Text

Electrical Load Forecasting: Modeling and Model Construction

---

Succinct and understandable, this book is a step-by-step guide to the mathematics and cosntruction of electrical load forecasting models. Written by one of the world's foremost experts on the subject, Electrical Load Forecasting provides a brief discussion of algorithms, their advantages and disadvantages, and when they are best utilized. The text begins with a description of the basic theory and models needed to truly understand how these models are prepared so that engineers are not just blindly plugging and chugging numbers. This is followed by a clear and rigorous exposition of the statistical techniques and algorithms such as regression, neural networks, fuzzy logic, and expert systems. The book is also supported by an online computer program that allows readers to construct, validate, and run short and long term models.rnEconomic development, throughout the world, depends directly on the availability of electric energy, especially because most industries depend almost entirelyon its use. The availability of a source of a source of continous , cheap, and reliable energy is of foremost economic importance.rnElectrical load forecasting is an important tool used to ensure that the energy supplied by utilities meets the load plus the energy lost in the systems. To this end, a staff of trained personnel is needed to carry out this specialized function. Load forecasting is always defined as basically the science or art of predicting the future load on a given system for a specified period of time ahead. These predictions may be just for a fraction of an hour ahead for operation purposes, or as much as 20 years into the future for planning purposes.rnLoad forecasting can be categorized into three subject areas, namely,rn1. Long-range forecasting, which is used to predict loads as distant as 50 years ahead so that expansion planning can be facilitated.rn2. Medium-range ahead so that efficient is used to predict weekly, monthly, and yearly peak loads up to 10 years ahead so that efficient operational planning can be carried out.rn3. Short-range forecasting, which is used to predict loads up to a week ahead so that daily running and dispatching costs can be minimized.rnIn the preceding three categories, an accurate load model is required to mathematically represent the relationship between the load and influential variables such as time, weather, economic factors, etc. The precise relationship between the load and these variables is usually determined by their role in the load model. After the mathematical models is constructed, the model parameters are determined through the use of estimation techniques.rnExtrapolating the mathematical relationship to the required lead time ahead and giving the corresponding values of influential variables to be available or predictable, forecasts can be made. Because factors such as weather and economic indices are increasingly difficult to predict accurately for longer lead times ahead, the greater the lead time, the less accurate the prediction is likely to be.rnThe final accuracy of any forecast thus depends on the load models employed, the accuracy of predicted variables, and the parameters assigned by the relevant estimation technique. Because different methods of estimation will result in different values of estimated parameters, it follows that the resulting forecasts will differ in prediction accuracy.rnOver the past 50 years, the parameter estimation algorithms used in load forecasting have been limited to those based on the least error squares minimization criterion, even though estimation theory indicates that algorithms based on the least absolute value criteria are viable alternatives. Furthermore, the artificial neural network (ANN) had showed success in estimating the load for the next hour. However, the ANN used by utility is not necessarily suitable for another utility and should be retrained to be suitable for that utility.rnIt is well known the electric load is a dynamic one and does not have a precise value form one hour to another. In this book, fuzzy systems theory is implemented to estimate the load model parameters, which are assumed to be fuzzy parameters having a certain middle and spread. Different membership functions, for load parameters, are used—namely, triangular membership and trapezoidalmembership functions. The problem of load forecasting in this book is restricted to short-term load forecasting and is formulated as a linear estimation problem in the parameters to be estimated. In this book, the parameters in the first part are assumed to be crisp parameters, whereas in the rest of the book these parameters are assumed to be fuzzy parameters. The objective is to minimize the spread of the available data points, taking into consideration the type membership of the fuzzy parameters, subject to satisfying constraints on each measurement point, to ensure that the original membership is included in the estimated membership.

---

Ketersediaan

090101964

Tersedia

Informasi Detil

Judul Seri

-

No. Panggil

621.3 SOL e

Penerbit

Elsevier : United States of America., 2010

Deskripsi Fisik

xix, 414 p.

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subyek

-

Info Detil Spesifik

-

Pernyataan Tanggungjawab

-

Versi lain/terkait

Lampiran Berkas

Komentar

---

You must be logged in to post a comment