Client Description

Pioneer Natural Resources Company is an independent oil and gas exploration and production company. The Company engages in onshore oil and gas drilling, exploration, and production in the United States.

Oil and gas explorer Pioneer Natural Resources’ frontier is not on the Western prairies, but below ground in the oil and gas basins of West Texas and a gas basin in the Southern Rocky Mountains. The large independent exploration and production company boasts proved reserves of more than 725 million barrels of oil equivalent. The vast majority of the company’s reserves are found in Texas (primarily in the oil rich and relatively low cost Permian Basin oil fields) and in Colorado (the Raton gas field). Pioneer Natural Resources has stakes in nearly 10,000 net producing wells.

Irving, Texas-based Pioneer’s single operating segment engages in oil, NGL (natural gas liquids), and gas exploration and production, primarily in the Spraberry/Wolfcamp oilfield in the Permian Basin in West Texas which holds some 75% of the company’s total proved oil and gas reserves. It employs oil drilling and hydraulic fracturing techniques.

Its development areas are the liquid-rich Eagle Ford Shale field in South Texas, the Raton gas field in Southern Colorado, the West Panhandle gas and liquids field in the Texas panhandle, and the Edwards gas field in South Texas.  Its 11,000-plus gross producing wells mine about 85 million barrels of oil each year.

Challenge

Pioneer was using several vendors for its IOT data analytics. In spite of using several vendors they were still challenged with integrating data between these vendor data silos. And data was not in a uniform consistent format. An in-house solution was necessary to avoid paying vendors and also to bring data in-house for data exploration, advanced deep analytics that helps business improve operations and save costs.

Solution

iOLAP helped Pioneer architect, build & develop a Hadoop platform (Cloudera) for storing and processing data. Data was processed in real-time and as well as in batches. IOT sensor data was processed in real-time using Cloudera, StreamSets, Spark, Impala, Hive technologies. SpotFire was used for reporting. Microsoft Azure was used as IAAS cloud platform. DataStax Enterprise (Cassandra) was used for real-time analytics/model scoring, while Hadoop was used for batch processing and model training. Data Lake was built to support cross-platform analytics between data from data warehouses, IOT sensors & historians.

Benefits

The new Hadoop platform enabled Pioneer to integrate all its structured, unstructured & semi-structured data in one place (data lake). By bringing IOT sensor data in-house, Pioneer was able to run critical models to predict equipment failures, improve well operations resulting in significant cost saving. Users were able to seamlessly query both real-time and batch data using various tools and get data in consistent format.

  • Tools: Cassandra | Cloudera | Hive | Impala | Kafka | Oracle Exadata | Spark | Spotfire | StreamSets
  • Categories: Analytics, Big Data, Enterprise Voice, Hadoop
  • Tags: Energy