Comprehensive Approach to Optimization of Macrooperations in Oil and Gas Production Based on Integrated Planning

The task of integrated planning, as one of the main tools to improve the operational efficiency of production activities of oil and gas production operators, is the most relevant. Due to the high intensity, today all operators emphasize the importance of automating the integrated planning process. An integrated plan means combining, ranking and possible combination, as well as timely updating the order of implementation of activities presented in separate functional plans, for which various services are responsible. At the same time, a functional plan is a group of activities united in its specificity. Examples of functional plans are well intervention (TR), well workover (KR), PP (routine maintenance), Research, OTM (organizational -technical measures), PPR (scheduled preventive work), VNS (commissioning of new wells). The goal of integrated planning is to execute the mining company's business plan in the most efficient way in terms of economic performance within the existing constraints. The constraints can be various aspects, such as the limited number of crews of the required specialization and special equipment for the activities, the need to move resources to the location of the activity taking into account the seasonality and types of transport, a strict sequence of operations within one activity, technological constraints associated with the inability to simultaneously conduct various activities at one cluster site, restrictions on the utilization of associated petroleum gas. Integrated planning distinguishes between planning horizons. As a rule, the horizon does not exceed one year and is designed to assess the feasibility of the company's business plan and justify capital and operating costs. Annual planning must take into account both targeted (named, assigned to a specific well or field site) and unaddressed (called "virtual") activities based on past year statistics. Monthly and 90-day plans are updated on a monthly basis and are more detailed and accurate than the annual plan, containing only targeted activities. Monthly planning clarifies the feasibility of the business plan in terms of production, budget and other criteria. In addition to the approved annual, monthly and 90-day plan, an operational (working) plan is formed, which is updated on a daily basis or upon request. As a rule, the operational plan is formed for a two-week planning horizon. The traditional integrated planning approach has its drawbacks and opportunities for improvement. The essence of the traditional approach of integrated planning is that different operational services, such as Geological Service, Well Intervention Service, Pipeline Maintenance Service, Chief Power Engineer, Chief Engineer, etc., annually and monthly submit a list of activities for inclusion in the annual, monthly (90-day) production program, after which the integrated planner combines all activities, combining them if possible, trying to achieve the targets as closely as possible, such as The main drawbacks of the traditional approach are the high intensity of forming an integrated plan, as well as its static nature. In fact, the approved integrated plan is actual no more than two days, as the life of oil and gas field is usually very dynamic - there are always unscheduled activities, there are always emergencies during crews, shifts in the start and end dates of already started crews, etc. All of the above aspects indicate that the integrated plan must be dynamic and must be constantly updated (Repin et al., 2018). The OIS UFAM integrated scheduling solution presented in this article provides extensive automation capabilities for the integrated scheduling process.

An Effective Memetic Algorithm for the Distributed Integrated Scheduling of Tree-Structured Products

Aiming at the distributed integrated scheduling of complex products with tree structure, a memetic algorithm-based distributed integrated scheduling algorithm is proposed. Based on the framework of the memetic algorithm, the algorithm uses a distributed estimation algorithm for global search and performs a local search strategy based on the critical operation set for the current optimal solution obtained in each evolutionary generation. A bi-chain-based individual representation method is presented and a simple greedy insertion-based decoding method is given; two position-based probability models are built, which are used to describe the distribution of the operation priority and factory assignment, respectively. Based on the designed probability models, two learning-based updating mechanisms and an improved sampling method are given, which ensures that the population evolves towards a promising region. In order to enhance the searchability for the superior solutions, nine disturbance operators based on the critical operation set are presented. The parameters are determined by the design-of-experiment (DOE) test, and the effectiveness of the proposed algorithm is verified by comparative experiments.