Driving Profitability in Oil and Gas production Operations by Leveraging on Business Process Automation Solutions: The AI Journey

Abstract

Abstract The Oil and Gas industry, traditionally non-digital native, is experiencing a significant uptick in the adoption of technology throughout its value chain. This paper unveils a compelling use case of the Microsoft Power series—Power BI, specifically—in revolutionizing reporting, streamlining approval processes, and optimizing for maximum economic outcomes. NNPC E & P Limited (NEPL) is the upstream operating subsidiary of the national oil company, NNPC Limited. This role presents a unique challenge of managing assets across various operational models. This raises the question of finding a way around creating a central production reporting system from which insights can be drawn for data-driven decision-making. This also opens the door to the potentially leverage on predictive analytics and artificial intelligence in revenue forecasting. The current challenge can be is summarized as lack of a standardized reporting template, long lead times in producing management reports, duplication of efforts in data entry and lack of a single source of truth. The Microsoft Power series, encompassing Power BI, Power Apps, and Power Automate, offers a versatile and integrated solution that empowers organizations to streamline processes, enhance data visualization, and automate workflows. In this paper, we delve into the areas where Power Platform has been successfully implemented to improve operational efficiency, data-driven decision-making, and collaboration across various facets of Oil and Gas production in NEPL. Data Entry and Processing: Microsoft’s collaborative workspace of SharePoint, Microsoft Teams and OneDrive played a pivotal role in setting up a data pipeline that streams data onto a central database in real-time. Data Manipulation: Data entry is partially decoupled from data manipulation as the ETL (Extract, Transform and Load) protocol is used. Data Visualization and Analytics: Power BI was used to create dynamic dashboards, enabling real-time monitoring of critical production metrics, reservoir performance, and equipment health. This was replicated across the different levels of organizational hierarchy. Conclusion & Outlook: The implementation of this solution has successfully led to the creation of a database with single-point entries, eliminated the duplication of efforts, automated the production management reports, and laid the foundation for a digitally transformed future where AI is leveraged for maximum profit. All these has been done at no cost. The outlook is to explore the predictive capabilities using the collected data and AI algorithms.