CN110288127A - A kind of energy big data processing method - Google Patents
A kind of energy big data processing method Download PDFInfo
- Publication number
- CN110288127A CN110288127A CN201910466101.0A CN201910466101A CN110288127A CN 110288127 A CN110288127 A CN 110288127A CN 201910466101 A CN201910466101 A CN 201910466101A CN 110288127 A CN110288127 A CN 110288127A
- Authority
- CN
- China
- Prior art keywords
- data
- energy
- energy consumption
- processing method
- data processing
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 238000005265 energy consumption Methods 0.000 claims abstract description 63
- 230000002159 abnormal effect Effects 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 8
- 230000001932 seasonal effect Effects 0.000 claims abstract description 6
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000013500 data storage Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 239000002245 particle Substances 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000011161 development Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009435 building construction Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- -1 electricity Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/182—Distributed file systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to big data processing technology fields, more particularly to a kind of energy big data processing method, the difference is that, its step includes: S1, multi-energy data acquisition: doing TCP communication by timing and energy device Centralized Controller, with the energy consumption data of certain frequency acquisition energy device, and data are stored in relational database；S2, energy consumption data processing: the collected energy consumption data from step S1 has abnormal data and exists, does correcting process to abnormal data；S3, energy consumption data storage: for revised power consumption values obtained in step S3, the data in relational database are imported into distributed file system；S4, energy consumption data prediction: the consumption of following a period of time energy consumption is predicted according to the variation of following seasonal variety and the weather of prediction.The present invention carries out processing analysis to energy big data, predicts the Expenditure Levels of the energy, reduces energy waste, optimizes energy consumption.
Description
Technical field
The present invention relates to big data processing technology fields, more particularly to a kind of energy big data processing method.
Background technique
The energy is the important material base that human society is depended on for existence and development.Make a general survey of the history of human social development, people
The major progress each time of class civilization is all along with the improvement of the energy and replacement.The development and utilization of the energy greatly advance the world
The development of economy and human society.With energy growing tension and environmental degradation, energy saving, raising efficiency of energy utilization is extremely
It is important.All kinds of water, electricity, gas equipment and classification energy consumption are industrial plants, social infrastructure and all kinds of building construction investments and day
One of the main composition part of normal operation cost, the configuration of rational deployment energy facilities and control function can significantly improve facility with
Efficiency of energy utilization simultaneously reduces cost.
Detection and collected energy consumption data can only be shown to user by current energy management, and there is no further
Analysis and prediction, user can not make improvement or precautionary measures accordingly, and the data utilization rate of energy resource system is not high.
In consideration of it, to overcome above-mentioned technological deficiency, a kind of energy big data processing method is provided becomes this field and urgently solve
Certainly the problem of.
Summary of the invention
The purpose of the present invention is to overcome the shortcomings of the existing technology, a kind of energy big data processing method is provided, to the energy
Big data carries out processing analysis, predicts the Expenditure Levels of the energy, reduces energy waste, optimizes energy consumption.
In order to solve the above technical problems, the technical solution of the present invention is as follows: a kind of energy big data processing method, difference
It is in step includes:
S1, multi-energy data acquisition: TCP communication is done by timing and energy device Centralized Controller, is acquired with certain frequency
The energy consumption data of energy device, and data are stored in relational database；
S2, energy consumption data processing: the collected energy consumption data from step S1 has abnormal data and exists, to exception
Data do correcting process；
S3, energy consumption data storage: for revised power consumption values obtained in step S3, by the data in relational database
It imported into distributed file system；
S4, energy consumption data prediction: it is predicted according to the variation of following seasonal variety and the weather of prediction one section following
The consumption of time energy consumption.
By above technical scheme, in the step S1, with the energy consumption data of frequency collection energy device once every minute,
The energy consumption data of 1440 points of acquisition daily.
By above technical scheme, in the step S2, specific steps are as follows:
S21, screening abnormal data；
S22, amendment abnormal data.
By above technical scheme, in the step S21, part normal data points are filtered out first for reducing to be treated
Data volume improves treatment effeciency simultaneously, then filters out abnormal power consumption values with the local factors check method that peels off.
By above technical scheme, the specific implementation step of the step S21 are as follows:
S211, arrangement generation energy consumption data collection is arranged energy consumption data；
S212, clustering algorithm is called to data set, obtain several particles after the completion of cluster, find out each point in each class and arrive
The distance average R of particle；
The percentage of normal data quantity that S213, setting need to reject, according to each point apart from mass center from small to large suitable
Sequence, rejects the normal point in part for being less than R from centroid distance, and accounting is pre-set percentage；
S214, remaining data application LOF algorithm calculate and the factor that peels off for all data points that sort, each data point
The factor that peels off is compared by the threshold values with setting, and output LOF value is greater than the data point of threshold values, obtains abnormal data with this
Point.
By above technical scheme, in the step S22, regression tree is established using tree algorithm is returned, and return using what is established
Gui Shu corrects energy consumption Value Data.
By above technical scheme, in the step S4, the pre- measurement of power of energy consumption data is realized using BP neural network model
Energy.
By above technical scheme, the step of energy consumption data is predicted are as follows:
A, network creation: history 6 months energy consumption data training neural networks are chosen, wherein doing to preceding 5 months data
It is trained for sample, last 1 month data are tested；
B, training: training process uses standard BP neural network algorithm, and increases momentum term to pass through using the adjustment of accumulation
It tests to accelerate pace of learning and keep stablizing；
C, it predicts: the network of foundation being used for energy consumption prediction, uses nearest 1 month sample data as input data,
Following one week energy consumption data is predicted using sample data, and compares verifying feasibility with truthful data.
By above technical scheme, in the step A, by ambient lighting, sun set/raise time, environment season, illumination period
Input variable of the weather condition as neural network, using power consumption values as output variable；For the number of hidden nodes of neural network,
Pass throughFormula determine.
By above technical scheme, in the step B, in training data in such a way that batch learns, by repeatedly following
Ring Training Control obtains stable training result.
Compare the prior art, beneficial features of the invention are as follows: processing analysis is carried out to energy big data, can predict the energy
Expenditure Levels, reduce energy waste, and optimize energy consumption, user allow preferably to make corrective measure.
Detailed description of the invention
Fig. 1 is the flow diagram of the embodiment of the present invention；
Fig. 2 is the network structure of BP neural network of embodiment of the present invention model.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawing and specific implementation
Invention is further described in detail for example.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention,
It is not intended to limit the present invention.
Hereinafter, many aspects of the invention will be more fully understood with reference to attached drawing.Component in attached drawing may not be according to
Ratio is drawn.Alternatively, it is preferred that emphasis is clearly demonstrate component of the invention.In addition, in several views in the accompanying drawings, it is identical
Appended drawing reference indicate corresponding part.
Word " exemplary " as used herein or " illustrative " expression are used as example, example or explanation.It retouches herein
Stating any embodiment for " exemplary " or " illustrative " to be not necessarily to be construed as is preferred relative to other embodiment or has
Benefit.All embodiments described below are illustrative embodiments, and providing these illustrative embodiments is to make
Those skilled in the art are obtained to make and use embodiment of the disclosure and be expected to be not intended to limit the scope of the present disclosure, the disclosure
Range is defined by the claims.In other embodiments, well known feature and method is described in detail so as not to obscure this
Invention.For purpose described herein, term " on ", "lower", "left", "right", "front", "rear", "vertical", "horizontal" and its spread out
New word is related by the invention oriented with such as Fig. 1.Moreover, having no intent to by technical field, background technique, summary of the invention above
Or any theoretical limitation expressed or implied provided in detailed description below.It should also be clear that being shown in the accompanying drawings and below
Specification described in specific device and process be the inventive concept limited in the following claims simple examples it is real
Apply example.Therefore, specific size relevant to presently disclosed embodiment and other physical features are understood not to restricted
, unless claims are separately clearly stated.
Referring to Figures 1 and 2, a kind of energy big data processing method of the embodiment of the present invention, the difference is that, step
Suddenly include:
S1, multi-energy data acquisition: TCP communication is done by timing and energy device Centralized Controller, is acquired with certain frequency
The energy consumption data of energy device, and data are stored in relational database, the energy device in the present embodiment is street lamp；
S2, energy consumption data processing: the collected energy consumption data from step S1 has abnormal data and exists, to exception
Data do correcting process；
S3, energy consumption data storage: for revised power consumption values obtained in step S3, by the data in relational database
It imported into distributed file system；
S4, energy consumption data prediction: it is predicted according to the variation of following seasonal variety and the weather of prediction one section following
The consumption of time energy consumption.
Preferably, it in the step S1, with the energy consumption data of frequency collection energy device once every minute, acquires daily
The energy consumption data of 1440 points.
Specifically, in the step S2, specific steps are as follows:
S21, screening abnormal data；
S22, amendment abnormal data.
Specifically, ratio shared by the characteristics of according to energy consumption data, abnormal data and missing data is compared and normal data
Can be very low, in the step S21, filters out part normal data points first for reducing data volume to be treated while improving
Treatment effeciency, then abnormal power consumption values are filtered out with the local factors check method (LOF algorithm) that peels off.
Specifically, the specific implementation step of the step S21 are as follows:
S211, arrangement generation energy consumption data collection is arranged energy consumption data；
S212, K-means clustering algorithm is called to data set, obtain several particles after the completion of cluster, find out each class
Distance average R of the middle each point to particle；
The percentage p of normal data quantity that S213, setting need to reject, according to each point apart from mass center from small to large suitable
Sequence, rejects the normal point in part for being less than R from centroid distance, and accounting is pre-set percentage p；
S214, remaining data application LOF algorithm calculate and the factor that peels off for all data points that sort, each data point
The factor that peels off is compared by the threshold values with setting, and output LOF value is greater than the data point of threshold values, obtains abnormal data with this
Point.
Preferably, in the step S22, regression tree is established using tree algorithm is returned, and correct using the regression tree established
Energy consumption Value Data.
Specifically, in the step S3, for revised power consumption values obtained in energy consumption data processing step, by
Data in relational database are imported into Hadoop distributed file system (HDFS) by Sqoop tool.Specific implementation is such as
Under:
The import order for calling Sqoop script obtains the information of database table from relational database；Sqoop is utilized
Order is generated the Map operation of multiple MapReduce by the advantages of MapReduce distribution batch processing；The Map operation of generation is connected
It is connected to Hadoop resource manager, executes Map operation parallel on Hadoop, the number after the completion of execution, in relational database
According to also having been imported into HDFS.
Preferably, in the step S4, the forecast function of energy consumption data is realized using BP neural network model.
In independently developed road lamp management plateform system, switch, brightness regulation to street lamp are provided with by strategy adjustment
And automatic adjustment, strategy adjustment press seasonal difference, can open and close street lamp in different times, while also can be according to day
The difference of gas incudes the illumination of surrounding enviroment, to automatically adjust the brightness of street lamp.Therefore season and weather history can be made
For the larger factor of correlation, judge street lamp brightness, street lamp opening time and two above factor relevance namely may determine that
Season and weather conditions for energy consumption influence degree, so as to according to the change of following seasonal variety and the weather of prediction
Change the consumption to predict following a period of time energy consumption.
Specifically, the step of energy consumption data is predicted are as follows:
A, network creation: history 6 months energy consumption data training neural networks are chosen, wherein doing to preceding 5 months data
It is trained for sample, last 1 month data are tested；
B, training: training process uses standard BP neural network algorithm, and increases momentum term to pass through using the adjustment of accumulation
It tests to accelerate pace of learning and keep stablizing；
C, it predicts: the network of foundation being used for energy consumption prediction, uses nearest 1 month sample data as input data,
Following one week energy consumption data is predicted using sample data, and compares verifying feasibility with truthful data.
Specifically, in the step A, by ambient lighting, sun set/raise time, environment season, illumination period weather condition
As the input variable of neural network, using power consumption values as output variable；For the number of hidden nodes of neural network, pass throughFormula determine.
Specifically, in the step B, in training data in such a way that batch learns, by multiple circuit training control
System, obtains stable training result.
The above content is specific embodiment is combined, further detailed description of the invention, and it cannot be said that this hair
Bright specific implementation is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, it is not taking off
Under the premise of from present inventive concept, a number of simple deductions or replacements can also be made, all shall be regarded as belonging to protection of the invention
Range.
Claims (10)
1. a kind of energy big data processing method, which is characterized in that its step includes:
S1, multi-energy data acquisition: doing TCP communication by timing and energy device Centralized Controller, acquires the energy with certain frequency
The energy consumption data of equipment, and data are stored in relational database；
S2, energy consumption data processing: the collected energy consumption data from step S1 has abnormal data and exists, to abnormal data
Do correcting process；
S3, energy consumption data storage: for revised power consumption values obtained in step S3, the data in relational database are imported
Into distributed file system；
S4, energy consumption data prediction: following a period of time is predicted according to the variation of following seasonal variety and the weather of prediction
The consumption of energy consumption.
2. energy big data processing method according to claim 1, it is characterised in that: in the step S1, with per minute
The energy consumption data of primary frequency collection energy device acquires the energy consumption data of 1440 points daily.
3. energy big data processing method according to claim 1, it is characterised in that: in the step S2, specific steps
Are as follows:
S21, screening abnormal data；
S22, amendment abnormal data.
4. energy big data processing method according to claim 3, it is characterised in that: in the step S21, first filter out
Part normal data points improve treatment effeciency for reducing data volume to be treated simultaneously, then with the local factors check that peels off
Method filters out abnormal power consumption values.
5. energy big data processing method according to claim 4, it is characterised in that: the specific implementation of the step S21
Step are as follows:
S211, arrangement generation energy consumption data collection is arranged energy consumption data；
S212, clustering algorithm is called to data set, obtain several particles after the completion of cluster, find out in each class each point to particle
Distance average R；
The percentage for the normal data quantity that S213, setting need to reject, the sequence according to each point apart from mass center from small to large are picked
Except the normal point in part for being less than R from centroid distance, accounting is pre-set percentage；
S214, remaining data application LOF algorithm calculate and the factor that peels off for all data points that sort, each data point peel off
The factor is compared by the threshold values with setting, and output LOF value is greater than the data point of threshold values, obtains abnormal data point with this.
6. energy big data processing method according to claim 3, it is characterised in that: in the step S22, use recurrence
Tree algorithm establishes regression tree, and corrects energy consumption Value Data using the regression tree established.
7. energy big data processing method according to claim 1, it is characterised in that: in the step S4, using BP mind
The forecast function of energy consumption data is realized through network model.
8. energy big data processing method according to claim 7, it is characterised in that: the step of energy consumption data is predicted
Are as follows:
A, network creation: history 6 months energy consumption data training neural networks are chosen, wherein to preceding 5 months data as sample
Originally it is trained, last 1 month data are tested；
B, training: training process use standard BP neural network algorithm, and increase momentum term with using accumulate adjustment experience come
Accelerate pace of learning and keeps stablizing；
C, it predicts: the network of foundation being used for energy consumption prediction, uses nearest 1 month sample data as input data, utilizes
Sample data predicts following one week energy consumption data, and compares verifying feasibility with truthful data.
9. energy big data processing method according to claim 8, it is characterised in that: in the step A, by environment light
According to, the input variable of sun set/raise time, environment season, illumination period weather condition as neural network, using power consumption values as
Output variable；For the number of hidden nodes of neural network, pass through's
Formula determines.
10. energy big data processing method according to claim 8, it is characterised in that: in the step B, in training number
According to when using batch learn by the way of, by multiple circuit training control, obtain stable training result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910466101.0A CN110288127A (en) | 2019-05-31 | 2019-05-31 | A kind of energy big data processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910466101.0A CN110288127A (en) | 2019-05-31 | 2019-05-31 | A kind of energy big data processing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110288127A true CN110288127A (en) | 2019-09-27 |
Family
ID=68003209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910466101.0A Pending CN110288127A (en) | 2019-05-31 | 2019-05-31 | A kind of energy big data processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288127A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112231306A (en) * | 2020-08-23 | 2021-01-15 | 山东翰林科技有限公司 | Big data based energy data analysis system and method |
| CN115912359A (en) * | 2023-02-23 | 2023-04-04 | 豪派(陕西)电子科技有限公司 | Digitalized potential safety hazard identification, investigation and treatment method based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105590174A (en) * | 2015-12-29 | 2016-05-18 | 南京因泰莱电器股份有限公司 | Enterprise power consumption load prediction method based on K-means clustering RBF neural network |
| CN106022521A (en) * | 2016-05-19 | 2016-10-12 | 四川大学 | Hadoop framework-based short-term load prediction method for distributed BP neural network |
| CN108876019A (en) * | 2018-05-31 | 2018-11-23 | 中国电力科学研究院有限公司 | A kind of electro-load forecast method and system based on big data |
| CN108985570A (en) * | 2018-08-17 | 2018-12-11 | 深圳供电局有限公司 | A kind of load forecasting method and its system |
| CN109214572A (en) * | 2018-09-06 | 2019-01-15 | 南京工业职业技术学院 | One kind is based on EPSO-BP to commercial building lamp decoration energy consumption prediction technique |
-
2019
- 2019-05-31 CN CN201910466101.0A patent/CN110288127A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105590174A (en) * | 2015-12-29 | 2016-05-18 | 南京因泰莱电器股份有限公司 | Enterprise power consumption load prediction method based on K-means clustering RBF neural network |
| CN106022521A (en) * | 2016-05-19 | 2016-10-12 | 四川大学 | Hadoop framework-based short-term load prediction method for distributed BP neural network |
| CN108876019A (en) * | 2018-05-31 | 2018-11-23 | 中国电力科学研究院有限公司 | A kind of electro-load forecast method and system based on big data |
| CN108985570A (en) * | 2018-08-17 | 2018-12-11 | 深圳供电局有限公司 | A kind of load forecasting method and its system |
| CN109214572A (en) * | 2018-09-06 | 2019-01-15 | 南京工业职业技术学院 | One kind is based on EPSO-BP to commercial building lamp decoration energy consumption prediction technique |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112231306A (en) * | 2020-08-23 | 2021-01-15 | 山东翰林科技有限公司 | Big data based energy data analysis system and method |
| CN115912359A (en) * | 2023-02-23 | 2023-04-04 | 豪派(陕西)电子科技有限公司 | Digitalized potential safety hazard identification, investigation and treatment method based on big data |
| CN115912359B (en) * | 2023-02-23 | 2023-07-25 | 豪派(陕西)电子科技有限公司 | Digital potential safety hazard identification, investigation and treatment method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | MPPT perturbation optimization of photovoltaic power systems based on solar irradiance data classification | |
| CN105069525B (en) | Round-the-clock 96 Day Load Curve Forecastings and optimization update the system | |
| CN106228274A (en) | Photovoltaic power station power generation amount Forecasting Methodology based on SOM Neural Network Data clustering recognition | |
| CN109685257A (en) | A kind of photovoltaic power generation power prediction method based on Support vector regression | |
| Oudjana et al. | Short term photovoltaic power generation forecasting using neural network | |
| CN103390200A (en) | Photovoltaic power station electricity generation output power forecasting method based on similar days | |
| CN110288127A (en) | A kind of energy big data processing method | |
| CN110298488A (en) | A kind of multi-energy data analysis method and system based on data mining | |
| Llorca et al. | SO2 emissions and the environmental Kuznets curve: the case of Chinese provinces | |
| CN104331844A (en) | Power network infrastructure project investment decision-making method | |
| CN108446808A (en) | A kind of short-term load forecasting method of glowworm swarm algorithm optimization neural network | |
| CN109507535A (en) | Grounding net of transformer substation operation phase and service life prediction technique and device | |
| CN104778506B (en) | Short-term wind speed forecasting method based on local integrated study | |
| CN106099945A (en) | A kind of big data modeling of GA for reactive power optimization and abnormal scheme detection method | |
| CN109002926A (en) | The photovoltaic power generation quantity prediction model and its construction method of a kind of high accuracy and application | |
| CN109242177A (en) | Active power distribution network planing method | |
| CN107274015A (en) | A kind of method and system of prediction of wind speed | |
| Veeramanikandan et al. | A fuzzy‐elephant herding optimization technique for maximum power point tracking in the hybrid wind‐solar system | |
| CN110070228A (en) | BP neural network wind speed prediction method for neuron branch evolution | |
| CN113311799A (en) | Urban drainage operation scheduling decision system and construction method | |
| CN106056233A (en) | Power load prediction method | |
| CN107862410A (en) | A kind of film screening system and method for machine simulation | |
| CN109272058A (en) | Integrated power load curve clustering method | |
| Hamid et al. | Optimal sizing of distributed generation using firefly algorithm and loss sensitivity for voltage stability improvement | |
| CN117151424A (en) | Artificial intelligence power scheduling decision-making system based on big data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190927 |