How Cairn Oil & Gas is using IT to overcome one business challenge after another
Cairn Oil & Gas is a major oil and gas exploration and production company in India. It currently contributes 25% of India’s domestic crude oil production (about 28.4 MMT) and aims to account for 50% of total production. The company plans to spend ₹3.16.09 crores (₹31.6 billion) over the next three years to boost its production.
The oil and gas industry currently faces three major challenges: massive price swings with volatile commodity prices, capital-intensive processes and long lead times, and managing production declines.
Sandeep Gupta, Chief Digital and Information Officer at Cairn Oil & Gas, uses advanced technologies to address these challenges and achieve business goals. “We have taken a value-oriented approach to deploying technological solutions. We work with multiple OEMs and service integrators to implement highly scalable projects across the value chain,” he says.
Lowering operational costs with drones, AI and edge computing
The oil and gas industry faces huge price volatility due to volatile commodity prices and geopolitical conditions. In such a scenario, it becomes critical for the business to control costs.
Sustainable oil production depends on an uninterrupted power supply. However, managing transmission lines is an expensive, labor-intensive task. For Cairn, this meant managing 250 km of power lines spread over 3,111 square kilometres. They supply power to the company’s Mangala, Bhagyam and Aishwarya oil fields and the Rageshwari gas fields in Rajasthan.
To reduce operational costs, the company decided to deploy drones. The images captured by the drones are passed through an AI image recognition system. The system analyzes potential damage to power lines, predicts potential points of failure and proposes preventive measures, encouraging data-driven decision-making rather than operator judgment.
“Algorithms such as convolutional neural networks were trained on images captured while overhead power lines were running in their ideal state. The algorithm then compares subsequent images captured at a six-month interval when any anomalies are recorded. An observation is then recorded in placed the portal so that the maintenance team can take corrective and preventive actions,” says Gupta.
This is a service contract between Cairn and the maintenance provider where monitoring is performed every two years for 220 kV power lines and annually for 500 kV power lines.
“Since the implementation of drone-based inspection, the average time between failures has increased from 92 to 182 days. This has reduced oil loss to 2,277 barrels per year, resulting in cost savings worth approximately ₹12 crores [₹120 million]† Effectively allowing employees to perform maintenance work allows a small team to work more efficiently and reduces the manpower required,” says Gupta.
The remote location of operations coupled with the sheer amount of data (Cairn generates approximately 300 GB of data per day) generated makes the oil and gas industry ideal for using edge-based devices for computing.
With smart edge devices, critical parameters are stored and processed in remote locations. The devices are field installed and transmit data over the MQTT protocol where cellular network connectivity is available. They store data up to 250 GB in the Microsoft Azure cloud and perform analytics using machine learning algorithms and provide intelligent alarms.
Without these devices, the generated data would be transported to distant data centers, congesting network bandwidth. “Edge computing helps reduce the cost of our IT infrastructure, as lower bandwidth is enough to handle the large amount of data. These devices in deployment monitor critical operational parameters such as pressure, temperature, emissions and flow rate. The opportunity cost of not having edge computing would result in the need for higher network bandwidth, which equates to about 2x the current network cost,” said Gupta. “This also affects the health and safety risks of our personnel and equipment.”
Reducing lead times through a cloud-first strategy
The oil exploration process has a lead time of about three to five years and requires a huge capital commitment. Out of these three to five years, petrotechnical experts (geologists, geophysicists, petroleum engineers and reservoir engineers) spend a significant amount of time simulating models that require enormous computational power.
Petrotechnical workflow involves the evaluation of the characteristics of the underground reservoir to identify the location for drilling the wells. These workflows are performed by petrotechnical experts through multiple suites of software applications that can help identify the location and trajectory of wells to be drilled.
“Capital allocation and planning for future exploration have become more risky due to long lead times. To achieve our goals, increasing computer capacity is essential. To do this, we adopted and executed a cloud-first strategy,” says Gupta. For example, Cairn has completely migrated the workloads for petrotechnical workflows to the cloud. “This migration has removed the limitations of on-premises compute capabilities. As a result, there is almost a 30% reduction in time to first oil,” he says.
Manage production decline through predictive analytics
Cairn has significant volume, variety and speed of data coming from a variety of production, exploration and administration sources. “Using this data, we have implemented multiple large-scale projects, including predictive analytics, predictive modeling control, and reservoir management, which have scaled across multiple locations,” Gupta says. Model Predictive Control (MPC) is a technology where the equipment is monitored for various operating parameters and then controlled in a certain range to get maximum efficiency while preserving the constraints in the system.
At the heart of this is Disha, a business intelligence initiative that uses dashboards that drive essential, actionable insights. “The philosophy in developing Disha was to make the right data available to the right people at the right time. We wanted to remove file-based data sharing and reporting as it takes a lot of time to create these reports. We have linked data from various sources such as SAP HANA, Historian, Microsoft SharePoint, Petrel, LIMS and Microsoft Azure cloud into one Microsoft PowerBI ecosystem where tailor-made reports can be created,” says Gupta.
Disha was developed over three years in a hybrid mode with an in-house team and an analytics provider. It offers more than 200 custom dashboards, including a well-monitored dashboard, a production optimization dashboard, a CEO and CCO dashboard, and a rig planning dashboard.
“Because data is now easily and quickly accessible in an interactive format across the organization, which was previously limited to a select few, corrective actions for resource allocation are now based on the data,” said Gupta. “For example, we use Disha to monitor the parameter and output of the electronic submersible pump, which processes oil and water. It helps us track the gains made from the implementation of MPC. All of this enables better decision making and has helped to allocate resources in an optimal way, managing the decline in productivity.” Going forward, Cairn plans to partner with a few major analytics providers and build a single platform to contextualize its data and deploy micro-solutions depending on business needs. “This will be a low-code platform that allows individual teams to build their own solutions,” Gupta said. “The initiatives aim to maintain production levels while reducing the time to first oil. Some of the initiatives include monitoring of artificial elevator systems, well monitoring and validation of well tests,” said Gupta.