CN110298567A - The method for determining typical day load curve using integrated energy system energy consumption big data - Google Patents
The method for determining typical day load curve using integrated energy system energy consumption big data Download PDFInfo
- Publication number
- CN110298567A CN110298567A CN201910526445.6A CN201910526445A CN110298567A CN 110298567 A CN110298567 A CN 110298567A CN 201910526445 A CN201910526445 A CN 201910526445A CN 110298567 A CN110298567 A CN 110298567A
- Authority
- CN
- China
- Prior art keywords
- load
- cluster
- data
- energy
- typical day
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000005265 energy consumption Methods 0.000 title claims abstract description 17
- 230000002159 abnormal effect Effects 0.000 claims abstract description 7
- 230000005611 electricity Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 4
- 241001269238 Data Species 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 235000006508 Nelumbo nucifera Nutrition 0.000 claims 1
- 240000002853 Nelumbo nucifera Species 0.000 claims 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 6
- 230000003750 conditioning effect Effects 0.000 description 4
- 238000010438 heat treatment Methods 0.000 description 4
- 230000007704 transition Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000013439 planning Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000033772 system development Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/067—Enterprise or organisation modelling
-
- 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)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of methods for determining typical day load curve using integrated energy system energy consumption big data, by being standardized pretreatment to original energy consumption historical data, it eliminates due to the larger brought influence of the data bulk grade difference for participating in clustering, and the abnormal data as caused by artificial and other irresistible power factors is excluded, guarantee accuracy, the reasonability of result；Preferable clustering number mesh is determined using the method that silhouette coefficient method SILHOUETTE index and elbow method SSE index Two indices mutually confirm, avoids the phenomenon non-optimal due to single index result due to caused by itself calculation features；The method for seeking typical daily load is handled using average data in classification cluster, compared to the typical day load curve that conventional peak load-amortization ratio method is chosen, what the present invention obtained uses energy data classification feature more representative closer to reality energy characteristics of demand, load prediction.
Description
Technical field
The present invention relates to a kind of energy management technologies, in particular to a kind of to be determined using integrated energy system energy consumption big data
The method of typical day load curve.
Background technique
With the increasingly promotion of the high speed development of social economy, commercial production levels and inhabitant's consumption level, energy demand
It is growing, and caused large-scale area type and global environmental problem.To crack the increasingly serious energy and environment quagmire,
Ou Deng developed country, America and Japan proposes integrated energy system development plan in the beginning of this century, it is therefore an objective to promote pushing away for distributed energy
It extensively applies and improves clean energy resource infiltration ratio.
It is intrinsic that the comprehensive architecture of integrated energy system makes integrated energy system at planning and designing initial stage just embody it
Complexity.For this purpose, the planning and designing of system just cause the extensive pass of domestic and foreign scholars since comprehensive energy concept proposes
Note, and respective theory and method is proposed one after another.In above-mentioned theory and method, used with the analysis of energy load character with Demand-side
Energy load prediction is regarded as the basis of integrated energy system planning and designing.
Intelligent energy is one of the trend of energy network development, in recent years, as a large amount of installations of intelligent sensing equipment make
With especially advanced measuring system (AMI) is universal, realizes the real time monitoring to energy consumption data, this is to energy consumptions such as cool and thermal powers
The applied analysis of data is provided convenience condition.The research of the existing preliminary data digging technology of the country such as America and Europe and real system are answered
With wherein the clustering method in data mining has obtained extensive research and development.
Summary of the invention
The problem of the present invention be directed to Utilizing Energy Sources in Reason proposes a kind of true using integrated energy system energy consumption big data
The method for determining typical day load curve is found hot and cold, electric with energy typical day using integrated energy system energy consumption data clustering
Load curve.
The technical solution of the present invention is as follows: a kind of determine typical day load curve using integrated energy system energy consumption big data
Method specifically comprises the following steps:
1) certain year known to certain enterprise or regional areas annual Power system load data is chosen according to daily 96 moment
Daily load data rejects the abnormal data occurred by the abnormal reason of maintenance, table tool failure when selection；
2) data put in order are put into database, carry out cluster evolutionary programming, generate silhouette coefficient figure and elbow figure,
Cluster numbers K is determined by i-th of extreme value of ordinate SILHOUETTE index in silhouette coefficient figurei, by KiIt takes in elbow figure and tests
Demonstrate,prove point KiSlope fall whether become to mitigate, then K in this wayiFor preferable clustering number, as found in silhouette coefficient figure
Next extreme point, and repeat the above process, obtain optimal cluster numbers n；
3) preferable clustering number is substituted into program and carries out load data cluster labels, 1 year load data presses load quantity
Grade is automatically separated into n label, obtains cluster result load chart, the load that every line is one day in figure, and abscissa represents 96
A moment, ordinate are load value, automatically generate n cluster according to load size and cluster numbers n after cluster, and show the width of every cluster
It is worth range；
4) the every daily load line corresponding date in every cluster load chart is marked in calendar figure with same mark, shape
At electricity power classification calendar figure, load characteristics clustering known to observation electricity power classification calendar figure is significantly closed with month with festivals or holidays
Connection relationship carries out name nominating to every cluster load chart；
5) every cluster load chart is averaged in 96 moment point load datas of whole day respectively, is obtained typical with energy
Daily load curve figure, every is named with the load curve that energy typical day load curve figure corresponds to step 4), forms final typical day
Load curve.
The beneficial effects of the present invention are: the present invention determines that typical daily load is bent using integrated energy system energy consumption big data
The method of line eliminates the data number due to participating in clustering by being standardized pretreatment to original energy consumption historical data
It is influenced brought by magnitude difference is larger, and excludes the abnormal data as caused by artificial and other irresistible power factors,
Guarantee accuracy, the reasonability of result；It is mutual using silhouette coefficient method SILHOUETTE index and elbow method SSE index Two indices
The method of confirmation determines preferable clustering number mesh, avoids since single index result due to caused by itself calculation features is non-optimal
The phenomenon that；Using K-means clustering methodology, have the advantages that it is simple, should be readily appreciated that and realize, time complexity is low etc., to big
There is type data very high treatment effeciency can achieve good cluster especially when mode is distributed, and reunion shape in class is presented
As a result, the analysis application of extremely suitable integrated energy system cool and thermal power energy consumption data；Data classification labeling processing mode is added,
So that classification results are it is clear that be conducive to the subsequent reprocessing to data in every class result；It is average using data in classification cluster
Change handles the method for seeking typical daily load, compared to the typical day load curve that conventional peak load-amortization ratio method is chosen, originally
What invention obtained uses energy data classification feature to use energy characteristics of demand, load prediction more representative closer to practical；It will cluster
As a result calendarization is handled, and combines current year climate change statistical result, and analysis is because of seasonal climate variation, festivals or holidays personnel variation etc.
Extraneous factor is to the influence with energy load.
Detailed description of the invention
Fig. 1 is the stream that the present invention is implemented using the method that integrated energy system energy consumption big data determines typical day load curve
Cheng Tu；
Fig. 2 is silhouette coefficient figure in embodiment；
Fig. 3 is elbow figure in embodiment；
Cluster result figure when Fig. 4 is K=5 in embodiment；
Fig. 5 is in embodiment for cold season group load chart；
Fig. 6 is conditioning in Transition Season group load chart in embodiment；
Fig. 7 is heating season group load chart in embodiment；
Fig. 8 is weekend group load chart in embodiment；
Fig. 9 is festivals or holidays group load chart in embodiment；
Figure 10 is five quasi-representative daily load curve figure in embodiment；
Figure 11 is in embodiment with energy load calendar figure；
Cluster result figure when Figure 12 is K=3 in embodiment；
Cluster result figure when Figure 13 is K=4 in embodiment；
Cluster result figure when Figure 14 is K=6 in embodiment；
Cluster result figure when Figure 15 is K=7 in embodiment.
Specific embodiment
The present embodiment is further located on the basis of integrated energy system tradition energy analysis, to initial data
Reason.It is programmed using the SKLEARN module in PYTHON, carries out clustering processing to energy data, determine best cluster
Number simultaneously carries out K-means cluster, to analyze with energy feature, determine typical day load curve figure.
Being applicable in integrated energy system as shown in Figure 1 can characteristic analysis and the flow chart with energy load forecasting method implementation.
By certain year known to certain enterprise or regional areas annual 96 point data of electric load (by taking electric load as an example, side
Method applies also for hot and cold load, and 96 points are that will be divided into 96 moment daily) it is standardized, and reject because of maintenance, table tool
The data put in order are put into CSV (Comma-Separated Values, comma by the reasons such as failure and the abnormal data occurred
Separation value) in database.Model, which is prejudged, by the SKLEARN in PYTHON carries out the preferable clustering number knot for being directed to above-mentioned database
Per moment load and data are associated programming by fruit evolutionary programming, run obtain silhouette coefficient figure and elbow figure such as Fig. 2,
Shown in Fig. 3, abscissa K is the cluster numbers being randomly generated；Pass through the i-th (i of ordinate SILHOUETTE index in silhouette coefficient figure
=1) a extreme value determines cluster numbers Ki, by KiTake check post K in elbow figureiSlope fall whether become to mitigate, in this way
Then KiFor preferable clustering number, as not being to find next extreme point in silhouette coefficient figure, and repeat the above process；By Fig. 2-3
It can determine that optimal cluster numbers are 5 in the present embodiment.After determining preferable clustering number mesh, the K- of K=5 is carried out by PYTHON
Means clustering, and cluster result is subjected to labeling programmed process (i.e. by all data in different cluster results point
It is not identified with A~E), obtain the cluster result load chart such as Fig. 4, the load that every line is one day in Fig. 4, horizontal seat
Mark represents 96 moment, and ordinate is load value, automatically generates 5 clusters according to load size and cluster numbers 5 after cluster, every in figure
A clustering cluster is presented with different gray scales, easily observes the amplitude range of every cluster.By the cluster result of same label (i.e. similar)
It is placed in same load chart, obtains such as five class cluster result load chart of Fig. 5-9；By the cluster knot of same label
Fruit marks in the calendar figure of current year, such as Fig. 5 is peak load cluster, and every load line corresponding date in Fig. 5 is being schemed
It is marked in 10 calendar watch with same, is similarly identified in 4 with other and mark the corresponding date of Fig. 6,7,8,9 respectively, in this way
Calendar figure of classifying such as the electricity power of Figure 10 is just obtained, the relationship of season in month and load is obtained according to Figure 10.Further according to obtaining
Five class cluster result load charts (Fig. 5-9) be averaged in 96 moment point load datas of whole day respectively, then obtain
Such as five electricity power typical day load curve figures of Figure 11, observe load characteristics clustering known to Figure 10 electricity power classification calendar figure with
There are apparent incidence relation in month and festivals or holidays, and five electricity power typical day load curve figures that Figure 11 is obtained and Figure 10 are seen
It can be respectively designated as after the result association of survey: for cold season typical day load curve figure, conditioning in Transition Season typical day load curve figure, heating
Season typical day load curve figure, weekend typical day load curve figure and festivals or holidays typical day load curve figure.
To Fig. 4-11 carry out with can feature and load prediction analyze, obtain the industrial enterprise power utilization load at any time, season
Continuity variation, several days generated because of temperature cataclysm discontinuity variation rule figure.Summer seven, August are Shanghai
In most hot season, due to the increase of air conditioner refrigerating workload demand amount, electric load demand is dramatically increased, and for cold season, typical case is in a few days electric
Power load fluctuates in the range of 2990kW-3869kW；Conditioning in Transition Season five, six, September are influenced and ring by enterprise's production plan
Border proper temperature becomes the electric power energy consumption grouping of enterprise whole year second level, and in a few days electric load exists conditioning in Transition Season typical case
It is fluctuated in the range of 2672kW-3332kW；Heating season one, two, three, ten, 11, the December be duration longest, it is continuous
Property the grouping of most complete electric power energy consumption, also indicate that simultaneously, the factor that electric load is influenced by weather is mainly hot weather, heating
Season typical case in a few days electric load fluctuated in the range of 2255kW-2866kW；Meanwhile by the fixed day off of employee in enterprise
It influences, electric load on every Sundays is both less than other workaday loads in this week, and in a few days electric load exists weekend typical case
It is fluctuated in the range of 2016kW-2236kW；Finally, being influenced by the Spring Festival and National Day, electric load is needed during two festivals or holidays
Ask minimum up to whole year, in a few days electric load fluctuates festivals or holidays typical case in the range of 1152kW-1246kW.
The optimal verifying that cluster result carries out preferable clustering number is obtained by carrying out different K values, is obtained such as Figure 12~15 (K=
3, K=4, K=6, K=7) cluster result load chart.By comparative analysis it is found that Figure 12-13 has ordinate in cluster
The excessive phenomenon of value span (single cluster be more than five cluster span scopes 43%)；Figure 14-15 has more clusters to intersect, it is unknown to classify
Aobvious phenomenon, therefore can determine that preferable clustering number is 5 with reasonability.
The above-described embodiments are merely illustrative of preferred embodiments of the present invention, not to model of the invention
It encloses and is defined, without departing from the spirit of the design of the present invention, this field ordinary engineering and technical personnel is to the technology of the present invention side
The various changes and improvements that case is made, should fall within the scope of protection determined by the claims of the present invention.
Claims (1)
1. a kind of method for determining typical day load curve using integrated energy system energy consumption big data, which is characterized in that specific
Include the following steps:
1) certain year known to certain enterprise or regional areas annual Power system load data is chosen daily according to daily 96 moment
Load data, the abnormal data occurred by the abnormal reason of maintenance, table tool failure is rejected when selection；
2) data put in order are put into database, carry out cluster evolutionary programming, generated silhouette coefficient figure and elbow figure, pass through
I-th of extreme value of ordinate SILHOUETTE index determines cluster numbers K in silhouette coefficient figurei, by KiTake check post in elbow figure
KiSlope fall whether become to mitigate, then K in this wayiFor preferable clustering number, as be not find it is next in silhouette coefficient figure
A extreme point, and repeat the above process, obtain optimal cluster numbers n；
3) preferable clustering number is substituted into program and carries out load data cluster labels, 1 year load data presses the load order of magnitude certainly
It is dynamic to be divided into n label, obtain cluster result load chart, the load that every line is one day in figure, when abscissa represents 96
It carves, ordinate is load value, automatically generates n cluster according to load size and cluster numbers n after cluster, and show the amplitude model of every cluster
It encloses；
4) the every daily load line corresponding date in every cluster load chart is marked in calendar figure with same mark, forms electricity
The power calendar figure that can classify, load characteristics clustering known to observation electricity power classification calendar figure are significantly associated with month with festivals or holidays
System carries out name nominating to every cluster load chart；
5) every cluster load chart is averaged in 96 moment point load datas of whole day respectively, is obtained negative with energy typical day
Lotus curve graph, every is named with the load curve that energy typical day load curve figure corresponds to step 4), forms final typical daily load
Curve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910526445.6A CN110298567A (en) | 2019-06-18 | 2019-06-18 | The method for determining typical day load curve using integrated energy system energy consumption big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910526445.6A CN110298567A (en) | 2019-06-18 | 2019-06-18 | The method for determining typical day load curve using integrated energy system energy consumption big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110298567A true CN110298567A (en) | 2019-10-01 |
Family
ID=68028322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910526445.6A Pending CN110298567A (en) | 2019-06-18 | 2019-06-18 | The method for determining typical day load curve using integrated energy system energy consumption big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298567A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583059A (en) * | 2020-04-20 | 2020-08-25 | 上海电力大学 | Distributed energy station typical daily load obtaining method based on k-means clustering |
| CN111612273A (en) * | 2020-05-28 | 2020-09-01 | 山东大学 | Regional-level comprehensive energy system partition design method and system |
| CN112566054A (en) * | 2020-12-18 | 2021-03-26 | 北京思特奇信息技术股份有限公司 | Method and system for optimizing message interaction process |
| CN114944654A (en) * | 2022-07-13 | 2022-08-26 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing real heavy load overload of line of photovoltaic access distribution network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956319A (en) * | 2016-05-18 | 2016-09-21 | 广州供电局有限公司 | Data driving-based bus load characteristic analysis |
| CN109034504A (en) * | 2018-09-14 | 2018-12-18 | 云南电网有限责任公司 | A kind of Short-term Load Forecasting Model method for building up and device |
| CN109766399A (en) * | 2018-12-29 | 2019-05-17 | 神思电子技术股份有限公司 | A kind of trajectory-based base station drive test point selection method |
-
2019
- 2019-06-18 CN CN201910526445.6A patent/CN110298567A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105956319A (en) * | 2016-05-18 | 2016-09-21 | 广州供电局有限公司 | Data driving-based bus load characteristic analysis |
| CN109034504A (en) * | 2018-09-14 | 2018-12-18 | 云南电网有限责任公司 | A kind of Short-term Load Forecasting Model method for building up and device |
| CN109766399A (en) * | 2018-12-29 | 2019-05-17 | 神思电子技术股份有限公司 | A kind of trajectory-based base station drive test point selection method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583059A (en) * | 2020-04-20 | 2020-08-25 | 上海电力大学 | Distributed energy station typical daily load obtaining method based on k-means clustering |
| CN111583059B (en) * | 2020-04-20 | 2024-01-23 | 上海电力大学 | Distributed energy station typical daily load acquisition method based on k-means clustering |
| CN111612273A (en) * | 2020-05-28 | 2020-09-01 | 山东大学 | Regional-level comprehensive energy system partition design method and system |
| CN111612273B (en) * | 2020-05-28 | 2023-09-08 | 山东大学 | Regional level comprehensive energy system partition design method and system |
| CN112566054A (en) * | 2020-12-18 | 2021-03-26 | 北京思特奇信息技术股份有限公司 | Method and system for optimizing message interaction process |
| CN112566054B (en) * | 2020-12-18 | 2022-04-19 | 北京思特奇信息技术股份有限公司 | Method and system for optimizing message interaction process |
| CN114944654A (en) * | 2022-07-13 | 2022-08-26 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing real heavy load overload of line of photovoltaic access distribution network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108009938B (en) | System load clustering and load period pattern recognition method based on shape | |
| CN110298567A (en) | The method for determining typical day load curve using integrated energy system energy consumption big data | |
| Dong et al. | Wind power day-ahead prediction with cluster analysis of NWP | |
| CN104076224B (en) | A kind of test method of power information collecting device reliability demonstration | |
| WO2018209913A1 (en) | Distribution network station area power shortage prediction method based on voltage quality | |
| CN102147839A (en) | Method for forecasting photovoltaic power generation quantity | |
| CN109685567A (en) | It is a kind of to be drawn a portrait new method based on convolutional neural networks and the Electricity customers of fuzzy clustering | |
| CN111191966A (en) | Time-space characteristic-based power distribution network voltage unqualified time period identification method | |
| CN111738573A (en) | Health evaluation method based on electric energy meter full life cycle data | |
| CN115660225A (en) | Electricity load prediction management method and system based on ammeter communication module | |
| CN106845748A (en) | A kind of INTELLIGENT IDENTIFICATION method of low-voltage collecting meter reading system data deviation reason | |
| CN106327359A (en) | Electricity consumption mode analysis-based meter centralized reading data anomaly judgment method | |
| CN106408125A (en) | Intelligent low-voltage centralized meter-reading and rechecking management and control system | |
| CN109241190A (en) | Electric power big data mixes computing architecture | |
| CN106651093A (en) | Smart re-check management and control method used for low voltage set copy system | |
| Lu et al. | Research on creating multi-attribute power consumption behavior portraits for massive users | |
| CN112307675A (en) | Neural network-based temperature-sensitive load separation identification method and system | |
| CN111489270A (en) | Distribution network power failure sensitivity evaluation method taking line as unit | |
| Zhu et al. | Load Forecasting of the power system: an investigation based on the method of random forest regression | |
| Zhang et al. | The research on smart power consumption technology based on big data | |
| Ya’An | Application of artificial intelligence in computer network technology in the era of big data | |
| CN114048200A (en) | User electricity consumption behavior analysis method considering missing data completion | |
| CN111487488A (en) | Intelligent station area outdoor transformer identification method based on grey correlation analysis | |
| Liu et al. | Power customer complaints model based on grey correlation analysis method | |
| Ogliari et al. | Machine Learning methods for clustering and day-ahead thermal load forecasting of an existing District Heating |
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 |