Many years before Power BI, there was Power Pivot. (Bonus points
for you if you remember that back then that it was known as PowerPivot.) I
remember attending a Birds of a Feather session at Microsoft TechEd to discuss
the implications of Power Pivot with a group of data professionals. There was
much gnashing of teeth over the perceived horrors of putting data directly into
the hands of users. Then, at the back of the room, a very relaxed gentleman, with
flowing locks and wearing a Hawaiian shirt and Birkenstocks, suggested in the
most soothing of tones, “Hey man, just let the data be free!”

I’ve never forgotten that scene and how it epitomized both the
goals and challenges of self-service business intelligence. On the one hand,
the self-service ideal is to free up data to empower users to discover and use
information in insightful ways. On the other hand, there are legitimate reasons
to control how people access, use, and share data.

Whereas traditional BI imposes many important controls on the
structure, composition, and consumption of data, the process often had
difficulty keeping up with the speed of business. While self-service tools can
accelerate the development and delivery of information to users, the lack of
controls had reintroduced the very problems that traditional BI was supposed to
solve: incomplete and inaccurate data, inconsistent calculations, hard to
repeat processes, and multiple versions of the truth. In short, chaos.

If you’re currently using Power BI and find yourself facing these
very problems, what can you do to conquer the chaos? Implement a data
governance strategy that strikes a balance between an IT-managed information
solution and user-driven exploration of data. Fortunately, Power BI has evolved
over the years since its initial incarnation as Power Pivot to include many
features that can support your data governance goals.

Data governance is a huge subject area and a specific
implementation approach is dependent on many factors, including organization
size, user skills, types of data in use, and the self-service tools available,
to name a few. My intent today is not to provide a comprehensive overview of
data governance in Power BI, but simply to give you a starting point for your
own implementation strategy with specific tactics that leverage features in
Power BI for better data governance.

One of the most important goals of data governance is to ensure
that the data in any shared spreadsheet, report, or dashboard is complete,
accurate, and consistent no matter what. That’s a lofty goal to try to apply to
all data assets in an organization. Instead, make a distinction between shared
data assets for organizational or departmental use and other data assets that
are developed for personal exploration, and then set up policies and processes
that support both use cases. That way, users can work with the data they feel is appropriate for the
question at hand, but can also easily identify sources that have been
officially approved. Importantly, users should be trained in the policies
related to the certification process and understand how the content they create
should be used and shared.

Towards this end, consider the following actions:

Provide
users with a sandbox environment in which they can combine data sources that
they are allowed to access and experiment with different types of calculations
or different ways to present the data.

Power BI has always included the components
necessary for a sandbox environment, regardless if users choose to work in the
desktop application or in a browser accessing the Power BI service online. Each
user can work in an isolated space and has complete freedom to access a wide
variety of data sources, whether certified or not.

If the content is saved or
published to the Power BI service, it stays within the user’s personal
environment called My Workspace. The user may later decide to share the content
with others in a few different ways, as described in ways
to share your work. You can control whether, and how,
content can be shared in the Tenant
Settings page of the Power BI admin portal.

Assign oversight responsibility to at least one individual per department
or subject area. This individual, commonly known as a data steward, reviews
data sources, validates report logic, watches for and eliminates duplicative
efforts, and promotes approved content from a sandbox environment to a shared
location, among other tasks. In addition, the data steward determines who has
access to the promoted content.

Power BI uses app
workspaces to organize content. You can
think of an app workspace as the logical equivalent of a shared folder on a
server. Consider creating separate workspaces to differentiate between
certified and non-certified content. Within a workspace, assign individual
users or groups to appropriate roles
that control access and also define the types of content creation and
management activities they can perform.

For users who only need to
consume the content created by others, all items or a subset of items, can be
published from an app workspace as an app,
which insulates users from any ongoing content changes in the originating app
workspace. In other words, the app is purely for end user consumption, whereas
the app workspace is the collaborative development environment.

Ideally, data stewards should have the
ability to move content between app workspaces when promoting content to a
certified status. However, Power BI does not yet support this capability. Until
this feature is added, the creator’s content in a PBIX file must be published
to the target app workspace. As long as you have edit access to a report (among
a few other limitations), you can download
its corresponding PBIX file from the Power BI service and then
republish it to a new location.

Monitor activity and usage by content and by user. Usage auditing ensures
compliance with policies and standards, and surfaces potentially valuable new
data sources that might be of use to a broader audience.

Power BI provides the following
options for monitoring:

Usage metrics. You can review data for dashboard and report usage from a built-in report or you can use a live connection to the underlying data source for these metrics if you prefer to build a custom report.Audit logs. You can access audited activity details through the Office 365 Security and Compliance Center, or by executing a PowerShell script.

When you take advantage of Power BI’s features with data governance in mind, you can make chaos a relic of the past. Instead, users can make better decisions because they are using higher quality content and more trustworthy data. A cooperative governed environment reduces duplication of effort inherent when users work in isolation and thereby improves everyone’s productivity. And you have better oversight of how data assets are being used–or not being used–and can intervene where appropriate.

Note: This post was originally published in the June 13, 2019 PASS Insights newsletter, but was written a couple of months prior to publication. On June 3, 2019, Microsoft announced the public preview of shared and certified datasets , which is another great feature for data governance in Power BI. Datasets can be certified by data stewards and discovered by users in a dataset catalog that is accessible in both the Power BI Desktop and the online Power BI service. Furthermore, usage metrics and audit logs are captured for these datasets.