Abstract:

The electricity price directly reflects the attributes of electricity commodities. However, influenced by various factors such as market supply and demand, power generation company bids, and line transmission capacity, the electricity price signals often exhibit diverse forms of anomalies. Recognizing and tracing these abnormal electricity price signals are crucial daily tasks for power trading centers at all levels. However, the existing tracing methods generally rely on manual experiences to analyze the causes of abnormal electricity prices, which is inefficient and difficult to ensure objective and scientific traceability of the causes of abnormal electricity prices. This paper proposes an abnormal electricity price cause tracing method based on comparative analysis of key features. Firstly, based on the historical electricity price data features, the abnormal spike amplitude and abnormal average value of electricity prices are categorized. And then, using the principal component analysis method, the collections of key features for each type of abnormal electricity price signals are established. Finally, using the alternative algorithms, the influencing degree of each element within the collection of key features on the electricity price are calculated respectively, and ranked based on their importance, thereby achieving filtering and tracing of the causes for abnormal electricity prices. The effectiveness of the proposed methodin is verified through case studies based on numerous actual power market data. The average accuracy rate of the proposed method for tracing the causes of average electricity price anomalies and spike anomalies reaches more than 85%, which can effectively reduce the labor costs in the process of tracing the causes of abnormal electricity prices.

Key words: abnormal electricity price, traceability method, principal component analysis (PCA), key features