Classifying C++ Solutions Based on Their Energy Profile

The algorithm classification problem consists of finding which algorithm a program implements among a given finite set of algorithms. We propose a novel classification strategy using the power slope that best represents an algorithm energy consumption profile. Thenwe classify a set of solutions by using a greedy approach to match two sets of solutions that are aimed to solve the same problem. To evaluate our approach, we used sets of random C++ solutions for 32 problems from CSES, a programming competition site. We executed two datasets twice in two different machines. In one machine, we restricted the classification task to a subset that varies from 14 to 16 CSES problems (a reduction of at least 50% in the search space). In the other one, we could reach a reduction in the search space that varied from 38% up to 53%.