Victor? Mayer? Sch?nberg has pointed out prospectively in the book "The Age of Big Data: The Great Transformation of Life, Work, and Thinking" that the information storm brought by big data is transforming our life, work, and thinking, and that big data opens up a major transformation of the times. The concept of energy big data is the related technology and idea of collecting, processing, analyzing and applying data in energy fields such as electricity, oil, gas and other fields as well as data in other fields such as population, geography and meteorology in a comprehensive way. Energy big data is not only the in-depth application of big data technology in the field of energy, but also the deep integration of energy production, consumption and related technological revolution with the concept of big data, which will accelerate the development of the energy industry and the innovation of the business model. 2013 is the first year of big data in China. In March 2013, the Informatization Committee of the Chinese Electrical Engineering Society released the White Paper on Big Data Development in China, designating 2013 as the "First Year of Big Data in China", which set off a research boom of big data in power. As the traditional power industry is being transformed to the energy Internet, the arrival of the era of big data and cloud computing will inject new vitality into the development of the traditional power industry, the traditional power industry is about to undergo revolutionary changes.

Electric power big data mainly comes from the power production and electricity use of power generation, transmission, substation, power distribution, electricity and scheduling of each link, can be broadly divided into three categories: First, the grid operation and equipment testing or monitoring data; Second, the electric power enterprise marketing data, such as trading tariffs, sales of electricity, electricity customers, and other aspects of the data; Third, the electric power enterprise management data. Electric power big data has four characteristics: (1) large data volume: petabytes; conventional dispatch automation system contains hundreds of thousands of collection points; power distribution, data center will reach ten million; (2) a wide range of data types: real-time data, historical data, text data, multimedia data, time-series data, and other types of structured, semi-structured data, as well as unstructured data; (3) low density of value: the vast majority of data collected is normal data, and the vast majority of data collected is normal data. The vast majority of the data collected are normal data, only a very small amount of abnormal data, and abnormal data is the most important basis for state overhaul; (4) fast processing speed: analyze a large amount of data in a fraction of a second to support decision making.