An Unsupervised Anomaly Detection in Electricity Consumption Using Reinforcement Learning and Time Series Forest Based Framework

TL;DR

This paper introduces an unsupervised anomaly detection framework for electricity consumption time series that dynamically selects the best detection model using reinforcement learning and time series forest techniques, improving accuracy across diverse datasets.

Contribution

The paper presents a novel unsupervised model selection approach combining TSF and RL, outperforming existing methods and adapting to various anomaly types without relying on labeled data.

Findings

Outperforms all models on real-time dataset in F1 score

Achieves 0.989 F1 score on synthetic dataset, surpassing all except KNN

Maintains high performance across datasets with different anomaly types

Abstract

Anomaly detection (AD) plays a crucial role in time series applications, primarily because time series data is employed across real-world scenarios. Detecting anomalies poses significant challenges since anomalies take diverse forms making them hard to pinpoint accurately. Previous research has explored different AD models, making specific assumptions with varying sensitivity toward particular anomaly types. To address this issue, we propose a novel model selection for unsupervised AD using a combination of time series forest (TSF) and reinforcement learning (RL) approaches that dynamically chooses an AD technique. Our approach allows for effective AD without explicitly depending on ground truth labels that are often scarce and expensive to obtain. Results from the real-time series dataset demonstrate that the proposed model selection approach outperforms all other AD models in terms of the F1 score metric. For the synthetic dataset, our proposed model surpasses all other AD models except for KNN, with an impressive F1 score of 0.989. The proposed model selection framework also exceeded the performance of GPT-4 when prompted to act as an anomaly detector on the synthetic dataset. Exploring different reward functions revealed that the original reward function in our proposed AD model selection approach yielded the best overall scores. We evaluated the performance of the six AD models on an additional three datasets, having global, local, and clustered anomalies respectively, showing that each AD model exhibited distinct performance depending on the type of anomalies. This emphasizes the significance of our proposed AD model selection framework, maintaining high performance across all datasets, and showcasing superior performance across different anomaly types.