CN108335042A - Method for calculating cleaning index of dynamic photovoltaic panel - Google Patents
Method for calculating cleaning index of dynamic photovoltaic panel Download PDFInfo
- Publication number
- CN108335042A CN108335042A CN201810114996.7A CN201810114996A CN108335042A CN 108335042 A CN108335042 A CN 108335042A CN 201810114996 A CN201810114996 A CN 201810114996A CN 108335042 A CN108335042 A CN 108335042A
- Authority
- CN
- China
- Prior art keywords
- index
- values
- cluster
- value
- regression analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06Q10/0639—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention relates to a method for calculating a dynamic photovoltaic panel cleaning index based on PM value data. The method comprises the following steps: collecting the dust accumulation degree, the power generation loss rate, the expected power generation value and the PM value of the location of a local power station; performing linear regression analysis using the PM value and the dust accumulation degree; predicting the power generation loss rate according to linear regression, and expanding an original data set; and rearranging by using a clustering method according to the power generation loss rate, wherein the final sequence is the recommended cleaning index. According to the invention, the dust accumulation degree and the PM value are fitted through regression analysis, after data fitting is completed, the PM value which is easy to obtain can be used as a characteristic parameter to be cooperatively filtered with other characteristics such as generating capacity and electric quantity loss index, an accurate cleaning index is obtained under the condition of minimum investment, a user is automatically reminded whether the dust deposition degree of the photovoltaic panel needs to be cleaned, the photovoltaic panel is cleaned in time, the power generation efficiency is improved, and the cost is saved.
Description
Technical field
The present invention relates to photovoltaic battery plate dust monitoring technology field, specifically a kind of dynamics assessed based on PM Value Datas
Photovoltaic battery plate cleans the computational methods of index.
Background technology
Since the generating capacity of photovoltaic generating system is the evaluation most important index of photovoltaic plant performance, and dust is to photovoltaic
The power generation performance of component is influenced there are generality, and atmospheric dust is to influence one of the key factor of solar energy generating efficiency, especially
Being prolonged dust storm causes the fouling products such as dust to block photovoltaic module, influences the transmissivity of light, and then influence assembly surface
The amount of radiation received.
Simultaneously as distance of these fouling products apart from photovoltaic cell is close, shade can be formed, and have in photovoltaic module
It is standby to form hot spot effect.If cleaned not in time to photovoltaic module for a long time, it will photovoltaic power station power generation is greatly lowered
Amount, cannot not only meet the requirement of power grid, but also also reduce the utilization rate of photovoltaic generating system.At present for the research of dust
It predominantly stays in and the accumulation degree of dust is monitored using sensor, this method deployment cost is high, needs to install a large amount of biography
Sensor.
Invention content
Effective means monitoring is lacked to dust for the monitoring of existing photovoltaic, complexity is high, has great dependence to sensor
Property, not mature enough perfect problem, the present invention provides a kind of assessing low temperatures battery plate according to PM Value Datas simple and easy to get
The computational methods for cleaning index, can realize the regression analysis of PM values and dust accumulation degree, be analyzed by characteristic value, be obtained
Clean the proposed algorithm of index.
The present invention solve its technical problem the technical solution adopted is that:
A kind of computational methods of low temperatures battery plate cleaning index, carry out as follows:
Data acquisition → regression analysis → standardized data → clustering → index is reset;Wherein, data acquisition is to receive
The dust accumulation degree in the local power station of collection, generation loss rate, expected power generation values, location PM values;Regression analysis uses PM values and ash
Dirt accumulation degree carries out linear regression analysis;Standardized data is predicted generation loss rate according to linear regression, is expanded former
Beginning data set;Clustering is using clustering method and according to generation loss rate rearrangement, and final sequence is to recommend
Clean index.
Using the present invention of above-mentioned technical proposal, compared with prior art, advantageous effect is:
The present invention is fitted dust accumulation degree and PM values by regression analysis, can be with after the completion of data fitting
It uses the PM values being easily obtained as characteristic parameter, carries out collaborative filtering with other features such as generated energy, electric quantity loss indexes, throwing
Enter it is as small as possible in the case of obtain accurately cleaning index, whether the dust stratification degree of automatically prompting user electro-optical package needs clearly
It washes, by cleaning photovoltaic battery plate in time, promotion generating efficiency is cost-effective.
Further, preferred embodiment of the present invention is:
The linear regression analysis, starting stage use the linear regression of PM indexes, dust stratification index and loss of power rate
Equation carries out regression analysis, automatically generates new regression analysis according to sensing data later;Specifically equation of linear regression is:
In formula, x is PM values, and y is dust accumulation degree, and linear relationship coefficients of the R between y and x, n is constant.
The PM values are the PM values according to the place power stations obtained disclosed API.
The clustering method uses the innovatory algorithm of K-means algorithms, K values is set as 100, specifically:
(1) 100 elements are taken at random from distinctiveness ratio calculation formula d, the respective center as k cluster;
(2) remaining element is calculated separately to the distinctiveness ratio at 100 cluster centers, incorporates these elements into distinctiveness ratio respectively
Minimum cluster;
(3) according to cluster result, the respective center of k cluster is recalculated, computational methods are to take in cluster all elements respectively
The arithmetic average of dimension;
(4) whole elements in distinctiveness ratio calculation formula d are clustered again according to new center;
(5) the 4th step is repeated, until cluster result no longer changes;
(6) result is exported;
(7) 100 are clustered by arranging from small to large according to loss late, is respectively divided into cleaning index 1%-100%.
Description of the drawings
Fig. 1 is PM indexes and dust stratification exponential dependence schematic diagram;
Fig. 2 is to recommend index schematic diagram.
Specific implementation mode
In order to more specifically describe the present invention, with reference to the accompanying drawings and embodiments to technical scheme of the present invention and correlation
Principle is described in detail.
A kind of computational methods of low temperatures battery plate cleaning index described in the present embodiment, are as follows:
(1) the PM values in power station, linear regression side is brought into according to the correlativity of prediction where being obtained according to disclosed API
Journey obtains PM values and exports the correlation of slip.
(2) input parameter is as characteristic value, and is standardized.
(3) it is clustered using K-means methods.
(4) cluster is reset according to the proportion of goods damageds, cluster is to recommend cleaning index from low to high.
Referring to Fig. 1, according to test data, regression analysis, PM indexes, dust stratification index are carried out to local PM values and measured data
It is as follows with the regression equation of loss of power rate:
In formula:X is PM values, and y is dust accumulation degree, and linear relationship coefficients of the R between y and x, n is constant.Between y and x
There are linear relationships, illustrate that its degree of contact, the size of the absolute value of coefficient R indicate degree of correlation with coefficient R
Just.For example, current coefficient is 0.82, explanation is part correlation, and deep pool value is larger, illustrates that degree of correlation is higher.
Under current PM values known case, the predicted value of dust accumulation degree, estimated standard deviation S are usedyAnd forecast interval, it is public
Formula is as follows:
Estimated standard deviation:
In formula:SyFor standard deviation, x is PM values, and y is dust accumulation degree, and n is constant,For subset.
Forecast interval:
In formula:SyFor standard deviation, x is PM values, and y is dust accumulation degree, and n is constant,For subset,For average.
Value in forecast interval formula can not directly apply to power station and go in practice, be according to other ginsengs of current plant
It counts to carry out content analysis.Such as the characteristic value of selection includes:PM values, setting angle, generation loss rate, cleaning frequency.
To acquire a believable cleaning index, need to be standardized.Min-max standardized methods are to original
Data carry out linear transformation and pass through an original value x of A if minA and maxA are respectively the minimum value and maximum value of attribute A
Min-max standardization is mapped to the value x' in section [0,1], and formula is:
New data=(former data-minimum)/(maximum-minimum).
Distinctiveness ratio calculating is carried out after data normalization, distinctiveness ratio calculation formula is as follows:
Wherein in formula:X is PM values, and y is dust accumulation degree, and m is quantitative, and λ is constant, and i is variable;
Using the innovatory algorithm of K-means algorithms, K values are set as 100:
1. taking 100 elements at random from distinctiveness ratio calculation formula d, the respective center as k cluster;
2. calculating separately remaining element to the distinctiveness ratio at 100 cluster centers, these elements are incorporated into distinctiveness ratio respectively
Minimum cluster;
3. according to cluster result, the respective center of k cluster is recalculated, computational methods are that all elements in cluster is taken respectively to tie up
The arithmetic average of degree;
4. whole elements in d are clustered again according to new center;
5. the 4th step is repeated, until cluster result no longer changes;
6. result is exported;
7. according to loss late by 100 clusters by arranging from small to large, it is respectively divided into recommendation cleaning index 1%-
100%,
Final result is as shown in Figure 2.
The foregoing is merely preferably feasible embodiments of the invention, not thereby limit to the interest field of the present invention,
It is all to change with equivalent structure made by description of the invention and accompanying drawing content, it is both contained within the interest field of the present invention.
Claims (4)
1. a kind of computational methods of low temperatures battery plate cleaning index, which is characterized in that carry out as follows:
Data acquisition → regression analysis → standardized data → clustering → index is reset;Wherein, data acquisition is to collect to work as
The dust accumulation degree in ground power station, generation loss rate, expected power generation values, location PM values;Regression analysis is tired using PM values and dust
Product degree carries out linear regression analysis;Standardized data is predicted generation loss rate according to linear regression, and original number is expanded
According to collection;Clustering is using clustering method and according to generation loss rate rearrangement, and final sequence is the cleaning recommended
Index.
2. the computational methods of low temperatures battery plate cleaning index according to claim 1, it is characterised in that:Described is linear
Regression analysis, starting stage carry out regression analysis using the equation of linear regression of PM indexes, dust stratification index and loss of power rate,
New regression analysis is automatically generated according to sensing data later;Specifically equation of linear regression is:
In formula, x is PM values, and y is dust accumulation degree, and linear relationship coefficients of the R between y and x, n is constant.
3. the computational methods of low temperatures battery plate cleaning index according to claim 1 or 2, it is characterised in that:Described
PM values are the PM values according to the place power stations obtained disclosed API.
4. the computational methods of low temperatures battery plate cleaning index according to claim 1 or 2, it is characterised in that:Described
Clustering method uses the innovatory algorithm of K-means algorithms, K values is set as 100, specifically:
(1) 100 elements are taken at random from distinctiveness ratio calculation formula d, the respective center as k cluster;
(2) remaining element is calculated separately to the distinctiveness ratio at 100 cluster centers, and it is minimum to incorporate these elements into distinctiveness ratio respectively
Cluster;
(3) according to cluster result, the respective center of k cluster is recalculated, computational methods are to take in cluster all elements respectively dimension
Arithmetic average;
(4) whole elements in distinctiveness ratio calculation formula d are clustered again according to new center;
(5) the 4th step is repeated, until cluster result no longer changes;
(6) result is exported;
(7) 100 are clustered by arranging from small to large according to loss late, is respectively divided into cleaning index 1%-100%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810114996.7A CN108335042B (en) | 2018-02-06 | 2018-02-06 | Method for calculating cleaning index of dynamic photovoltaic panel |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810114996.7A CN108335042B (en) | 2018-02-06 | 2018-02-06 | Method for calculating cleaning index of dynamic photovoltaic panel |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108335042A true CN108335042A (en) | 2018-07-27 |
CN108335042B CN108335042B (en) | 2022-02-01 |
Family
ID=62928106
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810114996.7A Active CN108335042B (en) | 2018-02-06 | 2018-02-06 | Method for calculating cleaning index of dynamic photovoltaic panel |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108335042B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112926798A (en) * | 2021-03-26 | 2021-06-08 | 苏州朋友保科技有限公司 | Method, device, equipment and medium for predicting photovoltaic power generation loss caused by dust |
CN113705881A (en) * | 2021-08-25 | 2021-11-26 | 陕西启迪瑞行清洁能源研究院有限公司 | Plate heat exchanger state prediction method based on logarithmic temperature difference |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102201037A (en) * | 2011-06-14 | 2011-09-28 | 中国农业大学 | Agricultural disaster forecast method |
CN103268366A (en) * | 2013-03-06 | 2013-08-28 | 辽宁省电力有限公司电力科学研究院 | Combined wind power prediction method suitable for distributed wind power plant |
CN104021427A (en) * | 2014-06-10 | 2014-09-03 | 上海电力学院 | Method for predicting daily generating capacity of grid-connected photovoltaic power station based on factor analysis |
CN107064165A (en) * | 2017-05-23 | 2017-08-18 | 扬州鸿淏新能源科技有限公司 | A kind of photovoltaic module surface area gray scale on-line measuring device and cleaning method |
US9740545B2 (en) * | 2015-03-20 | 2017-08-22 | Kabushiki Kaisha Toshiba | Equipment evaluation device, equipment evaluation method and non-transitory computer readable medium |
-
2018
- 2018-02-06 CN CN201810114996.7A patent/CN108335042B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102201037A (en) * | 2011-06-14 | 2011-09-28 | 中国农业大学 | Agricultural disaster forecast method |
CN103268366A (en) * | 2013-03-06 | 2013-08-28 | 辽宁省电力有限公司电力科学研究院 | Combined wind power prediction method suitable for distributed wind power plant |
CN104021427A (en) * | 2014-06-10 | 2014-09-03 | 上海电力学院 | Method for predicting daily generating capacity of grid-connected photovoltaic power station based on factor analysis |
US9740545B2 (en) * | 2015-03-20 | 2017-08-22 | Kabushiki Kaisha Toshiba | Equipment evaluation device, equipment evaluation method and non-transitory computer readable medium |
CN107064165A (en) * | 2017-05-23 | 2017-08-18 | 扬州鸿淏新能源科技有限公司 | A kind of photovoltaic module surface area gray scale on-line measuring device and cleaning method |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112926798A (en) * | 2021-03-26 | 2021-06-08 | 苏州朋友保科技有限公司 | Method, device, equipment and medium for predicting photovoltaic power generation loss caused by dust |
CN113705881A (en) * | 2021-08-25 | 2021-11-26 | 陕西启迪瑞行清洁能源研究院有限公司 | Plate heat exchanger state prediction method based on logarithmic temperature difference |
CN113705881B (en) * | 2021-08-25 | 2024-03-29 | 陕西启迪瑞行清洁能源研究院有限公司 | Method for predicting cleaning index of plate heat exchanger based on logarithmic temperature difference |
Also Published As
Publication number | Publication date |
---|---|
CN108335042B (en) | 2022-02-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110082699B (en) | Low-voltage transformer area intelligent electric energy meter operation error calculation method and system | |
US20170257255A1 (en) | Methods for orientation and tilt identification of photovoltaic systems and solar irradiance sensors | |
CN106059496B (en) | A kind of photovoltaic module array performance monitoring and the method and system of Fault Identification | |
CN112952820B (en) | Intelligent community micro-grid ultra-multi-target energy management method considering retired batteries | |
CN105260800A (en) | Photovoltaic module temperature prediction method and device | |
US20160363695A9 (en) | Methods for location identification of renewable energy systems | |
CN105956788A (en) | Dynamic management control method for cost of power transmission and transformation project | |
CN104361233A (en) | Anti-electric larceny management method under condition of access of distributed generation | |
CN106384015A (en) | Energy consumption data collection-based distributed photovoltaic system energy efficiency pre-estimation method | |
CN108335042A (en) | Method for calculating cleaning index of dynamic photovoltaic panel | |
CN103617447A (en) | Evaluation system and method for intelligent substation | |
CN115065078B (en) | Energy storage capacity configuration method and system in micro-grid environment | |
CN113036759A (en) | Power consumer load fine-grained identification method and identification system | |
CN105337574A (en) | Robust-regression-based distributed photovoltaic generating electricity-stealing identification method | |
Jain et al. | A clustering framework for residential electric demand profiles | |
CN114646888A (en) | Assessment method and system for capacity attenuation of power battery | |
Selvam et al. | Fuzzy based clustering of smart meter data using real power and THD patterns | |
CN115829168B (en) | New energy equipment remote coordination operation and maintenance management system based on data analysis | |
Chen et al. | A vision transformer-based deep neural network for state of health estimation of lithium-ion batteries | |
CN116523681A (en) | Load decomposition method and device for electric automobile, electronic equipment and storage medium | |
CN110796292A (en) | Photovoltaic power short-term prediction method considering haze influence | |
CN115752556A (en) | System and method for identifying abnormal electricity consumption of large customers | |
CN111815022A (en) | Power load prediction method based on time-delay coordinate embedding method | |
CN111062538A (en) | CEEMD method for determining reasonable maximum value of cellular load in space load prediction | |
CN116937816B (en) | Intelligent edge computing gateway |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20220507 Address after: 266100 1808, 18 / F, block B, Shenghe building, No. 58, shangdongtou Road, Laoshan District, Qingdao, Shandong Province Patentee after: Qingdao Guanxin Technology Co.,Ltd. Address before: 063100 middle section of Aimin Road, Tangjiazhuang, Guye District, Tangshan City, Hebei Province Patentee before: TANGSHAN YINGTONG TECHNOLOGY CO.,LTD. |