Deep Learning-Based Electricity Price Forecast for Virtual Bidding in Wholesale Electricity Market

Virtual bidding plays an important role in two-settlement electric power markets, as it can reduce discrepancies between day-ahead and real-time markets. Renewable energy penetration increases volatility in electricity prices, making accurate forecasting critical for virtual bidders, reducing uncertainty and maximizing profits. This study presents a Transformer-based deep learning model to forecast the price spread between real-time and day-ahead electricity prices in the ERCOT (Electric Reliability Council of Texas) market. The proposed model leverages various time-series features, including load forecasts, solar and wind generation forecasts, and temporal attributes. The model is trained under realistic constraints and validated using a walk-forward approach by updating the model every week. Based on the price spread prediction results, several trading strategies are proposed and the most effective strategy for maximizing cumulative profit under realistic market conditions is identified through backtesting. The results show that the strategy of trading only at the peak hour with a precision score of over 50% produces nearly consistent profit over the test period. The proposed method underscores the importance of an accurate electricity price forecasting model and introduces a new method of evaluating the price forecast model from a virtual bidder's perspective, providing valuable insights for future research.

Unbalanced Three-Phase Distribution Grid Topology Estimation and Bus Phase Identification

There is an increasing need for monitoring and controlling uncertainties brought by distributed energy resources in distribution grids. For such goal, accurate three-phase topology is the basis for correlating and exterminating measurements in unbalanced distribution networks. Unfortunately, such topology knowledge is often unavailable due to limited investment, especially for secondary distribution grids. Also, the bus phase connectivity information is inaccurate due to human errors or outdated records. For this challenge, we utilize smart meter data at different phases for an information-theoretic approach to learn the structures. Specifically, we convert the system of three unbalanced phasors into symmetrical components, namely the positive, negative, and zero sequences. Then, we prove that Chow-Liu algorithm can find the optimal topology by utilizing power flow equation and the conditional independence relationships implied by the radial three-phase structure of distribution grids with the presence of incorrect bus phase labels. At last, by utilizing Carson's equation, we prove that the bus phase connection can be correctly identified using voltage measurements. For validation, we extensively simulate on IEEE $37$- and $123$-bus systems using real data from PG\&E, ADRES Project, and Pecan Street. We observe that the algorithm is highly accurate for finding three-phase topology in distribution grids even with strong load unbalancing condition and DERs. This ensures close monitoring and controlling DERs in distribution grids.