Topic: MATLAB
Download (105) times
Last Download at Monday 23rd of April 2012 12:29:37 AM
Improving Simulink Design Optimization Performance Using Parallel Computing
Estimating plant model parameters and tuning controllers are challenging tasks. Optimization-based methods help to systematically accelerate the tuning process and let engineers tune multiple parameters at the same time. Further efficiencies can be gained by running the optimization in a parallel setting and distributing the computational load across multiple MATLAB workers.
To run a Simulink Design Optimization problem in parallel, we launch multiple MATLAB workers with the matlabpool command for an interactive parallel computing ses- sion2 and enable a Simulink Design Optimization option; no other model configuration is necessary. Figure 3 shows the optimization speed-up when running the HL-20 problem in parallel.
MATLAB workers run in roughly half the time, while the quad-core experiments using 4 MATLAB workers run in roughly a quarter of the time. Because of the overhead associated with running a simulation in parallel, a minimum number of simulations is needed to benefit from parallel computing. This crossover point can be seen on the extreme left of the two plots in Figure 4. It corresponds to 8 simulations in the dual- core case and 6 in the quad-core case
The problem complexity by increasing the number of parameters. In Figure 6 we increase the number of MATLAB workers as we increase the number of parameters. The plot shows that, if we have enough workers, running an optimization problem with more parameters takes the same amount of time as one with fewer parameters.
Source: www.mathworks.com
Related PDF Files
Comments for Improving Simulink Design Optimization Performance Using Parallel Computing