Statement of eligibility for the GECCO 2005 Human-Competitive Results competition Title: Optimizing Cyclic Steam Oil Production with Genetic Algorithms Authors/Team members: Anil Patel Chevron 100 Chevron Way Richmond, CA 94802 Anil.patel@chevrontexaco.com David Davis NuTech Solutions, Inc. 28 Green Street Newbury, MA 01951 David.davis@nutechsolutions.com Jim Ouimette Chevron 1546 China Grade Loop Bakersfield, CA 93308 Joui@chevrontexaco.com Charlie Guthrie Chevron 100 Chevron Way Richmond, CA 94802 Charlie.guthrie@chevrontexaco.com Dave Tuk Chevron 100 Chevron Way Richmond, CA 94802 Dave.Tuk@chevrontexaco.com John Williams Chevron 21429 Lost Hills Road McKittrick, CA 93251 John.Williams@ChevronTexaco.com Tai Nguyen Chevron 3646 W. Reward Road McKittrick, CA 93251 TaiNguygen@ChevronTexaco.com [Note: Davis and Guthrie will be attending GECCO 2005] Papers: 1. Optimizing Cyclic Steam Oil Production with Genetic Algorithms. Anil Patel, David Davis, Tai Nguyen, John Williams, Dave Tuk, Charles Guthrie. Society for Petroleum Engineering Conference refereed presentation included in the Proceedings, April 1, 2005. The conference was the 2005 Society for Petroleum Engineering yearly Western conference. 2. A two-page condensation of this paper was included in the Society For Petroleum Engineerings June edition of Journal of Petroleum Technology. This journal is essentially a digest, containing the best of the recently-presented results in the field of petroleum engineering. Abstract, excerpted from the paper: This case study describes a project applying a new technologygenetic algorithmsto the problem of scheduling oil production by cyclic steaming at an oil field in the San Joaquin Valley. The paper has seven parts. In the first part, we discuss the nature of the problem, the importance of solving it well, and the nature of the work process as it occurred before the project began. In the second part, we discuss genetic algorithms and the way that the project adapted them to solve the problem of scheduling cyclical steam injections. In the third section, we describe a pilot project that demonstrated the potential of the approach. In the fourth, we describe the full project that created an optimization tool that has been working daily with oil field personnel to schedule production for the entire field for more than a year. In the fifth, we discuss two types of results of the projectan increase in production and changes to the work process on the part of the oil field personnel owing to their enthusiastic adoption of the optimizer. In the sixth, we discuss some project management factors that led to the success of the project. Finally, we discuss ways in which the success of this project may be relevant to a variety of other types of scheduling and resource allocation problems in the field of oil production. The paper will center on three themes: the successful solution of a hard production problem with a new technology; the impact of that technology on the oil field personnel; and the potential of that technology to support other types of projects with similar levels of return. Criteria of Eligibility The genetic algorithm described in the paper satisfies two of the Human-Competitive Results criteria: (E) The result is equal to or better than the most recent human-created solution to a long-standing problem for which there has been a succession of increasingly better human-created solutions. The system described solves the extremely difficult task of scheduling which subset of 500+ wells in an oil field in California should receive steam to increase their production, subject to more than 15 types of constraints on production, delivery of steam, and wells that must or must not be steamed at the same time. The personnel at the oil field have been carrying out this task for 20 years, and have developed an array of heuristics to solve it. The task has not been described in the scientific literature. Instead, the oil field operators have evolved their own approaches to solving the problem over the years. They have never been fully satisfied with their approach, but owing to the complexity of the problem were unable to find a way to solve it satisfactorily until a genetic algorithm to solve the problem was created for them by the team of individuals listed above. (G) The result solves a problem of indisputable difficulty in its field. The system is used daily to schedule the delivery of steam to oil wells. The increase in production at the field has been estimated as between 4% and 18%--an increase of millions of dollars in production per year, even at the lowest estimated level. A good deal of attention had previously been paid at this oil field and at other similar ones across the world to the problem of increasing production using cyclic steam. The system described in the paper has effectively solved this previously unsolved problem, and has become a showcase of sortsmany top-level executives of Chevron Corporation (formerly ChevronTexaco) have made the 200-mile trip from the San Francisco area to the Bakersfield area to be briefed on the system and to see the system in operation. As an indication of the importance of the solution, the leader in Chevron who initiated the project has since been promoted to the highest technical level in Chevron Corporation, the other team members have also been advanced, and a number of other organizations in Chevron are seeking their advice on using similar techniques to solve their planning and distribution problems. Copies of papers 1 and 2 are attached to this email.