Page 149 - Intelligent Digital Oil And Gas Fields

112 Intelligent Digital Oil and Gas Fields

Fig. 4.4 The E&P industry needs processes to transform vast amounts of data into good
operational decisions.

dedicated approach to transform these vast volumes of data into decisions, to
devise processes to transform information into knowledge (Fig. 4.4).
However, according to recent studies and reports in Alain Charles
(2015), the oil and gas industry has been using only 1% of the data it gen-
erates; which means that 99% of acquired data remains to be exploited to
generate business value. With the evolution of the Big Data paradigm,
E&P companies are focusing on mining value from this data, with the main
objective of “getting value from all data by leveraging emerging technolo-
gies and pattern-based techniques for innovation, strategy, faster and better
decisions” (Davis, 2015). Moreover, we increasingly hear the E&P industry
saying that Big Data is now the new oil.
The gradual shift of the E&P industry to digital data-driven technology
in oil fields is expected to improve the productivity of pipeline operation and
safety by 30% (Alain Charles, 2015). Another striking example for potential
improvements is in the pump performance. If globally, the industry
improved pump performance and efficiency by even 1%, it could increase
oil production by half a million barrels per day and generate an additional
$19 billion of revenue per year. Moreover, the global oil and gas industry
is facing major challenges where improved data analytics could help, for
example, extraction costs are rising and the market has been affected by a
dramatic drop in oil prices and the turbulent state of international politics,
which adds to the uncertainty in exploration and drilling for new reserves.
To help address these and other challenges, key companies in E&P are
looking to Big Data in search of maximum optimization at minimum cost.
Fig. 4.5 shows the main areas of interaction between attributes of Big Data
analytics and E&P business segments with the most potential to add value.
In the current literature, experts usually refer to Big Data in terms of “the
Vs.” Brul (2013) and Davies (2014) categorize Big Data in terms of 3 Vs—
e
volume, velocity, and variety. The Oil Review (2015) considers 4 Vs, by
adding value, and Davis (2015) goes a few steps further and defines 7 Vs
as the 7 pillars of Big Data, which include the following:
• Volume: this component of Big Data addresses massive quantities of
acquired data, rising from terabytes to petabytes. Traditionally, the data
are collected and loaded into data warehouses. With Big Data, the focus