A Multi-Feature Based Approach Incorporating Variable Thresholds for Detecting Price Spikes in the National Electricity Market of Australia

Detecting electricity price spikes is crucial as it helps market participants to gain confidence and formulate appropriate strategy maximize their benefits. In this paper, a multi-feature based approach with the incorporation of variable thresholds developed detect in national Australia. The thresholds, which are determined using weighted sliding window average an adjusted standard deviation, help segregate from normal variations. Also, significant features extracted after thoroughly analyzing underlying causes resulting into spikes. These employed inputs support vector machine classify prices or non-spikes. A case study conducted dataset acquired state New South Wales, results show that proposed method can successfully high accuracy confidence.