Smart Meter Data Analysis Using Big Data Tools

摘要

In recent years, the problem of electrical load forecasting gained attention due to the arrival of new measurement technologies that produce electrical energy consumption data at very short intervals of time. Such short term measurements become voluminous in very short time. The availabilityof big electrical consumption data allows machine learning techniques to be employed to analyze consumption behavior of every consumer on a greater detail. Predicting the consumption of a residential customer is crucial at this point of time because tailor-made consumer-specific tariffs willplay a vital role in load balancing process of Utilities. This paper analyzes the electrical consumption of a single residential customer measured using a smart meter that is capable of measuring electrical consumption at circuit level. The issues and challenges in collecting the data andpre-processing required for making them suitable for data analytics are discussed in detail. A comparison of the performance of different machine learning algorithms implemented using Python’s Scikit-learn module gives an insight on the consumption pattern.