260
Y. Xu et al.
the existing pipeline system and original CSs facilities. The contributions of this paper
can be summarized as follows:
(1) Modification of compressors in original CSs which was neglected by previous
researches is taken into consideration to ensure that the optimal solution meet the
production capacity requirements in the mid to late stages of gas field development.
(2) The construction of new pipelines is taken into account as the original pipeline
cannot meet the new requirement of gas field production conditions.
(3) An effective two-stage hybrid algorithm is proposed to solve this problem and an
actual GGS in china is chosen as study objects to demonstrate the feasibility and
accuracy of this method.
2 Methodology
2.1 Generic Algorithm
The genetic algorithm (GA) approach is an efficient heuristic search technique that
conducts searches in parallel from several random initial solutions in a search space
to find the optimal solution by iteration, and evaluates the quality of solutions by their
fitness, thereby reducing the chance of the search being stuck in a local optimum. The
main processes of GA are shown in Fig. 1.
Fig. 1. The main processes of genetic algorithm
Chromosome Encoding
The initialization of the population is the first step in the GA procedure. A population
consists of a number of chromosomes, each a string of coded bits; and each chromosome
represents a single solution to the proposed problem. The initial population is created
by randomly choosing the binary value of 0 or 1 for each bit location through the
chromosome length. In this paper, the values of each bit denote the selection of newly
Y. Xu et al.
the existing pipeline system and original CSs facilities. The contributions of this paper
can be summarized as follows:
(1) Modification of compressors in original CSs which was neglected by previous
researches is taken into consideration to ensure that the optimal solution meet the
production capacity requirements in the mid to late stages of gas field development.
(2) The construction of new pipelines is taken into account as the original pipeline
cannot meet the new requirement of gas field production conditions.
(3) An effective two-stage hybrid algorithm is proposed to solve this problem and an
actual GGS in china is chosen as study objects to demonstrate the feasibility and
accuracy of this method.
2 Methodology
2.1 Generic Algorithm
The genetic algorithm (GA) approach is an efficient heuristic search technique that
conducts searches in parallel from several random initial solutions in a search space
to find the optimal solution by iteration, and evaluates the quality of solutions by their
fitness, thereby reducing the chance of the search being stuck in a local optimum. The
main processes of GA are shown in Fig. 1.
Fig. 1. The main processes of genetic algorithm
Chromosome Encoding
The initialization of the population is the first step in the GA procedure. A population
consists of a number of chromosomes, each a string of coded bits; and each chromosome
represents a single solution to the proposed problem. The initial population is created
by randomly choosing the binary value of 0 or 1 for each bit location through the
chromosome length. In this paper, the values of each bit denote the selection of newly