Electricity price forecasting explained

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.

Since the early 1990s, the process of deregulation and the introduction of competitive electricity markets have been reshaping the landscape of the traditionally monopolistic and government-controlled power sectors. Throughout Europe, North America, Australia and Asia, electricity is now traded under market rules using spot and derivative contracts.[1] However, electricity is a very special commodity: it is economically non-storable and power system stability requires a constant balance between production and consumption. At the same time, electricity demand depends on weather (temperature, wind speed, precipitation, etc.) and the intensity of business and everyday activities (on-peak vs. off-peak hours, weekdays vs. weekends, holidays, etc.). These unique characteristics lead to price dynamics not observed in any other market, exhibiting daily, weekly and often annual seasonality and abrupt, short-lived and generally unanticipated price spikes.[2]

Extreme price volatility, which can be up to two orders of magnitude higher than that of any other commodity or financial asset, has forced market participants to hedge not only volume but also price risk. Price forecasts from a few hours to a few months ahead have become of particular interest to power portfolio managers. A power market company able to forecast the volatile wholesale prices with a reasonable level of accuracy can adjust its bidding strategy and its own production or consumption schedule in order to reduce the risk or maximize the profits in day-ahead trading.[3] A ballpark estimate of savings from a 1% reduction in the mean absolute percentage error (MAPE) of short-term price forecasts is $300,000 per year for a utility with 1GW peak load. With the additional price forecasts, the savings double.[4]

Forecasting methodology

The simplest model for day ahead forecasting is to ask each generation source to bid on blocks of generation and choose the cheapest bids. If not enough bids are submitted, the price is increased. If too many bids are submitted the price can reach zero or become negative. The offer price includes the generation cost as well as the transmission cost, along with any profit. Power can be sold or purchased from adjoining power pools.[5] [6] [7]

The concept of independent system operators (ISOs) fosters competition for generation among wholesale market participants by unbundling the operation of transmission and generation. ISOs use bid-based markets to determine economic dispatch.[8]

Wind and solar power are non-dispatchable. Such power is normally sold before any other bids, at a predetermined rate for each supplier. Any excess is sold to another grid operator, or stored, using pumped-storage hydroelectricity, or in the worst case, curtailed.[9] Curtailment could potentially significantly impact solar power's economic and environmental benefits at greater PV penetration levels.[10] Allocation is done by bidding.[11]

The effect of the recent introduction of smart grids and integrating distributed renewable generation has been increased uncertainty of future supply, demand and prices.[12] This uncertainty has driven much research into the topic of forecasting.

Driving factors

Electricity cannot be stored as easily as gas, it is produced at the exact moment of demand. All of the factors of supply and demand will, therefore, have an immediate impact on the price of electricity on the spot market. In addition to production costs, electricity prices are set by supply and demand.[13] However, some fundamental drivers are the most likely to be considered.

Short-term prices are impacted the most by the weather.[14] Demand due to heating in the winter and cooling in the summer are the main drivers for seasonal price spikes.[15] Additional natural-gas fired capacity is driving down the price of electricity and increasing demand.

A country's natural resource endowment, as well as its regulations in place greatly influence tariffs from the supply side. The supply side of the electricity supply is most influenced by fuel prices, and CO2 allowance prices. The EU carbon prices have doubled since 2017, making it a significant driving factor of price.[16]

Weather

Studies show that demand for electricity is driven largely by temperature. Heating demand in the winter and cooling demand (air conditioners) in the summer are what primarily drive the seasonal peaks in most regions. Heating degree days and cooling degree days help measure energy consumption by referencing the outdoor temperature above and below 65 degrees Fahrenheit, a commonly accepted baseline.[17]

In terms of renewable sources like solar and wind, weather impacts supply. California's duck curve shows the difference between electricity demand and the amount of solar energy available throughout the day. On a sunny day, solar power floods the electricity generation market and then drops during the evening, when electricity demand peaks.

Forecasting for wind and solar renewable energy is becoming more important as the amount of energy generated from these sources increases.[18] Meteorological forecasts can improve the accuracy of electricity price forecasting models. While day-ahead forecasts can take advantage of autoregressive effects, forecasts featuring meteorological data are more accurate for 2-4 day-ahead horizons.[19] In some cases, renewable energy generation forecasts published by Transmission System Operators (TSOs) can be improved with simple prediction models and used provide more accurate electricity price predictions.[20]

Hydropower availability

Snowpack, streamflows, seasonality, salmon, etc. all affect the amount of water that can flow through a dam at any given time. Forecasting these variables predicts the available potential energy for a dam for a given period.[21] Some regions such as Pakistan, Egypt, China and the Pacific Northwest get significant generation from hydroelectric dams. In 2015, SAIDI and SAIFI more than doubled from the previous year in Zambia due to low water reserves in their hydroelectric dams caused by insufficient rainfall.[22]

Power plant and transmission outages

Whether planned or unplanned, outages affect the total amount of power that is available to the grid. Outages undermine electricity supply, which in turn affects the price.

Economic health

During times of economic hardship, many factories cut back production due to a reduction of consumer demand and therefore reduce production-related electrical demand.[23]

Government regulation

Governments may choose to make electricity tariffs affordable for their population through subsidies to producers and consumers. Most countries characterized as having low energy access have electric power utilities that do not recover any of their capital and operating costs, due to high subsidy levels.[24]

Taxonomy of modeling approaches

A variety of methods and ideas have been tried for electricity price forecasting (EPF), with varying degrees of success. They can be broadly classified into six groups.

Multi-agent models

Multi-agent (multi-agent simulation, equilibrium, game theoretic) models simulate the operation of a system of heterogeneous agents (generating units, companies) interacting with each other, and build the price process by matching the demand and supply in the market.[25] This class includes cost-based models (or production-cost models, PCM),[26] equilibrium or game theoretic approaches (like the Nash-Cournot framework, supply function equilibrium - SFE, strategic production-cost models - SPCM)[27] [28] [29] [30] [31] and agent-based models.[32] [33] [34]

Multi-agent models generally focus on qualitative issues rather than quantitative results. They may provide insights as to whether or not prices will be above marginal costs, and how this might influence the players’ outcomes. However, they pose problems if more quantitative conclusions have to be drawn, particularly if electricity prices have to be predicted with a high level of precision.

Fundamental models

Fundamental (structural) methods try to capture the basic physical and economic relationships which are present in the production and trading of electricity.[35] The functional associations between fundamental drivers (loads, weather conditions, system parameters, etc.) are postulated, and the fundamental inputs are modeled and predicted independently, often via statistical, reduced-form or computational intelligence techniques. In general, two subclasses of fundamental models can be identified: parameter rich models[36] [37] and parsimonious structural models[38] [39] [40] [41] of supply and demand.

Two major challenges arise in the practical implementation of fundamental models: data availability and incorporation of stochastic fluctuations of the fundamental drivers. In building the model, we make specific assumptions about physical and economic relationships in the marketplace, and therefore the price projections generated by the models are very sensitive to violations of these assumptions.

Reduced-form models

Reduced-form (quantitative, stochastic) models characterize the statistical properties of electricity prices over time, with the ultimate objective of derivatives valuation and risk management.[42] Their main intention is not to provide accurate hourly price forecasts, but rather to replicate the main characteristics of daily electricity prices, like marginal distributions at future time points, price dynamics, and correlations between commodity prices. If the price process chosen is not appropriate for capturing the main properties of electricity prices, the results from the model are likely to be unreliable. However, if the model is too complex, the computational burden will prevent its use on-line in trading departments. Depending on the type of market under consideration, reduced-form models can be classified as:

Statistical models

Statistical (such as econometric) methods forecast the current price by using a mathematical combination of the previous prices and/or previous or current values of exogenous factors, typically consumption and production figures, or weather variables. The two most important categories are additive and multiplicative models. They differ in whether the predicted price is the sum (additive) of a number of components or the product (multiplicative) of a number of factors. The former are far more popular, but the two are closely related - a multiplicative model for prices can be transformed into an additive model for log-prices. Statistical models are attractive because some physical interpretation may be attached to their components, thus allowing engineers and system operators to understand their behavior. They are often criticized for their limited ability to model the (usually) nonlinear behavior of electricity prices and related fundamental variables. However, in practical applications, their performances are not worse than those of the non-linear computational intelligence methods (see below). For instance, in the load forecasting track of the Global Energy Forecasting Competition (GEFCom2012) attracting hundreds of participants worldwide, the top four winning entries used regression-type models.Statistical models constitute a very rich class which includes:

Computational intelligence models

Computational intelligence (artificial intelligence-based, machine learning, non-parametric, non-linear statistical) techniques combine elements of learning, evolution and fuzziness to create approaches that are capable of adapting to complex dynamic systems, and may be regarded as "intelligent" in this sense. Artificial neural networks,[73] [74] [75] [76] including deep neural networks,[77] explainable AI models[78] and distributional neural networks,[79] as well as fuzzy systems[80] and support vector machines (SVM)[81] are unquestionably the main classes of computational intelligence techniques in EPF. Their major strength is the ability to handle complexity and non-linearity. In general, computational intelligence methods are better at modeling these features of electricity prices than the statistical techniques (see above). At the same time, this flexibility is also their major weakness. The ability to adapt to nonlinear, spiky behavior does not necessarily lead to better point or probabilistic predictions, and a lot of effort is required to find the right hyper-parameters.

Hybrid models

Many of the modeling and price forecasting approaches considered in the literature are hybrid solutions, combining techniques from two or more of the groups listed above. Their classification is non-trivial, if possible at all.As an example of hybrid model AleaModel (AleaSoft) combines Neural Networks and Box Jenkins models.

Forecasting horizons

It is customary to talk about short-, medium- and long-term forecasting, but there is no consensus in the literature as to what the thresholds should actually be:

Future of electricity price forecasting

In his extensive review paper, Weron looks ahead and speculates on the directions EPF will or should take over the next decade or so:

Fundamental price drivers and input variables

Seasonality

A key point in electricity spot price modeling and forecasting is the appropriate treatment of seasonality.[82] The electricity price exhibits seasonality at three levels: the daily and weekly, and to some extent - the annual. In short-term forecasting, the annual or long-term seasonality is usually ignored, but the daily and weekly patterns (including a separate treatment of holidays) are of prime importance. This, however, may not be the right approach. As Nowotarski and Weron[83] have recently shown, decomposing a series of electricity prices into a long-term seasonal and a stochastic component, modeling them independently and combining their forecasts can bring - contrary to a common belief - an accuracy gain compared to an approach in which a given model is calibrated to the prices themselves.

In mid-term forecasting, the daily patterns become less relevant and most EPF models work with average daily prices. However, the long-term trend-cycle component plays a crucial role. Its misspecification can introduce bias, which may lead to a bad estimate of the mean reversion level or of the price spike intensity and severity, and consequently, to underestimating the risk. Finally, in the long term, when the time horizon is measured in years, the daily, weekly and even annual seasonality may be ignored, and long-term trends dominate. Adequate treatment - both in-sample and out-of-sample - of seasonality has not been given enough attention in the literature so far.[84] [85] [86]

Variable selection

Another crucial issue in electricity price forecasting is the appropriate choice of explanatory variables.[87] [88] Apart from historical electricity prices, the current spot price is dependent on a large set of fundamental drivers, including system loads, weather variables, fuel costs, the reserve margin (i.e., available generation minus/over predicted demand) and information about scheduled maintenance and forced outages. Although "pure price" models are sometimes used for EPF, in the most common day-ahead forecasting scenario most authors select a combination of these fundamental drivers, based on the heuristics and experience of the forecaster.[89] Very rarely has an automated selection or shrinkage procedure been carried out in EPF, especially for a large set of initial explanatory variables.[90] However, the machine learning literature provides viable tools that can be broadly classified into two categories:[91]

Some of these techniques have been utilized in the context of EPF:

but their use is not common. Further development and employment of methods for selecting the most effective input variables - from among the past electricity prices, as well as the past and predicted values of the fundamental drivers - is needed.

Spike forecasting and the reserve margin

When predicting spike occurrences or spot price volatility, one of the most influential fundamental variables is the reserve margin, also called surplus generation. It relates the available capacity (generation, supply),

Ct

, to the demand (load),

Dt

, at a given moment in time

t

. The traditional engineering notion of the reserve margin defines it as the difference between the two, i.e.,

RM=Ct-Dt

, but many authors prefer to work with dimensionless ratios

\rhot=Dt/Ct

,

Rt=Ct/Dt-1

or the so-called capacity utilization

CUt=1-Dt/Ct

. Its rare application in EPF can be justified only by the difficulty of obtaining good quality reserve margin data. Given that more and more system operators (see e.g. http://www.elexon.co.uk) are disclosing such information nowadays, reserve margin data should be playing a significant role in EPF in the near future.

Probabilistic forecasts

The use of prediction intervals (PI) and densities, or probabilistic forecasting, has become much more common over the past three decades, as practitioners have come to understand the limitations of point forecasts.[98] Despite the bold move by the organizers of the Global Energy Forecasting Competition 2014 to require the participants to submit forecasts of the 99 percentiles of the predictive distribution (day-ahead in the price track) and not the point forecasts as in the 2012 edition,[99] this does not seem to be a common case in EPF as yet.

If PIs are computed at all, they usually are distribution-based (and approximated by the standard deviation of the model residuals) or empirical. A new forecast combination (see below) technique has been introduced recently in the context of EPF. Quantile Regression Averaging (QRA) involves applying quantile regression to the point forecasts of a small number of individual forecasting models or experts, hence allows to leverage existing development of point forecasting.[100]

Combining forecasts

Consensus forecasts, also known as combining forecasts, forecast averaging or model averaging (in econometrics and statistics) and committee machines, ensemble averaging or expert aggregation (in machine learning), are predictions of the future that are created by combining several separate forecasts which have often been created using different methodologies. Despite their popularity in econometrics, averaged forecasts have not been used extensively in the context of electricity markets to date. There is some limited evidence on the adequacy of combining forecasts of electricity demand,[101] but it was only very recently that combining was used in EPF and only for point forecasts.[102] [103] Combining probabilistic (i.e., interval and density) forecasts is much less popular, even in econometrics in general, mainly because of the increased complexity of the problem. Since Quantile Regression Averaging (QRA) allows to leverage existing development of point forecasting, it is particularly attractive from a practical point of view and may become a popular tool in EPF in the near future.

Multivariate factor models

The literature on forecasting daily electricity prices has concentrated largely on models that use only information at the aggregated (i.e., daily) level. On the other hand, the very rich body of literature on forecasting intra-day prices has used disaggregated data (i.e., hourly or half-hourly), but generally has not explored the complex dependence structure of the multivariate price series. If we want to explore the structure of intra-day electricity prices, we need to use dimension reduction methods; for instance, factor models with factors estimated as principal components (PC). Empirical evidence indicates that there are forecast improvements from incorporating disaggregated (i.e., hourly or zonal) data for predicting daily system prices, especially when the forecast horizon exceeds one week.[104] [105] With the increase of computational power, the real-time calibration of these complex models will become feasible and we may expect to see more EPF applications of the multivariate framework in the coming years.

A universal test ground

All major review publications conclude that there are problems with comparing the methods developed and used in the EPF literature. This is due mainly to the use of different datasets, different software implementations of the forecasting models and different error measures, but also to the lack of statistical rigor in many studies. This calls for a comprehensive, thorough study involving (i) the same datasets, (ii) the same robust error evaluation procedures, and (iii) statistical testing of the significance of one model's outperformance of another. To some extent, the Global Energy Forecasting Competition 2014 has addressed these issues. Yet more has to be done. A selection of the better-performing measures (weighted-MAE, seasonal MASE or RMSSE) should be used either exclusively or in conjunction with the more popular ones (MAPE, RMSE). The empirical results should be further tested for the significance of the differences in forecasting accuracies of the models.

See also

Notes and References

  1. Mayer . Klaus . Trück . Stefan . March 2018 . Electricity markets around the world . Journal of Commodity Markets . en . 9 . 77–100 . 10.1016/j.jcomm.2018.02.001.
  2. Weron . Rafał . 2014 . [Open Access] . Electricity price forecasting: A review of the state-of-the-art with a look into the future . International Journal of Forecasting . 30 . 4 . 1030–1081 . 10.1016/j.ijforecast.2014.08.008 . free.
  3. Book: Weron, Rafał. Modeling and Forecasting Electricity Loads and Prices: A Statistical Approach. Wiley. 2006. 978-0-470-05753-7.
  4. Crystal Ball Lessons in Predictive Analytics. Hong. Tao. 2015. EnergyBiz Magazine. Spring. 35–37. 2015-11-29. 2015-09-10. https://web.archive.org/web/20150910030519/http://www.energybiz.com/magazine/article/404587/crystal-ball-lessons-predictive-analytics. dead.
  5. https://wayback.archive-it.org/all/20140304044724/http://isoexpress.iso-ne.com/guest-hub ISO NE
  6. Web site: NY ISO Zone Maps. 18 June 2017.
  7. Web site: LMP Contour Map: Day-Ahead Market – Settlement Point Pricing. ERCOT. 18 June 2017.
  8. Web site: FERC: Electric Power Markets – National Overview. www.ferc.gov. en. 3 May 2018. 23 January 2019. https://web.archive.org/web/20190123104944/https://www.ferc.gov/market-oversight/mkt-electric/overview.asp. dead.
  9. Web site: Wind Power and Electricity Markets. 2011. 18 June 2017. https://web.archive.org/web/20160304082946/http://www.uwig.org/windinmarketstableOct2011.pdf. 4 March 2016. dead.
  10. Web site: Confronting the Duck Curve: How to Address Over-Generation of Solar Energy. Energy.gov. en. 3 May 2018.
  11. Web site: Wayback Machine. 16 August 2011. Eirgrid. 14 May 2017.
  12. 10.1016/j.rser.2017.05.234 . Recent advances in electricity price forecasting: A review of probabilistic forecasting . Renewable and Sustainable Energy Reviews . 81 . 1548–1568 . 2018 . Nowotarski . Jakub . Weron . Rafał . 2018RSERv..81.1548N . 157301643 .
  13. Web site: The power market. Nord Pool Spot. 18 June 2017. https://web.archive.org/web/20170606010200/http://nordpoolspot.com/How-does-it-work/. 6 June 2017. dead.
  14. Mosquera-López . Stephanía . Nursimulu . Anjali . March 2019 . Drivers of electricity price dynamics: Comparative analysis of spot and futures markets . Energy Policy . en . 126 . 76–87 . 10.1016/j.enpol.2018.11.020. 2019EnPol.126...76M .
  15. Web site: Six Key Factors Driving Gas and Electricity Prices APPI Energy. www.appienergy.com. 3 May 2018. 23 January 2019. https://web.archive.org/web/20190123223552/https://www.appienergy.com/news-and-resources/news/six-key-factors-driving-gas-and-electricity-prices/. dead.
  16. Web site: EU CO2 allowance prices continue to climb, hit Eur10.60/mt – Electric Power Platts News Article & Story. www.platts.com. 3 May 2018.
  17. Web site: What Does It Take to Heat a New Room?. https://web.archive.org/web/19991122201734/http://amstat.org/publications/jse/datasets/utility.txt. dead. November 22, 1999. Robert Carver. American Statistical Association. 14 February 2010.
  18. Sweeney . Conor . Bessa . Ricardo J. . Browell . Jethro . Pinson . Pierre . March 2020 . The future of forecasting for renewable energy . WIREs Energy and Environment . en . 9 . 2 . 10.1002/wene.365 . 2020WIREE...9E.365S . 2041-8396. 10197/11503 . free .
  19. Sgarlato . Raffaele . Ziel . Florian . May 2023 . The Role of Weather Predictions in Electricity Price Forecasting Beyond the Day-Ahead Horizon . IEEE Transactions on Power Systems . 38 . 3 . 2500–2511 . 10.1109/TPWRS.2022.3180119 . 0885-8950. free . 2023ITPSy..38.2500S .
  20. Maciejowska . Katarzyna . Nitka . Weronika . Weron . Tomasz . July 2021 . Enhancing load, wind and solar generation for day-ahead forecasting of electricity prices . Energy Economics . en . 99 . 105273 . 10.1016/j.eneco.2021.105273. 2021EneEc..9905273M .
  21. Web site: More Reliable Forecasts for Water Flows Can Reduce Price of Electricity. 19 January 2010. Body of Knowledge on Infrastructure Regulation. 18 June 2017.
  22. J. Arlet. 2017. “Electricity sector constraints for firms across economies : a comparative analysis.” Doing business research notes; no.1. Washington, D.C. : World Bank Group. http://documents.worldbank.org/curated/en/409771499690745091/Electricity-sector-constraints-for-firms-across-economies-a-comparative-analysis p.10
  23. Web site: Demand Forecasting for Electricity. Body of Knowledge on Infrastructure Regulation. 18 June 2017.
  24. C. Trimble, M. Kojima, I. Perez Arroyo, F. Mohammadzadeh. 2016. “Financial Viability of Electricity Sectors in Sub-Saharan Africa: Quasi-Fiscal Deficits and Hidden Costs.” Policy Research Working Paper; No. 7788.
  25. Electricity market modeling trends. Energy Policy. 2005. 897–913. 33. 7. 10.1016/j.enpol.2003.10.013. Mariano. Ventosa. Álvaro. Baı́llo. Andrés. Ramos. Michel. Rivier. 2005EnPol..33..897V .
  26. Book: Power Generation, Operation and Control. Wood. A.J.. Wiley. 1996. Wollenberg. B.F..
  27. A strategic production costing model for electricity market price analysis. IEEE Transactions on Power Systems. 2005. 0885-8950. 67–74. 20. 1. 10.1109/TPWRS.2004.831266. Carlos. Batlle. J.. Barquin. 2005ITPSy..20...67B. 11531/7777 . 22681492. free.
  28. Stochastic models for bidding strategies on oligopoly electricity market. Mathematical Methods of Operations Research. 2009. 1432-2994. 579–592. 69. 3. 10.1007/s00186-008-0252-7. Magdalena. Borgosz-Koczwara. Aleksander. Weron. Agnieszka. Wyłomańska. 8882103.
  29. Bello . Antonio . Bunn . Derek W. . Reneses . Javier . Munoz . Antonio . January 2017 . Medium-Term Probabilistic Forecasting of Electricity Prices: A Hybrid Approach . IEEE Transactions on Power Systems . 32 . 1 . 334–343 . 10.1109/TPWRS.2016.2552983 . 2017ITPSy..32..334B . 0885-8950.
  30. Wang . Xian . Yang . Jiaying . Zhang . Kai . Zhang . Shaohua . Wu . Lei . January 2022 . Game-theoretic analysis of market-based operation mechanism for demand response resources . International Journal of Electrical Power & Energy Systems . en . 134 . 107456 . 10.1016/j.ijepes.2021.107456. free . 2022IJEPE.13407456W .
  31. Boomsma . Trine Krogh . Pineda . Salvador . Heide-Jørgensen . Ditte Mølgård . June 2022 . The spot and balancing markets for electricity: open- and closed-loop equilibrium models . Computational Management Science . en . 19 . 2 . 309–346 . 10.1007/s10287-021-00418-4 . 1619-697X.
  32. Learning Agents in an Artificial Power Exchange: Tacit Collusion, Market Power and Efficiency of Two Double-auction Mechanisms. Computational Economics. 2008. 0927-7099. 73–98. 32. 1–2. 10.1007/s10614-008-9127-5. Eric. Guerci. Stefano. Ivaldi. Silvano. Cincotti. 154575281.
  33. Shafie-khah . Miadreza . Catalao . Joao P. S. . March 2015 . A Stochastic Multi-Layer Agent-Based Model to Study Electricity Market Participants Behavior . IEEE Transactions on Power Systems . 30 . 2 . 867–881 . 10.1109/TPWRS.2014.2335992 . 2015ITPSy..30..867S . 0885-8950.
  34. Fraunholz . Christoph . Kraft . Emil . Keles . Dogan . Fichtner . Wolf . May 2021 . Advanced price forecasting in agent-based electricity market simulation . Applied Energy . en . 290 . 116688 . 10.1016/j.apenergy.2021.116688. 2021ApEn..29016688F .
  35. Book: Managing Energy Risk: An Integrated View on Power and Other Energy Markets. 10.1002/9781119209102. Burger. M.. Graeber. B.. Schindlmayr. G.. Wiley. 2007. 9781119209102.
  36. Book: Energy and Power Risk Management: New Developments in Modeling, Pricing, and Hedging. Eydeland. Alexander. Wiley. 2003. 978-0-471-10400-1. Wolyniec. Krzysztof.
  37. Beran . Philip . Pape . Christian . Weber . Christoph . June 2019 . Modelling German electricity wholesale spot prices with a parsimonious fundamental model – Validation & application . Utilities Policy . en . 58 . 27–39 . 10.1016/j.jup.2019.01.008. 2019UtPol..58...27B .
  38. Book: A Survey of Commodity Markets and Structural Models for Electricity Prices. Springer New York. 2014. 978-1-4614-7247-6. 41–83. 10.1007/978-1-4614-7248-3_2. René. Carmona. Michael. Coulon. Fred Espen. Benth. Valery A.. Kholodnyi. Peter. Laurence. 10.1.1.380.3730. 2126558 .
  39. Kallabis . Thomas . Pape . Christian . Weber . Christoph . August 2016 . The plunge in German electricity futures prices – Analysis using a parsimonious fundamental model . Energy Policy . en . 95 . 280–290 . 10.1016/j.enpol.2016.04.025. 2016EnPol..95..280K .
  40. Ziel . Florian . Steinert . Rick . September 2016 . Electricity price forecasting using sale and purchase curves: The X-Model . Energy Economics . en . 59 . 435–454 . 10.1016/j.eneco.2016.08.008. 1509.00372 . 2016EneEc..59..435Z .
  41. Alasseur . C. . Féron . O. . September 2018 . Structural price model for coupled electricity markets . Energy Economics . en . 75 . 104–119 . 10.1016/j.eneco.2018.07.018. 1704.06027 . 2018EneEc..75..104A .
  42. Book: Modelling Prices in Competitive Electricity Markets . Wiley . 2004 . 978-0-470-84860-9 . Bunn . Derek W..
  43. Revisiting the relationship between spot and futures prices in the Nord Pool electricity market. Energy Economics. 2014. 178–190. 44. 10.1016/j.eneco.2014.03.007. Rafał. Weron. Michał. Zator. 2014EneEc..44..178W .
  44. Market price of risk implied by Asian-style electricity options and futures. Energy Economics. 2008. 1098–1115. 30. 3. 10.1016/j.eneco.2007.05.004. Rafał. Weron. 2008EneEc..30.1098W . 10.1.1.136.3016.
  45. A critical empirical study of three electricity spot price models. Energy Economics. 2012. 1589–1616. 34. 5. 10.1016/j.eneco.2011.11.012. Fred Espen. Benth. Rüdiger. Kiesel. Anna. Nazarova. 2012EneEc..34.1589B .
  46. Muniain . Peru . Ziel . Florian . October 2020 . Probabilistic forecasting in day-ahead electricity markets: Simulating peak and off-peak prices . International Journal of Forecasting . en . 36 . 4 . 1193–1210 . 10.1016/j.ijforecast.2019.11.006. 1810.08418 .
  47. Ciarreta . Aitor . Muniain . Peru . Zarraga . Ainhoa . November 2022 . Do jumps and cojumps matter for electricity price forecasting? Evidence from the German-Austrian day-ahead market . Electric Power Systems Research . en . 212 . 108144 . 10.1016/j.epsr.2022.108144. 2022EPSR..21208144C . 10810/58629 . free .
  48. An empirical comparison of alternate regime-switching models for electricity spot prices. Energy Economics. 2010. 1059–1073. 32. 5. 10.1016/j.eneco.2010.05.008. Joanna. Janczura. Rafal. Weron. 2010EneEc..32.1059J .
  49. Janczura . Joanna . February 2014 . Pricing electricity derivatives within a Markov regime-switching model: a risk premium approach . Mathematical Methods of Operations Research . en . 79 . 1 . 1–30 . 10.1007/s00186-013-0451-8 . 1432-2994. free .
  50. Sapio . Alessandro . October 2015 . The effects of renewables in space and time: A regime switching model of the Italian power price . Energy Policy . en . 85 . 487–499 . 10.1016/j.enpol.2015.07.025. 2015EnPol..85..487S .
  51. Apergis . Nicholas . Gozgor . Giray . Lau . Chi Keung Marco . Wang . Shixuan . February 2019 . Decoding the Australian electricity market: New evidence from three-regime hidden semi-Markov model . Energy Economics . en . 78 . 129–142 . 10.1016/j.eneco.2018.10.038. 2019EneEc..78..129A .
  52. Book: Stochastic Modeling of Electricity and Related Markets. 11. 10.1142/6811. Fred Espen. Benth. Jūratė Šaltytė. Benth. Steen. Koekebakker. World Scientific. 2008. Advanced Series on Statistical Science & Applied Probability. 978-981-281-230-8.
  53. Caldana . Ruggero . Fusai . Gianluca . Roncoroni . Andrea . September 2017 . Electricity forward curves with thin granularity: Theory and empirical evidence in the hourly EPEXspot market . European Journal of Operational Research . en . 261 . 2 . 715–734 . 10.1016/j.ejor.2017.02.016.
  54. Lago . Jesus . Marcjasz . Grzegorz . De Schutter . Bart . Weron . Rafał . July 2021 . Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark . Applied Energy . en . 293 . 116983 . 10.1016/j.apenergy.2021.116983. 2008.08004 . 2021ApEn..29316983L .
  55. Forecasting Electricity Spot Prices Accounting for Wind Power Predictions. IEEE Transactions on Sustainable Energy. 2013. 1949-3029. 210–218. 4. 1. 10.1109/TSTE.2012.2212731. T.. Jonsson. P.. Pinson. H.A.. Nielsen. H.. Madsen. T.S.. Nielsen. 2013ITSE....4..210J. 11850152.
  56. Forecasting electricity prices for a day-ahead pool-based electric energy market. International Journal of Forecasting. 2005. 435–462. 21. 3. 10.1016/j.ijforecast.2004.12.005. Antonio J.. Conejo. Javier. Contreras. Rosa. Espínola. Miguel A.. Plazas.
  57. Forecasting spot electricity prices: A comparison of parametric and semiparametric time series models. International Journal of Forecasting. 2008. 744–763. 24. Energy Forecasting. 4. 10.1016/j.ijforecast.2008.08.004. Rafał. Weron. Adam. Misiorek. 10.1.1.489.2637. 3999614 .
  58. Forecasting electricity prices: The impact of fundamentals and time-varying coefficients. International Journal of Forecasting. 2008. 764–785. 24. Energy Forecasting. 4. 10.1016/j.ijforecast.2008.09.008. Nektaria V.. Karakatsani. Derek W.. Bunn.
  59. Lago . Jesus . De Ridder . Fjo . De Schutter . Bart . July 2018 . Forecasting spot electricity prices: Deep learning approaches and empirical comparison of traditional algorithms . Applied Energy . en . 221 . 386–405 . 10.1016/j.apenergy.2018.02.069. 2018ApEn..221..386L . free .
  60. Ziel . Florian . Weron . Rafał . February 2018 . Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworks . Energy Economics . en . 70 . 396–420 . 10.1016/j.eneco.2017.12.016. 1805.06649 . 2018EneEc..70..396Z .
  61. Kremer . Marcel . Kiesel . Rüdiger . Paraschiv . Florentina . 2021-07-26 . An econometric model for intraday electricity trading . Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences . en . 379 . 2202 . 20190624 . 10.1098/rsta.2019.0624 . 34092107 . 2021RSPTA.37990624K . 1364-503X.
  62. Janczura . Joanna . Wójcik . Edyta . June 2022 . Dynamic short-term risk management strategies for the choice of electricity market based on probabilistic forecasts of profit and risk measures. The German and the Polish market case study . Energy Economics . en . 110 . 106015 . 10.1016/j.eneco.2022.106015. 2022EneEc.11006015J .
  63. Periodic Seasonal Reg-ARFIMA–GARCH Models for Daily Electricity Spot Prices. Journal of the American Statistical Association. 2007. 0162-1459. 16–27. 102. 477. 10.1198/016214506000001022. Siem Jan. Koopman. Marius. Ooms. M. Angeles. Carnero. 1871/9678. 11384864.
  64. Kostrzewski . Maciej . Kostrzewska . Jadwiga . May 2019 . Probabilistic electricity price forecasting with Bayesian stochastic volatility models . Energy Economics . en . 80 . 610–620 . 10.1016/j.eneco.2019.02.004. 2019EneEc..80..610K .
  65. Janczura . Joanna . Puć . Andrzej . 2023-01-10 . ARX-GARCH Probabilistic Price Forecasts for Diversification of Trade in Electricity Markets—Variance Stabilizing Transformation and Financial Risk-Minimizing Portfolio Allocation . Energies . en . 16 . 2 . 807 . 10.3390/en16020807 . free . 1996-1073.
  66. Billé . Anna Gloria . Gianfreda . Angelica . Del Grosso . Filippo . Ravazzolo . Francesco . April 2023 . Forecasting electricity prices with expert, linear, and nonlinear models . International Journal of Forecasting . en . 39 . 2 . 570–586 . 10.1016/j.ijforecast.2022.01.003.
  67. Maciejowska . Katarzyna . Weron . Rafał . September 2015 . Forecasting of daily electricity prices with factor models: utilizing intra-day and inter-zone relationships . Computational Statistics . en . 30 . 3 . 805–819 . 10.1007/s00180-014-0531-0 . 0943-4062. free .
  68. Maciejowska . Katarzyna . 2022 . Portfolio management of a small RES utility with a structural vector autoregressive model of electricity markets in Germany . Operations Research and Decisions . en . 32 . 4 . 10.37190/ord220405 . 2081-8858.
  69. Uniejewski . Bartosz . Maciejowska . Katarzyna . October 2023 . LASSO principal component averaging: A fully automated approach for point forecast pooling . International Journal of Forecasting . en . 39 . 4 . 1839–1852 . 10.1016/j.ijforecast.2022.09.004. 2207.04794 .
  70. Liebl . Dominik . 2013-09-01 . Modeling and forecasting electricity spot prices: A functional data perspective . The Annals of Applied Statistics . 7 . 3 . 10.1214/13-AOAS652 . 1932-6157. 1310.1628 .
  71. Chen . Ying . Li . Bo . 2017-07-03 . An Adaptive Functional Autoregressive Forecast Model to Predict Electricity Price Curves . Journal of Business & Economic Statistics . en . 35 . 3 . 371–388 . 10.1080/07350015.2015.1092976 . 0735-0015.
  72. Lisi . Francesco . Shah . Ismail . November 2020 . Forecasting next-day electricity demand and prices based on functional models . Energy Systems . en . 11 . 4 . 947–979 . 10.1007/s12667-019-00356-w . 1868-3967.
  73. Day-ahead price forecasting of electricity markets by a new fuzzy neural network. IEEE Transactions on Power Systems. 2006. 0885-8950. 887–896. 21. 2. 10.1109/TPWRS.2006.873409. N.. Amjady. 2006ITPSy..21..887A. 31604774.
  74. Keles. Dogan. Scelle. Jonathan. Paraschiv. Florentina. Fichtner. Wolf. 2016. Extended forecast methods for day-ahead electricity spot prices applying artificial neural networks. Applied Energy. 162. 218–230. 10.1016/j.apenergy.2015.09.087. 2016ApEn..162..218K .
  75. Hubicka . Katarzyna . Marcjasz . Grzegorz . Weron . Rafal . January 2019 . A Note on Averaging Day-Ahead Electricity Price Forecasts Across Calibration Windows . IEEE Transactions on Sustainable Energy . 10 . 1 . 321–323 . 10.1109/TSTE.2018.2869557 . 2019ITSE...10..321H . 1949-3029.
  76. Marcjasz . Grzegorz . Uniejewski . Bartosz . Weron . Rafał . October 2019 . On the importance of the long-term seasonal component in day-ahead electricity price forecasting with NARX neural networks . International Journal of Forecasting . en . 35 . 4 . 1520–1532 . 10.1016/j.ijforecast.2017.11.009.
  77. Wang . Long . Zhang . Zijun . Chen . Jieqiu . July 2017 . Short-Term Electricity Price Forecasting With Stacked Denoising Autoencoders . IEEE Transactions on Power Systems . 32 . 4 . 2673–2681 . 10.1109/TPWRS.2016.2628873 . 2017ITPSy..32.2673W . 0885-8950.
  78. Olivares . Kin G. . Challu . Cristian . Marcjasz . Grzegorz . Weron . Rafał . Dubrawski . Artur . April 2023 . Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx . International Journal of Forecasting . en . 39 . 2 . 884–900 . 10.1016/j.ijforecast.2022.03.001. 2104.05522 .
  79. Marcjasz . Grzegorz . Narajewski . Michał . Weron . Rafał . Ziel . Florian . September 2023 . Distributional neural networks for electricity price forecasting . Energy Economics . en . 125 . 106843 . 10.1016/j.eneco.2023.106843. 2207.02832 . 2023EneEc.12506843M .
  80. Energy price forecasting in the Ontario competitive power system market. IEEE Transactions on Power Systems. 2004. 0885-8950. 366–374. 19. 1. 10.1109/TPWRS.2003.821470. C.P.. Rodriguez. G.J.. Anders. 2004ITPSy..19..366R. 40031638.
  81. Mid-term electricity market clearing price forecasting: A hybrid LSSVM and ARMAX approach. International Journal of Electrical Power & Energy Systems. 2013. 20–26. 53. 10.1016/j.ijepes.2013.04.006. Xing. Yan. Nurul A.. Chowdhury. 2013IJEPE..53...20Y .
  82. Janczura. Joanna. Trück. Stefan. Weron. Rafał. Wolff. Rodney C.. 2013. Identifying spikes and seasonal components in electricity spot price data: A guide to robust modeling. Energy Economics. 38. 96–110. 10.1016/j.eneco.2013.03.013. 2013EneEc..38...96J .
  83. Nowotarski. Jakub. Weron. Rafał. 2016. On the importance of the long-term seasonal component in day-ahead electricity price forecasting. Energy Economics. 57. 228–235. 10.1016/j.eneco.2016.05.009. 2016EneEc..57..228N . 64028618 .
  84. Nowotarski. Jakub. Tomczyk. Jakub. Weron. Rafał. 2013. Robust estimation and forecasting of the long-term seasonal component of electricity spot prices. Energy Economics. 39. 13–27. 10.1016/j.eneco.2013.04.004. 2013EneEc..39...13N . 40459495 .
  85. Lisi. Francesco. Nan. Fany. 2014. Component estimation for electricity prices: Procedures and comparisons. Energy Economics. 44. 143–159. 10.1016/j.eneco.2014.03.018. 2014EneEc..44..143L .
  86. Weron. Rafał. Zator. Michał. 2015. A note on using the Hodrick–Prescott filter in electricity markets. Energy Economics. 48. 1–6. 10.1016/j.eneco.2014.11.014. 2015EneEc..48....1W .
  87. Gianfreda. Angelica. Grossi. Luigi. 2012. Forecasting Italian electricity zonal prices with exogenous variables. Energy Economics. 34. 6. 2228–2239. 10.1016/j.eneco.2012.06.024. 2012EneEc..34.2228G . 1814/25076. free.
  88. Ziel. Florian. Steinert. Rick. Husmann. Sven. 2015. Efficient modeling and forecasting of electricity spot prices. Energy Economics. 47. 98–111. 10.1016/j.eneco.2014.10.012. 1402.7027. 2015EneEc..47...98Z . 153565992.
  89. Energy price forecasting - problems and proposals for such predictions. IEEE Power and Energy Magazine. 2006. 1540-7977. 20–29. 4. 2. 10.1109/MPAE.2006.1597990. N.. Amjady. M.. Hemmati.
  90. Uniejewski. Bartosz. Nowotarski. Jakub. Weron. Rafał. 2016-08-05. Automated Variable Selection and Shrinkage for Day-Ahead Electricity Price Forecasting. Energies. en. 9. 8. 621. 10.3390/en9080621. free.
  91. Book: An Introduction to Statistical Learning with Applications in R. 103. James. Gareth. Witten. Daniela. Hastie. Trevor. Tibshirani. Robert. Springer. 2013. 978-1-4614-7137-0. 10.1007/978-1-4614-7138-7. Springer Texts in Statistics. 62973643 .
  92. Karakatsani. Nektaria V.. Bunn. Derek W.. 2008. Forecasting electricity prices: The impact of fundamentals and time-varying coefficients. International Journal of Forecasting. Energy Forecasting. 24. 4. 764–785. 10.1016/j.ijforecast.2008.09.008.
  93. Bessec. Marie. Fouquau. Julien. Meritet. Sophie. 2016. Forecasting electricity spot prices using time-series models with a double temporal segmentation. Applied Economics. 48. 5. 361–378. 10.1080/00036846.2015.1080801. 0003-6846. 52217843.
  94. Book: Barnes. A. K.. Balda. J. C.. 2013 4th IEEE International Symposium on Power Electronics for Distributed Generation Systems (PEDG) . Sizing and economic assessment of energy Storage with real-time pricing and ancillary services . 2013. 1–7. 10.1109/PEDG.2013.6785651. 978-1-4799-0692-5. 16068022.
  95. Ludwig. Nicole. Feuerriegel. Stefan. Neumann. Dirk. 2015. Putting Big Data analytics to work: Feature selection for forecasting electricity prices using the LASSO and random forests. Journal of Decision Systems. 24. 1. 19–36. 10.1080/12460125.2015.994290. 1246-0125. 20.500.11850/182404. 20620071. free.
  96. Gaillard. Pierre. Goude. Yannig. Nedellec. Raphaël. 2016. Additive models and robust aggregation for GEFCom2014 probabilistic electric load and electricity price forecasting. International Journal of Forecasting. 32. 3. 1038–1050. 10.1016/j.ijforecast.2015.12.001.
  97. Ziel. F.. 2016. Forecasting Electricity Spot Prices Using Lasso: On Capturing the Autoregressive Intraday Structure. IEEE Transactions on Power Systems. 31. 6. 4977–4987. 10.1109/TPWRS.2016.2521545. 0885-8950. 1509.01966. 2016ITPSy..31.4977Z. 30350943.
  98. 25 years of time series forecasting. International Journal of Forecasting. 2006. 443–473. 22. Twenty five years of forecasting. 3. 10.1016/j.ijforecast.2006.01.001. Jan G.. De Gooijer. Rob J.. Hyndman. 10.1.1.154.9227. 14996235 .
  99. Global Energy Forecasting Competition 2012. International Journal of Forecasting. 2014. 357–363. 30. 2. 10.1016/j.ijforecast.2013.07.001. Tao. Hong. Pierre. Pinson. Shu. Fan.
  100. Computing electricity spot price prediction intervals using quantile regression and forecast averaging. Computational Statistics. 2015. 0943-4062. 791–803. 30. 3. 10.1007/s00180-014-0523-0. Jakub. Nowotarski. Rafał. Weron. [Open Access]. 122926112. free.
  101. Using combined forecasts with changing weights for electricity demand profiling. Journal of the Operational Research Society. 72–82. 51. 1. 10.1057/palgrave.jors.2600856. J W. Taylor. S. Majithia. 2000. 10.1.1.501.5706. 8165916.
  102. Combining day-ahead forecasts for British electricity prices. Energy Economics. 2013. 88–103. 35. Quantitative Analysis of Energy Markets. 10.1016/j.eneco.2011.12.001. Silvano. Bordignon. Derek W.. Bunn. Francesco. Lisi. Fany. Nan. 2013EneEc..35...88B . 11577/3442493 .
  103. An empirical comparison of alternative schemes for combining electricity spot price forecasts. Energy Economics. 2014. 395–412. 46. 10.1016/j.eneco.2014.07.014. Jakub. Nowotarski. Eran. Raviv. Stefan. Trück. Rafał. Weron. 2014EneEc..46..395N .
  104. Forecasting of daily electricity prices with factor models: utilizing intra-day and inter-zone relationships. Computational Statistics. 2015. 0943-4062. 805–819. 30. 3. 10.1007/s00180-014-0531-0. Katarzyna. Maciejowska. Rafał. Weron. [Open Access]. free.
  105. Forecasting day-ahead electricity prices: Utilizing hourly prices. Energy Economics. 2015. 227–239. 50. 10.1016/j.eneco.2015.05.014. Eran. Raviv. Kees E.. Bouwman. Dick. van Dijk. 2015EneEc..50..227R . 1765/40407.