WO2020101617A2 - A system and method that allow estimation of the system direction for intraday market and imbalance power market - Google Patents
A system and method that allow estimation of the system direction for intraday market and imbalance power market Download PDFInfo
- Publication number
- WO2020101617A2 WO2020101617A2 PCT/TR2019/050774 TR2019050774W WO2020101617A2 WO 2020101617 A2 WO2020101617 A2 WO 2020101617A2 TR 2019050774 W TR2019050774 W TR 2019050774W WO 2020101617 A2 WO2020101617 A2 WO 2020101617A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- module
- data
- forecast
- market
- system direction
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000007637 random forest analysis Methods 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000007726 management method Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 description 18
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 12
- 230000005611 electricity Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000002146 bilateral effect Effects 0.000 description 6
- 239000003345 natural gas Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000003570 air Substances 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 231100000614 poison Toxicity 0.000 description 1
- 230000007096 poisonous effect Effects 0.000 description 1
- 239000002901 radioactive waste Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000002341 toxic gas Substances 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 230000003442 weekly effect Effects 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards
Definitions
- the present invention relates to a system and method that allow more accurate estimation of the energy generation and management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems as a result of dynamically changing parameters affecting the generation of energy from renewable energy sources.
- the present invention relates to a method that allows effective and reliable determination of the prices in the energy sector according to supply-demand balance by making estimation of the system direction for intraday market and imbalance power market by getting data such as weather forecast, energy procurement, intraday market, imbalance power market, bilateral agreements from internet platforms such as EPIAS (Elektrik Piyasalari isletme Anonim Sirketi - Electricity Markets Enterprise Inc.), MGM (Meteoroloji Genel Mudurlugu - Vietnamese State Meteorological Service) and a system therefor.
- EPIAS Elektrik Piyasalari isletme Anonim Sirketi - Electricity Markets Enterprise Inc.
- MGM Metaleoroloji Genel Mudurlugu - Turkish State Meteorological Service
- Wind energy is also one of the most popular renewable energy sources in recent times, and many entrepreneurs are making huge investments in this field and the amount of the renewable energy in the grid is gradually increasing. In our country, also, the investments made on this area are very high. The places exposed to the wind throughout the year are identified and wind turbines are positioned on this places. However, as in all renewable energy sources, instantaneous electricity generation from wind turbines is quite unstable. This is arising from that the natural conditions are constantly changing. Large fluctuations in electricity generation within minutes cause imbalances in grids and the amount of the energy generated cannot meet supply-demand amount.
- EPIAS ensures the elimination of supply-demand imbalance and thus enables the control of the system frequency imbalance arising from renewable energy sources and outages by collecting data of energy generation, distribution, consumption, plant maintenance and breakdown within a central platform and by encouraging energy suppliers in the private sector to make more accurate production planning.
- the services provided by EPIAS include GOP (Day Ahead Market), GIP (Intraday Market), DIP (Balancing Power Market) and Bilateral Agreements.
- Day ahead market determines the electricity reference price (electricity swap price).
- the transactions are daily carried out on hourly basis and bids can be submitted starting from the next day up to 5 days later. Each day up to 12:30 p.m., participants are required to submit their day ahead bids for the next day.
- the submitted bids are validated by being evaluated by the market manager between 12:30-13:00 p.m.
- Commercial business approvals including approved purchase and sale amounts are notified to the market participant by determining electricity reference price for each hour of a day by evaluating the submitted bids between 13:00-13:30 p.m. with the optimization tool.
- Intraday market was launched in order to offer portfolio balancing to market participants in the short term. In the day ahead market, there is a difference that is reaching maximum 36 hours between bid entry time and realization time. The imbalances before balancing power market were reduced by reporting unforeseen changes in the intraday market in production and consumption, such as plant failures. Intraday market participant can submit their bids each day for the next day by starting from 18:00 p.m., up to 1 ,5 hours before physical delivery. The bids can be submitted hourly and as block. Balancing power market, frequency control, demand control provide real-time balancing by resetting the difference between production and consumption. Participation is compulsory and plants that receive and discharge 10 MW of load within 15 minutes are bidding on a balancing unit basis. The marginal price of the system is notified to the participant by being determined within 4 hours following the relevant time.
- EPIAS In order to reduce the imbalance in the energy production, EPIAS requires that renewable energy producers to enter their next day production forecasts to the Day Ahead Market. The producers pay a penalty if they cannot produce the amount that they specify the day before. Since the amount of penalty depends on the difference between forecasted and actual production, the precision of the production estimates is very important for producers. Therefore, in order to estimate the energy they will produce the next day at the wind power plants, the producers get production forecast services from different companies. Power plants receive production forecasts from one or more than two companies and use the forecasts of the company they think that it has the best performance, as blocks. However, since each forecasting firm has own meteorology and production forecasting models, their production forecasting sensitivity varies widely on hourly, daily, weekly, monthly and annually basis.
- the document CN107451718 mentions a solution titled as“Random Forest Analysis Method-Based Large Customer Value Evaluation”.
- Random Forecast algorithm is used.
- the daily finalized production plan of Random Forest algorithm to forecast the system direction of the next day.
- data is taught to the developed system direction estimation algorithm as sequential time series.
- the system’s failure time is estimated by displaying current status instantly.
- data exchange bus method and distributed architecture are used during integrating meter data, weather and grid data in this system while in the present developed model, central architecture is used and data integration is performed on the database with web-based REST protocol. Energy market data is used as data.
- the aim of the present invention is to present a system and method that allow more accurate estimation of the energy generation and management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems as a result of dynamically changing parameters of renewable energy sources.
- Another aim of the present invention is to present a system and method that allow effective and reliable determination of the prices in the energy sector according to supply-demand balance by making estimation of the system direction for intraday market and imbalance power market in accordance with the publication date of data by getting financial data such as intraday market, imbalance power market, bilateral agreements from internet platforms.
- Another aim of the present invention is to present a method for making estimation of the system direction for intraday market and imbalance power market by getting data such as weather forecast, energy procurement, intraday market, imbalance power market, bilateral agreements from internet platforms such as EPIAS (Elektrik Piyasalari isletme Anonim Sirketi - Electricity Markets Enterprise Inc.), MGM (Meteoroloji Genel Mudurlugu - Vietnamese State Meteorological Service).
- EPIAS Elektrik Piyasalari isletme Anonim Sirketi - Electricity Markets Enterprise Inc.
- MGM Metaleoroloji Genel Mudurlugu - Turkish State Meteorological Service
- Another aim of the present invention is to use Random Forest algorithm as artificial learning method for estimating system direction. Another aim of the present invention is to prevent victimization that can be happen due to the imbalance in the grids, thanks to the making estimation of the system direction for intraday market and imbalance power market.
- Another aim of the present invention is to present a forecast system allowing more accurate estimation of the energy generation and management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems via internet servers from which model data such as financial, weather and energy loading information are obtained, an I/O module which is a hardware that allows control of the devices on internet or local network, a forecast database in which the data received from internet servers is stored, system direction forecast module where the calculations required for forecasting the system direction are made, a result database where the system direction forecast data is stored.
- Model data is retrieved from internet servers.
- Database integration is provided and time-based matching is performed. 1 10.
- the attributes (variables) to be used in the model are selected.
- Random Forest model top variables are optimized in the selected data range.
- Random Forest model is trained in the selected data range and model coefficients are learned.
- the present invention relates to a system and method that allow more accurate estimation of the energy generation and management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems as a result of dynamically changing parameters affecting the generation of energy from renewable energy sources.
- the present system comprises internet servers (10) from which model data such as financial, weather and energy loading information are obtained, an I/O module (20) which is a hardware that allows control of the devices on internet or local network, a forecast database (30) in which the data received from internet servers (10) is stored, system direction forecast module (40) where the calculations required for forecasting the system direction are made, a result database (50) where the system direction forecast data is stored.
- system direction forecast module (40) comprises a data acquisition module (41) interacting with the prediction database (30), a data analysis module (42) in which the networks with the data is established, a day ahead market module (43) where forecast of the system direction for 24 hours later is made for the intraday market, a balancing power market module (44) where forecast of the system direction for 48 hours later is made for the imbalance power market, a grouping module (45) where the data received from mentioned day ahead market module (43) and balancing power market module (44) are grouped, an adjustment module (46) wherein the model parameters are arranged to match the incoming data, an evaluation module (47) in which evaluation of the data received from mentioned adjustment module (46) is performed, a result module (48) where the evaluated information is finalized.
- the data required for making of system direction forecasting is received from internet servers (10) via the I/O module (20) and is transmitted to the forecast database (30).
- the data in the forecast database (30) is sent to the data acquisition module (41) within the system direction forecast module (40).
- the relevant data is transferred from the data acquisition module (41) to the data analysis module (42) and sent to the day ahead market module (43) and to the balancing power market module (44) by establishing the necessary relations related to the transaction.
- the day ahead market module (43) the forecast of the system direction for 24 hours later is made for the intraday market.
- the balancing power market module (44) the forecast of the system direction for 48 hours later is made for the imbalance power market.
- the data obtained from the day ahead market module (43) and from the balancing power market module (44) is sent to the grouping module (45) and grouped there.
- the data grouped in the related component is sent to adjustment module (46) and arranged to match with model parameters.
- the arranged data is sent to the evaluation module (47) and here, the system direction forecast is done and sent to the result module (48).
- the data obtained from the result module (48) is transmitted to result database (50) via I/O module (20).
- FIG. 2 A flow diagram summarizing the process steps of the present innovative method is given in Figure 2.
- the model data is retrieved from the internet servers (100) via I/O module (20).
- the forecast database (30) database integration is provided and time-based matching is performed (105).
- the system direction forecast module (40) the attributes (variables) to be used in the model are selected (1 10) and size is reduced.
- Random Forest model top variables are optimized in the selected data range (1 15).
- Random Forest model is trained in the selected data range and model coefficient are learned (120), system direction of 24 hours later is estimated for the intraday market (125) and system direction of 48 hours later is estimated for the imbalance power market (130).
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The present invention is a forecast system allowing more accurate estimation of the energy generation and management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems as a result of dynamically changing parameters of renewable energy sources via internet servers (10) from which model data such as financial, weather and energy loading information are obtained, an I/O module (20) which is a hardware that allows control of the devices on internet or local network, a forecast database (30) in which the data received from internet servers (10) is stored, system direction forecast module (40) where the calculations required for forecasting the system direction are made, a result database (50) where the system direction forecast data is stored.
Description
A SYSTEM AND METHOD THAT ALLOW ESTIMATION OF THE SYSTEM DIRECTION FOR INTRADAY MARKET AND IMBALANCE POWER MARKET
Technical Field
The present invention relates to a system and method that allow more accurate estimation of the energy generation and management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems as a result of dynamically changing parameters affecting the generation of energy from renewable energy sources.
More specifically, the present invention relates to a method that allows effective and reliable determination of the prices in the energy sector according to supply-demand balance by making estimation of the system direction for intraday market and imbalance power market by getting data such as weather forecast, energy procurement, intraday market, imbalance power market, bilateral agreements from internet platforms such as EPIAS (Elektrik Piyasalari isletme Anonim Sirketi - Electricity Markets Enterprise Inc.), MGM (Meteoroloji Genel Mudurlugu - Turkish State Meteorological Service) and a system therefor.
Prior Art
As a result of the rapid progress in the technology and industry, our individual and social energy needs have reached the highest levels. While natural gas and oil sources which are limited in nature, are rapidly depleted, they make the world uninhabitable by polluting the soil, water and air with the poisonous gases that they release. The use of nuclear energy remains as the last option for many countries due to the high interference probability of the radioactive waste being released into environment and bad accidents in the history.
The fact that the danger of the toxic gases arising from the use of resources such as natural gas and petroleum is better understood with the global warming, most importantly, the fact that these limited amounts of resources are insufficient in the face of our current energy consumption and will be depleted soon, has started to direct humanity to use the renewable energy sources which are alternative energy sources.
The fact that most of the energy production is sourced from natural gas and that Turkey does not have enough local sources and natural gas storage infrastructure, cause us to become externally dependent in energy. Especially in the winter months, the use of natural gas resources for heating
needs creates a risk for meeting the electricity demand. Therefore, it is important to focus on renewable energy instead of natural gas-based energy production in our country.
Wind energy is also one of the most popular renewable energy sources in recent times, and many entrepreneurs are making huge investments in this field and the amount of the renewable energy in the grid is gradually increasing. In our country, also, the investments made on this area are very high. The places exposed to the wind throughout the year are identified and wind turbines are positioned on this places. However, as in all renewable energy sources, instantaneous electricity generation from wind turbines is quite unstable. This is arising from that the natural conditions are constantly changing. Large fluctuations in electricity generation within minutes cause imbalances in grids and the amount of the energy generated cannot meet supply-demand amount.
T ogether with the privatization in the energy sector in our country, there is a need for a platform where energy prices can be determined transparently, reliably and according to supply-demand balance. As a result of this need, EPIAS was established on March 18, 2015 to contribute Turkey’s becoming a regional energy center. EPIAS ensures the elimination of supply-demand imbalance and thus enables the control of the system frequency imbalance arising from renewable energy sources and outages by collecting data of energy generation, distribution, consumption, plant maintenance and breakdown within a central platform and by encouraging energy suppliers in the private sector to make more accurate production planning. The services provided by EPIAS include GOP (Day Ahead Market), GIP (Intraday Market), DIP (Balancing Power Market) and Bilateral Agreements.
Day ahead market determines the electricity reference price (electricity swap price). The transactions are daily carried out on hourly basis and bids can be submitted starting from the next day up to 5 days later. Each day up to 12:30 p.m., participants are required to submit their day ahead bids for the next day. The submitted bids are validated by being evaluated by the market manager between 12:30-13:00 p.m. Commercial business approvals including approved purchase and sale amounts are notified to the market participant by determining electricity reference price for each hour of a day by evaluating the submitted bids between 13:00-13:30 p.m. with the optimization tool.
Intraday market was launched in order to offer portfolio balancing to market participants in the short term. In the day ahead market, there is a difference that is reaching maximum 36 hours between bid entry time and realization time. The imbalances before balancing power market were reduced by reporting unforeseen changes in the intraday market in production and consumption, such as plant failures. Intraday market participant can submit their bids each day for the next day by starting from 18:00 p.m., up to 1 ,5 hours before physical delivery. The bids can be submitted hourly and as block.
Balancing power market, frequency control, demand control provide real-time balancing by resetting the difference between production and consumption. Participation is compulsory and plants that receive and discharge 10 MW of load within 15 minutes are bidding on a balancing unit basis. The marginal price of the system is notified to the participant by being determined within 4 hours following the relevant time.
In order to reduce the imbalance in the energy production, EPIAS requires that renewable energy producers to enter their next day production forecasts to the Day Ahead Market. The producers pay a penalty if they cannot produce the amount that they specify the day before. Since the amount of penalty depends on the difference between forecasted and actual production, the precision of the production estimates is very important for producers. Therefore, in order to estimate the energy they will produce the next day at the wind power plants, the producers get production forecast services from different companies. Power plants receive production forecasts from one or more than two companies and use the forecasts of the company they think that it has the best performance, as blocks. However, since each forecasting firm has own meteorology and production forecasting models, their production forecasting sensitivity varies widely on hourly, daily, weekly, monthly and annually basis.
This situation revealed the necessity of more accurate estimation of the energy generation and of management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems as a result of stochastic changing parameters of renewable energy sources.
The document CN107451718 mentions a solution titled as“Random Forest Analysis Method-Based Large Customer Value Evaluation”. In this solution, there is a method to calculate usage value in the presence of the user and not to provide customer segmentation, here Random Forecast algorithm is used. However, there is no mention of the use of the daily finalized production plan of Random Forest algorithm to forecast the system direction of the next day. In addition, data is taught to the developed system direction estimation algorithm as sequential time series.
In the document US20170169344, a solution titled as“Methods, Systems and Computer Readable Media for A Data-Driven Demand Response (DR) Recommender” is presented. Here, it is mentioned about estimating new consumption information by using statistical methods based on past weather and consumption information, the system was developed for use at home scale. However, in the present invention, weather information of next day is also taken as well as past weather information. System imbalance direction is forecasted by integrating the received weather temperature information with the final daily production plan data announced by EPIAS for next day.
In the document CN1072741 15, a solution titled as“Active Power Distribution Network Situation Awareness System and Method Based on Distributed Monitoring and Multi-Source Information Fusion” is presented. Here, risk analysis is carried out by examining production, consumption and environmental factors. The system’s failure time is estimated by displaying current status instantly. However, in this system data exchange bus method and distributed architecture are used during integrating meter data, weather and grid data in this system while in the present developed model, central architecture is used and data integration is performed on the database with web-based REST protocol. Energy market data is used as data.
As a result of that the prior art is insufficient, presence of a solution intended for a method that allows effective and reliable determination of the prices in the energy sector according to supply-demand balance by making estimation of the system direction for intraday market and imbalance power market by getting data such as weather forecast, energy procurement, intraday market, imbalance power market, bilateral agreements from internet platforms such as EPIAS, MGM, was required.
Objectives and Short Description of the Invention
The aim of the present invention is to present a system and method that allow more accurate estimation of the energy generation and management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems as a result of dynamically changing parameters of renewable energy sources.
Another aim of the present invention is to present a system and method that allow effective and reliable determination of the prices in the energy sector according to supply-demand balance by making estimation of the system direction for intraday market and imbalance power market in accordance with the publication date of data by getting financial data such as intraday market, imbalance power market, bilateral agreements from internet platforms.
Another aim of the present invention is to present a method for making estimation of the system direction for intraday market and imbalance power market by getting data such as weather forecast, energy procurement, intraday market, imbalance power market, bilateral agreements from internet platforms such as EPIAS (Elektrik Piyasalari isletme Anonim Sirketi - Electricity Markets Enterprise Inc.), MGM (Meteoroloji Genel Mudurlugu - Turkish State Meteorological Service).
Another aim of the present invention is to use Random Forest algorithm as artificial learning method for estimating system direction.
Another aim of the present invention is to prevent victimization that can be happen due to the imbalance in the grids, thanks to the making estimation of the system direction for intraday market and imbalance power market.
Another aim of the present invention is to present a forecast system allowing more accurate estimation of the energy generation and management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems via internet servers from which model data such as financial, weather and energy loading information are obtained, an I/O module which is a hardware that allows control of the devices on internet or local network, a forecast database in which the data received from internet servers is stored, system direction forecast module where the calculations required for forecasting the system direction are made, a result database where the system direction forecast data is stored.
Description of the Figures
In Figure 1 , system components in which the present innovative method is applied and interaction between them are shown.
In Figure 2, a flow diagram summarizing the process steps of the present innovative method is shown.
Reference Numbers
10. internet server
20. I/O module
30. Forecast database
40. System direction forecast module
41. Data acquisition module
42. Data analysis module
43. Day ahead market module
44. Balancing power market module
45. Grouping module
46. Adjustment module
47. Evaluation module
48. Result module
50. Result database
100. Model data is retrieved from internet servers.
105. Database integration is provided and time-based matching is performed.
1 10. The attributes (variables) to be used in the model are selected.
1 15. Random Forest model top variables are optimized in the selected data range.
120. Random Forest model is trained in the selected data range and model coefficients are learned.
125. System direction of 24 hours later is estimated for the intraday market.
130. System direction of 48 hours later is estimated for the imbalance power market.
Detailed Description of the Invention
The present invention relates to a system and method that allow more accurate estimation of the energy generation and management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems as a result of dynamically changing parameters affecting the generation of energy from renewable energy sources.
In the present invention, in order to make accurate energy production forecast, data regarding day ahead market, intraday market, balancing power market and bilateral agreements should be received from an internet platform (such as EPIAS) having finance data; weather data and energy loading information should be received from the related internet platform. The necessary calculations are made by receiving data from system dynamically. In the present invention, Random Forest algorithm is used as an artificial learning method. In the Random Forest algorithm used in this system, finalized production plans are implemented in order to estimate the system direction of the next day. Algorithm learning is done sequentially based on time series.
System components in which the present innovative method is applied and interaction between them are shown in Figure 1. As seen as from this figure, the present system comprises internet servers (10) from which model data such as financial, weather and energy loading information are obtained, an I/O module (20) which is a hardware that allows control of the devices on internet or local network, a forecast database (30) in which the data received from internet servers (10) is stored, system direction forecast module (40) where the calculations required for forecasting the system direction are made, a result database (50) where the system direction forecast data is stored.
In addition, system direction forecast module (40) comprises a data acquisition module (41) interacting with the prediction database (30), a data analysis module (42) in which the networks with the data is established, a day ahead market module (43) where forecast of the system direction for 24 hours later is made for the intraday market, a balancing power market module (44) where forecast of the system direction for 48 hours later is made for the imbalance power market, a grouping module (45) where the data received from mentioned day ahead market module (43) and balancing power
market module (44) are grouped, an adjustment module (46) wherein the model parameters are arranged to match the incoming data, an evaluation module (47) in which evaluation of the data received from mentioned adjustment module (46) is performed, a result module (48) where the evaluated information is finalized.
In the present invention, firstly, the data required for making of system direction forecasting is received from internet servers (10) via the I/O module (20) and is transmitted to the forecast database (30). Subsequently, the data in the forecast database (30) is sent to the data acquisition module (41) within the system direction forecast module (40). The relevant data is transferred from the data acquisition module (41) to the data analysis module (42) and sent to the day ahead market module (43) and to the balancing power market module (44) by establishing the necessary relations related to the transaction. In the day ahead market module (43), the forecast of the system direction for 24 hours later is made for the intraday market. In the balancing power market module (44), the forecast of the system direction for 48 hours later is made for the imbalance power market. The data obtained from the day ahead market module (43) and from the balancing power market module (44) is sent to the grouping module (45) and grouped there. The data grouped in the related component is sent to adjustment module (46) and arranged to match with model parameters. The arranged data is sent to the evaluation module (47) and here, the system direction forecast is done and sent to the result module (48). The data obtained from the result module (48) is transmitted to result database (50) via I/O module (20).
A flow diagram summarizing the process steps of the present innovative method is given in Figure 2. Firstly, the model data is retrieved from the internet servers (100) via I/O module (20). Then, with the forecast database (30), database integration is provided and time-based matching is performed (105). In the system direction forecast module (40), the attributes (variables) to be used in the model are selected (1 10) and size is reduced. Then, with the hyperparameter adjustment, Random Forest model top variables are optimized in the selected data range (1 15). Subsequently, Random Forest model is trained in the selected data range and model coefficient are learned (120), system direction of 24 hours later is estimated for the intraday market (125) and system direction of 48 hours later is estimated for the imbalance power market (130).
Claims
1. A system direction forecast method allowing more accurate estimation of the energy generation and management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems as a result of dynamically changing parameters affecting the generation of energy from renewable energy sources, characterized in that it comprises the steps of receiving the data required for making of system direction forecasting, from internet server (10) via the I/O module (20) and, transmitting it to the forecast database (30), subsequently, sending the data in the forecast module (40) to the data acquisition module (41) within the system direction forecast module (40), transferring the relevant data from the data acquisition module (41) to the data analysis module (42), then sending it to the day ahead market module (43) and to the balancing power market module (44) by establishing the necessary relations related to the transaction, in the day ahead market module (43), making the forecast of the system direction for 24 hours later for the intraday market; in the balancing power market module (44), making the forecast of the system direction for 48 hours later for the imbalance power market, sending the data obtained from the day ahead market module (43) and from the balancing power market module (44) to the grouping module (45) and grouping it there, sending the data grouped in the grouping module (45) to the adjustment module (46) and arranging them to match with model parameters, sending the arranged data to the evaluation module (47) and here, making the system direction forecast and sending it to the result module (48), transmitting the data obtained from the result module (48) to the result database (50) via I/O module (20).
2. A system direction forecast method according to claim 1 and characterized in that it comprises the steps of retrieving the model data from the internet servers (100) via I/O module (20), then providing database integration with the forecast database (30) and matching time-based (105), in the system direction forecast module (40); selecting the attributes (variables) to be used in the
model (110) and reducing the size, then with the hyperparameter adjustment, optimizing Random Forest model top variables in the selected data range (115), subsequently training Random Forest model in the selected data range and learning model coefficient (120), estimating the system direction of 24 hours later for the intraday market (125) and estimating the system direction of 48 hours later for the imbalance power market (130).
3. A system direction forecast system allowing more accurate estimation of the energy generation and management of the energy supply-demand balance according to the free market model by avoiding imbalances that are happen in the grid systems as a result of dynamically changing parameters affecting the generation of energy from renewable energy sources, characterized in that it comprises internet servers (10) from which model data such as financial, weather and energy loading information are obtained, an I/O module (20) which is a hardware that allows control of the devices on internet or local network, a forecast database (30) in which the data received from internet servers (10) is stored, system direction forecast module (40) where the calculations required for forecasting the system direction are made, a result database (50) where the system direction forecast data is stored, and in addition to these; mentioned system direction forecast module (40) comprises a data acquisition module (41) interacting with the prediction database (30), a data analysis module (42) in which the networks with the data is established, a day ahead market module (43) where forecast of the system direction for 24 hours later is made for the intraday market, a balancing power market module (44) where forecast of the system direction for 48 hours later is made for the imbalance power market, a grouping module (45) where the data received from mentioned day ahead market module (43) and balancing power market module (44) are grouped, an adjustment module (46) wherein the model parameters are arranged to match the incoming data, an evaluation module (47) in which evaluation of the data received from mentioned adjustment module (46) is performed, a result module (48) where the evaluated information is finalized.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TR201813413 | 2018-09-19 | ||
TR2018/13413 | 2018-09-19 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2020101617A2 true WO2020101617A2 (en) | 2020-05-22 |
WO2020101617A3 WO2020101617A3 (en) | 2020-06-18 |
Family
ID=70050181
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/TR2019/050774 WO2020101617A2 (en) | 2018-09-19 | 2019-09-19 | A system and method that allow estimation of the system direction for intraday market and imbalance power market |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2020101617A2 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116433268A (en) * | 2023-06-13 | 2023-07-14 | 国网浙江省电力有限公司 | Processing method and system for unbalanced funds in electric power market |
-
2019
- 2019-09-19 WO PCT/TR2019/050774 patent/WO2020101617A2/en active Application Filing
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116433268A (en) * | 2023-06-13 | 2023-07-14 | 国网浙江省电力有限公司 | Processing method and system for unbalanced funds in electric power market |
CN116433268B (en) * | 2023-06-13 | 2023-09-05 | 国网浙江省电力有限公司 | Processing method and system for unbalanced funds in electric power market |
Also Published As
Publication number | Publication date |
---|---|
WO2020101617A3 (en) | 2020-06-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Egli | Renewable energy investment risk: An investigation of changes over time and the underlying drivers | |
Elgamal et al. | Optimization of a multiple-scale renewable energy-based virtual power plant in the UK | |
Botterud et al. | Risk management and optimal bidding for a wind power producer | |
Milligan et al. | Determining the capacity value of wind: An updated survey of methods and implementation | |
US7430534B2 (en) | System, method and computer program product for risk-minimization and mutual insurance relations in meteorology dependent activities | |
US20080228553A1 (en) | Method And System For Determination Of An Appropriate Strategy For Supply Of Renewal Energy Onto A Power Grid | |
Girard et al. | Assessment of wind power predictability as a decision factor in the investment phase of wind farms | |
JP2006235888A (en) | Computer system for profit forecasting and profit measurement in power company, profit forecasting method, and profit measurement method | |
Russo et al. | Short-term risk management of electricity retailers under rising shares of decentralized solar generation | |
Ribeiro et al. | Technical and economical aspects of wholesale electricity markets: An international comparison and main contributions for improvements in Brazil | |
Zarnikau et al. | Zonal merit-order effects of wind generation development on day-ahead and real-time electricity market prices in Texas | |
KR102513336B1 (en) | A control system for vpp platform and the method thereof | |
Ioannou et al. | Effect of electricity market price uncertainty modelling on the profitability assessment of offshore wind energy through an integrated lifecycle techno-economic model | |
WO2020101617A2 (en) | A system and method that allow estimation of the system direction for intraday market and imbalance power market | |
Nandakumar et al. | Impact of increased renewables on natural gas markets in eastern United States | |
KR20210015110A (en) | A Management Method Transaction Intermediary of Power Resource | |
Jónsson | Forecasting of electricity prices accounting for wind power predictions | |
Vardanyan | On stochastic optimization for short-term hydropower planning | |
Hasche et al. | Effects of improved wind forecasts on operational costs in the German electricity system | |
Liao et al. | Index‐based renewable energy insurance for Taiwan Solar Photovoltaic Power Plants | |
Mahler et al. | Simulation of day-ahead electricity market prices using a statistically calibrated structural model | |
Steber et al. | A comprehensive electricity market model using simulation and optimization techniques | |
Panda et al. | Risk assessment by security‐constrained unit commitment for hybrid wind‐thermal by pair copula approach in reserve power market: a stochastic approach | |
Del Grosso | Modelling electricity markets through quantitative methods | |
Lemos-Vinasco et al. | Economic evaluation of stochastic home energy management systems in a realistic rolling horizon setting |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19868167 Country of ref document: EP Kind code of ref document: A2 |