CN101145225A - Middle and long-term power load forecasting and pre-alarming system - Google Patents
Middle and long-term power load forecasting and pre-alarming system Download PDFInfo
- Publication number
- CN101145225A CN101145225A CNA2007101635670A CN200710163567A CN101145225A CN 101145225 A CN101145225 A CN 101145225A CN A2007101635670 A CNA2007101635670 A CN A2007101635670A CN 200710163567 A CN200710163567 A CN 200710163567A CN 101145225 A CN101145225 A CN 101145225A
- Authority
- CN
- China
- Prior art keywords
- forecasting
- long
- power
- early warning
- term
- 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
Images
Abstract
A power load forecasting and forewarning method for medium-long term is shown in the attached drawing in the abstract. A forecasting model is the core part for load forecast, while a forecasting module is the core part of the system; thus on the basis of the numerous models, how to rationally construct a historical data source, select a reasonable forecasting model and make the experience of forecasting staff penetrate through the whole forecast process to attain the optimal forecasting precision is a major characteristic of the system. With the advent of the great trend of global power marketization, the power load forecasting and forewarning system becomes a focus of development and application today and even tomorrow and, due to the forecasting and forewarning function, the invention promises to bring tremendous social and economic benefits.
Description
Affiliated technical field
The present invention relates to prediction and early warning system.
Background technology
Power plant construction is expensive big, construction period is long, electric energy is for the importance of national economy industry-by-industry and people's lives, especially the imbalance between supply and demand in a suitable period, everything is even more important load forecast, and load forecast has become one of important process of administrative authoritys such as electric power system dispatching, electricity consumption, plan, planning.Load prediction can be for satisfying and guaranteeing that this balance is ready in advance, system is exactly the adjustment and the management of loading on the basis of load prediction, and quantize by the supply and demand situation of pre-alarming system to adjusted electric system, finally the form with data, chart shows.
Medium-term and long-term load prediction and early warning are the important component parts of electricity markets at different levels as an economic information in the electricity market, for setting up power quantity measurement system, implementation peak and valley time electricity price and foundation simulation electricity market etc. profound influence are arranged all.Be embodied in:
(1) medium-term and long-term load prediction and early warning are to the influence of Power System Planning, operation
The result of medium-term and long-term load prediction and early warning helps rationally formulating electric system to be increased installed capacity, arranges the startup-shutdown batch total to draw; the power supply of schedule system, electricity consumption and overhaul of the equipments; keep the security and stability of operation of power networks, reduce unnecessary rotation idle capacity.
(2) medium-term and long-term load prediction and early warning are to the influence of transshipment
Medium-term and long-term load prediction and early warning helps correctly, arrange to formulate the electrical network production schedule economically adapts to the needs of " separate the factory and network, surf the Net at a competitive price ", has given play to the maximal efficiency of transshipment.Transshipment is a basic function of electrical network in the electricity market, transhipment is the necessary condition of electricity market fair competition, can bring huge benefit to electrical network, and electrical network is when carrying out transshipment, will be according to the data of load prediction and the operational factor of each generator, formulate generation schedule and operation plan, so load prediction accurately will promote confession, fortune, electricity consumption three parts's coordination.
(3) medium-term and long-term load prediction and early warning are to formulating the influence of Spot Price
Electricity price is the lever and the core content of electricity market, has embodied the competitive and open of electricity market, and the formulation of electricity price is to finish on the basis of the load prediction of given electricity price given period in future.Therefore, electricity power enterprise will guarantee the competitiveness and the profit of its electricity price, just must obtain more accurate load prediction, just can make not only competitive but also guarantees the electricity price of profit.Simultaneously, because the difference of electricity price can encourage the user that the load of peak period is moved to the low ebb phase.
(4) medium-term and long-term load prediction and early warning are to the influence of the energy
The result of medium-term and long-term load prediction and early warning helps the reasonable use energy, economizes on coal, fuel-economizing and reduction cost of electricity-generating, helps formulating rational power supply construction plan, helps improving the economic benefit and the social benefit of electric system.
At present for the medium-term and long-term prediction of loading of electric power, the research of comparison system has all been arranged both at home and abroad, research to various Forecasting Methodologies is more deep, but can really be applied to actual system and few at warning aspect, external application aspect electric system, or comparative maturity, but at prediction and warning aspect, particularly early warning this part, still do not have very successful example.The U.S. is the country that has largest power industry in the world, but in the processing of prediction and the research and development, particularly early warning of early warning system, there is not complete index system to carry out quantitative analysis yet, in the electric system as California, USA, good solution is not proposed yet.And domestic in medium-term and long-term load prediction of electric power and early warning system exploitation and use, the electricity market demand analysis prediction management system of Tsing-Hua University's department of electrical engineering research and development can be described as domestic state-of-the-art, use one of the widest system.This system now surplus nearly ten nets/provincial Utilities Electric Co., 80 a prefecture-level electric company promote the use of, as Jiangsu Province, Fujian Province, Gansu Province, Shandong Province, Tianjin, Chongqing City, Hebei province, Zhejiang Electric Power Company and subordinate's power supply branch thereof.In addition, domestic intellectual load prediction system, Beijing that also has the imperial HDHL research and development of the big China in lake is super thinks magnificent scientific research electricity power workload demand forecast system and is coming into operation.But these systems comprehensively do not analyze prediction result, more do not realize the function of early warning according to the index of electric system.
For a long time, the artificial experience forecast method is mostly adopted in China's power system load prediction, and the prediction work amount is big, and automaticity is low, and the prognosticator has been proposed very high requirement, and while precision of prediction is not accurate enough.Therefore, under the situation that medium-term and long-term load is accurately predicted to electric power, adopt early warning mechanism that effectively information is provided directly, make it to become managerial decision making's main foundation, can make enterprise and user reach the situation of a kind of ' doulbe-sides' victory '.
The technical solution adopted for the present invention to solve the technical problems is: in the load forecast module, on the basis of using for reference this area research achievement, set up the forecast model storehouse that includes multiple forecast model, and proposed comparatively reasonably predicting strategy: the choosing of the pre-service of data, historical data source, optimization model a series of method such as determine; In supply and demand monitoring and early warning module, rationally utilize existing index, warning index system and standard equilibrium value that foundation can monitor and discern the power supply and demand situation, the processing by computing machine is shown to the user in simple and clear, visual in image mode; In statistical analysis module, system provides multi-angle, multi-level data comparison and analytic function.Functions such as data typings, data derivation, data query, data maintenance and safety management that system is also integrated.The results of running proves: the prediction of long-medium term power load forecasting and early warning system, early warning ratio of precision as a result are higher, and stronger adaptive faculty and combination ability are arranged.
Forecast model is the core of load prediction, and prediction module is the core of system, thereby on numerous model based, the experience that how reasonably to make up the historical data source, select rational forecast model, makes the prognosticator is in whole forecasting process, and the optimum that reaches precision of prediction is the problem that prediction module need solve.System solves by following steps in the process of design:
(1) makes up reasonable historical data source: earlier data are carried out pre-service, select different data sources again;
(2) select rational model: system is selected or artificial selection automatically.During artificial selection, can revise parameter voluntarily;
(3) prognosticator's experience: voluntarily preference pattern, and can rule of thumb revise parameter or adjust predicting the outcome.
On definite mode of forecast model, because the foundation in forecast model storehouse when prediction, has multiple model to select for the prognosticator, system has designed " manually-operated " and " automated system operation dual mode " according to individual's demand.
(1) manually-operated: the prognosticator is in conjunction with the experience of self, selects the corresponding model and the parameter of input model voluntarily at different indexs, area.
(2) automated system operation:, when which kind of model the prognosticator is difficult to determine for optimum, can select " automated system operation " at different indexs.Automated system operation: promptly system all moves all forecast models once, according to the error analysis result of system, the forecast model that the conduct of Select Error minimum is final.Its processing procedure is as follows:
1) in pretreated data, the historical data source that the data of intercepting front are set up as forecast model stays
Nearly data are as the data u of model testing
1 ... i
2) dope the parameter of model one by one, set up model;
3) pass through Model Calculation: the historical data of model testing the predicting the outcome of corresponding time (be u1 ... the pairing v1 that predicts the outcome of i ... i;
4) result of calculation (v1 ... i) and between historical data (u1 ... relative error i);
5) contrast the pairing error result of each model, the model of Select Error minimum;
6) utilize all historical data sources and definite model to rebulid forecast model again, predict;
The invention has the beneficial effects as follows that the top priority of power scheduling is to ensure the stabilization of power grids, economy, normal operation, to the safe and reliable power supply of power consumer.Long-medium term power load forecasting and early warning are important process of electric power system dispatching operation department, it is the main foundation of formulating generation schedule and transmission of electricity scheme, carrying out power planning and construction, oneself becomes one of modern important content of power system management long-medium term power load forecasting and early warning, and oneself becomes an important topic in the dispatching automation of electric power systems to the research and development of long-medium term power load forecasting and early warning system.Along with the arrival of global electricity market megatrend, load forecast and early warning system more and more become focus current and even that Future Development is used, because its prediction and forewarning function will bring very big social benefit and economic benefit.
Description of drawings
The modular structure figure of Fig. 1 long-medium term power load forecasting and early warning system.
Embodiment
Long-medium term power load forecasting and early warning system are one and are a make a strategic decision application system of auxiliary or reference of enterprise, be on the basis that historical data is collected in a large number, set up model and carry out respective handling, shown in Figure 1 in its systematic functional structrue such as the Figure of description.Database adopts large database Microsoft SQL Server 2000, operate for convenience and the many-side of data is used, adopted the platform of Windows as exploitation, test and operation, the visual development platform Delphi7.0 that Borland company releases is as developing instrument.
Claims (1)
1. the method for long-medium term power load forecasting and early warning comprises:
(1) is used to set up the step of prediction module;
(2) be used for determining the step of forecast model;
The method that it is characterized in that described long-medium term power load forecasting and early warning also comprises:
(1) in the step of determining forecast model, comprises " manually-operated " and " automated system operation " dual mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2007101635670A CN101145225A (en) | 2007-10-16 | 2007-10-16 | Middle and long-term power load forecasting and pre-alarming system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2007101635670A CN101145225A (en) | 2007-10-16 | 2007-10-16 | Middle and long-term power load forecasting and pre-alarming system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101145225A true CN101145225A (en) | 2008-03-19 |
Family
ID=39207745
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNA2007101635670A Pending CN101145225A (en) | 2007-10-16 | 2007-10-16 | Middle and long-term power load forecasting and pre-alarming system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101145225A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101908190A (en) * | 2010-07-29 | 2010-12-08 | 中国电力科学研究院 | Radar chart index expression method for analysis and evaluation on power market |
CN101551884B (en) * | 2009-05-08 | 2011-07-27 | 华北电力大学 | A fast CVR electric load forecast method for large samples |
CN102855525A (en) * | 2012-08-16 | 2013-01-02 | 中国电力科学研究院 | System and method for forecasting and analyzing load of resident user |
CN102867221A (en) * | 2012-07-17 | 2013-01-09 | 中国电力科学研究院 | Method for dynamically and transversely correcting medium and long-term electric quantity forecasting |
CN102880917A (en) * | 2012-09-20 | 2013-01-16 | 湖北省电力公司电力科学研究院 | Method for predicting medium-term and long-term power load on basis of logarithmical load density growth curve |
CN103136669A (en) * | 2011-11-23 | 2013-06-05 | 腾讯科技(深圳)有限公司 | Product display method and product display system based on product model base |
CN103226736A (en) * | 2013-03-27 | 2013-07-31 | 东北电力大学 | Method for predicting medium and long term power load based on cluster analysis and target theory |
CN103617467A (en) * | 2013-12-13 | 2014-03-05 | 重庆大学 | Short-period combined load prediction method |
CN104318334A (en) * | 2014-10-29 | 2015-01-28 | 上海工程技术大学 | Short-time power load forecasting method based on long-range dependence FARIMA model |
CN104680313A (en) * | 2015-02-10 | 2015-06-03 | 北京国电通网络技术有限公司 | Method for monitoring and screening urban high-energy-consumptive enterprises |
CN106355285A (en) * | 2016-09-06 | 2017-01-25 | 北京华电天仁电力控制技术有限公司 | Electricity usage load predicting method based on parameter correction |
CN108009686A (en) * | 2017-12-13 | 2018-05-08 | 阳光电源股份有限公司 | A kind of photovoltaic power generation power prediction method, apparatus and system |
CN110674993A (en) * | 2019-09-26 | 2020-01-10 | 广东电网有限责任公司 | User load short-term prediction method and device |
US11689020B2 (en) | 2021-05-19 | 2023-06-27 | International Business Machines Corporation | Computer modeling to analyze electrical usage in an electrical grid for facilitating management of electrical transmission |
-
2007
- 2007-10-16 CN CNA2007101635670A patent/CN101145225A/en active Pending
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101551884B (en) * | 2009-05-08 | 2011-07-27 | 华北电力大学 | A fast CVR electric load forecast method for large samples |
CN101908190A (en) * | 2010-07-29 | 2010-12-08 | 中国电力科学研究院 | Radar chart index expression method for analysis and evaluation on power market |
CN103136669A (en) * | 2011-11-23 | 2013-06-05 | 腾讯科技(深圳)有限公司 | Product display method and product display system based on product model base |
CN102867221A (en) * | 2012-07-17 | 2013-01-09 | 中国电力科学研究院 | Method for dynamically and transversely correcting medium and long-term electric quantity forecasting |
CN102867221B (en) * | 2012-07-17 | 2016-08-31 | 中国电力科学研究院 | A kind of Middle and long term electricity consumption forecasting dynamically horizontal modification method |
CN102855525A (en) * | 2012-08-16 | 2013-01-02 | 中国电力科学研究院 | System and method for forecasting and analyzing load of resident user |
CN102855525B (en) * | 2012-08-16 | 2016-04-20 | 中国电力科学研究院 | A kind of resident's load prediction analytic system and method |
CN102880917B (en) * | 2012-09-20 | 2015-06-10 | 湖北省电力公司电力科学研究院 | Method for predicting medium-term and long-term power load on basis of logarithmical load density growth curve |
CN102880917A (en) * | 2012-09-20 | 2013-01-16 | 湖北省电力公司电力科学研究院 | Method for predicting medium-term and long-term power load on basis of logarithmical load density growth curve |
CN103226736B (en) * | 2013-03-27 | 2016-03-30 | 东北电力大学 | Based on the long-medium term power load forecasting method of cluster analysis and grey target theory |
CN103226736A (en) * | 2013-03-27 | 2013-07-31 | 东北电力大学 | Method for predicting medium and long term power load based on cluster analysis and target theory |
CN103617467A (en) * | 2013-12-13 | 2014-03-05 | 重庆大学 | Short-period combined load prediction method |
CN104318334B (en) * | 2014-10-29 | 2017-07-04 | 上海工程技术大学 | A kind of Short-Term Load Forecasting Method based on correlation FARIMA models long |
CN104318334A (en) * | 2014-10-29 | 2015-01-28 | 上海工程技术大学 | Short-time power load forecasting method based on long-range dependence FARIMA model |
CN104680313A (en) * | 2015-02-10 | 2015-06-03 | 北京国电通网络技术有限公司 | Method for monitoring and screening urban high-energy-consumptive enterprises |
CN106355285A (en) * | 2016-09-06 | 2017-01-25 | 北京华电天仁电力控制技术有限公司 | Electricity usage load predicting method based on parameter correction |
CN106355285B (en) * | 2016-09-06 | 2023-04-11 | 国能信控互联技术有限公司 | Power load prediction method based on parameter correction |
CN108009686A (en) * | 2017-12-13 | 2018-05-08 | 阳光电源股份有限公司 | A kind of photovoltaic power generation power prediction method, apparatus and system |
CN108009686B (en) * | 2017-12-13 | 2021-12-10 | 阳光电源股份有限公司 | Photovoltaic power generation power prediction method, device and system |
CN110674993A (en) * | 2019-09-26 | 2020-01-10 | 广东电网有限责任公司 | User load short-term prediction method and device |
US11689020B2 (en) | 2021-05-19 | 2023-06-27 | International Business Machines Corporation | Computer modeling to analyze electrical usage in an electrical grid for facilitating management of electrical transmission |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101145225A (en) | Middle and long-term power load forecasting and pre-alarming system | |
Li et al. | Short-term operation model and risk management for wind power penetrated system in electricity market | |
CN101567561B (en) | Comparing and selecting system of power transmission network planning scheme | |
CN106384168A (en) | Multi-objective coordinated optimization scheduling model for different power sources | |
CN104537428B (en) | One kind meter and the probabilistic economical operation appraisal procedure of wind power integration | |
CN102097828A (en) | Wind power optimal scheduling method based on power forecast | |
CN110929927A (en) | Artificial intelligence prediction model construction method applying power distribution network universe big data | |
CN103296701A (en) | Active power control method in wind power plant | |
CN104376372A (en) | Source network load interaction mode based intelligent power distribution network dispatching service optimization method | |
CN111784030B (en) | Distributed photovoltaic power prediction method and device based on spatial correlation | |
Zhang et al. | Ultra-short term wind power prediction model based on modified grey model method for power control in wind farm | |
CN103199616B (en) | Large regional grid wind-powered electricity generation group service data monitoring analysis system | |
Goutard | Renewable energy resources in energy management systems | |
Henry et al. | Going green: Transmission grids as enablers of the transition to a low-carbon European economy | |
CN108110756A (en) | Consider the industrial park distribution network planning method of uncertain factor | |
CN103427444A (en) | Control method for reducing wind power grid-connected scheduling plan error | |
CN105260789B (en) | A kind of wind-powered electricity generation data time scale preferred method towards ultrashort-term wind power prediction | |
Shendryk et al. | Decision Support System for Efficient Energy Management of MicroGrid with Renewable Energy Sources | |
Zhao et al. | Multi-objective decision-making on wind power projects based on AHP method | |
Goyena et al. | Sizing and analysis of big scale and isolated electric systems based on renewable sources with energy storage | |
Mouton et al. | Assessment of methods to measure power system flexibility: a review | |
Kerin et al. | Dynamic security indication in power systems with large amount of renewables | |
Rachmadhani | Utilization of technology and digitalization to bring equality energy access for remote areas | |
He et al. | A Survey on the Development of Smart Grid in China | |
Tang et al. | Requirements analysis of the interaction between renewable energy and power system in different penetration rate |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20080319 |