CN113487447A - Power distribution network load prediction and line loss cause analysis method based on big data - Google Patents
Power distribution network load prediction and line loss cause analysis method based on big data Download PDFInfo
- Publication number
- CN113487447A CN113487447A CN202110420222.9A CN202110420222A CN113487447A CN 113487447 A CN113487447 A CN 113487447A CN 202110420222 A CN202110420222 A CN 202110420222A CN 113487447 A CN113487447 A CN 113487447A
- Authority
- CN
- China
- Prior art keywords
- data
- line loss
- analysis
- load
- loss
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 121
- 238000009826 distribution Methods 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 claims abstract description 65
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 230000002159 abnormal effect Effects 0.000 claims description 38
- 230000008859 change Effects 0.000 claims description 26
- 238000012423 maintenance Methods 0.000 claims description 16
- 230000009466 transformation Effects 0.000 claims description 15
- 230000035515 penetration Effects 0.000 claims description 12
- 238000007726 management method Methods 0.000 claims description 11
- 230000003068 static effect Effects 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 8
- 238000011161 development Methods 0.000 claims description 7
- 230000018109 developmental process Effects 0.000 claims description 7
- 230000002441 reversible effect Effects 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 230000032683 aging Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims description 4
- 230000011664 signaling Effects 0.000 claims description 3
- 238000010835 comparative analysis Methods 0.000 claims description 2
- 230000009467 reduction Effects 0.000 abstract description 6
- 238000013024 troubleshooting Methods 0.000 abstract description 4
- 230000005856 abnormality Effects 0.000 description 8
- 238000007418 data mining Methods 0.000 description 8
- 230000009977 dual effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000000611 regression analysis Methods 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 238000009795 derivation Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 125000004432 carbon atom Chemical group C* 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012314 multivariate regression analysis Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of load prediction and line loss analysis of a power distribution network, and discloses a method for load prediction and line loss cause analysis of the power distribution network based on big data, which comprises the following steps: selecting proper data characteristics to establish a load prediction model according to the load characteristic analysis result and algorithm model selection; according to the short-term and ultra-short-term load prediction models, carrying out load prediction calculation aiming at an analysis object, carrying out line and distribution transformer operation analysis by combining equipment capacity, carrying out classification statistics aiming at the operation conditions of heavy overload, economic operation and light idle load of equipment, setting a corresponding threshold value aiming at the distribution transformer operation analysis result, carrying out early warning when the predicted value is equal to the threshold value, carrying out alarm when the predicted value exceeds the threshold value, and correspondingly outputting short-term and ultra-short-term early warning and alarm information; the method is based on the line loss actual analysis case, diagnoses the causes of the problems of high loss, negative loss and the like, and provides a primary solution to assist in commanding and carrying out loss reduction problem troubleshooting work by maintainers.
Description
Technical Field
The invention belongs to the technical field of power distribution network load prediction and line loss analysis, and particularly relates to a power distribution network load prediction and line loss cause analysis method based on big data.
Background
The power distribution network is used as an intermediate link for connecting a power grid and a power load, is a neural center of a power system, and is an important means for maintaining power production, ensuring safe and stable operation of power and realizing optimal allocation of power system resources. The method is also a recent production link directly oriented to power customers for power supply, and the reliable operation of the power distribution network is closely related to the production life of the power customers. In order to guarantee the customer service level, the national grid company is reformed from the organization, a power supply service command center is established, the construction of a power supply service command system is developed, and the power supply service command work is ensured by coordinating multi-party resources. From the current situation of Hebei companies, the power supply service command system has comprehensively fused the existing operation inspection, marketing, regulation and control professional system data, a large amount of work is carried out in the aspect of power distribution network management, the problems of 'unclear' sight, 'blindness' and 'inaccurate estimation' existing in the overall operation management work of the power distribution network are basically solved, each unit is prompted to construct a closed-loop working mechanism, perfect business application support is formed in the aspects of supporting operation and maintenance, overhaul and first-aid repair of the power distribution network, a large amount of high-value data are accumulated, however, in the aspects of deep data mining, equipment operation analysis and line loss analysis, a larger promotion space is provided, and particularly in the aspects of deep application such as load prediction and line loss analysis, the power distribution network operation future state evaluation and line loss deep-level cause analysis cannot be carried out. Meanwhile, the existing construction achievement of the power supply service command system provides a good data foundation for power distribution network load prediction and line loss cause big data analysis construction.
With the rapid development of national economy, the living standard of residents is also continuously improved, various novel high-power household appliances also enter thousands of households more widely, the power selling amount and revenue of a power grid company are increased, and simultaneously, greater challenges are brought to the safety and stability of a power distribution network, and the losses of equipment failure cost, power selling loss and the associated losses of power supply reliability index reduction, customer satisfaction reduction, customer complaints and the like caused by heavy overload of the equipment are unacceptable for power enterprises. How to ensure distribution network line and join in marriage economic reliable operation of becoming, the problem that awaits the solution urgently in the distribution network operation management has become, consequently, carries out distribution network load prediction and heavily transships, light no-load analysis, supports the electric wire netting enterprise and improves the operation mode, promotes distribution network safety and stability operation, promotes the power supply reliability, is very necessary.
The traditional line loss treatment method generally comprises the steps of data checking of a PMS/marketing/synchronous line loss system, site investigation, live inspection and the like. The mode has long working time and low efficiency, and is easy to have treatment dead angles. Particularly, in the verification link of problems such as a topological relation error, a large amount of power failure verification actions are needed, great risks and costs exist, the method is not economical, and the influence brought by comprehensively developing line loss management by using a traditional method cannot be borne by a power grid company, so that a large amount of historical problems are left and roll influence is caused. Therefore, by means of an informatization method, mining analysis is carried out on equipment ledgers and operation data, line loss cause analysis is developed by evaluating various characteristic data of the power distribution network, and accurate positioning, checking and correction of line loss treatment problems are guided.
In summary, it is necessary to develop load prediction and line loss cause big data analysis research for the power distribution network in the river and north of the national grid.
Disclosure of Invention
The invention aims to provide a power distribution network load prediction and line loss cause analysis method based on big data, and aims to solve the existing problems.
In order to achieve the purpose, the invention provides the following technical scheme: a power distribution network load prediction and line loss cause analysis method based on big data comprises the following steps:
selecting proper data characteristics to establish a load prediction model according to the load characteristic analysis result and algorithm model selection;
according to the short-term and ultra-short-term load prediction models, load prediction calculation is carried out on an analysis object, line and distribution transformation operation analysis is carried out by combining the capacity of equipment, classification statistics is carried out on the operation conditions of heavy overload, economic operation and light idle load of the equipment, and the analysis result is pushed to operation and maintenance personnel through app to be checked.
And constructing a flow line loss cause analysis model based on the line loss actual analysis case, diagnosing the causes of the high loss and negative loss problems and providing a primary solution.
Preferably, the method for power distribution network load prediction and line loss cause analysis based on big data according to the present invention comprises the following steps of developing load prediction calculation for an analysis object according to a short-term and ultra-short-term load prediction model, developing line and distribution transformation operation analysis by combining with device capacity, performing classification statistics for heavy overload, economic operation and light no-load operation conditions of the device, and pushing an analysis result to operation and maintenance personnel through app for checking:
and setting a corresponding threshold value aiming at the distribution transformer operation analysis result, performing early warning when the predicted value is equal to the threshold value, performing alarm when the predicted value exceeds the threshold value, correspondingly outputting short-term and ultra-short-term early warning and alarm information, pushing the analysis result to operation and maintenance personnel through app for checking, and pushing the analysis result to management personnel for decision making.
Preferably, the method for load prediction and line loss cause analysis of a power distribution network based on big data comprises the following steps before selecting suitable data characteristics to establish a load prediction model according to a load characteristic analysis result and an algorithm model selection:
collecting operation data, statistical data and meteorological data, and importing external static data;
performing source tracing verification and recalculation on the statistical data;
cleaning and processing the collected operation data, meteorological data, imported external static data and statistical data which are subjected to source tracing verification and recalculation;
and analyzing the load characteristics based on the N dimensions, and selecting a data modeling and prediction algorithm.
Preferably, the operation data comprises voltage data, current data and power data of a line/distribution transformer; the statistical data comprises historical load data and line loss index data; the meteorological data are integrated data of the power supply service command system, and comprise temperature and humidity data, wind speed data and weather data; the external static data comprises holidays and economic development indexes.
Preferably, the method for load prediction and line loss cause analysis of a power distribution network based on big data according to the present invention comprises the following steps of, after selecting suitable data characteristics to build a load prediction model according to the load characteristic analysis result and the algorithm model selection:
quantizing prediction accuracy by adopting an R square and a variance, and adaptively selecting an optimal model for prediction;
continuously monitoring the accuracy of prediction, and quantifying the prediction effect by adopting a measurement goodness-of-fit R square and a variance to realize the visualization of evaluation after prediction;
and detecting whether the load prediction model has the condition that the accuracy rate is not expected or reduced, and when the load prediction model has the condition that the accuracy rate is not expected or reduced, feeding back and adaptively optimizing the load prediction model again.
Preferably, the method for power distribution network load prediction and line loss cause analysis based on big data according to the present invention includes the steps of, in the line loss actual analysis case, constructing a streamlined line loss cause analysis model, diagnosing causes of high loss and negative loss problems, and providing a preliminary solution:
according to the actual analytic case of the line loss, the cause and the degree of association of the line loss are analyzed, the association and the characteristics of the cause and the characteristic including the problem of marketing and distribution breakthrough, the problem of gateway model configuration, the problem of abnormal metering of a power supply gateway, the problem of abnormal metering of a power selling gateway, technical problems and the occurrence of the line loss are developed, and a line loss cause characteristic library is formed.
Preferably, the method for power distribution network load prediction and line loss cause analysis based on big data according to the present invention analyzes causes and correlation degrees of line loss caused by the line loss actual analytic case, develops correlations and characteristics including marketing and distribution penetration problem, gateway model configuration problem, power supply gateway metering abnormality problem, power selling gateway metering abnormality problem, technical problems and line loss occurrence, and forms a line loss cause characteristic library specifically including the steps of:
by collecting configuration information of the integrated gateway model, the gateway model is contrasted and analyzed with the integrated gateway model, and inconsistent gateway configuration lists are automatically analyzed;
when high-loss negative loss occurs, judging whether the line-change relation is correct or not through voltage relativity, calculating correlation coefficients of line voltage and distribution transformer outlet voltage curves by using a big data algorithm, and identifying line-loss calculation errors caused by abnormal line-change relation through correlation degrees;
based on the distribution automation remote signaling state change event data, PMS equipment maintenance data and realization of monitoring the change of the setting state of the interconnection switch;
when two close circuits appear high loss, burden when losing simultaneously, because the liaison relation between the GIS automatic identification circuit, have liaison relation or dual supply user's circuit opposite line loss abnormal conditions appears simultaneously, supplementary realization liaison circuit and dual supply circuit high loss burden cause of losing study and judge.
Preferably, the method for power distribution network load prediction and line loss cause analysis based on big data according to the present invention analyzes causes and correlation degrees of line loss caused by the line loss actual analytic case, develops correlations and characteristics including marketing and distribution penetration problem, gateway model configuration problem, power supply gateway metering abnormality problem, power selling gateway metering abnormality problem, technical problems and line loss occurrence, and forms a line loss cause characteristic library specifically including the steps of:
and (3) based on the metering data of the state network power utilization information acquisition system and the configuration data of the integrated gateway model, the situation that the reverse electric quantity exists but the distributed gateway model is not configured is researched and judged.
Preferably, the method for power distribution network load prediction and line loss cause analysis based on big data according to the present invention analyzes causes and correlation degrees of line loss caused by the line loss actual analytic case, develops correlations and characteristics including marketing and distribution penetration problem, gateway model configuration problem, power supply gateway metering abnormality problem, power selling gateway metering abnormality problem, technical problems and line loss occurrence, and forms a line loss cause characteristic library specifically including the steps of:
whether the upper and lower bottom surfaces are empty or not, the upper bottom surface is larger than the lower bottom surface, the bottom surface is skipped, and the bottom surface is 0 is researched and judged based on the collected power supply side gateway metering data, and meanwhile, the meter replacement is monitored based on the metering configuration data;
and comparing and analyzing the integrated electric quantity of the EMS system and the electric quantity of the TMR system, and judging that the change of the transformer station account change ratio is wrong when the difference between the integrated electric quantity of the EMS system and the electric quantity of the TMR system exceeds a threshold value.
Preferably, the method for power distribution network load prediction and line loss cause analysis based on big data according to the present invention analyzes causes and correlation degrees of line loss caused by the line loss actual analytic case, develops correlations and characteristics including marketing and distribution penetration problem, gateway model configuration problem, power supply gateway metering abnormality problem, power selling gateway metering abnormality problem, technical problems and line loss occurrence, and forms a line loss cause characteristic library specifically including the steps of:
judging whether the multiplying power is normal or not by judging whether the multiplying power of the transformer area ratio error caused by new equipment or equipment aging is configured to be 1.1 to 1.7 times of the distribution transformer capacity value or whether the normal operation load current is not less than 30% of the rated value;
based on a TMR system and meter clock data and calendar clock data of a national grid power utilization information acquisition system, comparison analysis of a supply meter clock and a sale side meter clock and a calendar clock is realized, inconsistent list data is listed, and rectification and correction are performed.
Compared with the prior art, the invention has the following beneficial effects: according to the method, load characteristic analysis is carried out according to the cleaned data, a reliable algorithm performance is selected to form an algorithm library, a load prediction model is constructed, and training and optimization are carried out on the model by using training data; calculating conclusion and equipment capacity data based on a load prediction model, carrying out prediction analysis on running conditions of heavy overload, light idle load and the like of the equipment, and carrying out corresponding running abnormity warning according to a preset threshold; based on the actual line loss analysis case, a flow line loss cause analysis model is constructed, the causes of the problems of high loss, negative loss and the like are diagnosed, and a primary solution is provided to assist a command and a maintainer to carry out the troubleshooting work of the loss reduction problem.
Drawings
FIG. 1 is a schematic structural diagram of 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 derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Interpretation of terms:
EMS systems, energy management systems;
TMR system, electric energy measurement charging system.
Referring to fig. 1, the present invention provides the following technical solutions: a power distribution network load prediction and line loss cause analysis method based on big data comprises the following steps:
s100, selecting proper data characteristics to establish a load prediction model according to the load characteristic analysis result and algorithm model selection;
s200, carrying out load prediction calculation on an analysis object according to short-term and ultra-short-term load prediction models, carrying out line and distribution transformation operation analysis by combining equipment capacity, carrying out classification statistics on operation conditions of heavy overload, economic operation and light idle load of the equipment, and pushing an analysis result to operation and maintenance personnel through app for checking; it should be noted that the APP includes an operation and maintenance management APP with the publication number "CN 107832856A" and the patent name "a method for operation and maintenance management APP".
S210, setting a corresponding threshold value aiming at a distribution transformer operation analysis result, carrying out early warning when a predicted value is equal to the threshold value, carrying out alarm when the predicted value exceeds the threshold value, correspondingly outputting short-term and ultra-short-term early warning and alarm information, pushing the analysis result to operation and maintenance personnel through app for checking, and pushing the analysis result to management personnel for decision making;
s300, based on the line loss actual analysis case, a flow line loss cause analysis model is constructed, the causes of the high loss and negative loss problems are diagnosed, and a primary solution is provided.
In this embodiment, firstly, offline/online data of the national grid power consumption information acquisition system, the meteorological system, the integrated line loss and other business systems are acquired, the offline/online data enter a data center, and data cleaning and processing are performed based on a unified data analysis service of the data center. And constructing a load prediction model based on the cleaned data set, carrying out induction and arrangement on algorithms related to load prediction analysis, and researching and developing a core algorithm library for load prediction. Secondly, calculating and discussing the capacity data of the equipment based on a load prediction model, carrying out prediction analysis on the running conditions of heavy overload, light idle load and the like of the equipment, and carrying out corresponding running abnormity warning according to a preset threshold value. And finally, constructing a streamlined line loss cause analysis model. The method diagnoses the causes of the problems of high loss, negative loss and the like and provides a primary solution to assist in commanding and carrying out troubleshooting work on the loss reduction problems by maintainers.
It is worth to be explained that the theoretical basis of the distribution network short-term load prediction method comprises the following steps:
the regression analysis method is a quantitative prediction method and is mainly embodied in researching the mutual relation among things. According to the number of independent variables of the cause-and-effect relationship of things, a regression analysis method can be divided into a unitary or multivariate regression analysis method; when the expression describing the inter-causal function is linear or non-linear, it can be further classified into a linear regression analysis method and a non-linear regression analysis method. The regression analysis method has the advantages of indicating the remarkable relation between independent variables and dependent variables and indicating the influence strength of a plurality of independent variables on one dependent variable. The calculation principle is simple, the operation speed is high, and the extrapolation performance is good. The method has the defects that various load influence factors are not considered in the prediction process, the accuracy of a calculation result is low due to the simple structure, and strict requirements are imposed on initial data. The method has serious dependence on the accuracy of the model and the accuracy of the predicted value of the influence factor. When using this method, care is taken whether the fit intervals are all consistent.
The time series analysis is a theoretical method for establishing a mathematical model by performing curve fitting and parameter estimation on historical load data, is used for predicting future values of the load of the power system, and is a time series array obtained by continuously recording the historical load data. The method is a relatively mature algorithm developed in the short-term load prediction of the power system. The initial data of the time series method is obtained by system observation, the predicted value of the time series method reflects the continuity of load change, and the arithmetic speed of the algorithm is high. However, the time series method is the same as the regression analysis method, no load influence factor is considered in load prediction, and the load prediction error is large.
The load derivation method has a prediction formula for the load derivation method for the load sequence p (i) (i is 1,2,3 …) as follows:
p(i+1)fore＝p(i)re+Δp(i)fore
wherein, for represents a predicted value, and re represents an actual value;
the meaning of the formula is that the sum of the predicted value of the point load change rate and the actual value of the point load is equal to the predicted value of the point load (i + 1). The formula for the rate of change of load is as follows:
wherein D is the days of selecting the past load; kjIs a suitable factor for day j; Δ pj(i)reIs the actual value of the load at the ith point on day j.
From the above formula, the principle of the derivation method is simple and clear, and meanwhile, the change rate is required to have regularity and stability, but calculation errors are superposed.
Exponential smoothing, which is a method of directly predicting future values of a time series by exponentially weighted combining of history data. The basic form is as follows:
in the formula:
is a predicted load value; x (t-i) is an actual load value; alpha is an attenuation factor; n is the initial load number.
In the above formula, the first and second carbon atoms are,
the basic principle of the method is that the recent data have large influence on prediction and the long-term data have small influence on prediction. The larger alpha is, the faster the weight coefficient of the data from the near term to the far term is changed from large to small, and the function of emphasizing the recent data is.
The method takes the power demand as a whole to predict a single index, the principle of the method is simple, but the method does not well reflect the current power market, weather, holidays and other influence factors.
The artificial neural network is a nonlinear system simulating the human brain neural network to learn and process problems. The method is composed of a plurality of neuron nodes with parallel operation function and corresponding weights for connecting the neuron nodes, and realizes the nonlinear mapping from input variables to output variables through an excitation function. And (3) establishing a proper network structure by using the historical load as a training sample, and using the network as a prediction model for load prediction after the trained network structure meets the prediction requirement. The artificial neural network has the advantages of low requirement on a prediction model, high applicability to highly nonlinear objects, strong robustness, memory capability, nonlinear mapping capability and strong self-learning capability, and has the characteristics which are not possessed by other algorithms. The method has the disadvantages that the learning convergence speed is very slow, the result is likely to converge to a local minimum point, the knowledge expression capability is not good, fuzzy knowledge existing in the experience of a scheduler is not fully utilized, and the number of network layers and the number of neurons are determined according to subjective experience.
According to the data mining method, the load prediction has a large amount of historical data, and the accuracy of the load prediction of the power system depends on the accuracy of the historical data. The data mining provides a new method for load prediction analysis of a large amount of historical data, and can eliminate redundant information from the large amount of data and extract useful information, wherein the useful information mainly comprises data definition problems, data collection and preprocessing, mining implementation, interpretation and evaluation results, and the whole mining process is to continuously feed back and correct the data and find out the rule of short-term load change. The short-term load prediction of a support vector machine for processing historical data by using a data mining method is carried out, firstly, a hierarchical clustering method in data mining is used for clustering historical loads to establish a decision tree, and input load data of the support vector machine is obtained through the decision tree to carry out load prediction; dividing a support vector machine prediction model of a user by using a K-means data mining model in data mining, dividing the user into 6 groups with similarity by using the K-means data mining model, performing subentry prediction by using an optimized support vector machine, and comprehensively obtaining a prediction result.
Specifically, before the step S100 of selecting a suitable data feature to establish a load prediction model according to a load characteristic analysis result and an algorithm model selection, the method includes the steps of:
s10, collecting operation data, statistical data and meteorological data, and importing external static data;
s20, carrying out source tracing verification and recalculation on the statistical data;
s30, cleaning and processing the collected operation data, meteorological data, imported external static data and statistical data which are subjected to source tracing verification and recalculation;
s40 analyzes the load characteristics based on N dimensions, selects data modeling and prediction algorithms.
Specifically, the operational data includes line/distribution voltage data, current data, and power data; the statistical data comprises historical load data and line loss index data; the meteorological data are integrated data of the power supply service command system, and comprise temperature and humidity data, wind speed data and weather data; the external static data comprises holidays and economic development indexes.
In this embodiment, according to the data requirements of the load prediction analysis and line loss cause analysis model, the power supply service command system is used to collect operation data such as voltage, current, and power data of the line/distribution transformer, and collect and verify statistical data such as historical load data and line loss index data, so as to ensure the accuracy of the data, and collect meteorological data integrated by the power supply service command system, including temperature, humidity, wind speed, weather, and the like.
The method supports the import of external static data, such as holidays, economic development indexes and the like, and the data are unnecessary and difficult to acquire by integrating other systems due to the static characteristics of the data.
Many null values and abnormal data always exist in the original data, and in order to ensure the accuracy of prediction analysis, a set of proper cleaning rules needs to be established, so that an accurate data source is provided for load prediction and line loss analysis. In addition, the source data are distributed in different tables, and the data are required to be integrated to generate a uniform data model, which contains load values and other data characteristics (such as weather, etc.) for model establishment and load prediction.
Meanwhile, for various types of initial statistical data, source tracing data verification and recalculation are required, and accuracy of the statistical data is ensured.
Based on multiple dimensions such as climate, solar terms, holidays, economic development indexes and the like, load characteristics are analyzed, and modeling of support data and selection of prediction algorithms are carried out. The load characteristic analysis mainly comprises load component analysis, load periodicity analysis, load correlation analysis, holiday load analysis, climate load analysis, solar terms load analysis, economic development index load analysis and the like.
And carrying out induction and sorting on algorithms related to load prediction analysis according to the data basis of the user load prediction and the load characteristic analysis result, and researching and developing a core algorithm library of the load prediction.
Based on the load characteristic analysis result, the short-term (daily) and ultra-short-term (temporal) load prediction analysis can be regarded as a regression problem, and algorithms such as dragline regression, ridge regression, tree models (decision trees, random forests, xgboost), multi-model fusion (such as random forests and xgboost) and the like are mainly adopted to carry out analysis.
And selecting proper data characteristics for modeling according to the conclusion of the load characteristic analysis and the algorithm type selection. And integrating the equipment operation data, the load data, the climate data, the holiday data, the economic index data and other data to form a multi-factor training set.
After modeling and optimization are respectively carried out by adopting each algorithm and a mixing method, the prediction accuracy is quantized by adopting the R square and the variance, and the optimal model is adaptively selected for prediction.
In the operation process, the prediction accuracy is continuously monitored, the prediction effect is quantized by adopting a measurement goodness of fit R square and a variance, the visualization of estimation after prediction is realized, whether the accuracy rate of the model is not expected or reduced is detected, feedback is carried out, and the prediction model is adaptively optimized again.
Specifically, the step S100 of selecting a suitable data feature to establish a load prediction model according to the load characteristic analysis result and the algorithm model selection includes:
s110, quantizing prediction accuracy by adopting an R square and a variance, and adaptively selecting an optimal model for prediction;
s120, continuously monitoring the accuracy of prediction, and quantifying the prediction effect by adopting a measurement goodness of fit R square and a variance to realize the visualization of evaluation after prediction;
s130, whether the load prediction model has the condition that the accuracy rate is not expected or reduced or not is detected, and when the load prediction model has the condition that the accuracy rate is not expected or reduced, feedback is carried out and the load prediction model is adaptively optimized again.
In the embodiment, the load prediction model is used for calculating and discussing the capacity data of the equipment, carrying out prediction analysis on the running conditions of heavy overload, light idle load and the like of the equipment, and carrying out corresponding running abnormity warning according to a preset threshold value.
According to the short-term and ultra-short-term load prediction models, load prediction calculation is carried out on an analysis object, line and distribution transformation operation analysis is carried out by combining the capacity of equipment, and classified statistics is carried out on the operation conditions of heavy overload, economic operation, light idle load and the like of the equipment. And pushing the analysis result to operation and maintenance personnel through the app for checking.
And setting a corresponding threshold value aiming at the distribution transformer operation analysis result, performing early warning when the predicted value is equal to the threshold value, performing alarm when the predicted value exceeds the threshold value, correspondingly outputting short-term and ultra-short-term early warning and alarm information, pushing the analysis result to operation and maintenance personnel through app for checking, and pushing the analysis result to management personnel for decision making.
Specifically, the S300, based on the line loss actual analysis case, constructs a streamlined line loss cause analysis model, diagnoses causes of high loss and negative loss problems, and provides a preliminary solution, and then includes the steps of:
s400, according to the actual line loss analysis case, the cause and the degree of association of the line loss are analyzed, and the association and the characteristics of the cause and the degree of association of the line loss, including marketing and distribution through problems, gateway model configuration problems, power supply gateway metering abnormal problems, power selling gateway metering abnormal problems, technical problems and line loss are developed to form a line loss cause characteristic library.
Specifically, the S400 analyzes the cause and the degree of association of the line loss according to the actual line loss analytic case, develops the association and the characteristics including the marketing and distribution penetration problem, the gateway model configuration problem, the power supply gateway metering abnormal problem, the power selling gateway metering abnormal problem, the technical problem and the line loss occurrence, and forms the line loss cause characteristic library specifically including the steps of:
s410, by acquiring configuration information of the integrated gateway model, the gateway model is contrasted and analyzed with the integrated gateway model, and inconsistent gateway configuration lists are automatically analyzed;
s4101, when high loss and negative loss occur, judging whether the line change relation is correct or not through voltage relevance, calculating correlation coefficients of line voltage and distribution transformer outlet voltage curves by using a big data algorithm, and identifying line loss calculation errors caused by abnormal line change relation through correlation degrees;
s4102, based on the distribution automation remote signaling state change event data and PMS equipment maintenance data, monitoring the change of the setting state of the interconnection switch is realized;
s4103, when two close lines have high loss and negative loss at the same time, based on GIS, automatically identifying the contact relation between the lines, and when the lines with contact relation or dual-power-supply users have opposite line loss abnormal conditions at the same time, and assisting in judging the cause of the high loss and negative loss of the contact lines and the dual-power-supply lines.
Specifically, the S400 analyzes the cause and the degree of association of the line loss according to the actual line loss analytic case, develops the association and the characteristics including the marketing and distribution penetration problem, the gateway model configuration problem, the power supply gateway metering abnormal problem, the power selling gateway metering abnormal problem, the technical problem and the line loss occurrence, and forms the line loss cause characteristic library specifically including the steps of:
and S420, on the basis of the metering data of the state grid power utilization information acquisition system and the configuration data of the integrated gateway model, judging that reverse electric quantity exists but a distributed gateway model is not configured.
Specifically, the S400 analyzes the cause and the degree of association of the line loss according to the actual line loss analytic case, develops the association and the characteristics including the marketing and distribution penetration problem, the gateway model configuration problem, the power supply gateway metering abnormal problem, the power selling gateway metering abnormal problem, the technical problem and the line loss occurrence, and forms the line loss cause characteristic library specifically including the steps of:
s430, judging whether the upper bottom and the lower bottom are empty or not, whether the upper bottom and the lower bottom are larger than the lower bottom, whether the meter bottom is skipped or not and whether the meter bottom is 0 or not based on the collected power supply side gateway metering data, and meanwhile, monitoring meter replacement is realized based on metering configuration data;
s4301 carries out comparative analysis through EMS system integral electric quantity and TMR system electric quantity, and when the difference between the two electric quantities exceeds a threshold value, the flow change station ledger ratio error is judged.
Specifically, the S400 analyzes the cause and the degree of association of the line loss according to the actual line loss analytic case, develops the association and the characteristics including the marketing and distribution penetration problem, the gateway model configuration problem, the power supply gateway metering abnormal problem, the power selling gateway metering abnormal problem, the technical problem and the line loss occurrence, and forms the line loss cause characteristic library specifically including the steps of:
s440, judging whether the multiplying power is normal or not by judging whether the multiplying power of the transformer area transformation ratio error caused by new equipment or equipment aging is configured to be 1.1 to 1.7 times of the distribution transformer capacity value or whether the normal operation load current is not less than 30% of the rated value;
s4401 based on a TMR system and meter clock data and calendar clock data of a national grid power utilization information acquisition system, realizes comparison analysis of a supply meter clock, a sale side meter clock and a calendar clock, lists inconsistent list data and corrects the inconsistent list data.
In this embodiment, a streamlined line loss cause analysis model is constructed based on the line loss actual analysis case. The method diagnoses the causes of the problems of high loss, negative loss and the like and provides a primary solution to assist in commanding and carrying out troubleshooting work on the loss reduction problems by maintainers.
According to the actual analysis case of the line loss, the cause and the degree of association of the line loss are analyzed, and the association and the characteristics of various problems including marketing and distribution through problems, gateway model configuration problems, power supply gateway metering abnormal problems, power selling gateway metering abnormal problems, technical problems and the like and the occurrence of the line loss are developed. A library of line loss cause features is formed.
By collecting configuration information of the integrated gateway model, the gateway model is contrastively analyzed with the integrated gateway model, inconsistent gateway configuration lists are automatically analyzed, and the problem of synchronization line loss calculation errors caused by gateway model configuration errors is solved.
The line loss calculation deviation can be directly caused by the abnormal line change relation, and in an electric power system, under the condition that the electric distance is short, the voltage amplitude difference between nodes is small and the voltage waveforms are similar because the impedance is small. According to the characteristic, the correlation of the distribution transformation operating voltage of the same line is higher, otherwise, the correlation is lower, therefore, when high-loss negative loss occurs, whether the line transformation relation is correct or not can be judged through the voltage correlation, the correlation coefficients of the line voltage and the distribution transformation outlet voltage curve of the transformer area are calculated by using a big data algorithm, and line loss calculation errors caused by abnormal line transformation relation are identified through the correlation.
Based on distribution automation telesignalling state bit change incident data, PMS equipment overhauls data, realizes monitoring interconnection switch setting state change, mainly solves the power grid operation mode and changes and connect the back with the power grid, if the configuration of gateway model does not change in time, can lead to the problem of line loss height loss or burden loss.
When two close circuits appear high loss, burden and decrease simultaneously, on the basis of the contact relation between the GIS automatic identification circuit, the circuit that has contact relation or dual power supply user appears opposite line loss abnormal conditions simultaneously, if a circuit appears high loss, another circuit appears burden and decreases or appears abnormal line loss fluctuation simultaneously, the auxiliary achievement contacts circuit and dual power supply circuit high loss cause of burden and decreases and study and judge.
The line loss caused by the fact that a 10 kV high-voltage photovoltaic user reverse model is not configured or no reverse electric quantity data exists can be abnormal, the fact that reverse electric quantity exists can be mainly judged based on metering data of a state grid power utilization information acquisition system and integrated gateway model configuration data, but a distributed gateway model is not configured, and the problem that the line loss caused by the fact that the reverse electric quantity is abnormal or the distributed photovoltaic gateway configuration is abnormal cannot reach the standard is mainly solved.
Whether the upper and lower bottoms are empty or not, the upper bottom is larger than the lower bottom, the meter bottom is skipped, and the meter bottom is 0 is researched and judged based on the collected power supply side gateway metering data, and meanwhile, the meter replacement is monitored based on the metering configuration data, and a user is reminded to make an integrated gateway model change work in time.
And comparing and analyzing the integrated electric quantity of the EMS system and the electric quantity of the TMR system, and if the difference between the integrated electric quantity and the electric quantity exceeds a threshold value, judging that the change rate standing change ratio is wrong.
The transformation ratio of a transformer area can be wrong due to new equipment or equipment aging, negative loss can be caused due to too large transformation ratio, high loss can be caused due to too small transformation ratio, and whether the multiplying power is normal or not is judged by judging whether the multiplying power is configured to be 1.1 to 1.7 times of the capacity value of the distribution transformer or whether the normal operation load current is not less than 30% of the rated value.
Based on a TMR system and meter clock data and calendar clock data of a national grid power utilization information acquisition system, comparison analysis of a supply meter clock and a sale side meter clock and a calendar clock is realized, inconsistent list data is listed and corrected, and the problem of asynchronous line loss calculation data time caused by clock inconsistency is mainly solved.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A power distribution network load prediction and line loss cause analysis method based on big data is characterized by comprising the following steps:
s100, selecting proper data characteristics to establish a load prediction model according to the load characteristic analysis result and algorithm model selection;
s200, carrying out load prediction calculation on an analysis object according to short-term and ultra-short-term load prediction models, carrying out line and distribution transformation operation analysis by combining equipment capacity, carrying out classification statistics on operation conditions of heavy overload, economic operation and light idle load of the equipment, and pushing an analysis result to operation and maintenance personnel through app for checking;
s300, based on the line loss actual analysis case, a flow line loss cause analysis model is constructed, the causes of the high loss and negative loss problems are diagnosed, and a primary solution is provided.
2. The method according to claim 1, wherein in step S200, load prediction calculation is performed on an analysis object according to a short-term and ultra-short-term load prediction model, line and distribution transformation operation analysis is performed in combination with device capacity, classification statistics is performed on operation conditions of heavy overload, economic operation and light and no load of a device, and an analysis result is pushed to an operation and maintenance person through an app to be checked, and then the method comprises the steps of:
s210, setting a corresponding threshold value aiming at the distribution transformer operation analysis result, performing early warning when a predicted value is equal to the threshold value, performing alarm when the predicted value exceeds the threshold value, correspondingly outputting short-term and ultra-short-term early warning and alarm information, pushing the analysis result to operation and maintenance personnel through app to check, and pushing the analysis result to management personnel to make a decision for use.
3. The method for load prediction and line loss cause analysis of the power distribution network based on big data as claimed in claim 1, wherein before selecting suitable data characteristics to build a load prediction model according to the load characteristic analysis result and the algorithm model selection in S100, the method comprises the steps of:
s10, collecting operation data, statistical data and meteorological data, and importing external static data;
s20, carrying out source tracing verification and recalculation on the statistical data;
s30, cleaning and processing the collected operation data, meteorological data, imported external static data and statistical data which are subjected to source tracing verification and recalculation;
s40 analyzes the load characteristics based on N dimensions, selects data modeling and prediction algorithms.
4. The big data based distribution network load prediction and line loss cause analysis method according to claim 3, wherein the operation data comprises line/distribution transformer voltage data, current data and power data; the statistical data comprises historical load data and line loss index data; the meteorological data are integrated data of the power supply service command system, and comprise temperature and humidity data, wind speed data and weather data; the external static data comprises holidays and economic development indexes.
5. The method for load prediction and line loss cause analysis of the power distribution network based on big data as claimed in claim 1, wherein the step S100 of selecting suitable data characteristics to build a load prediction model according to the load characteristic analysis result and the algorithm model selection comprises the steps of:
s110, quantizing prediction accuracy by adopting an R square and a variance, and adaptively selecting an optimal model for prediction;
s120, continuously monitoring the accuracy of prediction, and quantifying the prediction effect by adopting a measurement goodness of fit R square and a variance to realize the visualization of evaluation after prediction;
s130, whether the load prediction model has the condition that the accuracy rate is not expected or reduced or not is detected, and when the load prediction model has the condition that the accuracy rate is not expected or reduced, feedback is carried out and the load prediction model is adaptively optimized again.
6. The method as claimed in claim 1, wherein the step S300 of constructing a streamlined line loss cause analysis model based on the line loss actual analysis case, diagnosing causes of high loss and negative loss problems, and providing a preliminary solution includes the steps of:
s400, according to the actual line loss analysis case, the cause and the degree of association of the line loss are analyzed, and the association and the characteristics of the cause and the degree of association of the line loss, including marketing and distribution through problems, gateway model configuration problems, power supply gateway metering abnormal problems, power selling gateway metering abnormal problems, technical problems and line loss are developed to form a line loss cause characteristic library.
7. The method as claimed in claim 6, wherein the step S400 of analyzing the cause and the correlation degree of the line loss according to the line loss actual analytic case, developing the correlation and the characteristics including marketing and distribution penetration problem, gateway model configuration problem, power supply gateway metering abnormal problem, power selling gateway metering abnormal problem, technical problem and line loss occurrence, and forming the line loss cause characteristic library specifically includes the steps of:
s410, by acquiring configuration information of the integrated gateway model, the gateway model is contrasted and analyzed with the integrated gateway model, and inconsistent gateway configuration lists are automatically analyzed;
s4101, when high loss and negative loss occur, judging whether the line change relation is correct or not through voltage relevance, calculating correlation coefficients of line voltage and distribution transformer outlet voltage curves by using a big data algorithm, and identifying line loss calculation errors caused by abnormal line change relation through correlation degrees;
s4102, monitoring the change of the setting state of the interconnection switch is realized based on the distribution automation remote signaling state change event data and PMS equipment maintenance data;
s4103, when two close lines have high loss and negative loss at the same time, based on GIS, automatically identifying the contact relation between the lines, and when the lines with contact relation or dual-power-supply users have opposite line loss abnormal conditions at the same time, and assisting in judging the cause of the high loss and negative loss of the contact lines and the dual-power-supply lines.
8. The method as claimed in claim 6, wherein the step S400 of analyzing the cause and the correlation degree of the line loss according to the line loss actual analytic case, developing the correlation and the characteristics including marketing and distribution penetration problem, gateway model configuration problem, power supply gateway metering abnormal problem, power selling gateway metering abnormal problem, technical problem and line loss occurrence, and forming the line loss cause characteristic library specifically includes the steps of:
and S420, on the basis of the metering data of the state grid power utilization information acquisition system and the configuration data of the integrated gateway model, judging that reverse electric quantity exists but a distributed gateway model is not configured.
9. The method as claimed in claim 6, wherein the step S400 of analyzing the cause and the correlation degree of the line loss according to the line loss actual analytic case, developing the correlation and the characteristics including marketing and distribution penetration problem, gateway model configuration problem, power supply gateway metering abnormal problem, power selling gateway metering abnormal problem, technical problem and line loss occurrence, and forming the line loss cause characteristic library specifically includes the steps of:
s430, judging whether the upper bottom and the lower bottom are empty, whether the upper bottom and the lower bottom are larger than the lower bottom, whether the meter bottom jumps or whether the meter bottom is 0 or not based on the collected power supply side gateway metering data, and monitoring meter replacement based on the metering configuration data;
s4301 carries out comparative analysis through EMS system integral electric quantity and TMR system electric quantity, and when the difference between the two electric quantities exceeds a threshold value, the flow change station ledger ratio error is judged.
10. The method as claimed in claim 6, wherein the step S400 of analyzing the cause and the correlation degree of the line loss according to the line loss actual analytic case, developing the correlation and the characteristics including marketing and distribution penetration problem, gateway model configuration problem, power supply gateway metering abnormal problem, power selling gateway metering abnormal problem, technical problem and line loss occurrence, and forming the line loss cause characteristic library specifically includes the steps of:
s440, judging whether the multiplying power is normal or not by judging whether the multiplying power of the transformer area transformation ratio error caused by new equipment or equipment aging is configured to be 1.1 to 1.7 times of the distribution transformer capacity value or whether the normal operation load current is not less than 30% of the rated value;
s4401 based on a TMR system and meter clock data and calendar clock data of a national grid power utilization information acquisition system, realizes comparison analysis of a supply meter clock, a sale side meter clock and a calendar clock, lists inconsistent list data and corrects the inconsistent list data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110420222.9A CN113487447A (en) | 2021-04-19 | 2021-04-19 | Power distribution network load prediction and line loss cause analysis method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110420222.9A CN113487447A (en) | 2021-04-19 | 2021-04-19 | Power distribution network load prediction and line loss cause analysis method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113487447A true CN113487447A (en) | 2021-10-08 |
Family
ID=77933393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110420222.9A Pending CN113487447A (en) | 2021-04-19 | 2021-04-19 | Power distribution network load prediction and line loss cause analysis method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113487447A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114389231A (en) * | 2021-12-31 | 2022-04-22 | 广东电网有限责任公司茂名供电局 | Load prediction diagnosis method based on power distribution network protection and equipment real-time data |
| CN114444397A (en) * | 2022-01-28 | 2022-05-06 | 国家电网有限公司 | Short-term power consumption prediction algorithm based on user portrait data model |
| CN114626487A (en) * | 2022-05-16 | 2022-06-14 | 南昌工程学院 | Line-variable relation checking method based on random forest classification algorithm |
| CN114757450A (en) * | 2022-06-13 | 2022-07-15 | 四川晨坤电气设备有限公司 | Line loss prediction method and device for intelligent power distribution operation and maintenance network |
| CN115080909A (en) * | 2022-07-15 | 2022-09-20 | 深圳市城市交通规划设计研究中心股份有限公司 | Analysis method for influencing data of internet of things sensing equipment, electronic equipment and storage medium |
| CN115933508A (en) * | 2022-11-18 | 2023-04-07 | 珠海康晋电气股份有限公司 | Intelligent power operation and maintenance system for power distribution network |
| CN117077989A (en) * | 2023-10-17 | 2023-11-17 | 广州市城市规划勘测设计研究院 | Overload alarm method for medical bed |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985570A (en) * | 2018-08-17 | 2018-12-11 | 深圳供电局有限公司 | Load prediction method and system |
| WO2020147349A1 (en) * | 2019-01-14 | 2020-07-23 | 中国电力科学研究院有限公司 | Power distribution network operation aided decision-making analysis system and method |
| CN111598380A (en) * | 2020-04-01 | 2020-08-28 | 国网江西省电力有限公司电力科学研究院 | Distribution line negative loss reason distinguishing method |
| CN111781463A (en) * | 2020-06-25 | 2020-10-16 | 国网福建省电力有限公司 | Auxiliary diagnosis method for abnormal line loss of transformer area |
-
2021
- 2021-04-19 CN CN202110420222.9A patent/CN113487447A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985570A (en) * | 2018-08-17 | 2018-12-11 | 深圳供电局有限公司 | Load prediction method and system |
| WO2020147349A1 (en) * | 2019-01-14 | 2020-07-23 | 中国电力科学研究院有限公司 | Power distribution network operation aided decision-making analysis system and method |
| CN111598380A (en) * | 2020-04-01 | 2020-08-28 | 国网江西省电力有限公司电力科学研究院 | Distribution line negative loss reason distinguishing method |
| CN111781463A (en) * | 2020-06-25 | 2020-10-16 | 国网福建省电力有限公司 | Auxiliary diagnosis method for abnormal line loss of transformer area |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114389231A (en) * | 2021-12-31 | 2022-04-22 | 广东电网有限责任公司茂名供电局 | Load prediction diagnosis method based on power distribution network protection and equipment real-time data |
| CN114444397A (en) * | 2022-01-28 | 2022-05-06 | 国家电网有限公司 | Short-term power consumption prediction algorithm based on user portrait data model |
| CN114626487A (en) * | 2022-05-16 | 2022-06-14 | 南昌工程学院 | Line-variable relation checking method based on random forest classification algorithm |
| CN114626487B (en) * | 2022-05-16 | 2023-09-05 | 南昌工程学院 | Linear transformation relation checking method based on random forest classification algorithm |
| CN114757450A (en) * | 2022-06-13 | 2022-07-15 | 四川晨坤电气设备有限公司 | Line loss prediction method and device for intelligent power distribution operation and maintenance network |
| CN114757450B (en) * | 2022-06-13 | 2022-09-02 | 四川晨坤电气设备有限公司 | Line loss prediction method and device for intelligent power distribution operation and maintenance network |
| CN115080909A (en) * | 2022-07-15 | 2022-09-20 | 深圳市城市交通规划设计研究中心股份有限公司 | Analysis method for influencing data of internet of things sensing equipment, electronic equipment and storage medium |
| CN115080909B (en) * | 2022-07-15 | 2022-11-25 | 深圳市城市交通规划设计研究中心股份有限公司 | Analysis method for influencing data of internet of things sensing equipment, electronic equipment and storage medium |
| CN115933508A (en) * | 2022-11-18 | 2023-04-07 | 珠海康晋电气股份有限公司 | Intelligent power operation and maintenance system for power distribution network |
| CN115933508B (en) * | 2022-11-18 | 2023-11-03 | 珠海康晋电气股份有限公司 | Intelligent power operation and maintenance system for power distribution network |
| CN117077989A (en) * | 2023-10-17 | 2023-11-17 | 广州市城市规划勘测设计研究院 | Overload alarm method for medical bed |
| CN117077989B (en) * | 2023-10-17 | 2024-04-05 | 广州市城市规划勘测设计研究院 | Overload alarm method for medical bed |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113487447A (en) | Power distribution network load prediction and line loss cause analysis method based on big data | |
| CN108491969B (en) | Big data-based space load prediction model construction method | |
| CN103872782A (en) | Electric energy quality data comprehensive service system | |
| CN116937575A (en) | Energy monitoring management system for grid system | |
| CN107908638A (en) | The operation of power networks efficiency rating method and system matched somebody with somebody are excavated based on big data | |
| CN114638425B (en) | Historical data-based large-user monthly electricity consumption prediction method and system | |
| CN114707739B (en) | Wind-solar output prediction and market risk management and control method and system based on big data | |
| CN115528817A (en) | Intelligent power distribution and utilization system, method, medium, equipment and terminal for user side | |
| CN114254806A (en) | Power distribution network heavy overload early warning method and device, computer equipment and storage medium | |
| CN112949207A (en) | Short-term load prediction method based on improved least square support vector machine | |
| CN114169709A (en) | State evaluation method and device for secondary equipment of transformer substation, storage medium and equipment | |
| Yılmaz | Real measure of a transmission line data with load fore-cast model for the future | |
| CN118396326A (en) | Resident electricity consumption prediction and scheduling system and method based on big data | |
| CN106548284A (en) | A kind of adaptive mode massing power grid security Alarm Assessment method towards operation regulation and control | |
| CN117856245A (en) | Grid management-based method, device and storage medium for analyzing line loss of transformer area | |
| CN112734274A (en) | Mining and comprehensive evaluation method for low-carbon power grid operation leading influence factors | |
| CN117498559A (en) | Low-voltage early warning analysis method and system for power distribution network | |
| CN108288122B (en) | Assessment method and device of multi-region interconnection system | |
| Tavakoli et al. | Reduce maintenance costs by improving human reliability in power grids | |
| CN112016631A (en) | Improvement scheme related to low-voltage treatment | |
| CN118508597B (en) | Emergency power supply method, system and equipment for power system guarantee object | |
| Grigoras et al. | Knowlegde extraction from Smart Meters for consumer classification | |
| Liu et al. | Research on Operation Error Detection Model of Metering Device | |
| CN117236532B (en) | Load data-based electricity consumption peak load prediction method and system | |
| Dogan et al. | Monte Carlo sampling vs. discrete forecast error scenarios in grid reliability assessment for short-term planning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211008 |
|
| RJ01 | Rejection of invention patent application after publication |