The economic benefit of short-term forecasting for wind energy in the UK electricity market

In the UK market, the total price of renewable electricity is made up of the Renewables Obligation Certificate and the price achieved for the electricity. Accurate forecasting improves the price if electricity is traded via the power exchange. In order to understand the size of wind farm for which short-term forecasting becomes economically viable, we develop a model for wind energy. Simulations were carried out for 2003 electricity prices for different forecast accuracies and strategies. The results indicate that it is possible to increase the price obtained by around £5/MWh which is about 14% of the electricity price in 2003 and about 6% of the total price. We show that the economic benefit of using short-term forecasting is also dependant on the accuracy and cost of purchasing the forecast. As the amount of wind energy requiring integration into the grid increases, short-term forecasting becomes more important to both wind farm owners and the transmission/distribution operators.     

Data analysis and short term load forecasting in Iran electricity market using singular spectral analysis (SSA)

In this paper, the data analysis and short term load forecasting (STLF) in Iran electricity market has been considered. The proposed method is an improved singular spectral analysis (SSA) method. SSA decomposes a time series into its principal components i.e. its trend and oscillation components, which are then used for time series forecasting, effectively. The employed data are the total load time series of Iran electricity market in its real size and is long enough to make it possible to take properties such as non-stationary and annual periodicity of the market into account. Simulation results show that the proposed method has a good ability in characterizing and prediction of the desired load time series in comparison with some other related methods.     

基于有偏t分布ARIVIAX模型的短期电价预测

基于正态分布假设的时间序列分析模型不能有效地处理电价的有偏厚尾性,在对电力市场现货电价的影响因素和波动规律综合分析的基础上,提出了一种基于有偏学生t分布ARMAX模型的短期电价预测方法。该方法可同时考虑电价分布的有偏厚尾性、多重周期性及其与负荷之间的非线性相关性。对PJM电力市场历史数据的算例研究表明,该方法计算量小,待估参数少。     

基于有偏t分布ARMAX模型的短期电价预测

基于正态分布假设的时间序列分析模型不能有效地处理电价的有偏厚尾性,在对电力市场现货电价的影响因素和波动规律综合分析的基础上,提出了一种基于有偏学生t分布ARMAX模型的短期电价预测方法.该方法可同时考虑电价分布的有偏厚尾性、多重周期性及其与负荷之间的非线性相关性.对PJM电力市场历史数据的算例研究表明,该方法计算量小,待估参数少.     

电价预测技术综述

电力工业从垄断走向市场,使得电价不再由政府确定,而是在市场机制下产生。电价波动会影响市场参与者的经济利益。对电力市场参与者而言,准确地预测电价具有非常重要的意义。该论文以电力系统短期边际价格为主要研究对象。首先分析了电价的变化特点、影响电价的主要因素,明确电价变化的规律性。然后介绍了一些现有因素分析的方法。并对当前电价预测方法按其工作原理进行分类总结,最后根据各类电价预测模型的特点尤其利用神经网络方法建立的预测模型进行了深入分析和总结。     

Distributional modeling and short-term forecasting of electricity prices by Generalized Additive Models for Location, Scale and Shape

In the context of the liberalized and deregulated electricity markets, price forecasting has become increasingly important for energy company's plans and market strategies. Within the class of the time series models that are used to perform price forecasting, the subclasses of methods based on stochastic time series and causal models commonly provide point forecasts, whereas the corresponding uncertainty is quantified by approximate or simulation-based confidence intervals. Aiming to improve the uncertainty assessment, this study introduces the Generalized Additive Models for Location, Scale and Shape (GAMLSS) to model the dynamically varying distribution of prices. The GAMLSS allow fitting a variety of distributions whose parameters change according to covariates via a number of linear and nonlinear relationships. In this way, price periodicities, trends and abrupt changes characterizing both the position parameter (linked to the expected value of prices), and the scale and shape parameters (related to price volatility, skewness, and kurtosis) can be explicitly incorporated in the model setup. Relying on the past behavior of the prices and exogenous variables, the GAMLSS enable the short-term (one-day ahead) forecast of the entire distribution of prices. The approach was tested on two datasets from the widely studied California Power Exchange (CalPX) market, and the less mature Italian Power Exchange (IPEX). CalPX data allow comparing the GAMLSS forecasting performance with published results obtained by different models. The study points out that the GAMLSS framework can be a flexible alternative to several linear and nonlinear stochastic models.     

A new recursive neural network algorithm to forecast electricity price for PJM day‐ahead market

This paper evaluates the usefulness of publicly available electricity market information in predicting the hourly prices in the PJM day‐ahead electricity market using recursive neural network (RNN) technique, which is based on similar days (SD) approach. RNN is a multi‐step approach based on one output node, which uses the previous prediction as input for the subsequent forecasts. Comparison of forecasting performance of the proposed RNN model is done with respect to SD method and other literatures. To evaluate the accuracy of the proposed RNN approach in forecasting short‐term electricity prices, different criteria are used. Mean absolute percentage error, mean absolute error and forecast mean square error (FMSE) of reasonably small values were obtained for the PJM data, which has correlation coefficient of determination (R²) of 0.7758 between load and electricity price. Error variance, one of the important performance criteria, is also calculated in order to measure robustness of the proposed RNN model. The numerical results obtained through the simulation to forecast next 24 and 72 h electricity prices show that the forecasts generated by the proposed RNN model are significantly accurate and efficient, which confirm that the proposed algorithm performs well for short‐term price forecasting. Copyright © 2009 John Wiley & Sons, Ltd.     

The future developments of the electricity prices in view of the implementation of the Paris Agreements: Will the current trends prevail,or a reversal is ahead?

We assess the impact on the European electricity market of the European Union “Clean energy for all Europeans” package, which implements the EU Nationally Determined Contribution in Paris COP 21. We focus on the year 2030, which is the year with defined climate targets. For the assessment, we employ a game-theoretic framework of the wholesale electricity market, with high technical detail. The model is applied to two core scenarios, a Base scenario and a Low Carbon scenario to provide insights regarding the future electricity capacity, generation mix, cross-border trade and electricity prices. We also assess three additional variants of the core scenarios concerning different levels of: a) fossil and CO₂ prices; b) additional flexibility provided by batteries; c) market integration. We find that the electricity prices in 2030 substantially increase from today's level, driven by the increase in fuel and CO₂ prices. The flexibility from batteries helps in mitigating the price peaks and the price volatility. The increased low marginal cost electricity generation, the expansion of non-dispatchable and distributed capacities, and the higher market integration further reduce the market power from producers in the electricity markets from today's level.     

Frequency domain methods applied to forecasting electricity markets

The changes taking place in electricity markets during the last two decades have produced an increased interest in the problem of forecasting, either load demand or prices. Many forecasting methodologies are available in the literature nowadays with mixed conclusions about which method is most convenient. This paper focuses on the modeling of electricity market time series sampled hourly in order to produce short-term (1 to 24 h ahead) forecasts. The main features of the system are that (i) models are of an Unobserved Component class that allow for signal extraction of trend, diurnal, weekly and irregular components; (ii) its application is automatic, in the sense that there is no need for human intervention via any sort of identification stage; (iii) the models are estimated in the frequency domain; and (iv) the robustness of the method makes possible its direct use on both load demand and price time series. The approach is thoroughly tested on the PJM interconnection market and the results improve on classical ARIMA models.     

On the importance of the long-term seasonal component in day-ahead electricity price forecasting

In day-ahead electricity price forecasting (EPF) the daily and weekly seasonalities are always taken into account, but the long-term seasonal component (LTSC) is believed to add unnecessary complexity to the already parameter-rich models and is generally ignored. Conducting an extensive empirical study involving state-of-the-art time series models we show that (i) decomposing a series of electricity prices into a LTSC and a stochastic component, (ii) modeling them independently and (iii) combining their forecasts can bring – contrary to a common belief – an accuracy gain compared to an approach in which a given time series model is calibrated to the prices themselves.     

Dynamic model for market-based capacity investment decision considering stochastic characteristic of wind power

This paper proposes a decentralized market-based model for long-term capacity investment decisions in a liberalized electricity market with significant wind power generation. In such an environment, investment and construction decisions are based on price signal feedbacks and imperfect foresight of future conditions in electricity market. System dynamics concepts are used to model structural characteristics of power market such as, long-term firms’ behavior and relationships between variables, feedbacks and time delays. For conventional generation units, short-term price feedback for generation dispatching of forward market is implemented as well as long-term price expectation for profitability assessment in capacity investment. For wind power generation, a special framework is proposed in which generation firms are committed depending on the statistical nature of wind power. The method is based on the time series stochastic simulation process for prediction of wind speed using historical and probabilistic data. The auto-correlation nature of wind speed and the correlation with demand fluctuations are modeled appropriately. The Monte Carlo simulation technique is employed to assess the effect of demand growth rate and wind power uncertainties. Such a decision model enables the companies to find out the possible consequences of their different investment decisions. Different regulatory policies and market conditions can also be assessed by ISOs and regulators to check the performance of market rules. A case study is presented exhibiting the effectiveness of the proposed model for capacity expansion of electricity markets in which the market prices and the generation capacities are fluctuating due to uncertainty of wind power generation.     

On the importance of the long-term seasonal component in day-ahead electricity price forecasting: Part II — Probabilistic forecasting

A recent electricity price forecasting study has shown that the Seasonal Component AutoRegressive (SCAR) modeling framework, which consists of decomposing a series of spot prices into a trend-seasonal and a stochastic component, modeling them independently and then combining their forecasts, can yield more accurate point predictions than an approach in which the same autoregressive model is calibrated to the prices themselves. Here, we show that further accuracy gains can be achieved when the explanatory variables (load forecasts) are deseasonalized as well. More importantly, considering a novel extension of the SCAR concept to probabilistic forecasting and applying two methods of combining predictive distributions, we find that (i) SCAR-type models nearly always significantly outperform the autoregressive benchmark but are in turn outperformed by combined SCAR forecasts, (ii) predictive distributions computed using Quantile Regression Averaging (QRA) outperform those obtained from historical simulation and bootstrap methods, and (iii) averaging over predictive distributions generally yields better probabilistic forecasts of electricity spot prices than averaging over quantiles. Given that probabilistic forecasting is a concept closely related to risk management, our study has important implications for risk officers and portfolio managers in the power sector.     

Carbon price volatility: Evidence from EU ETS

This paper examines carbon price volatility using data from the European Union Emission Trading Scheme from a nonlinear dynamics point of view. First, we use a random walk model, including serial correlation and variance ratio tests, to determine whether carbon price history information is fully reflected in current carbon price. The empirical research results show that carbon price is not a random walk: the price history information is not fully reflected in current carbon price. Second, use R/S, modified R/S and ARFIMA to analyse the memory of carbon price history. For the period April 2005–December 2008, the modified Hurst index of the carbon price is 0.4859 and the d value of ARFIMA is −0.1191, indicating short-term memory of the carbon price. Third, we use chaos theory to analyse the influence of the carbon market internal mechanism on carbon price, i.e., the market’s positive and negative feedback mechanism and the heterogeneous environment. Chaos theory proves that the correlation dimension of carbon price increases. The maximal Lyapunov exponent is positive and large. There is no obvious complex endogenous phenomenon of nonlinear dynamics the carbon price fluctuation. The carbon market is mildly chaotic, showing both market and fractal market characteristics. Price fluctuation is not only influenced by the internal market mechanism, but is also impacted by the heterogeneous environment. Finally, we provide suggestions for regulation and development of carbon market.     

Demand bidding construction for a large consumer through a hybrid IGDT-probability methodology

This paper provides a technique to derive the bidding strategy in the day-ahead market for a large consumer that procures its electricity demand in both day-ahead market and a subsequent adjustment market. It is considered that hourly market prices are normally distributed and this correlation is modeled by variance–covariance matrix. The uncertainty of procurement cost is modeled using concepts derived from information gap decision theory which allows deriving robust bidding strategies with respect to price volatility. First Order Reliability Method is applied to construct the robust bidding curve. The proposed technique is illustrated through a realistic case study.     

科学分析和处理煤与电的关系

煤与电既具有正相关性,也具有负相关性,煤电价格并轨对于煤炭和电力双方都是"双刃剑",并没有从根本上解决"煤电博弈"问题,推进电价市场化改革才是理顺煤炭与煤电企业关系的治本之策。电价市场化改革,短期需要完善煤电联动机制,长期应该形成真正由供需关系决定电价的机制。为此,煤炭和煤电企业应该认清波动规律,建立双赢理念,谋签长远合同,并通过互相参股,建立深层战略合作。     

The crucial relationship among energy commodity prices: Evidence from the Spanish electricity market

The main purpose of this article is twofold to analyze: (a) the long-term relation among the commodities prices and between spot electricity market price and commodity prices, and (b) the short-term dynamics among commodity prices and between electricity prices and commodity prices. Data between 2002 and 2005 from the Spanish electricity market was used. Econometric methods were used in the analysis of the commodity spot price, namely the vector autoregression model, the vector error correction model and the granger causality test. The co-integration approach was used to analyze the long-term relationship between the common stochastic trends of four fossil fuel prices. One of the findings in the long-term relation is that the prices of fuel and the prices of Brent are intertwined, though the prices of Brent ten to “move” to reestablish the price equilibrium. Another finding is that the price of electricity is explained by the evolution of the natural gas series.     

基于DPBIL-SVM混合模型的电力现货市场出清价预测研究

为准确预测现货市场出清价,利用改进的基于种群增量学习的进化算法(DPBIL)对SVM参数进行优化,构建了基于DPBIL-SVM的混合预测模型,将该模型应用于挪威电力市场短期电价预测中,并与灰色GM(1,1)模型和BP人工神经网络模型进行比较。结果表明,所提模型能够将现货市场出清价预测误差控制在5%以下,合格率97%,效果优于灰色GM(1,1)模型和BP人工神经网络模型,符合现货市场实际报价的要求。     

Day-ahead price forecasting of electricity markets by a new feature selection algorithm and cascaded neural network technique

With the introduction of restructuring into the electric power industry, the price of electricity has become the focus of all activities in the power market. Electricity price forecast is key information for electricity market managers and participants. However, electricity price is a complex signal due to its non-linear, non-stationary, and time variant behavior. In spite of performed research in this area, more accurate and robust price forecast methods are still required. In this paper, a new forecast strategy is proposed for day-ahead price forecasting of electricity markets. Our forecast strategy is composed of a new two stage feature selection technique and cascaded neural networks. The proposed feature selection technique comprises modified Relief algorithm for the first stage and correlation analysis for the second stage. The modified Relief algorithm selects candidate inputs with maximum relevancy with the target variable. Then among the selected candidates, the correlation analysis eliminates redundant inputs. Selected features by the two stage feature selection technique are used for the forecast engine, which is composed of 24 consecutive forecasters. Each of these 24 forecasters is a neural network allocated to predict the price of 1 h of the next day. The whole proposed forecast strategy is examined on the Spanish and Australia’s National Electricity Markets Management Company (NEMMCO) and compared with some of the most recent price forecast methods.     

Energy resources’ seasonal/daily dependencies under coupled operation of day-ahead markets

ABSTRACT

Studies on the benefits of electricity markets integration are scarce. With particular attention to the Romanian day-ahead electricity market (DAM), we analyze electricity prices’ seasonality and volatility and observe whether changes occurred after the 4 M Market Coupling project implementation. The focus lies on assessing the seasonal and cyclical components of DAM prices and coal/wind-based electricity generation. We address the changes in time series’ models that occurred after the DAM coupling and determine stationary models for those time series. The Dickey–Fuller test, augmented with qualitative variables assigned to seasons, days of the week, and legal holidays is our proposed method. Market integration could not prevent price spikes. The post-coupling period is characterized by smaller differences between peak and off-peak prices. This might indicate a positive effect (ceteris paribus) of market coupling on reducing price volatility. Most price models show complex dependencies on seasons, days, and dummies.     

考虑风电并网的分时段短期电价预测

考虑了并网风电量对电价影响,并将相关系数作为选取电价影响因素的标准,考虑了历史电价、负荷、并网风电量与负荷的比值等影响电价的因素。分别将负荷与历史清算电价,等效负荷与历史清算电价,负荷、并网风电量与负荷的比值及历史清算电价作为神经网络的输入因子对市场清算电价进行分时段预测。算例采用丹麦电力市场的历史数据,分别对其2010年并网风电量所占比例较大和较小的日期进行预测,验证了选择负荷、并网风电量与负荷的比值及历史清算电价作为预测神经网络的输入变量是恰当的,其预测精度能够满足电力市场实际运行的需要。