CN111582751A - Time-weighted electricity purchasing risk early warning method - Google Patents
Time-weighted electricity purchasing risk early warning method Download PDFInfo
- Publication number
- CN111582751A CN111582751A CN202010423104.9A CN202010423104A CN111582751A CN 111582751 A CN111582751 A CN 111582751A CN 202010423104 A CN202010423104 A CN 202010423104A CN 111582751 A CN111582751 A CN 111582751A
- Authority
- CN
- China
- Prior art keywords
- agdhis
- date
- days
- bsep
- dnet
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 101150048692 ABCB11 gene Proteins 0.000 claims description 25
- 238000010248 power generation Methods 0.000 claims description 6
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 claims description 3
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 abstract description 3
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000013058 risk prediction model 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
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- 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)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
According to the time-weighted electricity purchasing risk early warning method disclosed by the invention, the date interval enhancement operator is introduced to weight the electricity purchasing samples according to the dates, the regression neural network model is trained by weighting the decision content of the adjustment samples, and then the electricity purchasing risk early warning is carried out by utilizing the model. According to the method, under the conditions that auxiliary factors are not additionally input and the neural network structure is not adjusted, the sample point close to the prediction time point can play a greater role in the decision making process, and the prediction model can be used for dealing with market and policy situations of the electric power market, so that the early warning precision is improved.
Description
Technical Field
The invention provides a time-weighted electricity purchasing risk early warning method which can deal with market and policy situations appearing in the power market, so that the early warning precision is improved, and the method belongs to the technical field of power market power grid management.
Background
In the case of electricity market transactions, the core of the transaction is the price. The electricity purchasing under the condition that the policy, the transaction and the price are released is possibly in a certain default risk, the transaction can be guaranteed to be carried out under the condition that both the supply and demand parties can obtain benefits based on the market, therefore, the electricity purchasing risk under the condition of a certain period needs to be analyzed, and when the price possibly exceeds the market rule, early warning is carried out, which is very important for the healthy and ordered transaction of the power market.
The currently widely adopted technical means are: an artificial intelligence algorithm of regression analysis and decision analysis is introduced, historical data are learned by using the model so as to obtain a risk prediction model, and the risk of electricity purchasing can be warned by using the model. This kind of method can obtain good prediction results in both laboratories and papers, however in practical work, many influencing factors are emerging such as: the natural resources change (wind power, water power and the like can be greatly influenced), and the market and policy factors cause the change of the power supply and demand; on one hand, new influence factors may not be recorded into the system in a quantitative or qualitative manner, and specific numerical values of some factors cannot be obtained, so that the utilization of the new factors in the prediction model is difficult; on the other hand, adding new factors can cause great differences in model dimensionality and generalization capability, so that the original model fails; these emerging factors may be confounded with historical other factors, thereby interfering with the decision-making process.
Although the factors causing the risk of electricity purchase are various, the electricity transaction has certain stability within a certain period range. Therefore, when a power purchase risk early warning model is established, time factors need to be considered, and the occurrence time is weighted, so that a sample point close to a prediction time point can play a greater role in a decision process, and the early warning accuracy is improved.
The invention content is as follows:
according to the time-weighted electricity purchasing risk early warning method disclosed by the invention, the date interval enhancement operator is introduced to weight the electricity purchasing samples according to the dates, the regression neural network model is trained by weighting the decision content of the adjustment samples, and then the electricity purchasing risk early warning is carried out by utilizing the model.
The invention relates to a time-weighted electricity purchasing risk early warning method, which comprises the following steps:
s1, inputting historical electricity purchasing data AGDHis of a power plant; acquiring the number AGDNum of historical electricity purchasing data, the earliest date AOldday in the historical data and the latest date ANewday in the historical data;
s101, inputting power purchase history data AGDHis, wherein the AGDHis is a list, and each element in the list comprises the following fields;
ARQ: electricity purchase agreement date;
ARQY: the month value corresponding to the electricity purchasing agreement date ranges from 1 to 12;
AFDL: maximum power generation of the plant during the month;
ARL: the capacity of electricity purchase;
ALY: whether to perform, 1 is performing, and-1 is default;
s102, number of elements AGDNum ═ AGDHis;
s103, AOldDay is the minimum value of the ARQ field in the AGDHis list;
s104, ANewDay is the maximum value of the ARQ field in the AGDHis list;
s2, constructing a date division array BSep based on the AGDHis;
s201, establishing a date division temporary storage array BTempRay, wherein the number of elements is AGDNum;
s202, a date division counter BCounter ═ 1;
s203, BTempDay ═ Days (AGDHis [ BCounter ]. ARQ, AOldDay); wherein the Days function is the number of Days to calculate the difference between the two dates;
S204，BTempArray[BCounter]＝BTempDay；
s205, BCounter + 1; if BCounter is larger than AGDNum, then go to S206, otherwise go to S203;
s206, establishing BSep, wherein the number of elements is 4;
s207, clustering BTemphray by utilizing a K-Means algorithm, wherein the clustering number of the algorithm is 4, and the clustering centers are BK1, BK2, BK3 and BK4 respectively;
s208, set BSep [1] (BK1+ BK 2)/2;
s209, setting BSep [2] (BK2+ BK 3)/2;
s210, setting BSep [3] (BK3+ BK 4)/2;
s211, setting BSep [4] ═ the maximum value in btemphray;
s3, constructing a date interval enhancement operator CBigOpt, inputting a date CInputData and outputting an increase factor CResult;
s301, maximum phase difference day variable CMaxV ═ Days (ANewDay, AOldDay); wherein the Days function is the number of Days to calculate the difference between the two dates;
s302, the current day-out variable CTempDay ═ Days (CInputData, AOldDay); wherein the Days function is the number of Days to calculate the difference between the two dates;
s303, a date interval enhancement operator counter CCounter is 1;
s304, if BSep [ CCounter ] > ═ CTempDay, go to S306, otherwise go to S305;
s305, if CCounter is equal to or less than 3, go to S304, otherwise go to S305
S306, boundary distance CTao ═ (BSep [ ccount ] -CTempDay)/CMaxV;
s307, calculating CResult, wherein the formula is as follows:
s308, the calculation of the operator is finished, and the value of CResult is returned;
s4, processing the AGDHis through CBigOpt, and training a regression prediction neural network DNet;
s401, setting a sample iteration counter DCounter equal to 1;
s402, calculating a temporary storage increment factor TempCResult by using CBigOpt, and inputting CInputData AGDHis [ DCounter ]. ARQ;
S403，AGDHis[DCounter].ALY＝AGDHis[DCounter].ALY×TempCResult；
s404, if DCounter is larger than AGDNum, then going to S405, otherwise going to S402;
s405, establishing a regression prediction neural network DNet, wherein the output prediction content of the neural network corresponds to ALY fields of the AGDHis, the input of the neural network corresponds to ARQY, AFDL and ARL fields of the AGDHis, and training is carried out by utilizing data in the AGDHis;
s406, outputting DNet;
s5, for a power purchase scheme Struct, predicting by using DNet to obtain a risk early warning result;
s501, for the power purchase scheme Struct, the included fields include:
ARQY: the month value corresponding to the electricity purchasing agreement date;
AFDL: maximum power generation of the plant during the month;
ARL: the capacity of electricity purchase;
s502, using DNet access Struct, and using ARQY, AFDL and ARL of the Struct as the input of DNet, wherein the output prediction result of DNet regression prediction is ALY;
s503, if ALY is less than 0, go to S504, otherwise go to S505;
s504, if ALY is smaller than-1, outputting to have higher default risk, otherwise, outputting to have certain default risk, and going to S506;
s505, outputting that no default risk exists;
s506, the prediction process is finished.
The invention has the beneficial effects that:
weighting is carried out on the electricity purchasing samples according to dates by introducing a date interval enhancement operator, a regression neural network model is trained through decision content of weighting adjustment samples, and then electricity purchasing risk early warning is carried out by utilizing the model. According to the method, under the conditions that auxiliary factors are not additionally input and the neural network structure is not adjusted, the sample point close to the prediction time point can play a greater role in the decision making process, and the prediction model can be used for dealing with market and policy situations of the electric power market, so that the early warning precision is improved.
Detailed Description
The present invention is further illustrated by the following examples, which do not limit the present invention in any way, and any modifications or changes that can be easily made by a person skilled in the art to the present invention will fall within the scope of the claims of the present invention without departing from the technical solution of the present invention.
Example 1
Jilin province a wind farm as an example:
s1, inputting historical electricity purchasing data AGDHis of a power plant; acquiring the number AGDNum of historical electricity purchasing data, the earliest date AOldday in the historical data and the latest date ANewday in the historical data;
s101, inputting power purchase history data AGDHis, wherein the AGDHis is a list, and each element in the list comprises the following fields;
ARQ: electricity purchase agreement date;
ARQY: the month value corresponding to the electricity purchasing agreement date ranges from 1 to 12;
AFDL: maximum power generation of the plant during the month;
ARL: the capacity of electricity purchase;
ALY: whether to perform, 1 is performing, and-1 is default;
s102, number of elements AGDNum ═ AGDHis;
s103, AOldDay is the minimum value of the ARQ field in the AGDHis list;
s104, ANewDay is the maximum value of the ARQ field in the AGDHis list;
inputting electricity purchasing historical data AGDHis of a certain wind power plant in Jilin province as an example
AGDNum＝721；AOldDay＝2016-1-4；ANewDay＝2018-12-17；
S2, constructing a date division array BSep based on the AGDHis;
s201, establishing a date division temporary storage array BTempRay, wherein the number of elements is AGDNum;
s202, a date division counter BCounter ═ 1;
s203, BTempDay ═ Days (AGDHis [ BCounter ]. ARQ, AOldDay); wherein the Days function is the number of Days to calculate the difference between the two dates;
S204，BTempArray[BCounter]＝BTempDay；
s205, BCounter + 1; if BCounter is larger than AGDNum, then go to S206, otherwise go to S203;
s206, establishing BSep, wherein the number of elements is 4;
s207, clustering BTemphray by utilizing a K-Means algorithm, wherein the clustering number of the algorithm is 4, and the clustering centers are BK1, BK2, BK3 and BK4 respectively;
s208, set BSep [1] (BK1+ BK 2)/2;
s209, setting BSep [2] (BK2+ BK 3)/2;
s210, setting BSep [3] (BK3+ BK 4)/2;
s211, setting BSep [4] ═ the maximum value in btemphray;
the obtained value of the date division array BSep is [200.5,410.7,622.1,1078 ];
s3, constructing a date interval enhancement operator CBigOpt, inputting a date CInputData and outputting an increase factor CResult;
s301, maximum phase difference day variable CMaxV ═ Days (ANewDay, AOldDay); wherein the Days function is the number of Days to calculate the difference between the two dates;
s302, the current day-out variable CTempDay ═ Days (CInputData, AOldDay); wherein the Days function is the number of Days to calculate the difference between the two dates;
s303, a date interval enhancement operator counter CCounter is 1;
s304, if BSep [ CCounter ] > ═ CTempDay, go to S306, otherwise go to S305;
s305, if ccount is equal to or less than 3, go to S304, otherwise go to S305;
s306, boundary distance CTao ═ (BSep [ ccount ] -CTempDay)/CMaxV;
s307, calculating CResult, wherein the formula is as follows:
s308, the calculation of the operator is finished, and the value of CResult is returned;
s4, processing the AGDHis through CBigOpt, and training a regression prediction neural network DNet;
s401, setting a sample iteration counter DCounter equal to 1;
s402, calculating a temporary storage increment factor TempCResult by using CBigOpt, and inputting CInputData AGDHis [ DCounter ]. ARQ;
S403，AGDHis[DCounter].ALY＝AGDHis[DCounter].ALY×TempCResult；
s404, if DCounter is larger than AGDNum, then going to S405, otherwise going to S402;
s405, establishing a regression prediction neural network DNet, wherein the output prediction content of the neural network corresponds to ALY fields of the AGDHis, the input of the neural network corresponds to ARQY, AFDL and ARL fields of the AGDHis, and training is carried out by utilizing data in the AGDHis;
s406, outputting DNet;
s5, for a power purchase scheme Struct, predicting by using DNet to obtain a risk early warning result;
s501, for the power purchase scheme Struct, the included fields include:
ARQY: the month value corresponding to the electricity purchasing agreement date;
AFDL: maximum power generation of the plant during the month;
ARL: the capacity of electricity purchase;
s502, using DNet access Struct, and using ARQY, AFDL and ARL of the Struct as the input of DNet, wherein the output prediction result of DNet regression prediction is ALY;
s503, if ALY is less than 0, go to S504, otherwise go to S505;
s504, if ALY is smaller than-1, the output has higher default risk, otherwise, the output has certain default risk. Go to S506;
s505, outputting that no default risk exists;
s506, ending the prediction process;
when the input Struct is:
| ARQY | AFDL | ARL |
| 6 | 21 | 4.2 |
by DNet prediction, ALY of DNet outputs-1.34, with the result that there is a higher risk of breach;
when the input Struct is:
| ARQY | AFDL | ARL |
| 6 | 21 | 1.2 |
by DNet prediction, ALY of DNet outputs 0.27, and as a result, the breach risk does not exist, namely the detection method of the invention is correct.
Claims (1)
1. A time-weighted electricity purchasing risk early warning method is characterized by comprising the following steps:
s1, inputting historical electricity purchasing data AGDHis of a power plant; acquiring the number AGDNum of historical electricity purchasing data, the earliest date AOldday in the historical data and the latest date ANewday in the historical data;
s101, inputting power purchase history data AGDHis, wherein the AGDHis is a list, and each element in the list comprises the following fields;
ARQ: electricity purchase agreement date;
ARQY: the month value corresponding to the electricity purchasing agreement date ranges from 1 to 12;
AFDL: maximum power generation of the plant during the month;
ARL: the capacity of electricity purchase;
ALY: whether to perform, 1 is performing, and-1 is default;
s102, number of elements AGDNum ═ AGDHis;
s103, AOldDay is the minimum value of the ARQ field in the AGDHis list;
s104, ANewDay is the maximum value of the ARQ field in the AGDHis list;
s2, constructing a date division array BSep based on the AGDHis;
s201, establishing a date division temporary storage array BTempRay, wherein the number of elements is AGDNum;
s202, a date division counter BCounter ═ 1;
s203, BTempDay ═ Days (AGDHis [ BCounter ]. ARQ, AOldDay); wherein the Days function is the number of Days to calculate the difference between the two dates;
S204，BTempArray[BCounter]＝BTempDay；
s205, BCounter + 1; if BCounter is larger than AGDNum, then go to S206, otherwise go to S203;
s206, establishing BSep, wherein the number of elements is 4;
s207, clustering BTemphray by utilizing a K-Means algorithm, wherein the clustering number of the algorithm is 4, and the clustering centers are BK1, BK2, BK3 and BK4 respectively;
s208, set BSep [1] (BK1+ BK 2)/2;
s209, setting BSep [2] (BK2+ BK 3)/2;
s210, setting BSep [3] (BK3+ BK 4)/2;
s211, setting BSep [4] ═ the maximum value in btemphray;
s3, constructing a date interval enhancement operator CBigOpt, inputting a date CInputData and outputting an increase factor CResult;
s301, maximum phase difference day variable CMaxV ═ Days (ANewDay, AOldDay); wherein the Days function is the number of Days to calculate the difference between the two dates;
s302, the current day-out variable CTempDay ═ Days (CInputData, AOldDay); wherein the Days function is the number of Days to calculate the difference between the two dates;
s303, a date interval enhancement operator counter CCounter is 1;
s304, if BSep [ CCounter ] > ═ CTempDay, go to S306, otherwise go to S305;
s305, if CCounter is equal to or less than 3, go to S304, otherwise go to S305
S306, boundary distance CTao ═ (BSep [ ccount ] -CTempDay)/CMaxV;
s307, calculating CResult, wherein the formula is as follows:
s308, the calculation of the operator is finished, and the value of CResult is returned;
s4, processing the AGDHis through CBigOpt, and training a regression prediction neural network DNet;
s401, setting a sample iteration counter DCounter equal to 1;
s402, calculating a temporary storage increment factor TempCResult by using CBigOpt, and inputting CInputData AGDHis [ DCounter ]. ARQ;
S403，AGDHis[DCounter].ALY＝AGDHis[DCounter].ALY×TempCResult；
s404, if DCounter is larger than AGDNum, then going to S405, otherwise going to S402;
s405, establishing a regression prediction neural network DNet, wherein the output prediction content of the neural network corresponds to ALY fields of the AGDHis, the input of the neural network corresponds to ARQY, AFDL and ARL fields of the AGDHis, and training is carried out by utilizing data in the AGDHis;
s406, outputting DNet;
s5, for a power purchase scheme Struct, predicting by using DNet to obtain a risk early warning result;
s501, for the power purchase scheme Struct, the included fields include:
ARQY: the month value corresponding to the electricity purchasing agreement date;
AFDL: maximum power generation of the plant during the month;
ARL: the capacity of electricity purchase;
s502, using DNet access Struct, and using ARQY, AFDL and ARL of the Struct as the input of DNet, wherein the output prediction result of DNet regression prediction is ALY;
s503, if ALY is less than 0, go to S504, otherwise go to S505;
s504, if ALY is smaller than-1, outputting to have higher default risk, otherwise, outputting to have certain default risk, and going to S506;
s505, outputting that no default risk exists;
s506, the prediction process is finished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010423104.9A CN111582751B (en) | 2020-05-19 | 2020-05-19 | Time-weighted electricity purchasing risk early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010423104.9A CN111582751B (en) | 2020-05-19 | 2020-05-19 | Time-weighted electricity purchasing risk early warning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111582751A true CN111582751A (en) | 2020-08-25 |
| CN111582751B CN111582751B (en) | 2022-06-14 |
Family
ID=72112243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010423104.9A Active CN111582751B (en) | 2020-05-19 | 2020-05-19 | Time-weighted electricity purchasing risk early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111582751B (en) |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140380488A1 (en) * | 2011-10-14 | 2014-12-25 | Albeado, Inc. | Pervasive, domain and situational-aware, adaptive, automated, and coordinated analysis and control of enterprise-wide computers, networks, and applications for mitigation of business and operational risks and enhancement of cyber security |
| US20150331972A1 (en) * | 2014-05-16 | 2015-11-19 | HST Solar Farms, Inc. | System & methods for solar photovoltaic array engineering |
| CN204972187U (en) * | 2015-08-21 | 2016-01-20 | 刘华县 | Fat machine is got rid of in massage losing weight |
| CN105447304A (en) * | 2015-11-10 | 2016-03-30 | 重庆邮电大学 | Self-learning algorithm based warning system and mobile terminal |
| CN106021941A (en) * | 2016-05-27 | 2016-10-12 | 成都信汇聚源科技有限公司 | Method for obtaining risk predictions of sudden death with weight value matrices of artificial neural network |
| CN106485536A (en) * | 2015-08-31 | 2017-03-08 | 功典资讯股份有限公司 | Determine method and the system in next time buying interval |
| CN107609194A (en) * | 2017-10-17 | 2018-01-19 | 吉林省电力科学研究院有限公司 | A kind of storage method of time redundancy Power system load data towards cloud computing |
| CN107704967A (en) * | 2017-10-17 | 2018-02-16 | 吉林省电力科学研究院有限公司 | A kind of Short-Term Load Forecasting Method based on improvement fuzzy neural network |
| CN108053057A (en) * | 2017-11-29 | 2018-05-18 | 国网江苏省电力公司盐城供电公司 | A kind of virtual plant Optimized Operation modeling method based on CVaR |
| CN108229806A (en) * | 2017-12-27 | 2018-06-29 | 中国银行股份有限公司 | A kind of method and system for analyzing business risk |
| CN108335216A (en) * | 2018-01-12 | 2018-07-27 | 中国平安人寿保险股份有限公司 | A kind of insurance risk assessment method, apparatus, terminal device and storage medium |
| CN108767854A (en) * | 2018-06-20 | 2018-11-06 | 北京科东电力控制系统有限责任公司 | Power purchase scheme optimization method, apparatus and electronic equipment |
| CN109033027A (en) * | 2018-08-08 | 2018-12-18 | 长春工程学院 | A kind of high speed fitful wind leads to the prediction technique of climbing event under wind power |
| CN109523117A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Risk Forecast Method, device, computer equipment and storage medium |
| CN110023967A (en) * | 2016-12-09 | 2019-07-16 | 三菱电机株式会社 | Failure risk index estimation device and failure risk index estimation method |
| CN110110981A (en) * | 2019-04-26 | 2019-08-09 | 重庆第二师范学院 | A kind of credit rating Default Probability estimates and method for prewarning risk |
| CN110119870A (en) * | 2019-03-20 | 2019-08-13 | 平安直通咨询有限公司上海分公司 | Macro risks method for early warning, device, computer equipment and storage medium |
| CN110313009A (en) * | 2016-03-24 | 2019-10-08 | Www.信任科学.Com股份有限公司 | The trust model and risk tolerance of learning object carry out calculation risk score |
| CN110659772A (en) * | 2019-09-14 | 2020-01-07 | 安徽电力交易中心有限公司 | Optimal operation strategy determination method of power selling company under piecewise linear deviation electric quantity assessment mechanism |
| CN110826935A (en) * | 2019-11-22 | 2020-02-21 | 国网陕西省电力公司电力科学研究院 | Machine learning-based medium and long term electric power market risk assessment method |
| CN110929935A (en) * | 2019-11-25 | 2020-03-27 | 国网天津市电力公司 | Multi-scale rolling electric power transaction balance optimization method based on risk management |
-
2020
- 2020-05-19 CN CN202010423104.9A patent/CN111582751B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140380488A1 (en) * | 2011-10-14 | 2014-12-25 | Albeado, Inc. | Pervasive, domain and situational-aware, adaptive, automated, and coordinated analysis and control of enterprise-wide computers, networks, and applications for mitigation of business and operational risks and enhancement of cyber security |
| US20150331972A1 (en) * | 2014-05-16 | 2015-11-19 | HST Solar Farms, Inc. | System & methods for solar photovoltaic array engineering |
| CN204972187U (en) * | 2015-08-21 | 2016-01-20 | 刘华县 | Fat machine is got rid of in massage losing weight |
| CN106485536A (en) * | 2015-08-31 | 2017-03-08 | 功典资讯股份有限公司 | Determine method and the system in next time buying interval |
| CN105447304A (en) * | 2015-11-10 | 2016-03-30 | 重庆邮电大学 | Self-learning algorithm based warning system and mobile terminal |
| CN110313009A (en) * | 2016-03-24 | 2019-10-08 | Www.信任科学.Com股份有限公司 | The trust model and risk tolerance of learning object carry out calculation risk score |
| CN106021941A (en) * | 2016-05-27 | 2016-10-12 | 成都信汇聚源科技有限公司 | Method for obtaining risk predictions of sudden death with weight value matrices of artificial neural network |
| CN110023967A (en) * | 2016-12-09 | 2019-07-16 | 三菱电机株式会社 | Failure risk index estimation device and failure risk index estimation method |
| CN107609194A (en) * | 2017-10-17 | 2018-01-19 | 吉林省电力科学研究院有限公司 | A kind of storage method of time redundancy Power system load data towards cloud computing |
| CN107704967A (en) * | 2017-10-17 | 2018-02-16 | 吉林省电力科学研究院有限公司 | A kind of Short-Term Load Forecasting Method based on improvement fuzzy neural network |
| CN108053057A (en) * | 2017-11-29 | 2018-05-18 | 国网江苏省电力公司盐城供电公司 | A kind of virtual plant Optimized Operation modeling method based on CVaR |
| CN108229806A (en) * | 2017-12-27 | 2018-06-29 | 中国银行股份有限公司 | A kind of method and system for analyzing business risk |
| CN108335216A (en) * | 2018-01-12 | 2018-07-27 | 中国平安人寿保险股份有限公司 | A kind of insurance risk assessment method, apparatus, terminal device and storage medium |
| CN108767854A (en) * | 2018-06-20 | 2018-11-06 | 北京科东电力控制系统有限责任公司 | Power purchase scheme optimization method, apparatus and electronic equipment |
| CN109033027A (en) * | 2018-08-08 | 2018-12-18 | 长春工程学院 | A kind of high speed fitful wind leads to the prediction technique of climbing event under wind power |
| CN109523117A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Risk Forecast Method, device, computer equipment and storage medium |
| CN110119870A (en) * | 2019-03-20 | 2019-08-13 | 平安直通咨询有限公司上海分公司 | Macro risks method for early warning, device, computer equipment and storage medium |
| CN110110981A (en) * | 2019-04-26 | 2019-08-09 | 重庆第二师范学院 | A kind of credit rating Default Probability estimates and method for prewarning risk |
| CN110659772A (en) * | 2019-09-14 | 2020-01-07 | 安徽电力交易中心有限公司 | Optimal operation strategy determination method of power selling company under piecewise linear deviation electric quantity assessment mechanism |
| CN110826935A (en) * | 2019-11-22 | 2020-02-21 | 国网陕西省电力公司电力科学研究院 | Machine learning-based medium and long term electric power market risk assessment method |
| CN110929935A (en) * | 2019-11-25 | 2020-03-27 | 国网天津市电力公司 | Multi-scale rolling electric power transaction balance optimization method based on risk management |
Non-Patent Citations (5)
| Title |
|---|
| 刘皓明等: "供电公司多能量市场最优购电组合的加权CVaR模型", 《电网技术》 * |
| 张江林等: "基于WCVaR评估的虚拟发电厂能量市场收益――风险模型", 《电力系统自动化》 * |
| 柏小丽等: "动态风险评价指标下的配电侧最优购电分配", 《电力系统保护与控制》 * |
| 赵阳等: "基于偏度-加权条件风险价值的售电公司动态购电策略", 《电网与清洁能源》 * |
| 高帅雄等: "企业投资公路建设项目的风险和对策", 《公路交通科技(应用技术版)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111582751B (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | Improved GM (1, 1) model based on Simpson formula and its applications | |
| Sun et al. | Multi-objective optimization of crude oil-supply portfolio based on interval prediction data | |
| CN111460001B (en) | Power distribution network theoretical line loss rate evaluation method and system | |
| CN115759336A (en) | Prediction method and storage medium for short-term power load prediction | |
| CN113723668A (en) | Coal blending method, system, equipment and storage medium based on robust optimization | |
| CN104834975A (en) | Power network load factor prediction method based on intelligent algorithm optimization combination | |
| Zeng et al. | Forecasting the total energy consumption in China using a new-structure grey system model | |
| Jaipuria et al. | A study on behaviour of bullwhip effect in (R, S) inventory control system considering DWT-MGGP demand forecasting model | |
| Chen | House price prediction model of Zhaoqing city based on correlation analysis and multiple linear regression analysis | |
| CN113887809A (en) | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target | |
| CN109345021A (en) | A method of using LSTM modeling and forecasting labour demand increment | |
| CN111582751B (en) | Time-weighted electricity purchasing risk early warning method | |
| Yang et al. | Short-term demand forecasting method in power markets based on the KSVM–TCN–GBRT | |
| Su | Nonlinear ARIMA models with feedback SVR in financial market forecasting | |
| CN113705929B (en) | Spring festival holiday load prediction method based on load characteristic curve and typical characteristic value fusion | |
| Pang et al. | A photovoltaic power predicting model using the differential evolution algorithm and multi-task learning | |
| Feng et al. | Peak operation optimization of cascade hydropower reservoirs and solar power plants considering output forecasting uncertainty | |
| CN115130743A (en) | Wind turbine generator regulation rate prediction method and system based on variation inference | |
| Hong et al. | The study on affecting factors of regional marine industrial structure upgrading | |
| CN113657936A (en) | Power load prediction method and terminal | |
| Chambers et al. | Grey system theory supported markowitz portfolio optimization during high volatility periods | |
| CN114444750A (en) | Power load prediction method based on neural network | |
| Duan et al. | A novel grey model of impulse delay and its application in forecasting stock price | |
| CN116205361B (en) | Industrial water efficiency grading prediction method based on matching degree | |
| Liu et al. | Enterprise financial risk prevention and control and data analysis method based on blockchain technology |
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 |