Optimization Study of Cluster Well Platform Deployment Based on Genetic Algorithm

The location optimization of cluster well drilling platforms is an important issue that needs to be focused on before oilfield development. Relying on experience or methods themselves has certain limitations when the enumeration method and dynamic clustering method are used to optimize platform location. To this end, the total platform investment planning model was established with the goal of minimum lateral displacement in front of target points and minimum total investment cost, including the drilling and completion cost model, production engineering cost model, surface construction cost model, and maintenance cost model. The platform location and target point coordinates were optimally allocated by using double weight method. A genetic algorithm based on Python language was used to plan the platform location deployment. The coordinate data of 44 target points in a block of Daqing Oilfield was used for platform location optimization design. The results show that the total platform investment planning model with the minimum lateral displacement in front of target points as the optimal objective can optimize the location of the drilling platform quickly, provide the platform location range, and allocate the target points. It can also select the appropriate platform location and target point coordinates according to different terrains with less influence by human factors, and can solve the problem of cluster well platform deployment. It has a good reference for platform deployment of other blocks.