This article, written by Assistant Technology Editor Karen Bybee, contains highlights of paper SPE 93906, "Optimizing Cyclic-Steam Oil Production With Genetic Algorithms," by A. Patel, SPE, ChevronTexaco Energy Technology Co; D. Davis, Nutech Solutions Inc.; C. Guthrie, SPE, and D. Tuk, ChevronTexaco Energy Technology Co.; and Tai Nguyen, SPE, and J. Williams, ChevronTexaco North America Upstream, prepared for the 2005 SPE Western Regional Meeting, Irvine, California, 30 March-1 April. The full-length paper details a project that applied a new technology, genetic algorithms, to the problem of scheduling oil production by cyclic steaming at an oil field in the San Joaquin Valley. The paper focuses on three themes: the successful solution of a production problem with new technology; the impact of that technology on oilfield personnel; and the potential of that technology to support other types of projects. Introduction The Antelope reservoir in the Cymric field, in the San Joaquin Valley, is a siliceous shale reservoir containing 12 to 13°API heavy oil. The reservoir consists primarily of diatomite, characterized by its high porosity, high oil saturation, and very low permeability. Approximately 430 wells are producing from this reservoir, with an average daily production of 23,000 bbl. The oil from the field is recovered using a Chevron-patented cyclic-steam process. A fixed amount of saturated steam is injected into the reservoir during a 3- to 4-day period. The high-pressure steam fractures the rock, and the heat from the steam reduces oil viscosity. The well is shut in during the next couple of days, known as the soak period. Condensed steam is absorbed by the diatomite, and oil is displaced into the fractures and wellbore. After the soak period, the well is returned to production. The flashing of hot water into steam at the prevailing pressure provides the energy to lift the fluids to the surface. The well flows for approximately 20 to 25 days. After the well dies, the same cycle is repeated. Cycle length is 26 to 30 days. Because there is no oil production during the steaming and soaking period, there is an incentive to minimize the steaming frequency and increase the length of the cycle. But because well production is highest immediately after returning to production and declines quickly thereafter, a case can be made for increasing the steaming frequency and reducing the length of the cycle. This suggests that there is an optimum cycle length for every well that results in maximum productivity during the cycle. Because there are more than 400 wells in the field, and there are constraints of steam availability and distribution system, as well as facility constraints, the result is a formidable scheduling problem. Genetic Algorithms Genetic algorithms (GAs) are global optimization techniques developed by John Holland in 1975. They are one of several techniques in the family of evolutionary algorithms—algorithms that search for solutions to optimization problems by “evolving” better and better solutions. A genetic algorithm begins with a “population” of solutions and then chooses “parents” to reproduce. During reproduction, each parent is copied, and then parents may combine in an analog to natural crossbreeding, or the copies may be modified, in an analog to genetic mutation. The new solutions are evaluated and added to the population, and low-quality solutions are deleted from the population to make room for new solutions. As this process of parent selection, copying, crossbreeding, and mutation is repeated, the members of the population tend to get better. When the algorithm is halted, the best member of the current population is taken as the solution to the problem posed.