Stochastic Chance-Constrained Goal Programming Model and Algorithm of Oilfield Measures

• Main Authors: Jiekun Song, Tao Zhang, Zaixu Zhang
• Format: Conference Proceeding
• Language: English
• Subjects: Constraint theory; Costs; Genetic algorithms; hybrid intelligent algorithm; Intelligent networks; measures programming; Neural networks; oilfield; Petroleum; Production; stochastic chance-constrained goal programming model; Stochastic processes; Testing; Velocity measurement
• ISSN: 2155-1456; 2155-1472
• DOI: 10.1109/ICIII.2008.177

Measures programming is an important way for improving the effect of measures of oil fields, which can extend the stable production age limit of oil fields, reduce the mining difficulty and improve oil-producing speed and final recovery ratio. Based on the theory of stochastic chance-constrained goal programming, a stochastic chance-constrained goal programming model is put forward for measures programming of oil fields, which considers the per increasing production and per increasing cost of measures as stochastic variables, uses the increasing production and increasing cost as objectives and the total work load and work load of each measure as constraints. At the same time, the process of its hybrid intelligent algorithm including stochastic simulation, genetic algorithm and neural network is also provided. Finally, the real example, i .e. measures programming of DX Oilfield testifies the efficiency, practicability and intellectual ability of the model and its solution algorithm, which provides a new decision basis for the incremental measures program of oil fields.