Optimization & What-if Simulation Engine

What is Optimization & What-if Simulation?

Optimization is the process of finding the specific, optimal and best solution from the set of all the feasible solutions. This approach takes into account key variables, constraints and trade-offs so as to determine an optimal solution that is feasible and achieves certain objectives.

An optimization process consists of maximizing or minimizing a real function by systematically choosing input values from an allowed set and computing the value of the function and thus finding the best solution to a problem. In real life, optimization helps improve the efficiency of a system. It is used in a myriad of areas such as medicine, manufacturing, transportation, supply chain, finance, government, physics, economics, artificial intelligence, and so on. In an optimization model, the goal can be to minimize cost in a production system or in marketing, the goal can be to maximize the profit by targeting the right customers.

Simulation is the process to evaluate multiple different scenarios in an attempt to understand how a system would work. In simulation, a user runs multiple scenarios to predict how a system or process performs under different conditions. It allows the user to determine how a system responds to different inputs so as to better understand how it operates.

What-if Simulation is a data-intensive simulation with a goal to inspect the behavior of a complex system such as the corporate business or a part of it, under some given hypotheses called scenarios. In particular, what-if simulation measures how changes in a set of independent variables impact a set of dependent variables with reference to a given simulation model.

Why do you need Optimization & What-if Simulation?

There is an increase in demand by the operators using the Business Value Applications (BVAs) to get the optimized values (best values of the variables, which yield the desired quality/output) apart from the predicted values from the AI/ML models. BVAs will take these optimized values as inputs and monitor the predicted values. If the predicted value falls out of the optimized value range, then the alert is raised in the respective BVA dashboard so that the operator can take the necessary actions to bring the predicted value closer to the optimized value.

In order to be able to evaluate beforehand the impact of a strategic or tactical move so as to plan optimal strategies to reach their goals, decision makers need reliable predictive systems. Hence, there is a need to perform the What-if Simulation, where an operator can understand what would be the impact on the quality and output if the values of the variables change by so and so value.

The Genix Platform offers the Optimization & What-if Simulation Engine to address the need for Optimization and What-if Simulation features, which provide better monitoring and control over the system.

Optimization & What-if Simulation Engine is a Genix application, which helps in finding the optimal values of the control parameters based on the objective defined through proven optimization methods. The AI/ML model is being used to find out the optimal values, which can be monitored through business value applications for any deviation leading to proactive control. The model driven, what-if simulation provides actionable insights on objective functions by simulating control parameters.

Optimization & What-if Simulation Engine enables you to create an optimization job by defining the optimization job details, models to be consumed, objective to be achieved, scoring mode, bounds and constraints. Then, run different models, select optimization method, run optimization, view optimization result and benchmark the best optimization result. It also enables you to simulate the variables, run what-if simulation and view the result of the simulation instance in both tabular and chart view.

An Objective is a quantitative measure of the performance of the system that you want to minimize or maximize. In manufacturing, you may want to maximize the profits or minimize the cost of production, whereas in fitting experimental data to a model, you may want to minimize the total deviation of the observed data from the predicted data.

Scoring Mode is the optimization objective, which combines multiple objectives of range/minimization/maximization.

The Variables or the unknowns are the control parameters of the system for which you want to find values. In manufacturing, the variables may be the amount of each resource consumed or the time spent on each activity, whereas in data fitting, the variables can be the parameters of the model. Bounds of the variables defines the search space (base values/delta step with minimum and maximum values).

The Constraints are the functions that set boundaries to the search space defined by the bounds. In manufacturing, the amount of a resource consumed cannot exceed the available amount.

You can view all the details and the status of all the optimized jobs created in the Jobs page, where you can create a copy of an existing optimization job, edit or delete an existing optimization job.

To access the Optimization & What-if Simulation Engine, go to Genix Platform > Digital App Center > Optimization Engine > Optimization & What-if Simulation. The Job List page is displayed.