CN109583763A - Branch trade custom power load growth feature mining algorithm - Google Patents
Branch trade custom power load growth feature mining algorithm Download PDFInfo
- Publication number
- CN109583763A CN109583763A CN201811463661.2A CN201811463661A CN109583763A CN 109583763 A CN109583763 A CN 109583763A CN 201811463661 A CN201811463661 A CN 201811463661A CN 109583763 A CN109583763 A CN 109583763A
- Authority
- CN
- China
- Prior art keywords
- team
- parameter
- load
- growth
- typical
- 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
- 230000012010 growth Effects 0.000 title claims abstract description 40
- 238000005065 mining Methods 0.000 title claims abstract description 15
- 230000000630 rising effect Effects 0.000 claims abstract description 20
- 230000005611 electricity Effects 0.000 claims abstract description 8
- 230000003044 adaptive effect Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 11
- 240000002853 Nelumbo nucifera Species 0.000 claims 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 claims 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 claims 1
- 229920006395 saturated elastomer Polymers 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 238000012512 characterization method Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000018109 developmental process Effects 0.000 description 4
- 230000007773 growth pattern Effects 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000003698 anagen phase Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of branch trade custom power load growth feature mining algorithms, comprising the following steps: S1: collecting power consumer basic information, builds battalion with big data and collects warehouse；S2: power consumer rising characteristic parameter is calculated using Logsitic models fitting customer charge data and identifies the load pullulation module of user, the historical load data of various dimensions is converted into three dimensions；S3: using the DBSCAN cluster algorithm of parameter adaptive, clustering user's rising characteristic parameter, and point different industries, different electricity consumption scale search typical cases form a team；S4: counting the load growth Parameter Typical of all categorys of employment, forms industry typical load growth curve according to Exemplary parameter values, and application parameter standard deviation judges regular degree of strength.The present invention can be used in analyzing magnanimity power consumer load data, identifies the load pullulation module of power consumer, refines the custom power load growth feature of industries at different levels.
Description
Technical field
The present invention relates to Characteristics of Electric Load research fields, special more particularly to a kind of branch trade custom power load growth
Levy mining algorithm.
Background technique
With the lasting adjustment of urban industrial structure, the category of employment of power consumer, production model are just being presented with electrical characteristics
Diversified development trend, the electricity consumption behavior of different cities, different industries power consumer respectively have feature, and the electric power of same industry is used
Family because the segmented industry difference, it is also increasingly apparent with the difference of electrical characteristics.Diversified industry development situation is to traditional branch
Industry Load Characteristic Analysis and prediction technique propose challenge.At the same time, with electric power enterprise production and marketing system it is continuous
Perfect, electric power enterprise has accumulated containing numerous and jumbled battalion such as user's industry at different levels, electrical load over the years, capacity with data, and battalion is with big number
According to having the feature that the scale of construction is big, type is more, dimension is high.
Branch trade electricity consumption at present research primarily focus on different industries in the morning, afternoon and evening, seaonal load variation characteristic, to difference
Load pullulation module and the research of final saturated level are less year by year by industry user.Existing load Analysis means are excavating mass data
Message context is there is certain limitation, and there are two main classes.First is that usually choosing typical user carries out load Analysis, research pair
As less, being easy to appear human error；Second is that load data dimension is high, existing load data processing method is not extracting characteristic parameter
In the case where directly carry out big data analysis, obtained conclusion is relatively limited.
Therefore it is urgent to provide a kind of novel branch trade custom power load growth feature mining algorithms to solve above-mentioned ask
Topic.
Summary of the invention
Technical problem to be solved by the invention is to provide a kind of branch trade custom power load growth feature mining algorithm,
It can be used in analyzing magnanimity power consumer load data, identify the saturated water level values and growth rate of power consumer, it may finally
Extract the customer charge saturated velocity and the practical factor levels of power capacity of industry from different places.
In order to solve the above technical problems, one technical scheme adopted by the invention is that: a kind of branch trade custom power is provided
Load growth feature mining algorithm, comprising the following steps:
S1: collecting power consumer basic information, builds battalion with big data and collects warehouse；
S2: calculating power consumer rising characteristic parameter, using Logsitic models fitting customer charge data, identifies user
Load pullulation module, by the historical load data of various dimensions be converted to growth initial stage lag coefficient, increase mid-term velocity coeffficient,
Increase latter stage practical three dimensions of coefficient；
S3: using the DBSCAN cluster algorithm of parameter adaptive, clustering user's rising characteristic parameter, divides not
Of the same trade, different electricity consumption scale search typical cases form a team；
S4: counting all industry typical cases and form a team characterisitic parameter mean value, and the load growth parameter as the sector classification is typical
Value forms industry typical load growth curve according to Exemplary parameter values, and the standard deviation of application parameter judges regular strong and weak journey
Degree.
In a preferred embodiment of the present invention, in step s 2, the power consumer rising characteristic parameter includes increasing
Velocity coeffficient T1, T3, increase latter stage practical coefficient 1/k, be calculated using following formula:
Wherein, a is growth initial stage lag coefficient, and b is to increase mid-term velocity coeffficient.
Further, the power consumer rising characteristic parameter is calculated by following Logsitic model:
Wherein, ytIndicate customer charge value, the t expression of years, a, b, k are fitting parameter；
Enabling three rank of Logsitic model lead is zero, obtains two inflection point P1 (T1, Y1) and P3 (T3, Y3), is Logistic
Curve speedup changes inflection point.
In a preferred embodiment of the present invention, the detailed process of step S3 includes:
S3.1: different levels industry, the rising characteristic parameter of three dimensions of different capabilities section power consumer are obtained；
S3.2: it is corresponding to seek EPS according to cuclear density theory for the EPS initial value of given Density Clustering, circulation step-length, final value
Smallest sample number minPts；
S3.3: typical case is found by DBSCAN algorithm and is formed a team.
Further, the detailed process of step S3.3 includes:
If user is divided into Ganlei automatically by DBSCAN algorithm, judges whether there is density concentrated area and maximum is formed a team
Quantity accounting is big to form a team；
Maximum quantity accounting of forming a team is more than 60% to form a team if it exists, then the typical case to form a team as the sector, capacity section
It forms a team, is formed a team feature according to typical case's existing regular programming count of forming a team, judge regular significance degree；
Maximum quantity accounting of forming a team is more than 60% to form a team if it does not exist, then one circulation step-length of increase continues searching typical case
It forms a team, until circulation step-length terminates when being equal to final value.
Further, the value range of the EPS initial value is 0.05-0.3, and the circulation step-length is 0.05, the end
Value is 0.3.
The beneficial effects of the present invention are: the present invention is applied to regional branch trade customer charge rising characteristic analysis, by dividing
Magnanimity power consumer load data is analysed, the saturated water level values and growth rate of power consumer is identified, area may finally be extracted
The practical factor levels of customer charge saturated velocity and power capacity of different industries, after tested, algorithm strong applicability is calculated
Industry canonical parameter can preferably judge that different industries, the load growth of different type user are horizontal, to Utilities Electric Co.'s industry
Business has important supporting role.Specifically include following advantage:
(1) it applies mass data analysis load characteristic: compared to Load Characteristic Analysis, summarizing mass users data, lead to
It crosses and establishes parameter model, while rationally utilizing data, reduce data dimension, it is easier to refine industrial characteristic；
(2) user's growth pattern recognition capability is strong: increasing using the parameter of logistic models fitting as power consumer special
Property parameter, resolution is high, and parameter should be readily appreciated that；
(3) efficiency of algorithm is high: seeking using the rule that the density clustering algorithm of auto-adaptive parameter carries out industry step by step, operation
Speed is fast, is suitable for branch trade custom power load characteristic feature and excavates；
(4) relationship, the load growth mode of power consumer capacity and load are identified: user's Business Process System capacity is converted to
Electric load can intuitively understand the practical factor levels of capacity of different type power consumer；
(5) it is more scientific to expand access scheme for industry: branch trade customer charge growth pattern can assist regional grid company to formulate
Industry expands access scheme, reduces later period frequent capacity-increasing transformation, improves power equipment utilization rate；
(6) load prediction is more accurate: branch trade customer charge growth pattern facilitates regional overall load prediction, to electric power
System call operation, production and management mode are formulated, Electric Power Network Planning is programmed with preferable directive function.
Detailed description of the invention
Fig. 1 is the flow chart of branch trade custom power load growth feature mining algorithm of the present invention；
Fig. 2 is the schematic diagram of the industry typical load growth curve.
Specific embodiment
The preferred embodiments of the present invention will be described in detail with reference to the accompanying drawing, so that advantages and features of the invention energy
It is easier to be readily appreciated by one skilled in the art, so as to make a clearer definition of the protection scope of the present invention.
Referring to Fig. 1, the embodiment of the present invention includes:
A kind of branch trade custom power load growth feature mining algorithm, comprising the following steps:
S1: collecting the basic informations such as power consumer industry, capacity, load over the years, by the conversion of data, cleaning, builds
Battalion collects warehouse with big data, as data mining and the basis of strengthened research；
S2: calculating power consumer rising characteristic parameter, using 5-10 annual data of Logsitic models fitting customer charge,
The historical load data of various dimensions is converted to growth initial stage lag coefficient, increases mid-term by the load pullulation module for identifying user
Velocity coeffficient increases latter stage practical three dimensions of coefficient, avoids dimension disaster.Logsitic model expression and fitting parameter are fixed
Justice is as follows:
Wherein, ytIndicate customer charge value, the t expression of years, a, b, k are fitting parameter.
1) increase initial stage lag coefficient a
A characterization user rests on the length of time of slow build phase.The starting speed of different type power consumer is not
With, certain customers' load development speed early period is slow, and load is then initially entered when reaching certain condition and rapidly develops the stage.a
Value is bigger, shows that starting more lags.
2) increase mid-term velocity coeffficient b
B characterization user rests on the time of rapid growth phase, has reacted the speed into saturation state.Different type user
It is different to rest on time in the rapid growth phase, because that user's production model, personnel enter speed is different.B is smaller, and curve is steeper,
Fast-developing time phase is shorter.
3) increase latter stage practical coefficient 1/k
The final practical coefficient of the relationship of 1/k characterization user power utilization load and capacity when reaching saturation, i.e. user.
Using the parameter of logistic models fitting as power consumer rising characteristic parameter, resolution is high, and parameter is easy to manage
Solution, for mass data, can reduce data dimension, it is easier to refine industrial characteristic.Electricity is calculated by above-mentioned fitting parameter
Power user's rising characteristic parameter, the power consumer rising characteristic parameter include growth rate coefficient T 1, T3, increase latter stage it is practical
Coefficient 1/k is calculated using following formula:
Specific calculating process are as follows: enabling three rank of Logsitic model lead is zero, and two inflection point P1 (T1, Y1) and P3 can be obtained
(T3, Y3) changes inflection point for logistic curve speedup.As shown in Fig. 2, T1 characterization user complete initial stage build phase when
Between, corresponding Y1 representative reaches 20% of saturated level or so.T3 characterization user enters the saturated growth period time of needs, right
The Y3 representative answered reaches 80% of saturated level or so.I.e. the curve of origin O to P1 point is to increase developing stage at initial stage, and P1 point arrives
The curve of P3 point is mid-term Rapid development stage, and the curve after P3 point is that saturation increases developing stage.
S3: using the DBSCAN cluster algorithm of parameter adaptive, clustering user's rising characteristic parameter, divides not
Of the same trade, different electricity consumption scale search typical cases form a team；Detailed process includes:
S3.1: obtain different levels industry, three dimensions of different capabilities section power consumer rising characteristic parameter T1,
T3,1\k；
S3.2: it is corresponding to seek EPS according to cuclear density theory for the EPS initial value of given Density Clustering, circulation step-length, final value
Smallest sample number minPts；Wherein,
The value range of the EPS initial value is 0.05-0.3, and the circulation step-length is 0.05, and the final value is 0.3.
S3.3: typical case is found by DBSCAN algorithm and is formed a team, detailed process includes:
If user is divided into Ganlei automatically by DBSCAN algorithm, such as manufacturing industry, financial circles, real estate, judge whether
There are density concentrated area and maximum quantity accounting of forming a team is big forms a team；
Maximum quantity accounting of forming a team is more than 60% to form a team if it exists, then the typical case to form a team as the sector, capacity section
It forms a team, is formed a team feature according to typical case's existing regular programming count of forming a team, judge regular significance degree；
Maximum quantity accounting of forming a team is more than 60% to form a team if it does not exist, then one circulation step-length of increase continues searching typical case
It forms a team, until circulation step-length terminates when being equal to final value.
It is sought using the rule that the density clustering algorithm of auto-adaptive parameter carries out industry step by step, arithmetic speed is fast, is suitable for
Branch trade custom power load characteristic feature is excavated.
S4: counting all industry typical cases and form a team three characterisitic parameter mean values, the load growth parameter as the sector classification
Representative value finally quantitatively provides different industries, the practical coefficient of typical latter stage (1/k) of different scales user and growth rate system
Number (T1, T3) forms industry typical load growth curve according to Exemplary parameter values, and the standard deviation of application parameter judges rule
Degree of strength.
The present invention is applied to regional branch trade customer charge rising characteristic analysis, by analyzing magnanimity power consumer load number
According to identifying the saturated water level values and growth rate of power consumer, the customer charge that may finally extract industry from different places is full
With speed and the practical factor levels of power capacity, it is adapted to existing electric power acquisition business, algorithm is efficiently scientific, and strong applicability obtains
To industry typical case growth pattern stronger guidance can be provided for Business Process System, load prediction, Electric Power Network Planning.
The above description is only an embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (6)
1. a kind of branch trade custom power load growth feature mining algorithm, comprising the following steps:
S1: collecting power consumer basic information, builds battalion with big data and collects warehouse；
S2: calculating power consumer rising characteristic parameter, using Logsitic models fitting customer charge data, identifies that user's is negative
The historical load data of various dimensions is converted to growth initial stage lag coefficient, increases mid-term velocity coeffficient, growth by lotus pullulation module
Latter stage three dimensions of practical coefficient；
S3: using the DBSCAN cluster algorithm of parameter adaptive, clustering user's rising characteristic parameter, divides and does not go together
Industry, different electricity consumption scale search typical cases form a team；
S4: all industry typical cases are counted and are formed a team characterisitic parameter mean value, as the load growth Parameter Typical of the sector classification, root
Industry typical load growth curve is formed according to Exemplary parameter values, and the standard deviation of application parameter judges regular degree of strength.
2. branch trade custom power load growth feature mining algorithm according to claim 1, which is characterized in that in step
In S2, the power consumer rising characteristic parameter includes growth rate coefficient T 1, T3, increases latter stage practical coefficient 1/k, using such as
Lower formula is calculated:
Wherein, a is growth initial stage lag coefficient, and b is to increase mid-term velocity coeffficient.
3. branch trade custom power load growth feature mining algorithm according to claim 2, which is characterized in that the electricity
Power user's rising characteristic parameter is calculated by following Logsitic model:
Wherein, ytIndicate customer charge value, the t expression of years, a, b, k are fitting parameter；
Enabling three rank of Logsitic model lead is zero, obtains two inflection point P1 (T1, Y1) and P3 (T3, Y3), is Logistic curve
Speedup changes inflection point.
4. branch trade custom power load growth feature mining algorithm according to claim 1, which is characterized in that step S3
Detailed process include:
S3.1: different levels industry, the rising characteristic parameter of three dimensions of different capabilities section power consumer are obtained；
S3.2: the EPS initial value of given Density Clustering, circulation step-length, final value seek the corresponding minimum of EPS according to cuclear density theory
Sample number minPts；
S3.3: typical case is found by DBSCAN algorithm and is formed a team.
5. branch trade custom power load growth feature mining algorithm according to claim 4, which is characterized in that step
The detailed process of S3.3 includes:
If user is divided into Ganlei automatically by DBSCAN algorithm, judges whether there is density concentrated area and maximum is formed a team quantity
Accounting is big to form a team；
Maximum quantity accounting of forming a team is more than 60% to form a team if it exists, then this is formed a team forms a team as the typical case of the sector, capacity section,
It is formed a team feature according to typical case's existing regular programming count of forming a team, judges regular significance degree；
Maximum quantity accounting of forming a team is more than 60% to form a team if it does not exist, then one circulation step-length of increase continues searching typical group
Group, until circulation step-length terminates when being equal to final value.
6. according to the described in any item branch trade custom power load growth feature mining algorithms of claim 4 or 5, feature exists
In the value range of the EPS initial value is 0.05-0.3, and the circulation step-length is 0.05, and the final value is 0.3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811463661.2A CN109583763A (en) | 2018-12-03 | 2018-12-03 | Branch trade custom power load growth feature mining algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811463661.2A CN109583763A (en) | 2018-12-03 | 2018-12-03 | Branch trade custom power load growth feature mining algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109583763A true CN109583763A (en) | 2019-04-05 |
Family
ID=65926512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811463661.2A Pending CN109583763A (en) | 2018-12-03 | 2018-12-03 | Branch trade custom power load growth feature mining algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109583763A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111582406A (en) * | 2020-05-31 | 2020-08-25 | 重庆大学 | Power equipment state monitoring data clustering method and system |
| CN113743519A (en) * | 2021-09-09 | 2021-12-03 | 中国南方电网有限责任公司 | Power grid bus typical load curve identification method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462852A (en) * | 2014-12-25 | 2015-03-25 | 国家电网公司 | Power grid development stage division method based on Logistic model |
| CN105404935A (en) * | 2015-11-11 | 2016-03-16 | 国网浙江省电力公司经济技术研究院 | Electric power system monthly load prediction method considering business expansion increment |
| CN105678314A (en) * | 2015-10-15 | 2016-06-15 | 东南大学 | Typical demand-side user screening method based on fuzzy C clustering |
| CN107423769A (en) * | 2017-08-03 | 2017-12-01 | 四川大学 | Electric load curve adaptive clustering scheme based on morphological feature |
-
2018
- 2018-12-03 CN CN201811463661.2A patent/CN109583763A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462852A (en) * | 2014-12-25 | 2015-03-25 | 国家电网公司 | Power grid development stage division method based on Logistic model |
| CN105678314A (en) * | 2015-10-15 | 2016-06-15 | 东南大学 | Typical demand-side user screening method based on fuzzy C clustering |
| CN105404935A (en) * | 2015-11-11 | 2016-03-16 | 国网浙江省电力公司经济技术研究院 | Electric power system monthly load prediction method considering business expansion increment |
| CN107423769A (en) * | 2017-08-03 | 2017-12-01 | 四川大学 | Electric load curve adaptive clustering scheme based on morphological feature |
Non-Patent Citations (2)
| Title |
|---|
| 张帆 等: ""基于改进 Logistic 模型阶段划分理论的饱和负荷预测"", 《电力建设》 * |
| 胡可云 等: "《数据挖掘理论与应用》", 30 April 2008, 北京：北京交通大学出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111582406A (en) * | 2020-05-31 | 2020-08-25 | 重庆大学 | Power equipment state monitoring data clustering method and system |
| CN113743519A (en) * | 2021-09-09 | 2021-12-03 | 中国南方电网有限责任公司 | Power grid bus typical load curve identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| CN107346502A (en) | A kind of iteration product marketing forecast method based on big data | |
| CN105260803A (en) | Power consumption prediction method for system | |
| EP1866851A2 (en) | Constrained tree structure method and system | |
| CN109409561B (en) | Construction method of multi-time scale time sequence collaborative prediction model | |
| CN106067094A (en) | A kind of dynamic assessment method and system | |
| CN109858728A (en) | Load forecasting method based on branch trade Analysis of Electrical Characteristics | |
| CN109800898A (en) | A kind of intelligence short-term load forecasting method and system | |
| CN110119948B (en) | Power consumer credit evaluation method and system based on time-varying weight dynamic combination | |
| CN108388974A (en) | Top-tier customer Optimum Identification Method and device based on random forest and decision tree | |
| CN102279963B (en) | The method, apparatus and system of the prompting of two-stage budget reasonalbeness check and Automatic Optimal | |
| Brentan et al. | Correlation analysis of water demand and predictive variables for short‐term forecasting models | |
| CN112330077B (en) | Power load prediction method, power load prediction device, computer equipment and storage medium | |
| CN115423429A (en) | Multimode integrated distribution network operation system based on image and sound information | |
| CN108399553A (en) | It is a kind of to consider geographical and circuit subordinate relation user characteristics label setting method | |
| CN108154311A (en) | Top-tier customer recognition methods and device based on random forest and decision tree | |
| Ye et al. | Passenger flow prediction in bus transportation system using ARIMA models with big data | |
| CN111177216A (en) | Association rule generation method and device for behavior characteristics of comprehensive energy consumer | |
| CN108989092A (en) | A kind of wireless network predicting method, electronic equipment and storage medium | |
| CN109583763A (en) | Branch trade custom power load growth feature mining algorithm | |
| CN114119110A (en) | Project cost list collection system and method thereof | |
| CN108846692B (en) | Multi-factor recurrent neural network-based consumer consumption behavior prediction method | |
| CN107563402A (en) | A kind of social networks estimating method and system | |
| Yu et al. | Forecasting digital economy of China using an Adaptive Lasso and grey model optimized by particle swarm optimization algorithm | |
| CN110210677A (en) | A kind of bus Short-term Load Forecast method and apparatus of combination cluster and deep learning algorithm |
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: 20190405 |
|
| RJ01 | Rejection of invention patent application after publication |