I have 5 given datapoints in a xy-Space and would like to finde the best linear combination of these to fit a measurement point: multiple regression with constraint on positive parameters-mprender.php.png

I tried to solve this with a ridge regression which works quite well for my needs of accuracy.

But I need the parameters to be positive and have no idea how to do this.
How can I solve this fitting problem (doesn't have to be regression)?

Thanks Richard