Electricity Price Spikes Research Articles

On the practical aspects of machine learning based active power loss forecasting in transmission networks

AbstractThe cost for covering active power losses makes a significant item in transmission system operators (TSO) annual budgets, and still it received limited attention in the existing literature. The focus of accurate power loss forecasting and procurement is of high increase during the past 2 years due to spikes in electricity prices, making the cost of covering the active power losses a dominant factor of TSO operational costs. This paper presents practical aspects of the highly accurate models for transmission loss forecast in the day ahead time frame for the Croatian transmission system. The contributions are two‐fold: 1) Practical insights into usable TSO data are provided, filling a critical research gap and a foundational literature review is established on transmission loss forecasting. 2) A novel method utilizing only electricity transit data as input which outperforms existing practices is presented. For this, several algorithms such as gradient boosted decision tree model (XGB), support vector regressors, multiple linear regression and fully connected feedforward artificial neural networks are developed, and implemented and validated on data obtained from the Croatian TSO. The results show that the XGB model outperforms current TSO model by 32% for 4 months of comparison and TSCNET's commercial solution by 25% during a year‐long testing period. The developed XGB model is also implemented as a software tool and put into everyday operation with the Croatian TSO.

Electricity Demand, Forecasting the Peaks: Development and Implementation of C-EVA Method

Price spikes in electricity markets are very frequent, posing tremendous burden on household income and on manufacturing cost. Electricity demand (load) can be divided in two parts, energy (MWh) and peak (MW) and most of time peak is responsible for the price spikes. Literature review while devoting most of the discussion to energy, lags in the investigation of peak. In this research, a model for peak demand analysis and forecasting is developed. The model is based on a portfolio of cluster and extreme value analysis (C-EVA) methods using UIK, EDE and WSL innovations for the optimal determination of clusters and the daily peaks divulgence. C-EVA method consists of the Clustering part for optimal number of clusters determination and classification of day and month of peak, and the part of Extreme Value Analysis for computation of the statistical confidence interval for the load maxima. C-EVA after using all the currently available load maxima, estimates statistically the expected worst-case scenario for peaks of loads. Load peaks will be determined by EVA based on an estimated bimodal distribution while a signaling method will prompt the probability of extremes. The added value of the proposed method is that does not reject the extreme values as most methodologies do. Extreme Value Analysis for maxima and minima provide estimators for highest and lowest expected hourly load, while giving the confidence interval of the return level using an optimization method for the selection of a rolling time window, as the return period. It was found that distributed generation of renewables create a camel effect on the load peaks which increases sharpness. The proposed methodology solved this issue while opening the ground for future research for the role of storage, batteries as well as for virtual power plants as an integrated portfolio of renewables generation.

An Off-Site Power Purchase Agreement (PPA) as a Tool to Protect against Electricity Price Spikes: Developing a Framework for Risk Assessment and Mitigation

Significant price spikes occurred as early as 2021, initially driven by low gas storage levels, a post-pandemic economic rebound and then exacerbated by the Russian invasion of Ukraine. The situation had a range of wide-ranging consequences, from rising inflation, increasing energy poverty, food insecurity, business bankruptcies and recession. A well-known tool to protect energy consumers from energy price spikes, while at the same time contributing to the development of sustainable technologies, is Power Purchase Agreements. PPAs are long-term bilateral contracts for the purchase and sale of a certain amount of electricity, usually generated from renewable sources. The primary goal of this paper is to assess how the risk associated with PPAs has evolved between 2020 and 2023. It aims to examine whether, after the events in 2022, PPAs remain a robust solution that protects the off-taker from energy price spikes, ensures greater energy budget stability and enables savings. To achieve this, the probability of PPA prices being higher than market prices is evaluated, considering the changing market landscape. Furthermore, this paper intends to gain a thorough understanding of each risk related to PPAs and the best strategies for mitigating it, to maximize the protection of the off-taker.

A Joint Electricity Market-Clearing Mechanism for Flexible Ramping Products with a Convex Spot Market Model

A high proportion of renewable energy access makes the net load of the power system volatile and uncertain, increasing the demand for the ramping capacity of the power system. Traditional electricity spot markets compensate for the power imbalances caused by an insufficient ramping capacity through traditional flexibility services such as ancillary services and interconnection power. However, conventional flexibility services may lead to frequency deviations in the power system, increased response costs, spikes in electricity prices, and dramatic price volatility in the traditional spot market. To solve the above problems, this paper proposes an FRP and convex electricity spot market joint clearing (FCESMJC) market mechanism. The FCESMJC model can more accurately represent the relationship between electrical power output and the price of electricity and reduces the number of spikes in electricity prices. In addition, a novel FRP pricing method is proposed to compensate FRP market participants for their FRP costs more reasonably. Additionally, the difference in system performance is provided by comparing the energy prices, pricing method, clearing prices, and system costs in the FCESMJC method and the traditional electricity spot market. The FCESMJC system reduces the total system cost by 18.6% compared with the electricity spot market. Numerical experiments are simulated on the IEEE 14-bus test system to validate the superiority of the proposed model.

Forecasting the Occurrence of Electricity Price Spikes: A Statistical-Economic Investigation Study

This research proposes an investigative experiment employing binary classification for short-term electricity price spike forecasting. Numerical definitions for price spikes are derived from economic and statistical thresholds. The predictive task employs two tree-based machine learning classifiers and a deterministic point forecaster; a statistical regression model. Hyperparameters for the tree-based classifiers are optimized for statistical performance based on recall, precision, and F1-score. The deterministic forecaster is adapted from the literature on electricity price forecasting for the classification task. Additionally, one tree-based model prioritizes interpretability, generating decision rules that are subsequently utilized to produce price spike forecasts. For all models, we evaluate the final statistical and economic predictive performance. The interpretable model is analyzed for the trade-off between performance and interpretability. Numerical results highlight the significance of complementing statistical performance with economic assessment in electricity price spike forecasting. All experiments utilize data from Alberta’s electricity market.

Forecasting price spikes in day-ahead electricity markets: techniques, challenges, and the road ahead

Forecasting price spikes in day-ahead electricity markets: techniques, challenges, and the road ahead

Implications of electricity and gas price coupling in US New England region

The tight coupling between electricity and gas has put the US New England region at constant risk of electricity price spikes due to a shortage of gas supplies, especially in the wake of limited natural gas supply in 2022. Here, we investigate the electricity-gas price couplings in the six states in New England from 2006 to 2022. We found that the price coupling in New England has been high and consistent in the past five years across all states, despite varying levels of gas-fired power generation. Additionally, we anticipate it will remain high even with increasing renewables by 2030. Furthermore, the price coupling exhibits an asymmetrical influence with electricity prices closely tracking gas prices, while gas prices are weakly affected by electricity price variations. Our findings also suggest that promoting electricity-gas cooperations could potentially mitigate the asymmetrical influence and electricity price spikes in New England.

Short-Term Electricity Price Forecast Using Frequency Analysis and Price Spikes Oversampling

This paper proposes a new short-term electricity price forecast framework using frequency analysis and price spikes oversampling. To perform normal price forecast, firstly, the variational mode decomposition (VMD) method is adopted to decompose price data into multiple frequency band-limited modes where each mode has a center frequency. Then, the extended discrete Fourier transform (EDFT) method is utilized to transform the decomposed price modes from time domain into frequency domain to predict the price. In addition, to facilitate price spike prediction, over-sampling methods including the enhanced structure preserving oversampling (ESPO) and the synthetic minority oversampling technique (SMOTE) for regression, are adopted to synthesize price spike cases. Multiple electricity markets are studied and numerous comparison results illustrate that the proposed forecast framework is capable to accurately predict both normal electricity prices and price spikes.

Electricity price spike clustering: A zero-inflated GARX approach

Sudden dramatic rises in electricity prices, known as electricity “price spikes”, are ubiquitous in electricity spot markets worldwide. These price spikes often cluster. Energy retailers in many countries, including Australia, purchase electricity in an unregulated spot market and sell it to consumers at a heavily regulated price. As a result, the occurrence and clustering of spikes in the spot electricity price is particularly hazardous for retailers, and effective modelling and forecasting of these spikes is of foremost importance for effective risk management. This paper uses a data-dependent two-regime threshold autoregression to determine the electricity price spikes and proposes a zero-inflated generalized autoregression with exogenous covariates (ZIGARX) for modelling the time series count of price spikes. This model is shown to well capture the salient features of electricity price spikes, and can provide effective rolling probability forecasts of price spike occurrence. We apply the proposed approach to analyze the spot prices in four major regions in the Australian National Electricity Market (NEM) over the period April 2016 to February 2022. Results show that price spike clustering is captured very well using our model, and the persistence in price spike occurrence remains even after controlling for the relevant exogenous covariates. We also find that, in most of our sample period, the increasing use of renewable generation has mixed effects on the occurrence of price spikes.

Market failure or politics? Understanding the motives behind regulatory actions to address surging electricity prices

This paper aims to explore the underlying motivations that drive regulatory measures to address surging electricity prices. We discuss this question with a systematic review of the literature on price spikes in electricity markets and compare the recommended measures in the literature with political and regulatory actions taken during the 2021–22 European energy crisis. Our review shows a discrepancy between the arguments presented in the literature and the regulatory narrative in practice. Although theoretical arguments assume a general regulatory framework driven primarily by market efficiency, recent regulatory decisions show that political concerns can shape regulatory measures to a great extent, and the political economy of regulation should be incorporated into market analyses.

Electricity price spike formation and LNG prices effect under gross bidding scheme in JEPX

This study empirically analyzes the price spikes that occurred in the Japan Electric Power Exchange (JEPX) market in January 2021 and draws energy policy implications from the results. The contributions of this research are as follows. First, we propose a novel structural model to capture electricity price spikes based on the buy and sell bid curves of the JEPX order book and incorporate the effect of LNG spot price fluctuations on the price of electricity. Second, the results of our empirical analysis show that the model can adequately capture the price spike in the JEPX market that occurred in January 2021. Third, the estimation of the model parameters shows that the natural gas spot price immediately shifts the price curve upward. As an important energy policy implication from the results, we propose that to manage the risk of electricity price spikes, the LNG effect on the market players’ bidding behavior, rather than the marginal cost of the supply curve, be considered; from this perspective, the LNG spot price, rather than the trend of the LNG price a few months earlier, must be monitored, and the institutional design of the JEPX market should take this into account.

Spatio-temporal evaluation of electricity price risk considering multiple uncertainties under extreme cold weather

The increasing frequency of long-lasting price spikes in electricity markets caused by extreme weather has brought unbearable economic burdens to both electricity consumers and retailers, attracting wide attention on price risk evaluation and prevention. However, the precise and comprehensive evaluation of price risks has been hindered by the lack of spatio-temporal feature analysis and multi-uncertainty fusion modeling, including random failures, rapid surges in electricity demands and natural gas prices under extreme cold weather. To address this, a spatio-temporal evaluation model of electricity price risk considering the synthetic effects of multiple uncertainties is proposed based on the universal generating function (UGF) technique. Firstly, the UGF representations of standardized probabilistic models for different uncertainty factors induced by freezing temperatures are developed. On this basis, the market price calculation (MPC) operator is proposed to obtain the probabilistic model of the electricity market by aggregating these UGFs. Moreover, the spatio-temporal price risk indices are proposed to comprehensively evaluate the market risk level. Furthermore, the impact analysis based on sensitivity calculation is introduced to identify the most critical factor from multiple uncertainties. Case studies demonstrate that the extremely high price risks mainly occur during severe icing intervals and locate in the region away from major energy resources. Moreover, the surge in electricity demand is identified as the major factor for extremely high electricity prices. The findings can provide effective references for risk prevention and hedging for market operators and participants.

Short Term Load Forecasting of Residential and Commercial Consumers of Karnataka Electricity Board using CFNN

Electricity use and its access are correlated in the economic development of any country. Economically, electricity cannot be stored, and for stability of an electrical network a balance between generation and consumption is necessary. Electricity demand depends on various factors like temperature, everyday activities, time of day, days of the week days/Holidays. These parameters have led to price volatility and huge spikes in electricity prices. The research work proposes a short term Load prediction Model for LT2 (residential consumers), LT3 (Commercial Consumers) of Karnataka State Electricity Board using Cascaded Feed Forward Neural Network (CFNN). MATLAB software is utilized to design and test the forecasting model for predicting the power consumption. Furthermore, a shallow feed forward neural network-based prediction model is constructed and evaluated for performance comparison. The Performance metrics include Mean Absolute Percentage Error (MAPE) and Mean Squared Error (MSE). The suggested STLF CFNN prediction model outperformed shallow feed forward networks on both performance metrics with prediction errors of less than 1%.

Assessing risks for New England's wholesale electricity market from wind power losses during extreme winter storms

In the United States, New England faces difficulties from severe winter weather, during which its power grid simultaneously experiences high natural gas prices and electricity demand, leading to spikes in wholesale electricity prices. In recent years, a significant amount of offshore wind power capacity has been planned for the region, and previous studies have suggested the presence of offshore wind could lower emissions and market prices during cold snaps. However, there has been limited consideration of potential wind power losses during extreme winter weather due to excessive wind speeds, which could lead to sudden losses of wind power. This aim of this study is to quantify risks associated with sudden wind power losses during extreme winter weather, especially the potential for these events to cause spikes in the wholesale electricity price. Results suggest that these so-called wind turbine “cut-out” events likely represent a minor risk compared to the loss of wind power due to low wind speeds and sudden drops in wind speeds during summer, when demand for electricity is higher. Overall, the benefits of having offshore wind power during extreme winter weather appear to outweigh the risks associated with relatively rare cut-out events caused by excessive wind speeds.

Price spikes, temporary price caps, and welfare effects of regulatory interventions on wholesale electricity markets

There is growing empirical evidence of increasing price volatility and price spikes in electricity markets as a result of variable renewable energy generation, extreme weather events, and other factors. While price spikes are needed to cover the fixed costs of power plants, they may also signal market flaws and anti-competitive behavior. Regulatory authorities have imposed market price caps to protect consumers and prevent abusive supplier behavior. In addition, some regulators have imposed temporary price caps during or after severe events; however, these caps may be driven by political motives rather than economic logic in weak institutional settings. This paper evaluates the welfare effect of the temporary price cap implemented in 2017 on the Turkish electricity market. By using matching and panel data methods, we show that the temporary price cap reduced the total welfare but did not affect market clearing price and projected supply. Our detailed analysis shows that this decision was driven by non-economic motives, and identifies a number of fundamental problems in the Turkish market that limit the effective functioning of the market.

Electricity Market Liquidity and Price Spikes: Evidence from Hungary

This article examines how electricity market liquidity, renewable production and cross-border activity together in combination explain price spikes in the Hungarian Power Exchange day-ahead auctions. In the applied logit model, the dependent variable representing the price spike is binary, and the key explanatory variable is a modified bid-ask spread depicting liquidity. Weather-dependent renewable production and the difference between exports and imports appear as control variables in the model. The empirical analysis was based on data from 2017 and 2018. The results show that the control variables have no effect on the bid-ask spread and that the model explains 96 per cent of the spikes well, with an AUC-ROC of 0.75 and a Gini coefficient of 0.5. Based on the results, it may be worthwhile for traders to incorporate their data from sales and purchase curves into their forecasts, as this will improve their chances of successfully predicting extreme prices.

Economic optima for buffers in direct reduction steelmaking under increasing shares of renewable hydrogen

While current climate targets demand substantial reductions in greenhouse gas emissions, the potentials to further reduce carbon dioxide emissions in traditional primary steel-making are limited. One possible solution that is receiving increasing attention is the direct reduction (DR) technology, operated either with renewable hydrogen (H2) from electrolysis or with conventional natural gas (NG). DR technology makes it possible to decouple steel and H2 production by temporarily using overcapacities to produce and store intermediary products during periods of low renewable electricity prices, or by switching between H2 and NG. This paper aims to explore the impact of this decoupling on overall costs and the corresponding dimensioning of production and storage capacities. An optimization model is developed to determine the least-cost operation based on perfect-foresight. This model can determine the minimum costs for optimal production and storage capacities under various assumptions considering fluctuating H2 and NG prices and increasing H2 shares. The model is applied to a case study for Germany and covers the current situation, the medium term until 2030, and the long term until 2050. Under the assumptions made, direct reduced iron (DRI) storage mainly serves as long-term storage for several weeks, similar to usual balancing storage capacities. Storing H2, on the contrary, is used for short-term fluctuations and could balance H2 demand in the hourly range until 2050. From an economic perspective, DRI production using NG tends to be cheaper than using H2 in the short term, and potential savings from the flexible operation with storages are initially small. However, in the long term until 2050, NG and H2 could achieve similar total costs if buffers are used. Otherwise, temporarily occurring electricity price spikes imply substantial increases in total costs if high shares of H2 need to be achieved.

Energy Flexibility Chances for the Wastewater Treatment Plant of the Benchmark Simulation Model 1

Future energy systems must mainly generate electricity from renewable resources. To deal with the fluctuating availability of wind and solar power, new versatile electricity markets and sustainable solutions concentrating on energy flexibility are needed. In this research, we investigated the potential of energy flexibility achieved through demand-side response for the wastewater treatment plant of the Benchmark Simulation Model 1. First, seven control strategies were simulated and assessed. Next, the flexibility calls were identified, two energy flexibility scenarios were defined and incorporated into the model, and the control strategies were evaluated anew. In this research, the effluent ammonia concentration needed to be maintained within the limits for as long as possible. Strategy 5, which controlled ammonia in Tank 5 at a low value and did not control any nitrate in Tank 2, of Scenario 1, which was characterized by an undetermined on/off aeration cycle, was then found to be the best. Although this control strategy led to high total energy consumption, the percentage of time during which aeration was nearly suspended was one of the highest. This work proposes a methodology that will be useful to plant operators who should soon reduce energy consumption during spikes in electricity prices.

Environmental Benefit and Investment Value of Hydrogen-Based Wind-Energy Storage System

Alongside the rapid expansion of wind power installation in China, wind curtailment is also mounting rapidly due to China’s energy endowment imbalance. The hydrogen-based wind-energy storage system becomes an alternative to solve the puzzle of wind power surplus. This article introduced China’s energy storage industry development and summarized the advantages of hydrogen-based wind-energy storage systems. From the perspective of resource conservation, it estimated the environmental benefits of hydrogen-based wind-energy storages. This research also builds a valuation model based on the Real Options Theory to capture the distinctive flexible charging and discharging features of the hydrogen-based wind-energy storage systems. Based on the model, simulation results, including the investment value and operation decision of the hydrogen energy storage system with different electricity prices, system parameters, and different levels of subsidies, are presented. The results show that the hydrogen storage system fed with the surplus wind power can annually save approximately 2.19–3.29 million tons of standard coal consumption. It will reduce 3.31–4.97 million tons of CO2, SO2, NOx, and PM, saving as much as 286.6–429.8 million yuan of environmental cost annually on average. The hydrogen-based wind-energy storage system’s value depends on the construction investment and operating costs and is also affected by the mean-reverting nature and jumps or spikes in electricity prices. The market-oriented reform of China’s power sector is conducive to improve hydrogen-based wind-energy storage systems’ profitability. At present, subsidies are still essential to reduce initial investment and attract enterprises to participate in hydrogen energy storage projects.

A hybrid electricity price scenario generation method for stochastic virtual bidding in the electricity market

Stochastic optimization can be used to generate optimal bidding strategies for virtual bidders in which the uncertain electricity prices are represented by using scenarios. This paper proposes a hybrid scenario generation method for electricity price using a seasonal autoregressive integrated moving average (SARIMA) model and historical data. The electricity price spikes are first identified by using an outlier detection method. Then, the historical data are decomposed into base and spike components. Next, the base and spike component scenarios are generated by using the SARIMA- and historical data-based methods, respectively. Finally, the electricity price scenarios are obtained by combining the base and spike component scenarios. Case studies are carried out for a virtual bidder in the PJM electricity market to validate the proposed method. The optimal bidding strategies of the virtual bidder are generated by solving a stochastic optimization problem using the electricity price scenarios generated by the proposed method, the SARIMA method, and a historical data-based method, respectively. Case study results show that the proposed method is better than the SARIMA method in preserving statistical properties of the electricity price in the generated scenarios and is better than the historical data-based method in predicting the future trend of the electricity price and, therefore, can help the virtual bidder earn more profit in the electricity market.