Spot Price Forecasting Research Articles

Time series analysis for COMEX platinum spot price forecasting using SVM, MARS, MLP, VARMA and ARIMA models: A case study

This article looks at predicting the price of platinum, along with 12 other commodity prices, using both time series and machine learning models. Platinum, characterised by its rarity and significant industrial and artistic value, occupies a unique position among chemical elements. This research contributes to econometrics by showing the effectiveness of advanced modelling techniques in predicting precious metal prices, providing valuable insights for the field. Platinum prices are volatile, yet they serve as a crucial indicator of the global economy. Fluctuations in the platinum price can signal increased global growth or an impending economic downturn. The study focuses on the forecasting of platinum spot prices from the New York Commodity Exchange, using various time series machine learning models (MARS, SVM and MLP) as well as classical techniques (ARIMA and VARMA). In particular, the Artificial Neural Network (MLP) model emerges as the best performing model, with the highest predictive accuracy and a Root Mean Square Error (RMSE) of 9.24. The ARIMA time series model, on the other hand, is the worst performer with an RMSE of 74.94. The superior accuracy of the MLP method underlines its ability to identify complex relationships between platinum and other commodities. This research highlights the potential of machine learning techniques, particularly MLP, in accurately forecasting the price of platinum, with benefits for investors, industry professionals and policymakers alike.

Improving Amazon EC2 Spot Instances Price Prediction using Machine Learning Algorithm

Spot instances were introduced by Amazon EC2 in December 2009 to sell its spare capacity through auction based market mechanism. Despite its extremely low prices, cloud spot market has low utilization. Spot pricing being dynamic, spot instances are prone to out-of bid failure. Bidding complexity is another reason why users today still fear using spot instances. This work aims to present Regression Random Forests (RRFs) model to predict one-week-ahead and one-day-ahead spot prices. The prediction would assist cloud users to plan in advance when to acquire spot instances, estimate execution costs, and also assist them in bid decision making to minimize execution costs and out-of-bid failure probability. Simulations with 12 months real Amazon EC2 spot history traces to forecast future spot prices show the effectiveness of the proposed technique. Comparison of RRFs based spot price forecasts with existing non-parametric machine learning models reveal that RRFs based forecast accuracy outperforms other models. We measure predictive accuracy using MAPE, MCPE, OOBError and speed. Evaluation results show that

A Crude Oil Spot Price Forecasting Method Incorporating Quadratic Decomposition and Residual Forecasting

The world economy is affected by fluctuations in the price of crude oil, making precise and effective forecasting of crude oil prices essential. In this study, we propose a combined forecasting scheme, which combines a quadratic decomposition and optimized support vector regression (SVR). In the decomposition part, the original crude oil price series are first decomposed using empirical modal decomposition (CEEMDAN), and then the residuals of the first decomposition (RES) are decomposed using variational modal decomposition (VMD). Additionally, this work proposes to optimize the support vector regression model (SVR) by the seagull optimization algorithm (SOA). Ultimately, the empirical investigation created the feature-variable system and predicted the filtered features. By computing evaluation indices like MAE, MSE, R2, and MAPE and validating using Brent and WTI crude oil spot, the prediction errors of the CEEMDAN -RES.-VMD -SOA-SVR combination prediction model presented in this paper are assessed and compared with those of the other twelve comparative models. The empirical evidence shows that the combination model being proposed in this paper outperforms the other related comparative models and improves the accuracy of the crude oil price forecasting model.

ATTnet: An explainable gated recurrent unit neural network for high frequency electricity price forecasting

The primary contribution of this study is the proposal of an explainable deep-learning neural network (ATTnet) that employs an attention mechanism to achieve accurate electricity spot price forecasting and an explainable model pipeline. The concise, single-stream network consists of a 5-head attention mechanism and gated recurrent units, which have been developed to model the temporal dependencies of the volatile market data. In addition to introducing a novel neural network architecture for volatile time series data, this study makes a substantial contribution by investigating prediction factors in two ways: temporally via the attention scores from the input sequences and globally via feature Shapely values. In real-time electricity price prediction, historical prices, temperature, hour, and zonal load are found to be the most important variables. The deep learning model was tested on real-time price profiles from eight generators within the New York Independent System Operator (NYISO) network. The proposed model achieves performance gains of 21% in MAE and 22% in MAPE over the state-of-the-art benchmark methods.

A Novel Model for Spot Price Forecast of Natural Gas Based on Temporal Convolutional Network

Natural gas is often said to be the most environmentally friendly fossil fuel. Its usage has increased significantly in recent years. Meanwhile, accurate forecasting of natural gas spot prices has become critical to energy management, economic growth, and environmental protection. This work offers a novel model based on the temporal convolutional network (TCN) and dynamic learning rate for predicting natural gas spot prices over the following two weekdays. The residual block structure of TCN provides good prediction accuracy, and the dilated causal convolutions minimize the amount of computation. The dynamic learning rate setting was adopted to enhance the model’s prediction accuracy and robustness. Compared with three existing models, i.e., the one-dimensional convolutional neural network (1D-CNN), gate recurrent unit (GRU), and long short-term memory (LSTM), the proposed model can achieve better performance over other models with mean absolute percentage error (MAPE), mean absolute error (MAE), and root mean squared error (RMSE) scores of 4.965%, 0.216, and 0.687, respectively. These attractive advantages make the proposed model a promising candidate for long-term stability in natural gas spot price forecasting.

Comparison of exponential smoothing methods in forecasting global prices of main metals

Metals are indispensable raw materials for industry and have strategic importance in economic development. The price forecasting of metals is crucial for the production sector and production policies of countries. The paper presents the application of various exponential smoothing methods to metal spot price forecasting. Aluminum, copper, lead, iron, nickel, tin, and zinc prices were analyzed by using yearly data from 1990 to 2021. The root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE) values of the models were obtained and their performances were compared to determine the appropriate model for each metal price. These metal prices were forecasted up to 2030 by using the best-fitted models.

Electricity Spot Price Modeling and Forecasting in European Markets

In many competitive electricity markets around the world, the dynamic behavior of hourly electricity prices is subject to significant uncertainty and volatility due to electricity demand, availability of generation sources, fuel costs, and power plant availability. This work is devoted to describing and comparing the dynamics of electricity prices for some markets in Europe, selecting the five countries representing the largest economies in Western Europe (France, Germany, Italy, Spain, and the United Kingdom). Additionally, Denmark is included in the study to assess whether the size of the country is a determinant of price behavior. The six datasets of hourly price series, which exhibits a strong daily seasonality, are modelled using the most relevant well-known statistical models for time series analysis: ARIMA models and different versions of GARCH models. The comparison of the estimated models’ parameters, the analysis of outliers’ rate of appearance and the evaluation of out-of-sample one-day-ahead forecast let us draw some insightful similarities and dissimilarities between the analyzed countries.

Electricity Spot Price Forecast by Modelling Supply and Demand Curve

Electricity price forecasting has been a booming field over the years, with many methods and techniques being applied with different degrees of success. It is of great interest to the industry sector, becoming a must-have tool for risk management. Most methods forecast the electricity price itself; this paper gives a new perspective to the field by trying to forecast the dynamics behind the electricity price: the supply and demand curves originating from the auction. Given the complexity of the data involved which include many block bids/offers per hour, we propose a technique for market curve modeling and forecasting that incorporates multiple seasonal effects and known market variables, such as wind generation or load. It is shown that this model outperforms the benchmarked ones and increases the performance of ensemble models, highlighting the importance of the use of market bids in electricity price forecasting.

Empirical study of day-ahead electricity spot-price forecasting: Insights into a novel loss function for training neural networks

Within deregulated economies, large electricity volumes are traded in daily spot markets, which are highly volatile. To develop profitable trading strategies, all stakeholders must be empowered with robust forecasting tools. Although neural network approaches have become increasingly popular for time-series forecasting, they do not optimally capture unique features of financial datasets. A major factor hindering their performance is the choice of the backpropagation loss function. We performed a systematic and empirical study of loss functions that can optimize the forecasting of day-ahead electricity spot prices. We first outlined a set of properties that such a loss function should meet. We proposed Theil UII-S as a novel loss function, which is derived from Theil’s forecast accuracy coefficient. We also implemented five neural network models and trained them on the two most used loss functions—mean squared error and mean absolute error—and our Theil UII-S. We finally tested our models on a real dataset of the electricity spot market of Norway. Our results show that Theil UII-S provides more accurate forecasts on the average, best, and, worst case scenarios, converges faster, is twice differentiable, and has a variable gradient.

Understanding the Impact of Spot Market Electricity Price on Wastewater Asset Management Strategy

Development of an advanced pumping control scheme is one of the useful methods that can be applied in operational optimisation of wastewater pumps. Optimisation of pumping control can benefit the utility by overall cost saving using different electricity pricing schemes from the energy market. As electricity prices can be varied based on the spot market in some countries such as Australia, the consideration of operating the pumps at the most favourable electricity price, when managed correctly, can offer remarkable savings. This paper provides understanding on the electricity spot price behaviour of South Australia in the National Electricity Market (NEM). Half-hourly electricity spot price data of over 22 years from January 1999 to June 2021 were analysed to investigate the key characteristics of spot prices, including seasonality (intraday, intraweek and seasonal price patterns), spiky behaviour and occurrences of negative prices. In addition, the possible impacts of other factors on electricity spot prices such as electricity demand and weather conditions on pump control were examined. Results indicate a strong relationship between electricity demand and spot price with the Pearson correlation coefficient up to R = 0.95, and extreme high spot prices tended to occur on scorching days with the maximum temperature above 35 °C when air-conditioner usage was high. This paper also explains the importance of electricity spot prices in the wastewater pump on/off operations and analyses opportunities for cost savings by including electricity spot price forecasts as an input of the smart controller to enhance the efficiency of the real-time pumping control.

Forecasting day-ahead electricity prices: A comparison of time series and neural network models taking external regressors into account

The amount of renewable energies in electricity production has increased significantly in the last decade, resulting in more variability of the day-ahead electricity spot price. The Electricity Price Forecast (EPF) has to adapt to the new situation by applying flexible models. However, the numerous available forecasting methods differ widely, with no distinct candidate offering the best solution. Against this background, we conduct a comparative study of four different approaches to forecasting the German day-ahead electricity spot price. In addition to the prominent Seasonal Integrated Auto-Regressive Moving Average model ((S)ARIMA(X)) and the Long-Short Term Memory (LSTM) neural network models, we employ a Convolutional Neural Network LSTM (CNN-LSTM) and an extended two-stage multivariate Vector Auto-Regressive model (VAR) approach as hybrid models. For better performance, we include common external influences such as the consumer load, fuel and CO2 emission prices, average solar radiation and wind speed in our analysis. We analyse hourly data for twelve samples from October 2017 to September 2018. Each model is implemented to deliver price forecasts at three horizons, i.e., one day, seven days and thirty days ahead. While the LSTM model achieves the best forecasting performance on average, the two-stage VAR follows closely behind and performs exceedingly well for shorter prediction horizons. Further, we provide evidence that a combination of both forecasting methods outperforms each of the single models. This indicates that combining advanced methods could lead to further improvements in electricity spot price forecasts.

Financial Risk Control of Hydro Generation Systems through Market Intelligence and Stochastic Optimization

In the competitive electricity wholesale market, decisions regarding hydro generators are generally made under uncertain conditions, such as pool price, hydrological affluence, and other players’ strategies. From this perspective, this work presents a computational model formulation with associated market intelligence and game theory tools to support a decision-making process in a competitive environment. The idea behind using a market intelligence tool is to apply a stochastic optimization model with an associated conditional value at risk metric defining a utility function, which calculates the weight that the agents attribute to each stochastic variable associated with the problem to be faced. Subsequently, this utility function is used to emulate the other agents’ strategies based on their previous decisions. The final step finds the Nash equilibrium solution between a player and their competitors. The methodology is applied to the monthly allocation of firm energy by hydro generators under the current Brazilian regulatory framework. The results show a change in the generators’ behavior over the years, from risk-neutral agents seeking to maximize their return with 88% of decisions based on spot price forecasts in 2015, to risk-averse agents with 100% of decisions following a factor that is directly impacted by the hydrological affluence forecasts in 2018.

Enhancing load, wind and solar generation for day-ahead forecasting of electricity prices

In recent years, a rapid development of renewable energy sources (RES) has been observed across the world. Intermittent energy sources, which depend strongly on weather conditions, induce additional uncertainty to the system and impact the level and variability of electricity prices. Predictions of RES, together with the level of demand, have been recognized as one of the most important determinants of future electricity prices. In this research, it is shown that forecasts of these fundamental variables, which are published by Transmission System Operators (TSO), are biased and could be improved with simple regression models. Enhanced predictions are next used for forecasting of spot and intraday prices in Germany. The results indicate that improving the forecasts of fundamentals leads to more accurate predictions of both, the spot and the intraday prices. Finally, it is demonstrated that utilization of enhanced forecasts is helpful in a day-ahead choice of a market (spot or intraday), and results in a substantial increase of revenues.

Step‐ahead spot price densities using daily synchronously reported prices and wind forecasts

AbstractThis paper uses non‐linear methodologies to follow the synchronously reported relationship between the Nordic/Baltic electric daily spot auction prices and geographical relevant wind forecasts in MWh from early 2013 to 2020. It is a well‐known market (auctions) microstructure fact that the daily wind forecasts are information available to the market before the daily auction bid deadline at 11 a.m. The main objective is therefore to establish conditional and marginal step ahead spot price density forecast using a stochastic representation of the lagged, synchronously reported and stationary spot price and wind forecast movements. Using an upward expansion path applying the Schwarz (Bayesian information criterion [BIC]) criterion and a battery of residual test statistics, an optimal maximum likelihood process density is suggested. The optimal specification reports a significant negative covariance between the daily price and wind forecast movements. Conditional on bivariate lags from the SNP information and using the known market information for wind forecast movements at t1, the paper establishes one‐step‐ahead bivariate and marginal day‐ahead spot price movement densities. The result shows that wind forecasts significantly influence the synchronously reported spot price densities (means and volatilities). The paper reports day‐ahead bivariate and marginal densities for spot price movements conditional on several very plausible price and wind forecast movements. The paper suggests day‐ahead spot price predictions from conditional and synchronously reported wind forecasts movements. The information should increase market participants spot market insight and consequently make spot price predictions more accurate and the confidence interval considerably narrower.

High-Resolution Electricity Spot Price Forecast for the Danish Power Market

Energy markets with a high penetration of renewables are more likely to be challenged by price variations or volatility, which is partly due to the stochastic nature of renewable energy. The Danish electricity market (DK1) is a great example of such a market, as 49% of the power production in DK1 is based on wind power, conclusively challenging the electricity spot price forecast for the Danish power market. The energy industry and academia have tried to find the best practices for spot price forecasting in Denmark, by introducing everything from linear models to sophisticated machine-learning approaches. This paper presents a linear model for price forecasting—based on electricity consumption, thermal power production, wind production and previous electricity prices—to estimate long-term electricity prices in electricity markets with a high wind penetration levels, to help utilities and asset owners to develop risk management strategies and for asset valuation.

Amazon EC2 Spot Price Prediction Using Regression Random Forests

Spot instances were introduced by Amazon EC2 in December 2009 to sell its spare capacity through auction based market mechanism. Despite its extremely low prices, cloud spot market has low utilization. Spot pricing being dynamic, spot instances are prone to out-of bid failure. Bidding complexity is another reason why users today still fear using spot instances. This work aims to present Regression Random Forests (RRFs) model to predict one-week-ahead and one-day-ahead spot prices. The prediction would assist cloud users to plan in advance when to acquire spot instances, estimate execution costs, and also assist them in bid decision making to minimize execution costs and out-of-bid failure probability. Simulations with 12 months real Amazon EC2 spot history traces to forecast future spot prices show the effectiveness of the proposed technique. Comparison of RRFs based spot price forecasts with existing non-parametric machine learning models reveal that RRFs based forecast accuracy outperforms other models. We measure predictive accuracy using MAPE, MCPE, OOB Error and speed. Evaluation results show that MAPE <; = 10% for 66 to 92 percent and MCPE <; = 15% for 35 to 81 percent of one-day-ahead predictions with prediction time less than one second. MAPE <; = 15% for 71 to 96 percent of one-week-ahead predictions.

Spot Price Forecasting in a Restructured Electricity Market: An Artificial Neural Network Approach

Spot Price Forecasting in a Restructured Electricity Market: An Artificial Neural Network Approach

Probabilistic electricity price forecasting with Bayesian stochastic volatility models

The study is focused on probabilistic forecasts of day-ahead electricity prices. The Bayesian approach allows for conducting statistical inference about model parameters, latent volatility, jump times and their sizes. Moreover, the Bayesian forecasting takes into account uncertainty of parameter estimation. Using the PJM data sets we demonstrate that Bayesian stochastic volatility model with double exponential distribution of jumps and exogenous variables outperforms the non-Bayesian individual autoregressive models as well as three averaging schemes of spot price forecasts. We argue that the structure is a promising tool of modelling and forecasting electricity prices.

Analysis of a Stochastic Programming Model for Optimal Hydropower System Operation under a Deregulated Electricity Market by Considering Forecasting Uncertainty

In a deregulated electricity market, optimal hydropower operation should be achieved through informed decisions to facilitate the delivery of energy production in forward markets and energy purchase level from other power producers within real-time markets. This study develops a stochastic programming model that considers the influence of uncertain streamflow on hydropower energy production and the effect of variable spot energy prices on the cost of energy purchase (energy shortfall). The proposed model is able to handle uncertainties expressed by both a probability distribution and discretized scenarios. Conflicting decisions are resolved by maximizing the expected value of net revenue, which jointly considers benefit and cost terms under uncertainty. Methodologies are verified using a case study of the Three Gorges cascade hydropower system. The results demonstrate that optimal operation policies are derived based upon systematic evaluations on the benefit and cost terms that are affected by multiple uncertainties. Moreover, near-optimal operation policy under the case of inaccurate spot price forecasts is also analyzed. The results also show that a proper policy for guiding hydropower operation seeks the best compromise between energy production and energy purchase levels, which explores their nonlinear tradeoffs over different time periods.

Probabilistic Electricity Price Forecasting Models by Aggregation of Competitive Predictors

This article presents original probabilistic price forecasting meta-models (PPFMCP models), by aggregation of competitive predictors, for day-ahead hourly probabilistic price forecasting. The best twenty predictors of the EEM2016 EPF competition are used to create ensembles of hourly spot price forecasts. For each hour, the parameter values of the probability density function (PDF) of a Beta distribution for the output variable (hourly price) can be directly obtained from the expected and variance values associated to the ensemble for such hour, using three aggregation strategies of predictor forecasts corresponding to three PPFMCP models. A Reliability Indicator (RI) and a Loss function Indicator (LI) are also introduced to give a measure of uncertainty of probabilistic price forecasts. The three PPFMCP models were satisfactorily applied to the real-world case study of the Iberian Electricity Market (MIBEL). Results from PPFMCP models showed that PPFMCP model 2, which uses aggregation by weight values according to daily ranks of predictors, was the best probabilistic meta-model from a point of view of mean absolute errors, as well as of RI and LI. PPFMCP model 1, which uses the averaging of predictor forecasts, was the second best meta-model. PPFMCP models allow evaluations of risk decisions based on the price to be made.