Re: [Planner Dev] Uncertainty management / MonteCarlo simulation



Comments inline

On Thu, 2004-04-01 at 08:51, lincoln phipps openmutual net wrote:
> Mark/ Santiago ,
> 
> Some thoughts from me - I didn't actually see Santiago's
> original posting as an email but its on the web archive
> and sounds interesting. Done Monte Carlo on financial
> stuff - but not project times.
> 
> We all know its essential; after all when asking a
> supplier when will 'x' arrive, then they usually quote
> a range of dates e.g. 2-4 weeks and never a precise
> date unless there are penalties for late delivery.
> So we usually plan on the pessimistic duration if
> using anything that doesn't allow a range of durations.
> 
> What parameters do you think we'd need remembered for
> each task across project saves ?.
> 
> I'm guessing we'll need,
> - optimistic duration (3SD from mean),
> - most likely duration, and
> - pessimistic duration (3SD from mean),
> - probability distribution for this duration,

These are the common ones.  To use this method you have to assume some
things in order to translate it to the chosen probability distribution
parameters.

For the triangular distribution you don't have any problem.  If you want
to use the beta distribution, you can set the four parameter based on
PERT assumptions.  For normal distribution we should pick some way to
set mean and std deviation.

Anyway, sometimes it's just better to leave the parameters to be set by
the user.  You could make them autocalculated and if the user changed
them you don't update them anymore, or you can set a beta distribution
with a name Beta (PERT) and another one with Beta only.

> 
> Then given expected time we could store...
> - Earliest Start/End,
> - Latest Start/End,
> 

I would add the slack time and criticality (if it was in the critical
path)

> using the existing forward and backward passes on the Planner
> scheduler routine, with the "Monte Carlo" giving us the
> cumulative probability values. Is that it ? I'm guessing the
> duration probability function would be one of a set list
> of standard functions (like poisson, or uniform or one
> of many others that are used) or a user defined distribution
> table of probabilities.
> 
> /Lincoln.
> 
> Mark Durrenberger wrote:
> 
> > Great question.
> > 
> > I've just completed a basic monte carlo program that works as an add-in 
> > to MS Project (Visual basic)
> > 
> > As I get up to speed with Planner dev, I hope to build the same 
> > capability into planner - and then some...
> > 
> > IN the open source environment it will be substantially easier to add 
> > simulation capability than it is to "bolt on" after market capability 
> > with M$project
> > 
> > Mark
> > 
> > At 05:04 PM 3/31/2004, serquicia Argentina com wrote:
> > 
> >> Hi, I'm new to the list and I wanted to know some questions about future
> >> development.
> >>
> >> Is it planned to introduce any type of uncertainty management or the 
> >> possibility
> >> to run Monte Carlo simulations within planner?  (The first step would be
> >> the possibility to enter the uncertain durations)
> >>
> >> I'm a research assistant doing something about this.  I think that one of
> >> the biggest problems with the tools that implement something like that is
> >> that they were implemented as an after thought.  I find really difficult
> >> to visualize the results of a simulation and hard to tie it with the 
> >> scheduling
> >> of the project.
> >>
> >> I'm not a programer, although I have done some.  In my actual research 
> >> I'm
> >> doing some things in python like a Monte Carlo simulation solver.  It did
> >> it actually to benchmark a new method we are researching.  I've read that
> >> there is a possibility of using python with planner.  What would be a 
> >> good
> >> tutorial or starting point to use planner with python?
> >>
> >> Thanks in advance,
> >> Santiago
> >>
> >> ______________________________________________________________________
> >>
> >> Obtenga gratis su cuenta @Argentina.com con AntiVirus, 20mb de espacio,
> >>
> >> acceso POP3 y SMTP en 24 ciudades                     www.Argentina.com
> >>
> >>
> >>
> >> _______________________________________________
> >> Planner-dev mailing list
> >> Planner-dev lists imendio com
> >> http://lists.imendio.com/mailman/listinfo/planner-dev
> > 
> > 
> > You can lead a boy to college, but you cannot make him think.
> > 
> >                                               Elbert Hubbard
> > 
> > _______________________________________________
> > Planner-dev mailing list
> > Planner-dev lists imendio com
> > http://lists.imendio.com/mailman/listinfo/planner-dev
> > 
> _______________________________________________
> Planner-dev mailing list
> Planner-dev lists imendio com
> http://lists.imendio.com/mailman/listinfo/planner-dev




[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]