Ebook Evolutionary scheduling: Part 2

Part 2 book "Evolutionary scheduling" includes content: Optimum oil production planning using an evolutionary approach; a hybrid evolutionary algorithm for service restoration in power distribution systems; evolutionary generator maintenance scheduling in power systems; simultaneous planning and scheduling for multi autonomous vehicles; evolutionary optimization of business process designs; a genetic algorithm based reconfigurable scheduler.
Nội dung trích xuất từ tài liệu:
Ebook Evolutionary scheduling: Part 2 Optimum Oil Production Planning using an Evolutionary Approach Tapabrata Ray1 and Ruhul Sarker2 1 School of Aerospace, Civil and Mechanical Engineering 2 School of Information Technology and Electrical Engineering University of New South Wales at the Australian Defence Force Academy, Northcott Drive, Canberra 2600, Australia Email: {t.ray, r.sarker}@adfa.edu.au Summary. In this chapter, we discuss a practical oil production planning problem from a petroleum field. A field typically consists of a number of oil wells and to extract oil from these wells, gas is usually injected which is re- ferred as gas-lift. The total gas used for oil extraction is constrained by daily availability limits. The oil extracted from each well is known to be a nonlinear function of the gas injected into the well and varies between wells. The problem is to identify the optimal amount of gas that needs to be injected into each well to maximize the amount of oil extracted subject to the constraint posed by the daily gas availability. The problem has long been of practical interest to all major oil exploration companies as it has a potential of deriving large financial benefits. Considering the complexity of the problem, we have used an evolutionary algorithm to solve various forms of the production planning problem. The multiobjective formulation is at- tractive as it eliminates the need to solve such problems on a daily basis while maintaining the quality of solutions. Our results show significant im- provement over existing practices. We have also introduced a methodology to deliver robust solutions to the above problem and illustrated it using the six-well problem. Furthermore, we have also proposed a methodology to create and use a surrogate model within the framework of evolutionary op- timization to realistically deal with such problems where oil extracted from a well is a nonlinear function of gas injection and a piecewise linear model may not be appropriate. T. Ray and R. Sarker: Optimum Oil Production Planning using an Evolutionary Approach, Studies in Computational Intelligence (SCI) 49, 273–292 (2007) www.springerlink.com © Springer-Verlag Berlin Heidelberg 2007 274 T. Ray and R. Sarker 1 Introduction Petroleum, either oil or gas, is a finite and scare resource upon which modern society is heavily dependent on. Hence, mankind is forced to rationalize and optimize its production and consumption. In this chapter, we consider a crude oil production system. In the system, there is a underground oil reservoir and the reservoir has a number of wells. There are two basic methods of extracting oil from such reservoirs (Kosmidis et al., 2005): (i) naturally flowing and (ii) gas lift. In the first one, the oil is able to flow naturally to surface, while the second requires injection of high pressure gas to facilitate oil extraction. The gas lift is considered as the most eco- nomic method for artificial lifting of oil (Aaytollahi et al, 2004 and Cam- ponogara and Nakashima, 2005). In this study, we consider gas lift extraction method. As it will be dis- cussed later, for a given well, the oil production per day can be expressed as a nonlinear function of gas injected into the well in that day. The oil production per day increases with the increase of gas used to a certain level and then decreases. That means an excessive use of gas may increase the gas cost, as well as production cost, without providing any benefit in terms of oil production volume. For a given amount of gas used, the amount of oil extraction significantly varies from well to well. That means the nonlinear function of gas usage versus oil extracted varies from well to well. As a result, an inappropriate gas allocation to different wells, under limited gas availability, will reduce the overall production and hence prof- itability from the entire reservoir. So the single objective gas lift optimiza- tion problem is to allocate a limited amount of gas to a number wells in a reservoir while maximizing the total oil production in a day. However, the amount gas may vary from day to day. That means, the management has to re-solve the problem if the amount of gas is different. In such situations, it is appropriate to solve the problem as bi-objective problem where the ob- jectives would be: Maximize oil production and Minimize gas used. Prior research in gas-lift optimization only devoted to single objective optimization problem using either a single well model (Fang and Lo, 1996) or multiple wells model (Dutta-Roy and Kattapuram, 1997). A range of methodologies was used in solving this problem such as equal-slope method (Nishikiori et al., 1989), linear programming (Fang and Lo, 1996), mixed integer linear programming (Kosmidis et al., 2005) quadratic pro- gramming (Dutta-Roy and Kattapuram, 1997), dynamic programming (Camponogara and Nakashima, 2005) and others. In this research, we con- Oil Production Planning using an Evolutionary Approach 275 sider a six well and a fifty six well problem. We define the problem as a single and a multiobjective problem and use evolutionary algorithm to solve the mathematical models. Evolutionary algorithms have been used to solve a number of multiobjective optimization problems from the domain of operations research in recent years (Sarker et al., 2002). Excellent com- prehensive review of evolutionary multiobjective optimization appears in Coello (1999). This chapter is organized as follows. Following introduction, we present a mathematical model of the problem. The following section presents the algorithm used for solving the problem. The last two sections discuss about results an ...