Older competitions
 | This section is empty. You can help by adding to it. (March 2019) |
The Global Energy Forecasting Competition (GEFCom) is a competition conducted by a team led by Dr. Tao Hong that invites submissions around the world for forecasting energy demand. [1] GEFCom was first held in 2012 on Kaggle, [2] and the second GEFCom was held in 2014 on CrowdANALYTIX. [3] [1]
IEEE Working Group on Energy Forecasting opened Global Energy Forecasting Competition 2017 (GEFCom2017) termed: Hierarchical Probabilistic Load Forecasting.
GEFCom2017 brought together state-of-the-art techniques and methodologies for hierarchical probabilistic energy forecasting. The competition featured a bi-level setup: a three-month qualifying match that included two tracks, and a one-month final match on a large-scale problem. In total 177 academic and company teams enrolled the competition.
Qualifying match defined data track winners:
Qualifying match open track winners:
Final match winners:
| | This section is empty. You can help by adding to it. (March 2019) |
GEFCom2014 was announced by Dr. Tao Hong in an article for The Oracle, a publication of the International Institute of Forecasters. [4] The competition was scheduled to begin on August 15, 2014 and end on December 15, 2014. In addition to individual prizes, GEFCom2014 also featured institute prizes for institutes with multiple well-performing teams. [5] The best performers in the competition were invited to submit papers for a special issue of the International Journal of Forecasting on probabilistic energy forecasting. [6] According to the website, GEFCom2014 had additional tracks in 2014: in addition to the hierarchical load forecasting and wind energy forecasting tracks, there was a price forecasting track and solar energy forecasting track. [1] [7] The IEEE Power & Energy Society was a sponsor of the competition. [8]
GEFCom 2012 was organized by a team comprising Dr. Tao Hong (Chair), Dr. Shu Fan (Vice Chair, Load Forecasting), and Dr. Pierre Pinson (Vice Chair, Wind Forecasting). [2] Sponsors included the IEEE Working Group on Energy Forecasting, IEEE Power System Planning and Implementation Committee, IEEE Power and Energy Education Committee, IEEE Power and Energy Society, IEEE Transactions on Smart Grid, International Journal of Forecasting, WeatherBank Inc, and Kaggle. [2] The competition was hosted on Kaggle, a service that runs data science competitions. It included two tracks: a hierarchical load forecasting track and a wind power forecasting track; both opened to contestants in September 2012. [9] [10] More than 200 teams submitted more than 2,000 entries focusing on hierarchical load forecasting and wind power forecasting. The winners were announced by the IEEE Power & Energy Society (one of the sponsors of the competition) on September 30, 2013. [11] [12]
The organizers of the competition described the results in an article in the April–June 2014 issue of the International Journal of Forecasting. [13] Papers by the top performers in the competition describing their methods also appeared in the issue. [7]
According to competition Chair Dr. Tao Hong, GEFCom2012 had five main aims: [4]
Distributed generation, also distributed energy, on-site generation (OSG), or district/decentralized energy, is electrical generation and storage performed by a variety of small, grid-connected or distribution system-connected devices referred to as distributed energy resources (DER).
Terence Chi-Shen Tao is an Australian mathematician who is a professor of mathematics at the University of California, Los Angeles (UCLA), where he holds the James and Carol Collins Chair in the College of Letters and Sciences. His research includes topics in harmonic analysis, partial differential equations, algebraic combinatorics, arithmetic combinatorics, geometric combinatorics, probability theory, compressed sensing and analytic number theory.
A microgrid is a local electrical grid with defined electrical boundaries, acting as a single and controllable entity. It is able to operate in grid-connected and in island mode. A 'stand-alone microgrid' or 'isolated microgrid' only operates off-the-grid and cannot be connected to a wider electric power system. Very small microgrids are called nanogrids.
Maximum power point tracking (MPPT), or sometimes just power point tracking (PPT), is a technique used with variable power sources to maximize energy extraction as conditions vary. The technique is most commonly used with photovoltaic (PV) solar systems but can also be used with wind turbines, optical power transmission and thermophotovoltaics.
Probabilistic forecasting summarizes what is known about, or opinions about, future events. In contrast to single-valued forecasts, probabilistic forecasts assign a probability to each of a number of different outcomes, and the complete set of probabilities represents a probability forecast. Thus, probabilistic forecasting is a type of probabilistic classification.
A wind power forecast corresponds to an estimate of the expected production of one or more wind turbines in the near future, up to a year. Forecast are usually expressed in terms of the available power of the wind farm, occasionally in units of energy, indicating the power production potential over a time interval.
The smart grid is an enhancement of the 20th century electrical grid, using two-way communications and distributed so-called intelligent devices. Two-way flows of electricity and information could improve the delivery network. Research is mainly focused on three systems of a smart grid – the infrastructure system, the management system, and the protection system. Electronic power conditioning and control of the production and distribution of electricity are important aspects of the smart grid.
Electricity pricing can vary widely by country or by locality within a country. Electricity prices are dependent on many factors, such as the price of power generation, government taxes or subsidies, CO
2 taxes, local weather patterns, transmission and distribution infrastructure, and multi-tiered industry regulation. The pricing or tariffs can also differ depending on the customer-base, typically by residential, commercial, and industrial connections.
China is the world's largest electricity producer, having overtaken the United States in 2011 after rapid growth since the early 1990s. In 2021, China produced 8.5 petawatt-hour (PWh) of electricity, approximately 30% of the world's electricity production.
In probability theory, a Markov model is a stochastic model used to model pseudo-randomly changing systems. It is assumed that future states depend only on the current state, not on the events that occurred before it. Generally, this assumption enables reasoning and computation with the model that would otherwise be intractable. For this reason, in the fields of predictive modelling and probabilistic forecasting, it is desirable for a given model to exhibit the Markov property.
Kaggle is a data science competition platform and online community of data scientists and machine learning practitioners under Google LLC. Kaggle enables users to find and publish datasets, explore and build models in a web-based data science environment, work with other data scientists and machine learning engineers, and enter competitions to solve data science challenges.
IEEE Smart Grid is an initiative launched by IEEE to help provide expertise and guidance for individuals and organizations involved in the modernization and optimization of the power grid, better known as the "smart grid". IEEE Smart Grid encompasses an array of activities, including development of new smart grid-related standards, best practices, publications, and conferences and educational opportunities.
Variable renewable energy (VRE) or intermittent renewable energy sources (IRES) are renewable energy sources that are not dispatchable due to their fluctuating nature, such as wind power and solar power, as opposed to controllable renewable energy sources, such as dammed hydroelectricity or bioenergy, or relatively constant sources, such as geothermal power.
Rajit Gadh is a Professor of Mechanical and Aerospace Engineering at the UCLA Henry Samueli School of Engineering and Applied Science and the founding director of the UCLA Smart Grid Energy Research Center (SMERC), the UCLA Wireless Internet for Mobile Enterprise Consortium (WINMEC), and the Connected and Autonomous Electric Vehicles Consortium (CAEV).
Roy Billinton is a Canadian scholar and a Distinguished Emeritus Professor at the University of Saskatchewan, Saskatoon, Saskatchewan, Canada. In 2008, Billinton won the IEEE Canada Electric Power Medal for his research and application of reliability concepts in electric power system. In 2007, Billinton was elected a Foreign Associate of the United States National Academy of Engineering for "contributions to teaching, research and application of reliability engineering in electric power generation, transmission, and distribution systems."
Quantile Regression Averaging (QRA) is a forecast combination approach to the computation of prediction intervals. It involves applying quantile regression to the point forecasts of a small number of individual forecasting models or experts. It has been introduced in 2014 by Jakub Nowotarski and Rafał Weron and originally used for probabilistic forecasting of electricity prices and loads. Despite its simplicity it has been found to perform extremely well in practice - the top two performing teams in the price track of the Global Energy Forecasting Competition (GEFCom2014) used variants of QRA.
Energy forecasting includes forecasting demand (load) and price of electricity, fossil fuels and renewable energy sources. Forecasting can be both expected price value and probabilistic forecasting.
Electricity price forecasting (EPF) is a branch of energy forecasting which focuses on using mathematical, statistical and machine learning models to predict electricity prices in the future. Over the last 30 years electricity price forecasts have become a fundamental input to energy companies’ decision-making mechanisms at the corporate level.
Pierre Pinson is a French applied mathematician known for his work on forecasting, optimisation and management science for energy systems, e.g., including probabilistic forecasting, participation of renewable energy generation in electricity markets, market-based coordination of energy systems, peer-to-peer energy markets, as well as data markets. He is a professor at the Technical University of Denmark and has been Editor-in-Chief of the International Journal of Forecasting from 2019 onwards.
Reliability index is an attempt to quantitatively assess the reliability of a system using a single numerical value. The set of reliability indices varies depending on the field of engineering, multiple different indices may be used to characterize a single system. In the simple case of an object that cannot be used or repaired once it fails, a useful index is the mean time to failure representing an expectation of the object's service lifetime. Another cross-disciplinary index is forced outage rate (FOR), a probability that a particular type of a device is out of order. Reliability indices are extensively used in the modern electricity regulation.