The term "Real-Time Optimization" (RTO) has rapidly found its way into common usage in the oil and gas industry, as it already has in many others. However, RTO in the oil and gas industry is usually used more as a slogan rather than describing a system or process that truly optimizes anything at all, let alone does so in real-time. In this paper, we describe what RTO means in the exploitation of hydrocarbons and what technologies are available now and are likely to be available in the future. We discuss how it is misunderstood and what real financial benefits await those who adopt it. Furthermore, we are working toward developing a method of classification to allow us to establish where a field operation lies on the RTO ladder, and to help plan a strategy to generate the benefits that moving up the RTO ladder can offer on specific fields and assets. The paper also describes a new SPE Technical Interest Group (TIG), explaining why it has been formed, and outlining its objectives and some planned deliverables. Real-time Optimization - Concepts and Definitions What is optimization? Intuitively most people agree on what we mean by "optimize." This comes down to understanding the dictionary definition; that is, to make the most of; to plan or carry out an economic activity with maximum efficiency; to find the best compromise among several often conflicting requirements, as in engineering design. Therefore, examples of what is usually meant by optimization in the oil and gas industry include:Maximizing hydrocarbon production or recovery,Finding the best solution in the region of physical and financial constraints to produce a decision,Maximizing net present value (NPV) through changes in capital expenditure (CAPEX) and/or operational expenses (OPEX). These elements, in turn, improve financial efficiency in portfolio management and risk analysis, andAdvanced real-time optimization: behavioral prediction and inference, pattern recognition to identify states of a group of wells, continuous adaptation and self-tuning ability. Although we may readily agree on these (and other) descriptions of what would be the outcome of optimization, agreeing what it actually means appears to be more complex. The reason for this is that the term optimization is usually used very loosely, whereas it needs to be defined rigorously and mathematically, while honoring the real-life physical system constraints that exist in the overall production process.

We propose a decision-making approach for optimizing the profitability of hydrocarbon reservoirs. The proposed approach addresses the overwhelming complexity of the overall optimization problem by suggesting an oilfield operations hierarchy that entails different time scales. We discuss system identification, optimization, and control that are appropriate at various levels of the hierarchy and capitalize on the abilities of permanently instrumented and remotely actuated fields. Optimization is performed in real-time and is based on feedback. We provide details on real-time identification of hybrid models and their use at the scheduling and supervisory control levels. Case studies using field-calibrated simulation data demonstrate the applicability and value of the proposed approach. Directions for future development are given.

The Real-Time Optimization Technical Interest Group (RTO TIG) has endeavored to clarify the value of real-time optimization projects. RTO projects involve three critical components: People, Process, and Technology. Understanding these components will help to establish a framework for determining the value of RTO efforts. In this paper, the Technology component is closely examined and categorized. Levels within each Technology category are illustrated using spider diagrams, which help decision-makers understand the current status of operations and the impact of future RTO projects. Uncertain value perception in our industry has been one of the critical issues in adopting RTO systems. Therefore, case histories are reviewed to demonstrate the impact of RTO projects. To assist RTO project promotion, we list lessons learned through case histories, suggest a justification process, and present a simple economic example. Introduction Industry case histories demonstrate many types of benefits from RTO, such as volume increase, ROI increase, decision quality, HSE improvement, and opex reduction. However, they have lacked systematic project evaluation methods or processes for justification. Today, promoting RTO is in essence a competition for capital within producing companies. The project teams that recognize this fact and then clearly outline the purpose, benefits, costs (direct or indirect), and strategic business alignment of their proposals will be in an advantageous position to secure funding. Because RTO is still an emerging discipline, classifying projects of this nature is still dependent on an individual's point of view. This paper is intended to enable classification of RTO in an objective manner and to help provide a common vocabulary to address issues. Three Cornerstones in Adopting New Technology In adopting any new technology, TIG members realize that there are three major factors: People, Process, and Technology, as shown in Fig. 1. New RTO technology can achieve the benefits we seek, but it is not likely without corresponding changes in the way we work with others and in the processes or workflow in which we perform tasks. This challenge is common to the implementation of any new technology, whether RTO or not. Engineers tend to emphasize the technology aspect because we are most familiar with it, but the other aspects are equally important. For example, the lack of workflow modification, which requires training and possible organizational changes, is tends to result in unsustainable efforts and ultimately underperformance of the investment in RTO. People People issues manifest themselves in several ways1: corporate culture, organizational structure, and training. Corporate culture is the set of tacit understandings and beliefs that form the foundation of how an organization works. It is a mental model that people have about the nature of an organization and how it sees itself. Within an organization, culture is "how things are done around here." The culture of an organization can be appropriate and supportive to an organization's goals and strategies, or it can hinder its initiatives and projects. Usually any major change in an organization, such as deployment of new technology, radical strategic shifts, or new initiatives, is countercultural. That is, the change breaks existing cultural rules and assumptions, and the change is automatically resisted and thereby impeded.

Summary In this work, we present an industrial automation framework for control and optimization of hydrocarbon-producing fields while satisfying business and physical constraints. The all-encompassing reservoir-management problem is decomposed into a hierarchy of decision-making problems at different time scales. We exemplify the proposed approach through a case study on a multiple-layer reservoir with a classical waterflood problem, in which a numerical reservoir model is used as a virtual field. A model-predictive control (MPC) strategy is used to regulate well and field instrumentation at economically optimal set points determined by an overlying supervisory control level. The study demonstrates significant reduction in water-handling costs and increased oil recovery. This work is a starting point for further development in automatic intelligent reservoir technologies, which capitalize on the abilities of permanent instrumented wells and remotely activated downhole completions.

Artificial intelligence (AI) has been used for more than two decades as a development tool for solutions in several areas of the E&P industry: virtual sensing, production control and optimization, forecasting, and simulation, among many others. Nevertheless, AI applications have not been consolidated as standard solutions in the industry, and most common applications of AI still are case studies and pilot projects. In this work, an analysis of a survey conducted on a broad group of professionals related to several E&P operations and service companies is presented. This survey captures the level of AI knowledge in the industry, the most common application areas, and the expectations of the users from AI-based solutions. It also includes a literature review of technical papers related to AI applications and trends in the market and R&D. The survey helped to verify that (a) data mining and neural networks are by far the most popular AI technologies used in the industry; (b) approximately 50% of respondents declared they were somehow engaged in applying workflow automation, automatic process control, rule-based case reasoning, data mining, proxy models, and virtual environments; (c) production is the area most impacted by the applications of AI technologies; (d) the perceived level of available literature and public knowledge of AI technologies is generally low; and (e) although availability of information is generally low, it is not perceived equally among different roles. This work aims to be a guide for personnel responsible for production and asset management on how AI-based applications can add more value and improve their decision making. The results of the survey offer a guideline on which tools to consider for each particular oil and gas challenge. It also illustrates how AI techniques will play an important role in future developments of IT solutions in the E&P industry.

A number of new technologies introduced into the oil field over the last couple of decades now provide the hardware basis for continuous field-wide optimization (CFO). CFO will require computer integration of field hardware (e.g., downhole sensors, remotely activated completions, surface facilities) for continuous decision-making in a feedback fashion (data acquisition, data processing, actuation). We introduce a hierarchy of oil field operations that identifies various levels of detail and time-scales for decision-making processes. We propose to use this hierarchy in a multi-level / multi-scale approach to CFO. An important element in that approach is the availability of predictive models that can be used at various levels of the hierarchy, so that optimal actions can be continuously selected through optimization over a moving horizon.. In this context, artificial neural networks (ANN) are a tool that has been used to build data-driven models. This paper is structured in two parts:elements of CFO, andbrief review of ANN basics, known ANN applications in the petroleum industry, and a critical view of ANN capabilities. Background Oil field efficiencies from integration of diverse new technologies After almost two decades of intensive efforts to increase its competitiveness, the oil industry has shifted its focus from depending on oil prices for its viability to using advanced technology for more efficient exploration, drilling, and production. Innovations in seismic data processing, high-angle drilling, complex well architectures, and downhole monitoring and control instruments have revolutionized the industry and are drastically lowering finding and lifting costs. Realized or projected benefits stemming from the use of new technologies include improved overall recovery; increased/accelerated production; reduced well construction costs; reduced frequency and cost of well intervention (the largest single expense to occur during the life of most producing wells); and reduced surface facilities (Drakeley and Douglas, 2002). Spurred by the successful application of individual well and surface innovations such as the above, the oil industry is now seeking the next technological level to be realized by bringing these disparate tools under a single completion scenario known as smart wells, or intelligent completions. In fact, there is a vision of computer integrated operation and continuous optimization &control of entire fields, succinctly described by the term intelligent fields. Continuous optimization and control will require careful orchestration of hardware, software, and humans. It can capitalize on the key elements of a feedback loop which may impart intelligence to a field and which are already individually available in the oil industry, namely (a) real-time measurements; (b) downhole flow-control valves; and (c) computing/communication power and algorithms for data processing and decision making. There is also good potential to benefit from related technologies developed in other industries, such as real-time optimization and plantwide control of oil refineries and chemical plants, or completely paperless aircraft design. Currently, data processing and decision making (item c in last paragraph) is a key area needing development (Airlie, 2002). Huge volumes of field data are being gathered, but due to lack of appropriate data management, well/completion models, and skilled people, much of this important data is not being used to the best possible effect. Appropriate data-driven modeling of systems, coupled with optimization and control - either fully automated or manual - is essential to closing the feedback loop and realizing the full potential of intelligent fields. Oil field efficiencies from integration of diverse new technologies After almost two decades of intensive efforts to increase its competitiveness, the oil industry has shifted its focus from depending on oil prices for its viability to using advanced technology for more efficient exploration, drilling, and production. Innovations in seismic data processing, high-angle drilling, complex well architectures, and downhole monitoring and control instruments have revolutionized the industry and are drastically lowering finding and lifting costs. Realized or projected benefits stemming from the use of new technologies include improved overall recovery; increased/accelerated production; reduced well construction costs; reduced frequency and cost of well intervention (the largest single expense to occur during the life of most producing wells); and reduced surface facilities (Drakeley and Douglas, 2002). Spurred by the successful application of individual well and surface innovations such as the above, the oil industry is now seeking the next technological level to be realized by bringing these disparate tools under a single completion scenario known as smart wells, or intelligent completions. In fact, there is a vision of computer integrated operation and continuous optimization &control of entire fields, succinctly described by the term intelligent fields. Continuous optimization and control will require careful orchestration of hardware, software, and humans. It can capitalize on the key elements of a feedback loop which may impart intelligence to a field and which are already individually available in the oil industry, namely (a) real-time measurements; (b) downhole flow-control valves; and (c) computing/communication power and algorithms for data processing and decision making. There is also good potential to benefit from related technologies developed in other industries, such as real-time optimization and plantwide control of oil refineries and chemical plants, or completely paperless aircraft design. Currently, data processing and decision making (item c in last paragraph) is a key area needing development (Airlie, 2002). Huge volumes of field data are being gathered, but due to lack of appropriate data management, well/completion models, and skilled people, much of this important data is not being used to the best possible effect. Appropriate data-driven modeling of systems, coupled with optimization and control - either fully automated or manual - is essential to closing the feedback loop and realizing the full potential of intelligent fields.

Artificial intelligence (AI) has been used for more than 2 decades as a development tool for solutions in several areas of the exploration and production (E&P) industry: virtual sensing, production control and optimization, forecasting, and simulation, among many others. Nevertheless, AI applications have not been consolidated as standard solutions in the industry, and most common applications of AI still are case studies and pilot projects.In this work, an analysis of a survey conducted on a broad group of professionals related to several E&P operations and service companies is presented. This survey captures the level of AI knowledge in the industry, the most common application areas, and the expectations of the users from AI-based solutions. It also includes a literature review of technical papers related to AI applications and trends in the market and in research and development.The survey helped to verify that (a) data mining and neural networks are by far the most popular AI technologies used in the industry; (b) approximately 50% of respondents declared they were somehow engaged in applying workflow automation, automatic process control, rule-based case reasoning, data mining, proxy models, and virtual environments; (c) production is the area most affected by the applications of AI technologies; (d) the perceived level of available literature and public knowledge of AI technologies is generally low; and (e) although availability of information is generally low, it is not perceived equally among different roles.This work aims to be a guide for personnel responsible for production and asset management on how AI-based applications can add more value and improve their decision making. The results of the survey offer a guideline on which tools to consider for each particular oil and gas challenge. It also illustrates how AI techniques will play an important role in future developments of information-technology (IT) solutions in the E&P industry. IntroductionAlthough there is hardly a rigorous definition of the term "artificial intelligence" that is unequivocally accepted, the tools of AI and its intended uses have been well studied for decades and many applications have appeared. Loosely speaking, AI is the capability of machines (usually in the form of computer hardware and software) to mimic or exceed human intelligence in everyday engineering and scientific tasks associated with perceiving, reasoning, and acting. Because human intelligence is multifaceted, so is AI, comprising goals that range from knowledge representation and reasoning to learning, visual perception, and language understanding (Winston 1992). AI techniques have been present in the E&P industry for many years. A quick literature search reveals application of AI in SPE scientific and engineering papers as early as in the 1970s. There are numerous references about the

More than 90% of producing oil wells require some form of artificial lift for pumping production fluids to the surface (Bates, Cosad et al. 2004). The electrical submersible pump (ESP) is widely used and is currently the fastest growing form of artificial-lift pumping technology. About 15 to 20 percent of almost one million wells worldwide produce oil with the help of ESPs (Breit and Ferrier 2008). ESPs are usually considered more efficient and reliable among all oilfield lift systems and enable recovery of hydrocarbon fluids from greater depths at higher temperatures while handling a range of viscosities, gas-liquid ratios, and solids production. Over the years, the most common concern of operators using ESPs in their assets has been high workover costs and inadequately low system run life (Vandevier 2010). It is often observed that ESP performance declines gradually and reaches the point of service interruption due to a number of factors such as high gas volumes, high temperature, and corrosive environments. Should an ESP fail, the financial impact would be substantial, in terms of both lost production and replacement or intervention costs. Given the high cost of an ESP failure, operators are increasingly investing in real-time surveillance sytems to monitor ESP performance using downhole measurements and raise alarms in case of abnormal events such as trippings or failures. However, such systems are reactive in nature, i.e. action is taken after an event occurs. Consequently, there is a need and an opportunity to utilize the large amount of data being collected in real time from ESP operations, and to create solutions that advance from a reactive to a more proactive approach that would ideally detect issues well in advance, diagnose causes, and suggest corrective action. This paper offers such an approach. Specifically, a data-driven analytical solution is proposed to proactively monitor and transform vital statistics related to ESP performance into actionable information using multivariate statistical techniques for dimensionality reduction and pattern recognition. This real-time framework combines engineering principles with mathematical models to detect impending problems long before they occur, diagnose potential causes, and prescribe preventive action. This can safeguard ESP operations and increase uptime, extend ESP life expectancy, reduce intervention costs, and optimize production.