Data-driven Two-step Day-ahead Electricity Price Forecasting Considering Price Spikes

In the electricity market environment,electricity price forecasting plays an essential role in the decision-making process of a power generation company,especially in developing the optimal bidding strategy for maximizing revenues.Hence,it is necessary for a power generation company to develop an accurate electricity price forecasting algorithm.Given this background,this paper proposes a two-step day-ahead electricity price forecasting algorithm based on the weighted Knearest neighborhood(WKNN)method and the Gaussian process regression(GPR)approach.In the first step,several predictors,i.e.,operation indicators,are presented and the WKNN method is employed to detect the day-ahead price spike based on these indicators.In the second step,the outputs of the first step are regarded as a new predictor,and it is utilized together with the operation indicators to accurately forecast the electricity price based on the GPR approach.The proposed algorithm is verified by actual market data in Pennsylvania-New JerseyMaryland Interconnection(PJM),and comparisons between this algorithm and existing ones are also made to demonstrate the effectiveness of the proposed algorithm.Simulation results show that the proposed algorithm can attain accurate price forecasting results even with several price spikes in historical electricity price data.

Explainability-based Trust Algorithm for electricity price forecasting models

Advanced machine learning(ML)algorithms have outperformed traditional approaches in various forecasting applications,especially electricity price forecasting(EPF).However,the prediction accuracy of ML reduces substantially if the input data is not similar to the ones seen by the model during training.This is often observed in EPF problems when market dynamics change owing to a rise in fuel prices,an increase in renewable penetration,a change in operational policies,etc.While the dip in model accuracy for unseen data is a cause for concern,what is more,challenging is not knowing when the ML model would respond in such a manner.Such uncertainty makes the power market participants,like bidding agents and retailers,vulnerable to substantial financial loss caused by the prediction errors of EPF models.Therefore,it becomes essential to identify whether or not the model prediction at a given instance is trustworthy.In this light,this paper proposes a trust algorithm for EPF users based on explainable artificial intelligence techniques.The suggested algorithm generates trust scores that reflect the model’s prediction quality for each new input.These scores are formulated in two stages:in the first stage,the coarse version of the score is formed using correlations of local and global explanations,and in the second stage,the score is fine-tuned further by the Shapley additive explanations values of different features.Such score-based explanations are more straightforward than feature-based visual explanations for EPF users like asset managers and traders.A dataset from Italy’s and ERCOT’s electricity market validates the efficacy of the proposed algorithm.Results show that the algorithm has more than 85%accuracy in identifying good predictions when the data distribution is similar to the training dataset.In the case of distribution shift,the algorithm shows the same accuracy level in identifying bad predictions.

Short-Term Electricity Price Forecasting Using Random Forest Model with Parameters Tuned by Grey Wolf Algorithm Optimization

Accurately forecasting short-term electricity prices is of great significance to electricity market participants.Compared with the time series forecasting methods,machine learning forecasting methods can consider more external factors.The forecasting accuracy of machine learning models is greatly affected by the parameters,meanwhile,the manual selection of parameters usually cannot guarantee the accuracy and stability of the forecasting.Therefore,this paper proposes a random forest(RF)electricity price forecasting model based on the grey wolf optimizer(GWO)to improve the accuracy of forecasting.Among them,RF has a good ability to deal with the problem of non-linear and unstable electricity prices.The optimization of model parameters by GWO can overcome the instability of the forecasting accuracy of manually tune parameters.On this basis,the short-term electricity prices of the PJM power market in four seasons are separately predicted.Experimental results show that the RF algorithm can better predict the short-term electricity price,and the optimization of the RF forecasting model by GWO can effectively improve the accuracy of the RF forecasting model.

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

Under dynamic pricing, stable and accurate electricity price forecasting on the demand side is essential forefficient energy management. We have developed a new electricity price forecasting model that providesconsistently accurate forecasts. The base prediction model decomposes the time series using wavelet transformand then predicts it by Long Short-Term Memory. Previous studies using this model have always decomposedtime series in the same way without changing the mother wavelet. However, this makes it difficult to respond tochanges 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 priceforecasting. In an experiment, the model improved prediction accuracy by up to 42.8% compared to predictionwith a fixed mother wavelet. Experimental results show that the proposed flexible forecasting method canconsistently provide highly accurate forecasts.

Energy Price Forecasting Through Novel Fuzzy Type-1 Membership Functions

Electricity price forecasting is a subset of energy and power forecasting that focuses on projecting commercial electricity market present and future prices.Electricity price forecasting have been a critical input to energy corporations’strategic decision-making systems over the last 15 years.Many strategies have been utilized for price forecasting in the past,however Artificial Intelligence Techniques(Fuzzy Logic and ANN)have proven to be more efficient than traditional techniques(Regression and Time Series).Fuzzy logic is an approach that uses membership functions(MF)and fuzzy inference model to forecast future electricity prices.Fuzzy c-means(FCM)is one of the popular clustering approach for generating fuzzy membership functions.However,the fuzzy c-means algorithm is limited to producing only one type of MFs,Gaussian MF.The generation of various fuzzy membership functions is critical since it allows for more efficient and optimal problem solutions.As a result,for the best and most improved results for electricity price forecasting,an approach to generate multiple type-1 fuzzy MFs using FCM algorithm is required.Therefore,the objective of this paper is to propose an approach for generating type-1 fuzzy triangular and trapezoidal MFs using FCM algorithm to overcome the limitations of the FCM algorithm.The approach is used to compute and improve forecasting accuracy for electricity prices,where Australian Energy Market Operator(AEMO)data is used.The results show that the proposed approach of using FCM to generate type-1 fuzzy MFs is effective and can be adopted.

A Temporal Convolutional Network Based Hybrid Model for Short-term Electricity Price Forecasting

Electricity prices have complex features,such as high frequency,multiple seasonality,and nonlinearity.These factors will make the prediction of electricity prices difficult.However,accurate electricity price prediction is important for energy producers and consumers to develop bidding strategies.To improve the accuracy of prediction by using each algorithms’advantages,this paper proposes a hybrid model that uses the Empirical Mode Decomposition(EMD),Autoregressive Integrated Moving Average(ARIMA),and Temporal Convolutional Network(TCN).EMD is used to decompose the electricity prices into low and high frequency components.Low frequency components are forecasted by the ARIMA model and the high frequency series are predicted by the TCN model.Experimental results using the realistic electricity price data from Pennsylvania-New Jersey-Maryland(PJM)electricity markets show that the proposed method has a higher prediction accuracy than other single methods and hybrid methods.

A Reinforcement Learning approach for the continuous electricity market ofGermany: Trading from the perspective of a wind park operator

With the rising extension of renewable energies, the intraday electricity markets have recorded a growingpopularity amongst traders as well as electric utilities to cope with the induced volatility of the energysupply. Through their short trading horizon and continuous nature, the intraday markets offer the abilityto adjust trading decisions from the day-ahead market or reduce trading risk in a short-term notice. Producersof renewable energies utilize the intraday market to lower their forecast risk, by modifying their providedcapacities based on current forecasts. However, the market dynamics are complex due to the fact that thepower grids have to remain stable and electricity is only partly storable. Consequently, robust and intelligenttrading strategies are required that are capable to operate in the intraday market. In this work, we proposea novel autonomous trading approach based on Deep Reinforcement Learning (DRL) algorithms as a possiblesolution. For this purpose, we model the intraday trade as a Markov Decision Process (MDP) and employ theProximal Policy Optimization (PPO) algorithm as our DRL approach. A simulation framework is introducedthat enables the trading of the continuous intraday price in a resolution of one minute steps. We test ourframework in a case study from the perspective of a wind park operator. We include next to general tradeinformation both price and wind forecasts. On a test scenario of German intraday trading results from 2018,we are able to outperform multiple baselines with at least 45.24% improvement, showing the advantage of theDRL algorithm. However, we also discuss limitations and enhancements of the DRL agent, in order to increasethe performance in future works.