From a utility owner’s perspective, cost risk analysis means determining that the amount of capital expenditure allocated to a venture is appropriate, i.e. the most cost-sensitive variable in our project is time.
We also have to consider that CAPEX projects have a well-earned reputation for running over with regard to time. Often, you have competing work, competing work phases and limited resources. There’s also a considerable degree of dependency between the sequence of design, procurement, fabrication, delivery, installation, commission, and closeout. Such a highly sequential set of dependencies puts the owner organisations at extreme schedule risk.
But what if we could use science to understand a project’s risk and uncertainty upfront and set our expectations closer to reality right from the beginning? Driven by today’s Artificial Intelligence, or AI, project risk analysis brings a new layer of value and depth for utility owners.
The “Best Case Scenario” Trap
Many people are familiar with the traditional risk analysis process, where we start with what we call a deterministic forecast. We strip out any contingency already built into that forecast because, ultimately, we’re trying to ascertain the percentage of contingency. InEight can then model the risk through two variables: uncertainty and actual threats. We then do a risk analysis, which amounts to running the project or simulating executing the project thousands and thousands of times. Then, out of that come the risk results.
Unfortunately, traditional estimating and scheduling tend to generate a best-case scenario rather than a most likely scenario. This is because a planner or scheduler will develop a schedule forecast, but very rarely will that forecast include some potential unknowns in the form of risk events that could happen during execution. So, the plan that is created assumes uneventful, perfectly executed events. And as we all know, best-case scenarios very rarely occur.
How AI can Help
One giant step forward for utilities about AI involves eliminating some of the statistical complexity that legacy risk analysis carries. Previously, we would interview team members and ask them for three-point estimates or distributions of best, most likely and worst-case scenarios. Well, that’s very difficult to extract from a team member. But with AI, we have large quantities of historical data at our fingertips. The benefit is that we’re no longer limited to just three-point estimates. For example, if we have ten historical projects in our AI knowledge library, we can end up with an input distribution with ten points, not three. So it becomes much more accurate.
Another challenge with traditional risk analysis has been to accurately capture those inputs. With AI, we can leverage historical project information throughout the project life cycle. Computers can now review prior project schedules, cost estimates and even previously generated risk registers and start making suggestions to the planner and the scheduler during the planning process. This eliminates the need to build a plan and then reactively come back and throw contingency at it later.
Overall, with AI, we’ve reduced the overhead and complexity of developing a risk register by allowing the computer to make suggestions based on historical risk events that have occurred before that impact schedule and cost. That’s an incredible step forward because now we can build our risk register on human expertise and the suggestions of AI, calibrating a risk register based on the best of machine and human input.
Learn more about InEight’s risk analysis and construction scheduling software.
Related Articles:
- A DIY toolbox for predictive maintenance
- Reviewing water research with Voeu
- Assessing risk with Annette