Electricity Price Forecasting Research Articles

Models of Electricity Price Forecasting: Bibliometric Research

Electricity Price Forecasting (EPF) influences the sale conditions in the energy sector. Proper models of electricity price prognosis can be decisive for choice between energy sources as a start point of transformation toward renewable energy sources. This article aims to present and compare various EPF models scientific publications. Adopted in this study procedure, the EPF publications models are compared into two main categories: the most popular and the most accurate. The adopted method is a bibliometric study as a variation of Systematic Literature Review (SLR) with specified automated queries supported by the VOSviewer bibliometric maps exploration. The subject of this research is the exploration of EPF models in two databases, Web of Science and Scopus, and their content comparison. As a result, the SLR research queries were classified into two groups, the most cited and most accurate models. Queries characteristics were explained, along with the graphical presentation of the results. Future promising research avenues can be dedicated to the most accurate EPF model formulation proved by statistical testing of its significance and accuracy.

Flexible electricity price forecasting by switching mother wavelets based on wavelet transform and Long Short-Term Memory

Under dynamic pricing, stable and accurate electricity price forecasting on the demand side is essential for efficient energy management. We have developed a new electricity price forecasting model that provides consistently accurate forecasts. The base prediction model decomposes the time series using wavelet transform and then predicts it by Long Short-Term Memory. Previous studies using this model have always decomposed time series in the same way without changing the mother wavelet. However, this makes it difficult to respond to changes in time series that vary daily or seasonally. Therefore, we periodically switch the mother wavelet, i.e., flexibly change the time series decomposition method, to achieve stable and highly accurate electricity price forecasting. In an experiment, the model improved prediction accuracy by up to 42.8% compared to prediction with a fixed mother wavelet. Experimental results show that the proposed flexible forecasting method can consistently provide highly accurate forecasts.

A Free-Market Environmentalist Enquiry on Spain's Energy Transition along with Its Recent Increasing Electricity Prices.

This paper analyzes the Spanish energy transition’s general situation and its increasing electricity prices in recent years from a free-market environmentalist (FME) approach. We hypothesize and argue that high taxes, high government subsidies, and government industrial access restrictions breach private property rights, hindering Spain’s renewable energy (RE) development. Our paper discovers that Spain’s state-interventionist policies have increased the cost of the energy and power industries, leading to electricity prices remaining relatively high before and after the outbreak of the COVID-19 pandemic. After reviewing the literature on the FME approach and Spain’s case, a Box–Jenkins (ARIMA) model is used to clarify the economic performance of the Spanish electricity industry with a proposal for forecasting electricity prices. It is observed that Spain fails the EU and its national goal of providing an affordable energy price as a part of the green energy transition. Finally, free-market environmental solutions and policy reforms are proposed to facilitate Spain’s energy transition.

ELECTRICITY PRICE FORECASTING IN TURKISH DAY-AHEAD MARKET VIA DEEP LEARNING TECHNIQUES

Day-Ahead Market offers electricity market participants the opportunity to trade electricity one day ahead of real-time. For each hour, a separate Market Clearing Price is created in Day-Ahead Market. This study aims to predict the hourly Market Clearing Price using deep learning techniques. In this context, 24-hour Market Clearing Prices were forecasted with MLP, CNN, LSTM, and GRU. LSTM had the best average forecasting performance with an 8.15 MAPE value, according to the results obtained. MLP followed the LSTM with 8.44 MAPE, GRU with 8.72 MAPE, and CNN with 9.27 MAPE. In the study, the provinces where the power plants producing with renewable resources are dense were selected for meteorological variables. It is expected that the trend towards electricity generation with renewable resources will increase in the future. In this context, it is thought important for market participants to consider the factors that may affect the production with these resources in the electricity price forecasting.

Electricity Price Instability over Time: Time Series Analysis and Forecasting

Competition in electricity markets leads to volatile conditions which cause persistent price fluctuations over time. This study explores the problem of electricity pricing fluctuations in the DE-LU bidding zone from October 2018 to March 2022 by applying time series analysis. The determinants of electricity price fluctuations are broken down into three groups: exogenous prices (gas, coal and CO2 prices), internal (consumption and generation) and external (net import between neighboring bidding zones) electricity flows. Based on the SARIMAX model, we tried to combine all these factors to forecast electricity prices in the single bidding zone. It was found that the SARIMAX (1, 1, 2) × (3, 1, 0, 7) model with exogenous prices, internal and external electricity flows, which has the lowest AIC and MAPE values, is the best-fitted model for the DE-LU bidding zone. Anonymous trading and unpredictable individual bidding strategies lead to persistent price volatility, which causes electricity prices to deviate from fundamental trends. To reveal the risk factors, the SARIMAX model of electricity prices needs to be supplemented with a GARCH model of the residual returns. For forecasting electricity price residual volatility in the DE-LU bidding zone, the SARIMAX model with exogenous prices, internal and external electricity flows must be accompanied with the GARCH (7, 0) model.

Forecasting electricity prices using bid data

Market liberalization and the expansion of variable renewable energy sources in power systems have made the dynamics of electricity prices more uncertain, leading them to show high volatility with sudden, unexpected price spikes. Thus, developing more accurate price modeling and forecasting techniques is a challenge for all market participants and regulatory authorities. This paper proposes a forecasting approach based on using auction data to fit supply and demand electricity curves. More specifically, we fit linear (LinX-Model) and logistic (LogX-Model) curves to historical sale and purchase bidding data from the Iberian electricity market to estimate structural parameters from 2015 to 2019. Then we use time series models on structural parameters to predict day-ahead prices. Our results provide a solid framework for forecasting electricity prices by capturing the structural characteristics of markets.

Forecasting Hourly Spot Prices in Indian Electricity Market

In this paper, we present a study on forecasting hourly electricity spot prices for India. Forecasting electricity prices is challenging for its special characteristics. Based on hourly data covering several years, ARMAX models are estimated for forecasting for individual regions. Along with ARMA, intra-day, inter-day and hourly variations and seasonalities on weekdays, holidays and festive days are incorporated. Combinations of static and dynamic forecasts are also examined. The results indicate that prices for Sundays and holidays differ significantly from weekdays; also, a clear region-specific difference between prices in winter and summer months is observed. Price behaviour in the Southern region is different from other regions. The fitted models perform well for forecasting horizons of hourly prices of up to five days. The fitted ARMAX models have an easily implementable simple structure. Such forecasts provide valuable insights for policymakers and market participants, as they incorporate several features of the Indian electricity market, including various dimensions of seasonality of demand. JEL Classifications: C53, Q47, C51

TECHNO-ECONOMIC COMPARISON OF BIFACIAL VS MONOFACIAL SOLAR PANELS

A techno-economic analysis is performed for a solar farm with a 35 MWe installed capacity using bifacial solar panels and compared with standard monofacial solar panels at the same installed capacity level. The bifacial panel usage gain from total panel efficiency is identified from 4-year measurements to be within a range of 7.9–16.8% depending on monthly yield. A Monte Carlo simulation is carried out to forecast electricity prices under uncertainty. In terms of Net Present Value, it is found that the bifacial farm yields 12.6% higher values than the monofacial options under reference assumptions. An incremental internal rate of return (IRR) analysis is carried out yielding an IRR for the bifacial panels of 44% under various scenarios. The sensitivity analysis reveals that results are highly sensitive to discount rate and lifetime, and less sensitive to electricity prices. SWOT analysis performed to compare the bifacial with the monofacial panel and evaluate panels according to internal and external factors. The study was concluded with a summary of the technical specifications based on the test results. The results were used to identify that 12.2% added net present value corresponding to $186.7 – $214.5 per unit MW (under various electricity price trajectories) can be used as a reference for assessing the benefit for usage of bifacial PV for 35 MW type medium-size projects. In summary, it is suggested that bifacial solar PV with its outstanding techno-economic results can be the driving force of the growing solar PV market.

Multi-Step-Ahead Electricity Price Forecasting Based on Temporal Graph Convolutional Network

Traditional electricity price forecasting tends to adopt time-domain forecasting methods based on time series, which fail to make full use of the regional information of the electricity market, and ignore the extra-territorial factors affecting electricity price within the region under cross-regional transmission conditions. In order to improve the accuracy of electricity price forecasting, this paper proposes a novel spatio-temporal prediction model, which is combined with the graph convolutional network (GCN) and the temporal convolutional network (TCN). First, the model automatically extracts the relationships between price areas through the graph construction module. Then, the mix-jump GCN is used to capture the spatial dependence, and the dilated splicing TCN is used to capture the temporal dependence and forecast electricity price for all price areas. The results show that the model outperforms other models in both one-step forecasting and multi-step forecasting, indicating that the model has superior performance in electricity price forecasting.

Do jumps and cojumps matter for electricity price forecasting? Evidence from the German-Austrian day-ahead market

This paper analyzes the potential for including jumps and cojumps in electricity price forecasting models. The study is carried out on the German–Austrian day-ahead electricity market with a multivariate framework in which each hour of the day is treated as an individual time series. Three models are specified: The ARX model, the ARX-J model (which includes jumps), and the ARX-J-CJ model (which also includes cojumps). Prices are transformed using several variance stabilizing transformations. The forecasting performance of the three models with original and transformed prices is compared using several forecast horizons running from one day-ahead to one week-ahead. Results show that the forecast horizon is crucial in determining whether jumps and cojumps should be included in electricity price forecasting. Jumps and cojumps add important information to forecast prices for horizons longer than 4 days, but there is no gain in forecast accuracy for shorter horizons. The results are of interest to market participants for taking optimal decisions and pricing base week futures contracts.

Trading on short-term path forecasts of intraday electricity prices

We introduce a profitable trading strategy that can support decision-making in continuous intraday markets for electricity. It utilizes a novel forecasting framework, which generates prediction bands from a pool of path forecasts or approximates them using probabilistic price forecasts. The prediction bands then define a time-dependent price level that, when exceeded, indicates a good trading opportunity. Results for the German intraday market show that, in terms of the energy score, our path forecasts beat two well performing literature benchmarks by over 30%. Moreover, the forecasts provide empirical evidence that the increased computational burden induced by generating realistic price paths is offset by higher trading profits. Still, the proposed approximate and bootstrap-based methods offer a reasonable trade-off — they do not require generating path forecasts and yield only slightly lower profits.

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.

Day-ahead Electricity Price Forecasting using Long-short Term Memory Recurrent Neural Network

The availability of accurate day-ahead electricity price forecasts is very important for electricity market participants and it is an essential challenge to accurately forecast the electricity price. Therefore, this study proposes an efficient method suitable for electricity price forecasting (EPF) and processing time-series data from the Bulgarian day-ahead market based on a long-short term memory (LSTM) recurrent neural network model. The LSTM model is used to forecast the day-ahead electricity price for the Bulgarian day-ahead market. As inputs to the model are used historical hourly prices for the period between 20.01.2016 and 05.03.2022. The output is the electricity price forecasts for hours and days ahead. The future values of prices are forecasted recursively. LSTM can model temporal dependencies in larger Time Series set horizons without forgetting the short-term patterns. LSTM networks are composed of units that are called LSTM memory cells and these cells contain some gates that process the inputs. Since electricity price is affected by various seasonal effects, the model is trained for several years. The effectiveness of the proposed method is verified using real market data.

ARIMA Model for Day-Ahead Electricity Market Price Forecasting

Electricity price forecasting becomes a significant challenge on a day-to-day basis and price variations are even more volatile on an hourly basis. Therefore, this paper is used several approaches to analyze the Bulgarian hourly electricity price dynamics in the day-ahead market. Proper analysis crucially depends on the choice of an adequate model. Reviewed are the factors which may influence the electricity spot prices and characteristics of the time series of prices. Methods include and variety of modeling approaches that are applied and evaluated for forecasting electricity prices such as time-series models and regression models. The forecasting technique is to model day-ahead spot prices using well known ARIMA/SARIMA model including stationarity checks, seasonal decompose, differencing, autoregressive modeling, and autocorrelation to analyze and forecast time series hourly data. For each approach, model estimates and forecasts are developed using hourly price data, reshaped, and aggregated data on a daily and monthly basis for the Bulgarian day-ahead market.

ПРОГНОЗИРОВАНИЕ И УПРАВЛЕНИЕ ЭЛЕКТРОПОТРЕБЛЕНИЕМ СООБЩЕСТВА МИКРОСЕТЕЙ С ПРИМЕНЕНИЕМ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА

A characteristic feature of the modern electric power industry in recent decades is the sharp increase in electricity consumption. This can be explained by technological, social, economic, and other reasons. Therefore, the forecasting of electricity consumption is important for many processes, including the planned operation of genera¬ting equipment and managing and optimizing the operating modes of energy systems. It is also a significant aspect in the opera-tion of industrial enterprises, since breaches can result in fines. One of the urgent tasks in the electricity market today is the forecasting of electricity consumption for a certain period. The article presents a description of a microgrid model with a built-in block for predicting power consumption, as well as intelligent load control for several objects at the same time, including those with distributed generation. Decisions are made the previous day, in order to forme stra¬tegies or the generation profile and control of power receivers. This timing is dictated by the information available to the intelli-gent system. This information includes forecast of demand and electricity prices of the centralized energy system for every hour of the next day. The process of switching at peak time to additional sources of electricity, distribution over microgrids is also described. The forecast was implemented using the Holt-Winters model from the statsmodels library (Python 3). The model uses the ideas of exponential smoothing, but is more complex and can be applied to series containing trend and seasonality. The trained model predicts with 95.21% accuracy.

Artificial intelligence with attention based BiLSTM for energy storage system in hybrid renewable energy sources

Hybrid renewable energy sources with energy storage systems (ESS) are becoming more prevalent in offering remote consumers with efficient, affordable, and dependable energy alternatives to traditional systems. The ESS is essential for the integration of hybrid RES in order to balance the supply of power with demand. Simultaneously, the price fluctuations and intermittent nature of RES led to the invention of ESS for RES. To do this, the recently established deep learning (DL) models can be utilized to optimize the ESS for RES for maximum performance. With this purpose in mind, this study presents an optimal attention-based bidirectional long and short-term memory (OABLSTM-ESS) technique for energy storage systems utilizing renewable energy sources. By resolving the optimization problem, the described OABLSTM-ESS technique attempts to minimize electricity costs while achieving productivity requirements. In addition, an attention based BiLSTM (ABLSTM) method has been created to take advantage of the inherent benefits of anticipated future processes. Moreover, the improved coyote optimization algorithm (ICOA) is used to best select the ABLSTM model's hyperparameters. The ICOA is created by merging the COA with the hill climbing (HC) idea, which helps to search for and improve the learning strategy while determining the candidate solutions for the COA. A vast array of simulation analyses are implemented to assure the improved performance of the OABLSTM-ESS approach. According to the results, the minimal CT for the OABLSTM-ESS approach was 0.53 min for the forecast of electricity prices, 0.50 min for the forecast of wind energy, and 0.47 min for the forecast of solar energy. The OABLSTM-ESS method outperformed the other methods, as evidenced by the data and discussion in their totality. Based on a comparison of the results, it was found that the OABLSTM-ESS method is better than recent approaches in many ways.

Blockchain Based Smart-Grid Stackelberg Model for Electricity Trading and Price Forecasting Using Reinforcement Learning

A smart grid is an intelligent electricity network that allows efficient electricity distribution from the source to consumers through telecommunication technology. The legacy smart grid follows the centralized oligopoly marketplace for electricity trading. This research proposes a blockchain-based electricity marketplace for the smart grid environment to introduce a decentralized ledger in the electricity market for enabling trust and traceability among the stakeholders. The electricity prices in the smart grid are dynamic in nature. Therefore, price forecasting in smart grids has paramount importance for the service providers to ensure service level agreement and also to maximize profit. This research introduced a Stackelberg model-based dynamic retail price forecasting of electricity in a smart grid. The Stackelberg model considered two-stage pricing between electricity producers to retailers and retailers to customers. To enable adaptive and dynamic price forecasting, reinforcement learning is used. Reinforcement learning provides an optimal price forecasting strategy through the online learning process. The use of blockchain will connect the service providers and consumers in a more secure transaction environment. It will help tackle the centralized system’s vulnerability by performing transactions through customers’ smart contracts. Thus, the integration of blockchain will not only make the smart grid system more secure, but also price forecasting with reinforcement learning will make it more optimized and scalable.

Electricity price forecasting with high penetration of renewable energy using attention-based LSTM network trained by crisscross optimization

Accurate electricity price forecasts is the common concern of market participants. With the integration of high penetration of wind and solar energy resources into the power system, the renewable energy sources will have a great impact on the electricity price volatility undoubtedly. In this regard, a novel attention mechanism (AM) based electricity price forecasting model for electricity market with high proportion of renewable energy is proposed in this paper. In order to investigate the effect of renewable energy on the electricity price prediction, the wind power generation, solar power generation, predicted load and the historical price series are simultaneously taken as the input features. In the data preprocessing stage, the empirical wavelet transform (EWT) is applied to decompose each of the input features into multiple components to avoid learning the autocorrelation of the original sequence. In the model training stage, a hybrid AM-based long short-term memory network (LSTM) is proposed as the forecasting model, aiming to make full use of the AM to dynamically evaluate the importance of different input feature. Furthermore, the crisscross optimization algorithm (CSO) is adopted to retrain the parameters of fully-connected layer so as to further enhance the generalization ability. The proposed method is validated on the datasets of Danish electricity market with a high proportion of renewable energy, and the experimental results show that the proposed model is superior to other hybrid models involved in this study.

Short-Term Electricity Prices Forecasting Using Functional Time Series Analysis

In recent years, efficient modeling and forecasting of electricity prices became highly important for all the market participants for developing bidding strategies and making investment decisions. However, as electricity prices exhibit specific features, such as periods of high volatility, seasonal patterns, calendar effects, nonlinearity, etc., their accurate forecasting is challenging. This study proposes a functional forecasting method for the accurate forecasting of electricity prices. A functional autoregressive model of order P is suggested for short-term price forecasting in the electricity markets. The applicability of the model is improved with the help of functional final prediction error (FFPE), through which the model dimensionality and lag structure were selected automatically. An application of the suggested algorithm was evaluated on the Italian electricity market (IPEX). The out-of-sample forecasted results indicate that the proposed method performs relatively better than the nonfunctional forecasting techniques such as autoregressive (AR) and naïve models.

Electricity Price Forecasting: The Dawn of Machine Learning

Electricity price forecasting (EPF) is a branch of forecasting on the interface of electrical engineering, statistics, computer science, and finance, which focuses on predicting prices in wholesale electricity markets for a whole spectrum of horizons. These range from a few minutes (real-time/intraday auctions and continuous trading), through days (day-ahead auctions), to weeks, months or even years (exchange and over-the-counter traded futures and forward contracts). Over the last 25 years, various methods and computational tools have been applied to intraday and day-ahead EPF. Until the early 2010s, the field was dominated by relatively small linear regression models and (artificial) neural networks, typically with no more than two dozen inputs. As time passed, more data and more computational power became available. The models grew larger to the extent where expert knowledge was no longer enough to manage the complex structures. This, in turn, led to the introduction of machine learning (ML) techniques in this rapidly developing and fascinating area. Here, we provide an overview of the main trends and EPF models as of 2022.