China
Africa
Explore chapters and articles related to this topic
Market and trading in oil and gas (petroleum) industry
Published in Manan Shah, Ameya Kshirsagar, Jainam Panchal, Applications of Artificial Intelligence (AI) and Machine Learning (ML) in the Petroleum Industry, 2023
Manan Shah, Ameya Kshirsagar, Jainam Panchal
Abolfazli et al. (2014) discuss how time-series and artificial neural networks can improve energy forecasting in the rail transportation sector. The optimal input variables for the integrated ANN model are determined using autocorrelation and partial autocorrelation functions in an integrated ANN model. The suggested ANN uses partial autocorrelation function and autocorrelation function, retrieved from time-series information, to pick applicable inputs for ANN. The two regressive auto models are compared using analysis of variance techniques to evaluate the ANN results (Yildirim et al., 2019). Total weekly consumption of the crude oil in Iran railway transportation is used to build and compare time-series and ANN models from January 2009 to October 2011. It is estimated that ANN produces excellent results and may be further utilized for prediction. Another study shows partial autocorrelation function and autocorrelation function analysis to determine time-series modeling using the ANN inputs. The integrated ANN in this work can deal with data correlation, autocorrelation, complexity, and nonlinearity due to its mechanism.
Energy security as a concept
Published in David Bernell, Christopher A. Simon, The Energy Security Dilemma, 2016
David Bernell, Christopher A. Simon
Diversification of energy sources. This goal includes diversification of both fuel types and geographic sources of energy. Diversity of supplies and suppliers supports all of the energy security elements described above, while also serving the objective of mitigating national and global security vulnerabilities. Success in achieving diversification, ideally, would greatly reduce dependence upon oil for transportation and dirty fuels for electricity generation. With respect to diversifying suppliers of oil, away from OPEC countries in particular, this is commonly referred to as “energy independence,” a term which should not be equated with total self-sufficiency. More properly understood it means diminishing or ending the role of oil as the world’s ultimate strategic commodity, making it just another commodity in which to trade, and thereby mitigating the national security and economic impacts of political instability, terrorism and military conflict in the Middle East.36 This objective maintains an even lower priority than the other specified goals, as it is based upon long-term objectives that are desirable, but inherently elusive. However, it is probably the most important element of any effort to achieve a long-term, resilient state of greater energy security. Continual changes in supply and demand, prices, technologies, and policies, along with conflict and violence around the globe, all routinely present challenges to governments, firms and consumers (energy forecasting is notoriously difficult). Diversification of energy sources can significantly diminish the importance and impacts of disruptions and surprises relating to any one fuel source or supplier.
Estimation of Daily Energy Production of a Solar Power Plant Using Artificial Intelligence Techniques
Published in Salah-ddine Krit, Mohamed Elhoseny, Valentina Emilia Balas, Rachid Benlamri, Marius M. Balas, Internet of Everything and Big Data, 2021
Anass Zaaoumi, Hajar Hafs, Abdellah Bah, Mohammed Alaoui, Abdellah Mechaqrane
Long-term alternatives to fossil fuels are renewable energies. Renewable energy resources are clean and inexhaustible. One of the most suitable renewable energies is solar energy. It is clean and free and can perfectly help to solve the problem of climatic change. The most advantageous way to exploit this energy is by concentrating the sunlight in solar plants. A parabolic trough solar thermal power plant (PTSTPP) is one of the concentrated solar power (CSP) technologies that transforms the energy radiated by the sun into heat at high temperature, then into mechanical and electrical energy through a thermodynamic cycle (Cac 2013). Once the energy is captured, the main challenge is to control, manage, and transport it to the electricity grid in compliance with regulations. Unfortunately, solar energy has certain number of intrinsic limitations: production fluctuations or geographical possibilities for implementation. Production fluctuations generate problems on the electricity grid for maintaining the balance between consumption and production. The uncertainty about cloud cover or wind speed and the rapid variation of their production force the manager to compensate by using and increasing the reserves of the energy storage. The storage of energy can stabilize the production of electricity by storing thermal power during periods of high production to restore it when production falls (Guney 2016). However, energy storage reduces efficiency and increases the costs of the power plant. Energy forecasting helps to anticipate the availability of generation sources and thus facilitates the management of the grid. The forecasting methods are based on historical data. Generally, forecasting tools are based on artificial intelligence algorithms like fuzzy logic, neural network, genetic algorithm, or a combination of two techniques.
The grey Theta forecasting model and its application to forecast primary energy consumption in major industrial countries
Published in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2021
Reasonable energy forecasting technology can more accurately predict the changes of the energy market, which is conducive to preventing overcapacity or surging energy prices. In this paper, a grey Theta forecasting method was established to forecast primary energy consumption of the major industrial countries. The predictions show that global primary energy consumption will continue to grow slowly overall. However, due to the implementation of environmental protection policies in various countries, the annual primary energy consumption of the United States, Japan and other countries will not continue to increase. China’s and India’s primary energy consumption is set to creep up by 1% a year over the next few years. As might be expected, the transformation of energy structure relates to the cost of energy use and the country’s ability to control pollution.
A framework of developing machine learning models for facility life-cycle cost analysis
Published in Building Research & Information, 2020
Xinghua Gao, Pardis Pishdad-Bozorgi
Understanding the underlying dynamics of building utility consumption (energy, water, and gas) and predicting the consumption are essential for building resource planning, management, and conservation (Amasyali & El-Gohary, 2018; Zhang, Cao, & Romagnoli, 2018). Energy (electricity) consumption prediction is the most extensively studied topic in the facility LCC prediction field. This is probably because the electricity meters and sensors distributed in facilities provide sufficient high-resolution data, hourly or even quarter-hourly, for researchers to investigate utility costs in detail (Moon, Park, Hwang, & Jun, 2018; Park, Choi, Hong, Lee, & Moon, 2018; Sala-Cardoso, Delgado-Prieto, Kampouropoulos, & Romeral, 2018). The most commonly used machine learning methods for energy forecasting involve (1) ANNs (Mocanu, Nguyen, Kling, & Gibescu, 2016; Park et al., 2018; Sala-Cardoso et al., 2018), (2) SVM regression (Chou & Ngo, 2016; Jain, Smith, Culligan, & Taylor, 2014), and (3) CBR (An, Kim, & Kang, 2007; Ji, Hong, Jeong, & Leigh, 2014).
Wind speed forecasting using deep learning and preprocessing techniques
Published in International Journal of Green Energy, 2023
Wind energy is a growing energy source and an essential cornerstone of sustainable energy supply. Wind speed forecasting plays a huge role in the planning and operation process of wind energy generation (Rodriguez & Xydis, G., 2021). However, due to the fluctuating and non-stationary characteristics of wind speed, accurate wind speed forecasting poses challenges to the safety and stability of the electric power grid. Therefore, a lot of research has been done attempting to improve wind speed accuracy. With the advancement of artificial intelligence technologies, particularly deep learning, a growing number of deep learning-based models are being considered for wind speed forecasting due to their superior ability to capture complex wind speed properties. Wind energy prediction is an essential tool. It provides significant estimates of accessible wind energy data that can be used in energy scheduling and resource balancing. Energy prediction, mainly the prediction of electricity, is being utilized throughout the whole sections of the utility industry including transmission, generation, distribution, and retail. Energy forecasting applications extend distribution and transmission planning, power supply planning, power system maintenance and operations, demand-side management, and financial planning (Ahmad, Zhang, and Yan 2020). This shows the importance of energy prediction in the utility business services. Forecasting of wind energy is required for the good operation of the power grid (Niswander and Xydis 2022). There is a growing demand for reliable and precise forecasts of wind energy to be able to trade the energy more efficiently. This has led to an increase in forecasting methods over the past decade.