optimization algorithm is proposed. It optimizes the
execution time, the energy consumption and the cost of
booked nodes in the grid architecture at the same time.
The proposed algorithm selects the best frequencies
depends on a new optimization function that optimized
these three objectives, while giving equivalent trade-off
for each one. Dynamic voltage and frequency scaling
(DVFS) is used to reduce the energy consumption of the
message passing parallel iterative method executed over
grid. DVFS is also reduced the computing power of each
processor executing the parallel applications.
Therefore, the performance of these applications is
decreased and so on the paid cost for the booking nodes
is increased. However, the proposed multi-objective
algorithm gives the minimum energy consumption and
minimum cost with maximum performance at the same
time. The proposed algorithm is evaluated on the
SimGrid/SMPI simulator while running the parallel
iterative Jacobi method. The experiments show that it
reduces on average the energy consumption by up to
19.7 %, while limiting the performance and cost
degradations to 3.2 % and 5.2 % respectively.