GAMS World Forum

Syntax :: $ifThen set X or Y :: Author zamry

no_email@example.com (zamry) — Mon, 01 Apr 2024 17:38:40 +0000

Hello,

Is there a way to execute the following condition when solving a model?

$ifThen set X or Y
Solve MODEL using nlp minimizing OBJ;
$else
Solve MODEL using lp minimizing OBJ;
$endIf

X and Y are compilation variables, and either one exists at a time.

Thanks,
Zamry

Syntax :: Re: $ifThen set X or Y :: Reply by bussieck

no_email@example.com (bussieck) — Tue, 02 Apr 2024 05:57:28 +0000

No, the "$if set" only works on a single compile time variable name, not an expression. You can work around this by having a parallel set of numerical compile time variables and then use $ifThenE:

Code: Select all

$set xset 0
$if set x $set xset 1
$set yset 0
$if set y $set yset 1
$log %xset%%yset%
$ifThenE (%xset%)or(%yset%)
Solve MODEL using nlp minimizing OBJ;
$else
Solve MODEL using lp minimizing OBJ;
$endIf

-Michael

Syntax :: Re: $ifThen set X or Y :: Reply by zamry

no_email@example.com (zamry) — Tue, 02 Apr 2024 14:00:36 +0000

Thanks Michael!

Syntax :: Re: Error 2, Error 149, Error 243 :: Reply by Rodrigue

no_email@example.com (Rodrigue) — Mon, 01 Apr 2024 10:17:12 +0000

Hello Aziz,

You might be a French speaker.
J'ai crois que tes équations ont un sérieux problèmes. Je ne sais pas comment tu les as obtenues. J'ai néanmoins fourni quelques pistes qui aident à corriger ton problème.

Cordialement,
Rodrigue

Attachments

new.gms (14.24 KiB)

Syntax :: Re: Error 2, Error 149, Error 243 :: Reply by Essouaied Aziz

no_email@example.com (Essouaied Aziz) — Mon, 01 Apr 2024 15:58:54 +0000

@Rodriguez

Merci bien pour votre réponse, ça m'a aidé à comprendre les défauts de mon code.
Mais là, ça me donne des résultats un peu étrange, finalement, j'ai besoin de minimiser le nombre de bus par lignes et par saison, tout en servant la méme demande par ces bus.
Les résultats sont du genre "668.000" pour un nombre de bus, ce qui n'est pas assez logique déjà. Je pense qu'il faut multiplier le résultat do code que vous avez suggérer par le facteur FV0(i,j), qui est le minimum de voyages qu'un bus peut faire par ligne i et par période j.
Aussi, je ne comprends pas pourquoi on a définit W.up, X. up, Y.up et Z.up par 34454 alors que la taille de la flotte des bus est de 76.

Votre clarification me sera utile.
Merci

Syntax :: Re: Error 2, Error 149, Error 243 :: Reply by Rodrigue

no_email@example.com (Rodrigue) — Wed, 03 Apr 2024 06:18:11 +0000

Cher Aziz,

Je n'ai pas solutionné ton problème. J'ai juste fait en sorte que ton code fonctionne. Les valeurs maximales que j'ai affectées à ces variables (en utilisant l'extension.Up) permettent juste que certaines valeurs croissent infiniment et empêchent GAMS de trouver une solution à ton problème. C'est à toi de les modifier pour attribuer des valeurs raisonnables.

Je dis encore ton modèle ne me semble pas bien monté. Il faut repenser les équations et s'assurer qu'elles sont correctes. Tu ne peux pas en l'état actuel interpréter ce que je t'ai envoyé. Ça ne signifie rien de bon.

Cordialement

Syntax :: Re: Error 2, Error 149, Error 243 :: Reply by Essouaied Aziz

no_email@example.com (Essouaied Aziz) — Wed, 03 Apr 2024 08:51:39 +0000

@Rodriguez

Cher Rodriguez, merci beaucoup pour la réponse. Je comprends, je vais essayé de travailler encore sur le code et le solutionner (même si je suis encore un débutant à ce niveau).
Je partagerais le résultat une fois qu'il est trouvé.

Cdt;

Syntax :: A problem with parentheses :: Author Essouaied Aziz

no_email@example.com (Essouaied Aziz) — Wed, 03 Apr 2024 16:15:55 +0000

Hello GAMS users;

I'am running a GAMS code with this command:

W.lo(i, j)$[(D(i, j)/55) ≤ (FV0(i, j) ∗ P(i) ∗ 55)] = FV0(i, j)/55;

Yet, I always get "Error 8: ')' expected", I've tried my best to count the parentheses and correct the command, but i didn't succeed.

Any help with this please?

Thnaks!

Syntax :: Re: A problem with parentheses :: Reply by vistro

no_email@example.com (vistro) — Thu, 04 Apr 2024 05:31:34 +0000

Try this: W.lo(i, j)$(D(i, j)/55 <= (FV0(i, j)* P(i) * 55) ) = FV0(i, j)/55;

Syntax :: Re: A problem with parentheses :: Reply by bussieck

no_email@example.com (bussieck) — Thu, 04 Apr 2024 07:06:13 +0000

Not sure what editor you used, but GAMS does not like your "≤" nor the "∗". These are unicode characters not part of the GAMS language, hence the compiler gets confused. Just use the regular ASCII characters/character sequence "<=" and "*".

-Michael

Syntax :: Re: A problem with parentheses :: Reply by Essouaied Aziz

no_email@example.com (Essouaied Aziz) — Thu, 04 Apr 2024 07:47:01 +0000

@vistro and @bussieck
Thnak you both of you for the help!

Syntax :: Connecting ordered sets :: Author Exlaw

no_email@example.com (Exlaw) — Wed, 10 Apr 2024 16:09:28 +0000

Hello,
I am currently learning GAMS and I came up on this issue:
I am using these sets:

Sets
y "Set of years in the planning horizon" /y2023*y2045/
d "Set of all days in a year" /d1*d366/
t "Set of all hours in a day" /h1*h24/;

Then I am importing data for some parameters from excel. e.g. E(y,d,t)
Therefore I would prefer not to change the way my sets are defined, because I will need to change everything in my excel as well.

And further down the code, in certain equations I need to use variables like this one: "E_b_res(y,d,t-1)"
So is should work like this:

if ( ord(t)=1 AND ord(d)=1 AND E(y-1,'d366','h24') <> 0 )
x=E_b_res(y-1,'d366','h24')
else if ( ord(t=1) AND ord(d)=1 )
x=E_b_res(y-1,'d365','h24')
else if( ord(t=1) )
x=E_b_res(y,d-1,'h24')
else
x=E_b_res(y,d,t-1)

Where x is the value I need E_b_res(y,d,t-1) to have.

*note: in the E(y-1,'d366','h24') <> 0 part, I am checking whether or not its a leap year. My excel doesn't input values for d366 of non leap years so this is an easy way of checking

This felt very complex to do using the $ operator. I am also considering using Multi-Dimensional Sets, but I couldn't really figure out how they work just using the documentation. For example: why can't I define a variable over a multi-dimensional set?
I am pretty sure there are some easy solutions for this that I am missing.

Syntax :: Re: Connecting ordered sets :: Reply by bussieck

no_email@example.com (bussieck) — Thu, 18 Apr 2024 11:56:01 +0000

If you need the previous "period" in your model, you should think in terms single dimension time periods rather than (y,d,t) tuples and model with this. If you need occasionally access to data of a particular year, date, hour of a period you can do this by mapping from the period to the y,d,t tuple and access the data (or variable). I hope the GAMS code below will help you understand what I mean.

-Michael

Code: Select all

Sets
  y "Set of years in the planning horizon" /y2023*y2045/
  d "Set of all days in a year" /d1*d366/
  t "Set of all hours in a day" /h1*h24/;
  
$eval P card(y)*card(d)*card(t)
Set p period / p1*p%P% /;

Parameter E(y,d,t), cnt /0/;
loop((y,d,t), cnt=cnt+1; E(y,d,t) = cnt);

* Remove data for non leap years
set leap(y) / y2024, y2028, y2032, y2036, y2040, y2044 /;
E(y,'d366',t)$(not leap(y)) = 0;

* Now match non-zero E to p:
set ydt(y,d,t), pydtmap(p,y,d,t);
option ydt



Syntax :: Re: Connecting ordered sets :: Reply by Exlaw
no_email@example.com (Exlaw) — Fri, 19 Apr 2024 18:20:38 +0000
I actually managed to do it using the $ operator pretty easily, thank you thought either way!


Syntax :: BESS modeling Error 148 and 258 in obj function. :: Author GeGo
no_email@example.com (GeGo) — Sat, 20 Apr 2024 13:06:10 +0000
Hello i am new in gams and i want help with a battery energy storage system modeling in GAMS, 

I get in the last line the following errors. I cant understand why,

 *** Error 148 in C:\Users\eirini\Documents\GAMS\Studio\workspace\gams 240\PPA_PV_BESS.gms[ERR:"C:\Users\eirini\Documents\GAMS\Studio\workspace\gams 240\PPA_PV_BESS.gms",115,40][LST:102]

    Dimension different - The symbol is referenced with more/less

       indices as declared

*** Error 257 in C:\Users\eirini\Documents\GAMS\Studio\workspace\gams 240\PPA_PV_BESS.gms[ERR:"C:\Users\eirini\Documents\GAMS\Studio\workspace\gams 240\PPA_PV_BESS.gms",115,42][LST:102]

    Solve statement not checked because of previous errors

--- PPA_PV_BESS.gms(115) 3 Mb 2 Errors[FIL:"C:\Users\eirini\Documents\GAMS\Studio\workspace\gams 240\PPA_PV_BESS.gms",115,0]

*** Status: Compilation error(s)[LST:151]

--- Job PPA_PV_BESS.gms Stop 04/20/24 15:52:36 elapsed 0:00:10.719



I want to maximize income so i am trying to fine the best combination of z and h for all t.



This is my code:

Set t "Time" /t1*t240/;

Set h "hour of bess" /h1*h4/;

Set z 'safety level of contracted energy' /z1*z2/;





Parameters

 P_real(t) 

 P_ppa(t,z)

 P_excess(t,z)

 pvf(t) pv is in producing

 mp(t) more profitable market price

 iseop(t,z) there is excess of power P_real-P_ppa>0

 SoCz1(t,h) 'state of charge time, hours of batery, z1'

 SoCz2(t,h) 'state of charge time, hours of batery, z2'

 SoC(t,h,z) 'state of charge time, hours of batery, safety level'

 P_b2g(t,z) 'Power battery to grid';

 

 

$CALL GDXXRW P_r.xlsx trace=3 par=P_real rng=New_Sheet! rdim=1

$CALL GDXXRW P_p.xlsx trace=3 par=P_ppa rng=New_Sheet! rdim=1 cdim=1

$CALL GDXXRW P_e.xlsx trace=3 par=P_excess rng=Sheet1! rdim=1 cdim=1

$CALL GDXXRW pvf.xlsx trace=3 par=pvf rng=New_Sheet! rdim=1

$CALL GDXXRW iseop.xlsx trace=3 par=iseop rng=Sheet1! rdim=1 cdim=1

$CALL GDXXRW mp.xlsx trace=3 par=mp rng=New_Sheet! rdim=1

$CALL GDXXRW P_b2g.xlsx trace=3 par=P_b2g rng=Sheet1! rdim=1 cdim=1

$CALL GDXXRW SoC_z1.xlsx trace=3 par=SoCz1 rng=New_Sheet! rdim=1 cdim=1

$CALL GDXXRW SoC_z2.xlsx trace=3 par=SoCz2 rng=New_Sheet! rdim=1 cdim=1





$GDXIN P_r.gdx

$LOAD P_real

$GDXIN

*Display P_real;





$GDXIN P_p.gdx

$LOAD P_ppa

$GDXIN



$GDXIN P_e.gdx

$LOAD P_excess

$GDXIN



$GDXIN pvf.gdx

$LOAD pvf

$GDXIN



$GDXIN mp.gdx

$LOAD mp

$GDXIN



$GDXIN P_b2g.gdx

$LOAD P_b2g

$GDXIN



$GDXIN iseop.gdx

$LOAD iseop

$GDXIN



$GDXIN SoC_z1.gdx

$LOAD SoCz1

$GDXIN



$GDXIN SoC_z2.gdx

$LOAD SoCz2

$GDXIN



SoC(t,h,z)$(ord(z)=1) = SoCz1(t,h);

SoC(t,h,z)$(ord(z)=2) = SoCz2(t,h);



Scalar P_pv_max max PV power out put same as battery /8/;

Scalar SP_ppa strike price of the PPA /85/; 





Parameter  hb(h) hours of battery

/h1 1

 h2 2

 h3 4 

 h4 6/;

 



  



Variables

 obj(h,z) objective function

 C(h) 'variable for CAPEX'

 ppa_i(z) 'income through ppa';

 





*SP_ppa.up = 195;

*SP_ppa.lo = 175;





Equations

 Income ObjetiveFunction

 CAPEX 'capital cost of pv+storage'

 ppa_income 'income through ppa'

 con_ppa_income_lb 'income through ppa lower bound';





*sto 2o athrisma tis antikimenikis sinartisis prepei na mpi mia diadiki metavliti

*b=1 otan SoC(T)>0, b=0 otan SoC(T)<=0 mporei na gini xoris senaria?

Income(h,z) ..  obj(h,z)  =e=  sum(t,(P_ppa(t,z)/1000)*SP_ppa) + sum(t,(mp(t)*(1-pvf(t))*(P_b2g(t,z))))

                                +sum(t,(182*(P_excess(t,z)/1000)*(1-iseop(t,z))*pvf(t)))-C(h);



CAPEX(h) ..   C(h)  =e= (200000*P_pv_max+220000*hb(h)*P_pv_max)*240/(12*8760);

ppa_income(z).. ppa_i(z) =e= sum(t,(P_ppa(t,z)/1000)*SP_ppa);   

con_ppa_income_lb(h,z).. ppa_i(z) =g= 0.5*C(h);







Model PP_PV_BESS /all/ ;

Option mip=cplex;

Solve PP_PV_BESS using lp maximizing obj ;


Syntax :: Re: BESS modeling Error 148 and 258 in obj function. :: Reply by bussieck
no_email@example.com (bussieck) — Sun, 21 Apr 2024 07:20:44 +0000
Hi,



First the is a very nice formatting control to copy and paste code. Please use that. On the particular question. You have an objective variable obj(h,z), so for every h and z there is a variable and you ask the solver to optimize it. A solver can only optimize a single variable not h times z many. So GAMS assumes your obj is a scalar variable and hence complains that you use z as a 2-dim variable in the declaration and equations and as a scalar variable in the solve statement. Perhaps, you want to add all income, then you should redefine your income equation:


Code: Select all
Variables
obj objective function
Income .. obj =e= sum((h,z),sum(t,(P_ppa(t,z)/1000)*SP_ppa) + sum(t,(mp(t)*(1-pvf(t))*(P_b2g(t,z)))));



Hope this helps,

-Michael


Modeling :: Erorr 149 :: Author osmane
no_email@example.com (osmane) — Sat, 06 Apr 2024 23:19:46 +0000
cons8(j).. sum(i, z(i,j)) =e= d(j) * s(i);



why am i getting error 149 here



s(i) service level of state i

d(j) Demand of state j

z(i,j) number of humanitarian kits sent from state i to state j


Modeling :: Re: Erorr 149 :: Reply by bussieck
no_email@example.com (bussieck) — Mon, 08 Apr 2024 06:25:34 +0000
What i should GAMS use for the s(i)? The control of i stops with the sum. The equation is controlled over j.



-Michael


Modeling :: Nonlinear Programming/ Steiner Weber Modell with barriers :: Author Student75
no_email@example.com (Student75) — Mon, 08 Apr 2024 20:32:21 +0000
Hello everyone,

I would like to solve a mathematical model with GAMS and unfortunately I can't find the solution. I would like to solve the following problem with the GAMS programme:



I would like to carry out location planning taking a barrier into account. I will take the federal state of Brandenburg as an example. My demand/requirement locations are all cities in Brandenburg. I get the coordinates of the cities from Excel using geocoordinates and can thus determine the respective distances between the cities. To do this, I form a distance matrix between the cities and insert the values in a table in GAMS. I have one demand point per 200 inhabitants. For example, if I have 1000 inhabitants in a small town, then I have 5 demand points for this town. My barrier should be Berlin. The barrier area is represented by a circle or, even more simply, by the corner points of the rectangle as an area. The corner points of the rectangle represent the area for the barrier zone. The new locations should be shown with X and Y coordinates. If a new location falls on the barrier area, the location is moved to the edge of the barrier. There should also be a capacity limit for the new location. For example, a location can only cover 20 demand points.



My objective function is to minimise the distance between demand points and new locations.There should also be the possibility to limit the number of new locations.



How can I create a formula, that moves locations out of the barrier zone to the edge of the barrier zones?



Many thanks in advance 


Modeling :: Re: Nonlinear Programming/ Steiner Weber Modell with barriers :: Reply by bussieck
no_email@example.com (bussieck) — Tue, 09 Apr 2024 05:24:42 +0000
This is a straight forward text book optimization problem. Get the math straight and GAMS will follow. If you have detailed questions on how to to particular formulations or tasks in GAMS you will find answers here. Getting the math right is the whole fun and you should not shortcut this experience. Good luck and have fun.



-Michael


Modeling :: Zero Division Error :: Author Merey
no_email@example.com (Merey) — Wed, 17 Apr 2024 14:11:13 +0000
Hi! 

I was trying to create a model for Mozambique. But the program gets zero division error every time. I see gaps in my data set, but I don't know how I can fill them. Any ideas?
Attachments
MOZSAM.xlsx (179.57 KiB)
MOZSAM_test.gms (5.86 KiB)



Modeling :: Re: Zero Division Error :: Reply by Fred
no_email@example.com (Fred) — Thu, 18 Apr 2024 12:21:29 +0000
Hi Merey,



Running your code, I get


Code: Select all
--- MOZSAM_test.gms(165) 4 Mb[FIL:"C:\Users\ffian\Documents\support\MOZSAM_test.gms",165,0]
*** Error at line 165: division by zero (0)[LST:522]
--- MOZSAM_test.gms(171) 4 Mb 1 Error[FIL:"C:\Users\ffian\Documents\support\MOZSAM_test.gms",171,0]
*** Error at line 171: division by zero (0)[LST:523]
--- MOZSAM_test.gms(899) 6 Mb 2 Errors


The corresponding lines in the echo print are


Code: Select all
165  tq(c)=SAM("stax",c)/QQ0(c);
[...]
171  tim(c) = SAM("mtax",c)/SAM("ROW",c);


If QQ0(c) is zero for certain c, you get a division by zero error. The question is, what should tq(c) be for those elements in c? You could for example just skip those c by adding a simple dollar condition


Code: Select all
tq(c)$QQ0(c)=SAM("stax",c)/QQ0(c);


You could use the same "trick" in line 171 as well. The question is, whether this gives you the desired results? You are the only person that can answer this question.



I hope this helps!



Fred


Modeling :: How can I random the consecutive number? :: Author celebpanama
no_email@example.com (celebpanama) — Sat, 20 Apr 2024 21:22:50 +0000
I would like to random the consecutive 1 for 4 times in each column j. 

My target is like, for example,


Code: Select all
i/j  1    2    3    4    5   6
1    0    1    0    0    0   1
2    0    1    0    0    0   1
3    0    1    1    0    0   1
4    1    1    1    0    0   1
5    1    0    1    0    1   0
6    1    0    1    0    1   0
7    1    0    0    0    1   0
8    0    0    0    0    1   0
9    0    0    0    0    0   0
10   0    0    0    0    0   0

Thank you for the recommendation.



Right now, I cannot fix 4 times each column



set i /r1*r10/, j /c1*c6/, iter /1*3/;



parameter

    randval(i,j) Random values,

    randvalloop(iter, i,j) Store the random values;



$set seed 123456

loop(iter,

    randval(i, j) = uniformInt(0,1);

    randvalloop(iter, i,j) = randval(i,j);

    );



* Check the results

display randvalloop;


Modeling :: Re: How can I random the consecutive number? :: Reply by bussieck
no_email@example.com (bussieck) — Sun, 21 Apr 2024 07:12:16 +0000
Here is some GAMS code of what I think you want to accomplish. Not sure what the iter was about, but I create now iter many of such tables with random starting position of 4 consecutive ones in the columns:


Code: Select all
set i /r1*r10/, j /c1*c6/, iter /1*3/;

parameter
rowstart, cnt,
randval(i,j) Random values,
randvalloop(iter, i,j) Store the random values;

$set seed 123456
loop(iter,
  loop(j,
    rowstart = uniformInt(1,card(i)-3);
    loop(i$(ord(i)=rowstart),
      for (cnt=0 to 3,
        randvalloop(iter, i+cnt,j) = 1;
      )
    )
  )
);

* Check the results
option randvalloop:0:1:1;
display randvalloop;

-Michael


Modeling :: Re: How can I random the consecutive number? :: Reply by celebpanama
no_email@example.com (celebpanama) — Sun, 21 Apr 2024 18:56:55 +0000
Thank you very much.

I have some question. How GAMS can start 1 from r1 at some column and 1 end up with the last row (r10) in every iteration?  As shown in the table below, 1 can start in row 1 (r1) both c2 and c6, and 1 end at row 10 (r10) in c5.


Code: Select all
      c1   c2   c3   c4   c5  c6
r1    0    1    0    0    0   1
r2    0    1    0    0    0   1
r3    0    1    1    0    0   1
r4    1    1    1    0    0   1
r5    1    0    1    0    0   0
r6    1    0    1    0    0   0
r7    1    0    0    0    1   0
r8    0    0    0    0    1   0
r9    0    0    0    0    1   0
r10   0    0    0    0    1   0


Modeling :: Re: How can I random the consecutive number? :: Reply by bussieck
no_email@example.com (bussieck) — Mon, 22 Apr 2024 13:53:04 +0000
You can just check if no 1-sequence starts in r1 or ends in r10. If that's the case you just take first column or last column to be the start/end. -Michael


Code: Select all
set i /r1*r10/, j /c1*c6/, iter /1*3/;

parameter
rowstart, cnt,
randval(i,j) Random values,
randvalloop(iter, i,j) Store the random values;

$set seed 123456
loop(iter,
  loop(j,
    rowstart = uniformInt(1,card(i)-3);
    loop(i$(ord(i)=rowstart),
      for (cnt=0 to 3,
        randvalloop(iter, i+cnt,j) = 1;
      )
    )
  )
* No start in any column  
  if (sum(j, randvalloop(iter,'r1',j))=0, randvalloop(iter,i,'c1') = ord(i)<5);
* No end in any column  
  if (sum(j, randvalloop(iter,'r10',j))=0, randvalloop(iter,i,'c6') = ord(i)>card(i)-4);
);

* Check the results
option randvalloop:0:1:1;
display randvalloop;


Modeling :: Re: How can I random the consecutive number? :: Reply by celebpanama
no_email@example.com (celebpanama) — Mon, 22 Apr 2024 23:17:04 +0000
It was as I expected. Thank you very much.


Modeling :: Re: How can I random the consecutive number? :: Reply by celebpanama
no_email@example.com (celebpanama) — Wed, 24 Apr 2024 00:02:44 +0000
Sorry to disturb you again. It seems that the patterns in every iteration are fixed. How the same pattern baesd on above conditions will change if I click run every time and set only 1 iteration? I attempt to solve but I am not sure whether it involves in seed or anything? Thank you.


Code: Select all
set t /1*10/, i /1*6/, [b]iter /1*1/[/b];

parameter
rowstart, cnt, q,
randval(t,i) Random values,
randvalloop(iter, t,i) Store the random values

$set seed 123456

loop(iter,
  q = 6  
  loop(i,
    rowstart = uniformInt(1,card(t)-(q-1));
    loop(t$(ord(t)=rowstart),
      for (cnt=0 to (q-1),
        randvalloop(iter, t+cnt,i) = 1;
      )
    )
  )
* No start in any column  
  if (sum(i, randvalloop(iter,'1',i))=0, randvalloop(iter,t,'1') = ord(t)<(q+1));
* No end in any column  
  if (sum(i, randvalloop(iter,'10',i))=0, randvalloop(iter,t,'6') = ord(t)>card(t)-q);
  
);

* Check the results
option randvalloop:0:1:1;
display randvalloop;


Modeling :: Error on finding max value in MIP :: Author Agustino
no_email@example.com (Agustino) — Fri, 26 Apr 2024 08:32:43 +0000
Hi, I stuck on finding max value each column by writing constraint in MIP. Unfortunately, the error was


Code: Select all
 Error 59 Endogenous prod smin smax require model type "dnlp"
 Error 256 equation eq2.. VAR prod smin smax

Suppose I have EM(f,t,i) as the positive variable, which is the result from previous constraints like this


Code: Select all
      i1 i2 i3 i4 i5
f1.t1  7  5  6  0  6
f1.t2  8  4  6  1  6
f1.t3  6  7  3  2  4
f2.t1  8  7  5  3  1
f2.t2  0  5  5  7  0
f2.t3  0  8  0  5  9

Code: Select all
eq2(f,i)..         last(i) =e= smax((t),EM(f,t,i));

So, I would like to fix the above coding and find the max value each column, and then collect in last(i) variable.

My target should be 



last(1) = 8 

last(2) = 8 

last(3) = 6 

last(4) = 7 

last(5) = 9 



Please help me to achieve this MIP model. Thank you.


Modeling :: Re: Error on finding max value in MIP :: Reply by bussieck
no_email@example.com (bussieck) — Sat, 27 Apr 2024 07:03:57 +0000
Hi, you need to reformulate this in a linear way. There is plenty of good literature out there that gives this type of reformulation tricks. I personally like the book Model Building in Mathematical Programming by HP Williams . Knowing the literature and understanding the basics helps you write good models. Nowadays, you can also shortcut and ask ChatGPT:


Can you help me reformulate a non-linear constraint of a mathematical optimization model using the max operator like x(i) = max(j, y(i,j)) into linear constraints with additional binary variables?

Sure, I can help with that. To reformulate a non-linear constraint using the max operator into linear constraints with additional binary variables, you can use a common technique called "big M" method. 



Here's how you can do it:



Let's say you have a non-linear constraint of the form:



x(i) = max_{j} (y(i,j))



You can reformulate it using the following linear constraints:



1. Introduce a binary variable z(i,j) for each pair of indices i and j.

2. Add a constraint ensuring that z(i,j) = 1 if and only if y(i,j) is greater than or equal to all other values of y(i,.):



y(i,j) - y(i,k) <= M (1 - z(i,j)), for all j, k where j <> k



3. Add a constraint enforcing that z(i,j) = 1 if and only if x(i) = y(i,j):



x(i) - y(i,j) <= M (1 - z(i,j)), for all j



4. Add a constraint ensuring that x(i) is no less than any y(i,j):



x(i) - y(i,j) >= 0, for all j



In these constraints, M is a sufficiently large constant, which acts as a "big M" to ensure that the binary variables z(i,j) and the auxiliary variables do not violate the logic of the original non-linear constraint.



Keep in mind that the value of M should be chosen carefully to ensure that it is larger than the maximum possible value of y(i,j) in your problem. If it is too large, it may lead to numerical instability or suboptimal solutions.



This reformulation allows you to model the non-linear constraint using only linear constraints and binary variables.

ChatGPT even gives you some GAMS code


Code: Select all
Sets
    i /i1*iN/
    j /j1*jM/;

Parameters
    M /1000/;  // Adjust this value based on the problem

Variables
    x(i)  // Your decision variable
    y(i,j)  // Your original variable
    z(i,j) binary;  // Binary variable for reformulation

Binary Variables z;

Equations
    non_linear_constraint1(i,j)
    non_linear_constraint2(i,j)
    non_linear_constraint3(i);

non_linear_constraint1(i,j)..
    y(i,j) - y(i,k) - M * (1 - z(i,j)) =L= 0
    $(j <> k);

non_linear_constraint2(i,j)..
    x(i) - y(i,j) - M * (1 - z(i,j)) =L= 0;

non_linear_constraint3(i)..
    x(i) - y(i,j) =G= 0;

Model reformulated_constraint /all/;


which is not correct GAMS code but that's what you get from AI today and you have to use your knowledge and experience to interpret ChatGPT's answer (you should do that with the theoretical one too). In any case here is the correct GAMS code:


Code: Select all
$eolcom //
$set N 10
$set M 15
Sets
    i /i1*i%N%/
    j /j1*j%M%/;

Parameters
    M /1000/;  // Adjust this value based on the problem

Variables
    x(i)  // Your decision variable
    y(i,j)  // Your original variable
    z(i,j) binary;  // Binary variable for reformulation

Binary Variables z;

alias (j,k);
Equations
    non_linear_constraint1(i,j,k)
    non_linear_constraint2(i,j)
    non_linear_constraint3(i,j);
 
non_linear_constraint1(i,j,k)$(not sameas(j,k))..
    y(i,j) - y(i,k) - M * (1 - z(i,j)) =L= 0;

non_linear_constraint2(i,j)..
    x(i) - y(i,j) - M * (1 - z(i,j)) =L= 0;

non_linear_constraint3(i,j)..
    x(i) - y(i,j) =G= 0;

Model reformulated_constraint /all/;


With GAMS you can also just solve the problem as a DNLP and choose a solver that still gives you a global optimal solution. SCIP and LINDO both accepts DNLP with smax. If you have other discrete variables, turn the model into an MINLP. 



Lots of choices... Good luck.

-Michael


Tools :: GDX MPS2GMS :: Author Rester
no_email@example.com (Rester) — Sun, 21 Apr 2024 11:11:04 +0000
I wanted to use tasks from the miplib2017 library. I used MPS2GMS. I received .gdx instead of .mps. Is it possible to provide .gdx as input to the solver? I would be grateful for your help.


Tools :: Re: GDX MPS2GMS :: Reply by bussieck
no_email@example.com (bussieck) — Mon, 22 Apr 2024 06:43:25 +0000
MPS2GMS reads an MPS file and provides you with a pretty generic GMS file and the data (coefficients, bounds, rhs) in the GDX data. Hence, you can solve your MPS file abc.mps by running "mps2gms abc.mps" and afterwards "gams abc.gms".





Good luck,

-Michael


Tools :: Re: GDX MPS2GMS :: Reply by ClssicSupreme11
no_email@example.com (ClssicSupreme11) — Tue, 23 Apr 2024 07:24:57 +0000
Yes, it is possible to provide a .gdx file as input to some solvers. However, it depends on the solver you are using and whether it supports reading data from .gdx files.



GAMS (General Algebraic Modeling System) is often used with .gdx files, as it is a modeling language and environment that supports optimization modeling. If you have a .gdx file generated from MPS2GMS, you can use GAMS to read the data from the .gdx file and formulate and solve your optimization model.



After formulating your optimization model in GAMS, you can solve it using a solver compatible with GAMS, such as CPLEX, Gurobi, or others.



If you have specific requirements or constraints for your optimization problem, please provide more details, and I can assist you further.


API :: Python API picking up wrong GAMS version :: Author akingCCC
no_email@example.com (akingCCC) — Mon, 15 Apr 2024 04:22:43 +0000
I'm trying to install the GAMS Python API using Anaconda, but it is picking up an old version of GAMS (38) that I have installed on my machine.  I have GAMS 38-46 currently installed, and am trying to use the api with Gams 46.4.0, the latest version installed on my machine.



I started by creating a new environment in Anaconda, and in a command line entered:
Code: Select all
(gams_py46) C:\Users\myusername>pip install gamsapi[all]==46.4.0
which seemed to install successfully.  Then (following the instructions in https://www.gams.com/latest/docs/API_PY ... ARTED.html), I entered
Code: Select all
python -c "import gams; print(f'API OK -- Version {gams.__version__}')"
 which gave me
Code: Select all
Traceback (most recent call last):
  File "", line 1, in 
  File "C:\GAMS\38\apifiles\Python\gams\gams\__init__.py", line 32, in 
    from .workspace import *
  File "C:\GAMS\38\apifiles\Python\gams\gams\workspace.py", line 32, in 
    from .database import *
  File "C:\GAMS\38\apifiles\Python\gams\gams\database.py", line 26, in 
    from gdxcc import *
ModuleNotFoundError: No module named 'gdxcc'
so clearly it is trying to get something from GAMS 38 instead of GAMS 46.  So I tried 
Code: Select all
(gams_py46) C:\Users\myusername>python -m site
and got
Code: Select all
sys.path = [
    'C:\\Users\\myusername',
    'C:\\GAMS\\38\\apifiles\\Python\\gams',
    'C:\\Users\\myusername\\%PYTHONPATH%',
    'C:\\Anaconda3\\envs\\gams_py46\\python311.zip',
    'C:\\Anaconda3\\envs\\gams_py46\\DLLs',
    'C:\\Anaconda3\\envs\\gams_py46\\Lib',
    'C:\\Anaconda3\\envs\\gams_py46',
    'C:\\Anaconda3\\envs\\gams_py46\\Lib\\site-packages',
]
USER_BASE: 'C:\\Users\\myusername\\AppData\\Roaming\\Python' (exists)
USER_SITE: 'C:\\Users\\myusername\\AppData\\Roaming\\Python\\Python311\\site-packages' (doesn't exist)
ENABLE_USER_SITE: True
The instructions tell me to correct the GAMS path in the file sitecustomize.py, but there is no such file in the USER_BASE folder (and the USER_SITE folder doesn't exist), and any other files I can find with this name don't have a C:\GAMS\38 path in them (or any other explicit GAMS path for that matter).



I don't really want to uninstall GAMS 38 as I need to retain that for the working version of the code I want to upgrade.  How do I fix this path issue?  Thanks!


API :: Re: Python API picking up wrong GAMS version :: Reply by Clemens
no_email@example.com (Clemens) — Wed, 17 Apr 2024 10:41:44 +0000
Hi,



Something seems to put in the GAMS 38 path into your configuration. Have you checked if the PYTHONPATH environment variable is set? Run from the Anaconda command prompt:
Code: Select all
echo %PYTHONPATH%

Best,

Clemens


API :: Re: Python API picking up wrong GAMS version :: Reply by dirkse
no_email@example.com (dirkse) — Wed, 17 Apr 2024 15:15:46 +0000
Hello,



It sounds to me like the GAMS 38 in the sitecustomize.py file is confusing your fresh conda install.



Many years ago I used the Python site package, but once I started to use miniconda I dropped it completely.  I found that the two don't work well together.  And at some level they are fundamental incompatible.  With conda I want to create a self-contained environment that is independent of other Python stuff (conda or otherwise).  But with the site package, I am sharing settings between Python versions.



-Steve


API :: Re: Python API picking up wrong GAMS version :: Reply by akingCCC
no_email@example.com (akingCCC) — Thu, 18 Apr 2024 03:38:45 +0000
Clemens wrote: ↑1 week ago
Hi,



Something seems to put in the GAMS 38 path into your configuration. Have you checked if the PYTHONPATH environment variable is set? Run from the Anaconda command prompt:
Code: Select all
echo %PYTHONPATH%

Best,

Clemens


Hi Clemens,



Yes, thanks, I think that's it!  When I put that into the command prompt, I get
Code: Select all
C:\GAMS\38\apifiles\Python\gams;%PYTHONPATH%
and I remember changing something along those lines a year or two ago when we were setting up the original connection between GAMS and Python.  



To remove it, in my Windows search I looked up "edit environment variables for your account", which opened the Environment Variables box (similar to but distinct from the System Environment Variables).  In the top box User variables, I had a couple of variables that had values that included the path to GAMS 38.  I deleted those and closed that box, closed and restarted Anaconda, then checked the echo %PYTHONPATH% command again, and the reference to GAMS 38 was gone.  I then reinstalled the API using the commands above and checked the install, and this time it told me it was using the right version of GAMS:
Code: Select all
C:\Users\myusername>python -c "import gams; print(f'API OK -- Version {gams.__version__}')"
API OK -- Version 46.4.0

Now I just need to try using it...


Solvers :: Re: CNS Solver: Pivot Too Small :: Reply by Rodrigue
no_email@example.com (Rodrigue) — Mon, 01 Apr 2024 09:09:01 +0000
You had better send the code as attached file.

Note that many equations do not solve either because they are not correctly written or the initialisation of variables is wrong.

Rodrigue,



Cheers


Archive Google Group :: Re: GAMS Installation Error :: Reply by Clemens
no_email@example.com (Clemens) — Wed, 17 Apr 2024 07:22:21 +0000
Hi,



This is a Windows problem that can most likely be prevented by running the installer from a command prompt with /SILENT or /VERYSILENT. There is a note on this in the documentation: https://www.gams.com/latest/docs/UG_WIN_INSTALL.html


image.png

1. Open command prompt

2. Switch to directory containing the GAMS installer

3. Run "windows_x64_64.exe /SILENT" or "windows_x64_64.exe /VERYSILENT"



Best,

Clemens
Attachments

image.png (23.6 KiB)



(Click on the image to see it full size.)


Bugs :: Re: Search in Studio :: Reply by Rob Davies
no_email@example.com (Rob Davies) — Fri, 12 Apr 2024 10:36:28 +0000
Following on from the above problem. 

I am using search and replace. The search still finds the wrong thing, but now in all of the files, not just the lst file.

I also notice that it tells me at the start there are, say, 5 matches found, but when I replace the first one, it still indicates 5 remaining, and after replacing all, it indicates there is 1 match remaining.

Trivial, but clearly a bug. I am scared to use replace all, since it may replace the wrong thing.

Best

Rob


Bugs :: Re: Search in Studio :: Reply by Lutz
no_email@example.com (Lutz) — Fri, 12 Apr 2024 19:05:17 +0000
Rob,



Thanks again for the report! Would it be possible, that you send an example of this to support@gams.com? 

Just two days ago, I discovered, that the replace action works correctly, but the find afterwards still reports the old results (though, they were replaced correctly), if I use use "This project" as serach scope. That problem does not happenn, if I do a replace in a single file. I am not sure, if that is actually the same, you ran into.



Best regards,

Lutz