Energy Demand Forecasting

This book is written for researchers and postgraduates who are interested in developing high-accurate energy demand forecasting models that outperform traditional models by hybridizing intelligent technologies. It covers meta-heuristic algorithms, chaotic mapping mechanism, quantum computing mechanism, recurrent mechanisms, phase space reconstruction, and recurrence plot theory. The book clearly illustrates how these intelligent technologies could be hybridized with those traditional forecasting models. This book provides many figures to deonstrate how these hybrid intelligent technologies are being applied to exceed the limitations of existing models.

As industrial, commercial, and residential demands increase and with the rise of privatization and deregulation of the electric energy industry around the world, it is necessary to improve the performance of electric operational management. Intelligent Energy Demand Forecasting offers approaches and methods to calculate optimal electric energy allocation to reach equilibrium of the supply and demand. Evolutionary algorithms and intelligent analytical tools to improve energy demand forecasting accuracy are explored and explained in relation to existing methods. To provide clearer picture of how these hybridized evolutionary algorithms and intelligent analytical tools are processed, Intelligent Energy Demand Forecasting emphasizes on improving the drawbacks of existing algorithms. Written for researchers, postgraduates, and lecturers, Intelligent Energy Demand Forecasting helps to develop the skills and methods to provide more accurate energy demand forecasting by employing novel hybridized evolutionary algorithms and intelligent analytical tools.

The use of data collectors in energy systems is growing more and more. For example, smart sensors are now widely used in energy production and energy consumption systems. This implies that huge amounts of data are generated and need to be analyzed in order to extract useful insights from them. Such big data give rise to a number of opportunities and challenges for informed decision making. In recent years, researchers have been working very actively in order to come up with effective and powerful techniques in order to deal with the huge amount of data available. Such approaches can be used in the context of energy production and consumption considering the amount of data produced by all samples and measurements, as well as including many additional features. With them, automated machine learning methods for extracting relevant patterns, high-performance computing, or data visualization are being successfully applied to energy demand forecasting.

Although the energy headlines of 1985 proclaim the waning of OPEC, the collapse of oil prices, and the demise of the nuclear power industry, few policy analysts are examining the dynamic challenges and opportunities that may confront the electric power industry during the remainder of this century. In this pioneering work, Adela Maria Bolet attempts to do exactly this, namely, to reconcile the differences among forecasters as to the future of electricity demand in the industrial, commercial, and residential sectors.

The master thesis of Kevin Berk develops a stochastic model for the electricity demand of small and medium-sized companies that is flexible enough so that it can be used for various business sectors. The model incorporates the grid load as an exogenous factor and seasonalities on a daily, weekly and yearly basis. It is demonstrated how the model can be used e.g. for estimating the risk of retail contracts. The uncertainty of electricity demand is an important risk factor for customers as well as for utilities and retailers. As a consequence, forecasting electricity load and its risk is now an integral component of the risk management for all market participants.

The overarching aim of this open access book is to present self-contained theory and algorithms for investigation and prediction of electric demand peaks. A cross-section of popular demand forecasting algorithms from statistics, machine learning and mathematics is presented, followed by extreme value theory techniques with examples. In order to achieve carbon targets, good forecasts of peaks are essential. For instance, shifting demand or charging battery depends on correct demand predictions in time. Majority of forecasting algorithms historically were focused on average load prediction. In order to model the peaks, methods from extreme value theory are applied. This allows us to study extremes without making any assumption on the central parts of demand distribution and to predict beyond the range of available data. While applied on individual loads, the techniques described in this book can be extended naturally to substations, or to commercial settings. Extreme value theory techniques presented can be also used across other disciplines, for example for predicting heavy rainfalls, wind speed, solar radiation and extreme weather events. The book is intended for students, academics, engineers and professionals that are interested in short term load prediction, energy data analytics, battery control, demand side response and data science in general.