich represents the output of the computer system,setting the maximum iteration times for the first building prediction model, and recording as T;
at the loss functionWhen the minimum value is taken, the weak learner is initialized and recorded as;
Performing iterative training on the initialized weak learner, and calculating the negative gradient of each data sample i in the initial training set:
Wherein, the first and the second end of the pipe are connected with each other,is the value of the data sample i,is composed ofA corresponding loss function; in the formulaAdopts a strong learning device in the previous roundA first building prediction model of; t represents the number of iterations;a differential is indicated;
using acquired negative gradientsFitting a regression tree, recording as the t-th regression tree, and recording as the corresponding leaf node regionCalculating the best fit value:
Wherein i and j are labels; c is a constant;
the best fit value refers to the output value that minimizes the loss function in the samples in each leaf node region, i.e., the best output value that fits the leaf node region;
and adding the weak learner of each round into the trained model to obtain a new strong learner:
wherein the content of the first and second substances,representing a leaf region;representing a strong learner obtained by the t-th iteration; i represents the value of best fitCombining, representing the decision tree fitting function of the current round;
when T = T, ending the iterative process and obtaining the final strong learnerAnd as an output first building prediction model, generating two groups of time data of newly added buildings by using the first building prediction model respectively, wherein a newly added time data set of the buildings using industrial production electricity is recorded as:(ii) a The newly added time data set of the building using the commercial life electricity is recorded as:(ii) a Wherein m and n are constants related to the preset period and satisfy、The time point is less than or equal to the end time of the preset period, and、at a time point greater than the end time of the preset period.
According to the above technical solution, the second building prediction model includes:
respectively acquiring classified electric power use data information, and taking historical information of electric power use data under the same building as a second training set;
respectively establishing a horizontal smooth equation, a trend smooth equation and a season smooth equation to predict the season and the trend of the data;
wherein the horizontal smoothing equation is:
the trend smoothing equation is:
the seasonal smoothing equation is:
the second building prediction model is constructed as follows:
wherein u is the current power usage data; v is the cycle length;a smoothing parameter that is horizontal;a smoothing parameter that is a trend;a smoothing parameter for the season;is a firstA predicted value of the period, i.e., power usage data at the h-th period;is the actual value of the u-th period, i.e., the power usage data at the u-th period;is the estimated level of phase u;is the predicted trend of the u-th stage;a season smoothing prediction for the u-th stage;
and respectively generating power use data change predicted values of two buildings in the new area by using a second building prediction model, wherein the power use data change predicted values of the buildings using industrial production power are integrated as:(ii) a The set of predicted values of the change of the electricity utilization data of the building using the electricity of the commercial life is recorded as:(ii) a Wherein、All represent constant values.
According to the above technical solution, the generating time early warning information includes:
constructing a time early warning model:
wherein, the first and the second end of the pipe are connected with each other,at a time pointPower usage data of the time;represents rounding up;representing a data set for using industrial production electricity when selecting electricity use data;representing a data set for using commercial life electricity when selecting electricity usage data;represents a serial number;representing the time pointThe total number of buildings using industrial production electricity is newly added in the new area;representing the time pointThe total number of buildings using electricity for commercial life is newly added in the new region;representing the time point of the newly added building;representing a period duration between data in the second building prediction model;at the time pointA predicted value of a change in electricity usage data of a building that uses electricity for industrial production;at the time pointThe total number of buildings using electricity in the original industrial production;at the time pointA predicted value of a change in electricity usage data of a structure using electricity for business life;at the time pointThe total number of buildings powered by the original commercial life;
in the above formula, consideration is given to the difference between the change of the power usage data of the newly added building and the change of the power usage data of the existing building, and refinement is performed.
Wherein the content of the first and second substances,by taking the time pointAccording to the calculation, selecting and calculating in the sets A and B; e.g. at time point k1, satisfyThen getIs 9; can be obtained by the same principle。
Obtaining the threshold value of the power supply of the distributed power supply, and recording as;
ObtainingIs greater than or equal to for the first timeTime point of timeAnd acquiring the average time required for constructing a new distributed power supply station by indicating that the currently required power data exceeds the load value of the distributed power supplyGenerating time warning information atThe time point of the power consumption is output to an administrator port, and the administrator is reminded to restrict the power consumption planning in a new area or construct a new distributed power supply station; whereinRepresents the average value of the proportion of the supplied power of the distributed power supply and the urban power grid.
A distributed power supply comprehensive monitoring system based on a convergence terminal comprises: the system comprises an electric power usage data processing module, a new region prediction module, a threshold analysis module and a distributed power supply monitoring module;
the electric power usage data processing module is used for acquiring electric power usage data acquired by a new area from the fusion terminal according to a preset acquisition frequency, wherein the new area refers to a development area in a city, and the electric power usage data comprises distributed power supply electric power data and urban power grid electric power data; classifying the collected power usage data according to the type of the power usage data, wherein the type of the power usage data comprises industrial production power consumption of each building in the new area and commercial life power consumption of each building in the new area, and power usage information of each building in the new area is obtained; the new area prediction module is used for constructing a first building prediction model of a new area, generating the time and the type of newly added buildings in the new area in a preset period, constructing a second building prediction model of the new area, and generating predicted power use data change of each building in the new area in the preset period; the threshold analysis module is used for generating a predicted sharing proportion value of the distributed power supply according to proportion data of the electric quantity provided by the urban power grid and the distributed power supply; the distributed power supply monitoring module is used for acquiring a prediction sharing proportion value of the distributed power supply as threshold information of power utilization data according to output results of the first building prediction model and the second building prediction model, generating time early warning information when the predicted power utilization data in a new area exceed a threshold value, and outputting the time early warning information to an administrator port;
the output end of the power usage data processing module is connected with the input end of the new region prediction module; the output end of the new region prediction module is connected with the input end of the threshold analysis module; and the output end of the threshold analysis module is connected with the input end of the distributed power supply monitoring module.
According to the technical scheme, the power usage data processing module comprises a power usage data acquisition unit and a power usage data classification unit;
the electric power usage data acquisition unit is used for acquiring electric power usage data acquired in a new area from the fusion terminal according to a preset acquisition frequency; the electric power usage data classification unit is used for classifying the collected electric power usage data according to the type of the electric power usage data.
According to the technical scheme, the new area prediction module comprises a first building prediction unit and a second building prediction unit;
the first building prediction unit is used for constructing a first building prediction model of the new area and generating the time and the type of newly added buildings in the new area under a preset period; and the second building prediction unit is used for constructing a second building prediction model of the new area and generating predicted power use data change of each building of the new area under a preset period.
According to the technical scheme, the threshold analysis module comprises a historical data acquisition unit and an output unit;
the historical data acquisition unit is used for acquiring the proportion data of the electric quantity provided by the urban power grid and the distributed power supply; and the output unit is used for selecting an average value to generate a predicted sharing proportion value of the distributed power supply according to historical proportion data of the electric quantity provided by the urban power grid and the distributed power supply.
According to the technical scheme, the distributed power supply monitoring module comprises a threshold selecting unit and a time early warning unit;
the threshold selecting unit acquires a predicted sharing proportion value of the distributed power supply as threshold information of the power use data; and the time early warning unit is used for generating time early warning information according to the output results of the first building prediction model and the second building prediction model when the predicted power utilization data in the new region exceeds a threshold value, and outputting the time early warning information to an administrator port.
Compared with the prior art, the invention has the following beneficial effects:
the method can accurately detect the power use data in the development of a new region, reduces the urban power grid pressure through a mechanism of the distributed power supply, provides time early warning analysis for the power use data under the condition that buildings are continuously added in the new region, can provide time points for constructing the distributed power supply station to relieve the urban power grid pressure, and improves the power dispatching level.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic flow diagram of a distributed power supply comprehensive monitoring system and method based on a convergence terminal according to the present invention.
Detailed Description
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 obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1, in the first embodiment: selecting a new economic development area in a city as a new area, acquiring power usage data acquired by the new area from a fusion terminal according to preset acquisition frequency, and classifying the acquired power usage data according to the type of the power usage data, wherein the type of the power usage data comprises industrial production power consumption of each building in the new area and commercial life power consumption of each building in the new area, so as to obtain power usage information of each building in the new area; constructing a first building prediction model of the new area, generating the time and the type of newly added buildings in the new area under a preset period,
the first building prediction model comprises:
constructing an initial training set, and acquiring the time of the same newly-added building in a new area, wherein the newly-added buildings comprise two types, one type is a building using industrial production electricity, and the other type is a building using commercial life electricity;
establishing an initial training set according to historical time data of the same newly added building;
for example, the same newly added building is marked as a building for commercial life electricity, taking an office building as an example, and recording the newly added time as follows: 30 days, 22 days, 12 days, 20 days;
setting the mean square error function as the loss function, and recording asWhereinWhich represents the output of the computer system,setting the maximum iteration times for the first building prediction model, and recording as T;
at the loss functionWhen the minimum value is taken, initializing the weak learner and recording the result as;
Performing iterative training on the initialized weak learner, and respectively calculating the negative gradient of each data sample i in the initial training set:
Wherein the content of the first and second substances,for the value of the data sample i,is composed ofA corresponding loss function; in the formulaAdopts the strong learning device of the previous roundA first building prediction model of; t represents the number of iterations;means differentiation;
using acquired negative gradientsFitting a regression tree, recording as the t-th regression tree, and recording as the corresponding leaf node regionCalculating the best fit value:
Wherein i and j are labels; c is a constant;
the best fit value refers to the output value that minimizes the loss function in the samples in each leaf node region, i.e., the best output value that fits the leaf node region;
and adding the weak learner of each round into the trained model to obtain a new strong learner:
wherein, the first and the second end of the pipe are connected with each other,representing a leaf region;representing a strong learner obtained by the t-th iteration; i represents the value of the best fitCombining, representing the decision tree fitting function of the current round;
continuously fitting and calculating by using MATLAB, and finishing the iterative process when T = T to obtain the final strong learnerAnd as the output first building prediction model, generating two groups of time data of the newly added building by using the first building prediction model respectively, wherein a newly added time data set of the building using industrial production electricity is recorded as:(ii) a The newly added time data set of the building using the commercial life electricity is recorded as:(ii) a Wherein m and n are constants related to the preset period and satisfy、The time point is less than or equal to the end time of the preset period, and、the time point is greater than the end time of the preset period.
Constructing a second building prediction model of the new area, and generating predicted power use data changes of buildings in the new area in a preset period;
the main change points are the commercial living directions, such as the business buildings are continuously moved into new enterprises, the residential buildings are continuously provided with new users to live in, and the like, and the increase of the electric power caused by the change points is obviously in a trend;
respectively acquiring classified electric power use data information, and taking historical information of electric power use data under the same building as a second training set;
respectively establishing a horizontal smooth equation, a trend smooth equation and a season smooth equation to predict the season and the trend of the data;
wherein the horizontal smoothing equation is:
the trend smoothing equation is:
the seasonal smoothing equation is:
constructing a second building prediction model as follows:
wherein u is the current period power usage data; v is the cycle length;a smoothing parameter that is horizontal;a smoothing parameter that is a trend;a smoothing parameter for the season;is as followsA predicted value of the period, i.e., power usage data at the h-th period;actual value for the u-th period, i.e., power usage data for the u-th period;is the estimated level of phase u;is the predicted trend of the u-th stage;a season smoothing prediction for the u-th stage;
and respectively generating power utilization data change predicted values of two buildings in the new area by using a second building prediction model, wherein the power utilization data change predicted values of the buildings using industrial production power are integrated as:(ii) a The set of predicted values of the change of the electricity utilization data of the building using the electricity of the commercial life is recorded as:(ii) a Wherein、All represent constant values.
The change curve of the power use data of the building using the industrial production power is generally gentle, and the average of the industrial production power is reflected; the change curve of the electricity usage data of the building using the electricity for business life generally fluctuates greatly and tends to be in a rising trend, for example, in an office building in a new area, the electricity consumption is gradually increased due to the continuous entering of merchants and enterprises, so in the second building prediction model, the continuous change condition of the electricity for business life is mainly considered.
The generating of the time warning information includes:
constructing a time early warning model:
wherein, the first and the second end of the pipe are connected with each other,at a point of timePower usage data of the time;represents rounding up;representing a data set for using industrial production electricity when selecting electricity use data;representing a data set for using commercial life electricity when selecting electricity usage data;represents a serial number;represents the time pointThe total number of buildings using industrial production electricity is newly added in the new area;representing the time pointThe total number of buildings using electricity for commercial life is newly added in the new region;representing the time point of the newly added building;representing a period duration between data in the second building prediction model;at the time pointA predicted value of a change in electricity usage data of a building using electricity for industrial production;at the time pointThe total number of buildings using electricity in the original industrial production;at the time pointA predicted value of a change in electricity usage data of a structure using electricity for business life;at the time pointThe total number of buildings consumed by the original commercial life;
in the above formula, consideration is given to the difference between the change of the power usage data of the newly added building and the change of the power usage data of the original building, and refinement is performed.
Wherein the content of the first and second substances,by taking the time pointAccording to the calculation, selecting and calculating in the sets A and B; e.g. at time point k1, satisfyThen getIs 9; the same can be obtained。
ObtainingIs greater than or equal to for the first timeTime point of timeAnd acquiring the average time required for constructing a new distributed power supply station by indicating that the currently required power data exceeds the load value of the distributed power supplyGenerating time warning information atThe time point of the power consumption is output to an administrator port, and the administrator is reminded to restrict the power consumption planning in a new area or construct a new distributed power supply station; whereinRepresents the average value of the proportion of the supplied power of the distributed power supply and the urban power grid.
In the second embodiment, a distributed power supply comprehensive monitoring system based on a convergence terminal is provided, where the system includes: the system comprises an electric power use data processing module, a new region prediction module, a threshold analysis module and a distributed power supply monitoring module;
the electric power usage data processing module is used for acquiring electric power usage data acquired from a new area from the fusion terminal according to a preset acquisition frequency, wherein the new area refers to a development area in a city, and the electric power usage data comprises distributed power supply electric power data and city power grid electric power data; classifying the collected power use data according to the type of the power use data, wherein the type of the power use data comprises industrial production power consumption of each building in the new area and commercial life power consumption of each building in the new area, and power use information of each building in the new area is obtained; the new area prediction module is used for constructing a first building prediction model of a new area, generating the time and the type of newly added buildings in the new area in a preset period, constructing a second building prediction model of the new area, and generating predicted power use data change of each building in the new area in the preset period; the threshold analysis module is used for generating a predicted sharing proportion value of the distributed power supply according to proportion data of the electric quantity provided by the urban power grid and the distributed power supply; the distributed power supply monitoring module is used for acquiring a prediction sharing proportion value of the distributed power supply as threshold information of power utilization data according to output results of the first building prediction model and the second building prediction model, generating time early warning information when the predicted power utilization data in a new area exceed a threshold value, and outputting the time early warning information to an administrator port;
the output end of the power usage data processing module is connected with the input end of the new region prediction module; the output end of the new region prediction module is connected with the input end of the threshold analysis module; and the output end of the threshold analysis module is connected with the input end of the distributed power supply monitoring module.
The electric power usage data processing module comprises an electric power usage data acquisition unit and an electric power usage data classification unit;
the electric power usage data acquisition unit is used for acquiring electric power usage data acquired in a new area from the fusion terminal according to a preset acquisition frequency; the electric power usage data classification unit is used for classifying the collected electric power usage data according to the type of the electric power usage data.
The new area prediction module comprises a first building prediction unit and a second building prediction unit;
the first building prediction unit is used for constructing a first building prediction model of the new area and generating the time and the type of newly added buildings in the new area under a preset period; the second building prediction unit is used for constructing a second building prediction model of the new area and generating predicted power use data changes of buildings in the new area in a preset period.
The threshold analysis module comprises a historical data acquisition unit and an output unit;
the historical data acquisition unit is used for acquiring the proportion data of the electric quantity provided by the urban power grid and the distributed power supply; and the output unit is used for selecting an average value to generate a predicted sharing proportion value of the distributed power supply according to historical proportion data of the electric quantity provided by the urban power grid and the distributed power supply.
The distributed power supply monitoring module comprises a threshold selecting unit and a time early warning unit;
the threshold selecting unit acquires a predicted sharing proportion value of the distributed power supply as threshold information of power use data; and the time early warning unit is used for generating time early warning information according to the output results of the first building prediction model and the second building prediction model when the predicted power utilization data in the new region exceeds a threshold value, and outputting the time early warning information to an administrator port.
It should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described above, or equivalents may be substituted for elements thereof. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A distributed power supply comprehensive monitoring method based on a fusion terminal is characterized in that: the method comprises the following steps:
the method includes the steps that S1, electric power usage data collected in a new area are obtained from a fusion terminal according to a preset collection frequency, the new area refers to a development area in a city, and the electric power usage data comprise distributed power supply electric power data and city power grid electric power data;
s2, classifying the collected power utilization data according to the type of the power utilization data, wherein the type of the power utilization data comprises industrial production power consumption of each building in the new area and commercial life power consumption of each building in the new area, and power utilization information of each building in the new area is obtained;
s3, constructing a first building prediction model of the new area, generating the time and the type of newly added buildings in the new area in a preset period, constructing a second building prediction model of the new area, and generating predicted power use data changes of buildings in the new area in the preset period;
and S4, acquiring threshold information of the power utilization data according to output results of the first building prediction model and the second building prediction model, generating time early warning information when the power utilization data predicted in the new area exceeds the threshold, and outputting the time early warning information to an administrator port.
2. The integrated monitoring method for the distributed power supply based on the converged terminal according to claim 1, wherein the integrated monitoring method comprises the following steps: the distributed power supply power data refers to power usage data provided by distributed power supplies in a new area to each building; the urban power grid power data refers to power utilization data provided by the urban power grid for each building in the new area.
3. The integrated monitoring method for the distributed power supply based on the converged terminal according to claim 2, wherein the integrated monitoring method comprises the following steps: the first building prediction model comprises:
constructing an initial training set, and acquiring the time of the same newly added building in a new area, wherein the newly added buildings comprise two buildings, one is a building using industrial production electricity, and the other is a building using commercial life electricity;
establishing an initial training set according to historical time data of the same newly added building;
setting the mean square error function as the loss function, and recording asIn whichWhich represents the output of the optical fiber,setting the maximum iteration times for the first building prediction model, and recording as T;
at the loss functionWhen the minimum value is taken, the weak learner is initialized and recorded as;
Performing iterative training on the initialized weak learner, and respectively calculating the negative gradient of each data sample i in the initial training set:
Wherein, the first and the second end of the pipe are connected with each other,is the value of the data sample i,is composed ofA corresponding loss function; in the formulaAdopts the strong learning device of the previous roundA first building prediction model of; t represents the number of iterations;a differential is indicated;
using acquired negative gradientsFitting a regression tree, recording as the t-th regression tree, and recording as the corresponding leaf node regionCalculating the best fit value:
Wherein i and j are labels; c is a constant;
and adding the weak learner of each round into the trained model to obtain a new strong learner:
wherein the content of the first and second substances,representing a leaf area;representing a strong learner obtained by the t-th iteration; i represents the value of the best fitCombining, representing the decision tree fitting function of the current round;
when T = T, ending the iterative process and obtaining the final strong learnerAnd as an output first building prediction model, generating two groups of time data of newly added buildings by using the first building prediction model respectively, wherein a newly added time data set of the buildings using industrial production electricity is recorded as:(ii) a The newly added time data set of the building using the commercial life electricity is recorded as:(ii) a Wherein m and n are constants related to the preset period and satisfy、The time point is less than or equal to the end time of the preset period, and、at a time point greater than the end time of the preset period.
4. The integrated monitoring method for the distributed power supply based on the converged terminal according to claim 3, wherein: the second building prediction model comprises:
respectively acquiring classified electric power use data information, and taking historical information of electric power use data under the same building as a second training set;
respectively establishing a horizontal smoothing equation, a trend smoothing equation and a season smoothing equation to predict the seasons and the trends of the data;
wherein the horizontal smoothing equation is:
the trend smoothing equation is:
the seasonal smoothing equation is:
constructing a second building prediction model as follows:
wherein u is the current period power usage data; v is the cycle length;a smoothing parameter that is horizontal;a smoothing parameter that is a trend;a smoothing parameter for the season;is a firstA predicted value of the period, i.e., power usage data at the h-th period;actual value for the u-th period, i.e., power usage data for the u-th period;is the estimated level of the u-th stage;is the predicted trend of the u-th stage;seasonal smooth prediction for the u-th stage;
and respectively generating power utilization data change predicted values of two buildings in the new area by using a second building prediction model, wherein the power utilization data change predicted values of the buildings using industrial production power are integrated as:(ii) a The set of predicted values of the change of the electricity utilization data of the building using the electricity of the commercial life is recorded as:(ii) a Wherein、All represent constant values.
5. The integrated monitoring method for the distributed power supply based on the converged terminal according to claim 4, wherein: the generating time early warning information comprises:
constructing a time early warning model:
wherein the content of the first and second substances,at a time pointPower usage data of the time;represents rounding up;representing a data set for using industrial production electricity when selecting electricity use data;representing a data set for using commercial life electricity when selecting electricity use data;represents a serial number;representing the time pointThe total number of buildings using industrial production electricity is newly added in the new area;representing the time pointThe total number of buildings using electricity for commercial life is newly added in the new region;representing the time point of the newly added building;representing a cycle duration between data in the second building prediction model;at the time pointA predicted value of a change in electricity usage data of a building using electricity for industrial production;at the time pointThe total number of buildings using electricity in the original industrial production;at the time pointA predicted value of a change in electricity usage data of a structure using electricity for business life;at the time pointThe total number of buildings powered by the original commercial life;
wherein the content of the first and second substances,by taking the time pointAccording to the calculation, selecting and calculating in the sets A and B; obtaining the threshold value of the power supply of the distributed power supply, and recording as;
ObtainingIs greater than or equal to for the first timeTime point of timeObtaining an average time required to build a new distributed power stationGenerating time warning information atTo the administrator port at the time point of (c); whereinRepresents the average value of the proportion of the supplied power of the distributed power supply and the urban power grid.
6. A distributed power supply comprehensive monitoring system based on a fusion terminal is characterized in that: the system comprises: the system comprises an electric power usage data processing module, a new region prediction module, a threshold analysis module and a distributed power supply monitoring module;
the electric power usage data processing module is used for acquiring electric power usage data acquired from a new area from the fusion terminal according to a preset acquisition frequency, wherein the new area refers to a development area in a city, and the electric power usage data comprises distributed power supply electric power data and city power grid electric power data; classifying the collected power use data according to the type of the power use data, wherein the type of the power use data comprises industrial production power consumption of each building in the new area and commercial life power consumption of each building in the new area, and power use information of each building in the new area is obtained; the new area prediction module is used for constructing a first building prediction model of a new area, generating the time and the type of a newly added building in the new area under a preset period, constructing a second building prediction model of the new area, and generating predicted power use data change of each building in the new area under the preset period; the threshold analysis module is used for generating a predicted sharing proportion value of the distributed power supply according to proportion data of the electric quantity provided by the urban power grid and the distributed power supply; the distributed power supply monitoring module is used for acquiring a predicted sharing proportion value of the distributed power supply as threshold information of power utilization data according to output results of the first building prediction model and the second building prediction model, generating time early warning information when the predicted power utilization data in the new area exceed the threshold, and outputting the time early warning information to an administrator port;
the output end of the power usage data processing module is connected with the input end of the new region prediction module; the output end of the new region prediction module is connected with the input end of the threshold analysis module; and the output end of the threshold analysis module is connected with the input end of the distributed power supply monitoring module.
7. The integrated monitoring system for the distributed power supply based on the converged terminal according to claim 6, wherein: the electric power usage data processing module comprises an electric power usage data acquisition unit and an electric power usage data classification unit;
the electric power usage data acquisition unit is used for acquiring electric power usage data acquired in a new area from the fusion terminal according to a preset acquisition frequency; the power usage data classification unit is used for classifying the collected power usage data according to the type of the power usage data.
8. The integrated monitoring system for the distributed power supply based on the converged terminal according to claim 6, wherein: the new area prediction module comprises a first building prediction unit and a second building prediction unit;
the first building prediction unit is used for constructing a first building prediction model of the new area and generating the time and the type of newly added buildings in the new area under a preset period; the second building prediction unit is used for constructing a second building prediction model of the new area and generating predicted power use data changes of buildings in the new area in a preset period.
9. The integrated monitoring system for the distributed power supply based on the converged terminal according to claim 6, wherein: the threshold analysis module comprises a historical data acquisition unit and an output unit;
the historical data acquisition unit is used for acquiring the proportion data of the electric quantity provided by the urban power grid and the distributed power supply; and the output unit is used for selecting an average value to generate a predicted sharing proportion value of the distributed power supply according to historical proportion data of the electric quantity provided by the urban power grid and the distributed power supply.
10. The integrated monitoring system for the distributed power supply based on the converged terminal according to claim 6, wherein: the distributed power supply monitoring module comprises a threshold selecting unit and a time early warning unit;
the threshold selecting unit acquires a predicted sharing proportion value of the distributed power supply as threshold information of power use data; and the time early warning unit is used for generating time early warning information according to the output results of the first building prediction model and the second building prediction model when the predicted power utilization data in the new region exceed a threshold value, and outputting the time early warning information to the administrator port.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211230968.4A CN115296424B (en) | 2022-10-10 | 2022-10-10 | Distributed power supply comprehensive monitoring system and method based on fusion terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211230968.4A CN115296424B (en) | 2022-10-10 | 2022-10-10 | Distributed power supply comprehensive monitoring system and method based on fusion terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115296424A true CN115296424A (en) | 2022-11-04 |
CN115296424B CN115296424B (en) | 2023-01-31 |
Family
ID=83819221
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211230968.4A Active CN115296424B (en) | 2022-10-10 | 2022-10-10 | Distributed power supply comprehensive monitoring system and method based on fusion terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115296424B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115967175A (en) * | 2022-11-30 | 2023-04-14 | 广州汇电云联互联网科技有限公司 | Edge end data acquisition control device and method for energy storage power station |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104732295A (en) * | 2015-03-31 | 2015-06-24 | 国家电网公司 | Power load predicating model based on big data technology |
CN106570581A (en) * | 2016-10-26 | 2017-04-19 | 东北电力大学 | Attribute association based load prediction system and method in energy Internet environment |
CN107563539A (en) * | 2017-07-24 | 2018-01-09 | 佛山市顺德区中山大学研究院 | Short-term and long-medium term power load forecasting method based on machine learning model |
CN108038572A (en) * | 2017-12-08 | 2018-05-15 | 天津天大求实电力新技术股份有限公司 | Method for predicting new situation load potential in rural area |
CN111091232A (en) * | 2019-11-25 | 2020-05-01 | 黑龙江电力调度实业有限公司 | Power load prediction method considering power demand change trend |
US20200333767A1 (en) * | 2018-02-17 | 2020-10-22 | Electro Industries/Gauge Tech | Devices, systems and methods for predicting future consumption values of load(s) in power distribution systems |
-
2022
- 2022-10-10 CN CN202211230968.4A patent/CN115296424B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104732295A (en) * | 2015-03-31 | 2015-06-24 | 国家电网公司 | Power load predicating model based on big data technology |
CN106570581A (en) * | 2016-10-26 | 2017-04-19 | 东北电力大学 | Attribute association based load prediction system and method in energy Internet environment |
CN107563539A (en) * | 2017-07-24 | 2018-01-09 | 佛山市顺德区中山大学研究院 | Short-term and long-medium term power load forecasting method based on machine learning model |
CN108038572A (en) * | 2017-12-08 | 2018-05-15 | 天津天大求实电力新技术股份有限公司 | Method for predicting new situation load potential in rural area |
US20200333767A1 (en) * | 2018-02-17 | 2020-10-22 | Electro Industries/Gauge Tech | Devices, systems and methods for predicting future consumption values of load(s) in power distribution systems |
CN111091232A (en) * | 2019-11-25 | 2020-05-01 | 黑龙江电力调度实业有限公司 | Power load prediction method considering power demand change trend |
Non-Patent Citations (1)
Title |
---|
姜世公等: "基于改进集成学习的交直流配电系统短期负荷预测方法", 《科技通报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115967175A (en) * | 2022-11-30 | 2023-04-14 | 广州汇电云联互联网科技有限公司 | Edge end data acquisition control device and method for energy storage power station |
CN115967175B (en) * | 2022-11-30 | 2024-05-10 | 广州汇电云联数科能源有限公司 | Edge data acquisition control device and method for energy storage power station |
Also Published As
Publication number | Publication date |
---|---|
CN115296424B (en) | 2023-01-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Xu et al. | A distributed and robust energy management system for networked hybrid AC/DC microgrids | |
Ma et al. | A review of forecasting algorithms and energy management strategies for microgrids | |
CN106684915A (en) | Wind-hydrogen coupling power generation system optimization method and device thereof | |
CN110266010A (en) | DC distribution net grid structure and distributed photovoltaic multiple target cooperative optimization method | |
Sun | Energy internet and we-energy | |
Zhang et al. | Grid–source coordinated dispatching based on heterogeneous energy hybrid power generation | |
CN115296424B (en) | Distributed power supply comprehensive monitoring system and method based on fusion terminal | |
Wang et al. | Multi-attribute decision analysis for optimal design of park-level integrated energy systems based on load characteristics | |
CN114861539A (en) | Modeling and implementation method for 5G urban comprehensive energy Internet digital twin system | |
Yang et al. | Deep learning-based distributed optimal control for wide area energy Internet | |
Chen et al. | Spatiotemporal analysis of line loss rate: A case study in China | |
CN112865101B (en) | Linear transaction method considering uncertainty of output of renewable energy | |
CN105391091A (en) | Distributed energy management method based on analytic hierarchy process and membership | |
CN110689248A (en) | First-class city power distribution network evaluation method based on cloud model and probability analysis | |
Gao et al. | Green Energy Cloud-Taxonomy, Infrastructure, Platform, and Services | |
CN113673141A (en) | Energy router modeling and optimization control method based on data driving | |
CN108233373B (en) | Probability harmonic analysis method considering weather scene for distributed photovoltaic access power distribution network | |
CN109861272B (en) | Multi-voltage-level power grid distributed power supply optimal configuration method considering electric quantity delivery | |
Ibrahim et al. | Modelling an Artificial Intelligence-Based Energy Management for Household in Nigeria. | |
Qingyang et al. | Application analysis of big data technology in energy internet | |
CN117913866B (en) | Energy storage system based on photovoltaic power generation | |
Wei | Multi-Scale Optimal Design of Sustainable Future Urban Energy System | |
Wang et al. | Optimal Scheduling of Electrical Energy Systems Using a Fluid Dynamic Analogy | |
Wu et al. | Electricity Market Clearing Model Considering Uncertainty of Wind Power | |
CN108470223A (en) | A kind of distributed home photovoltaic energy efficiency management system and management method |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |