ABUBAKAR TAFAWA BALEWA UNIVERSITY, BAUCHI
SCHOOL OF POSTGRADUATE STUDIES
FACULTY OF ENGINEERING
M. ENG IN POWER SYSTEM & MACHINE ENGINEERING
PAPER PRESENTATION
ON
SHORT-TERM LOAD FORECASTING
Using Artificial Neural Network
BY
ADAMU MUHAMMED BELLO
(PGS/17-18/2/M/8505)
10th April, 2019 10:00 AM
CONTENTS
1. Title Page
2. Contents
3. Introduction
4. Short Term Load Forecasting
5. Aim & Objectives
6. Factor Affecting STLF
7. Need for STLF
8. Artificial Neural Networks
9. ANN-BASED Forecasting Systems
10. Reference
INTRODUCTION
Electrical load forecasting plays a vital role in order to achieve the concept of
next generation power system such as smart grid, efficient energy management
and better power system planning. As a result, high forecast accuracy is
required for multiple time horizons that are associated with regulation,
dispatching, scheduling and unit commitment of power grid.
Generally:
Load forecasting is a technique used by power or energy-providing companies
to predict the power/energy needed to meet the demand and supply
equilibrium. The accuracy of forecasting is of great significance for the
operational and managerial loading of a utility company.
Types of Load Forecasting:
In electricity markets, the load has to be predicted with the highest possible
precision in different time horizons.
Load Forecasting
Short-Term Medium-Term Long-Term
(one hour to a week) (a month up to a year) (over one year)
SHORT-TERM LOAD FORECASTING (STLF)
The STLF is performed to predict the load within the range from hours to a few
days ahead (Methaprayoon, 2003). The STLF is required for economic
operations of a power system such as scheduling of generating capacity,
scheduling of fuel purchases, power transfer analysis and planning of market
based power transfer. This implies that the STLF is important for power system
planning in order to ensure a secure, reliable and cost effective operation of a
power system whilst sustaining an inexpensive energy supply to the customers.
AIM AND OBJECTIVES
Electric power generation, transmission, distribution, security
1. Increase or decrease output of generators
2. Interchange power with neighboring systems
3. Prevent overloading and reduce occurrences of equipment failures
Electric power market:
1. Price settings
2. Schedule spinning reserve allocation properly
FACTOR AFFECTING STLF
1. Weather Data
Temperature
Humidity / Rain Fall
Wind Speed
2. Hour of the day, Day of the Week, Month of the Year
3. Econometric Factor
Residential Growth
Agricultural Growth
Commercial Growth
Industrial Growth
4. Events / Special Events
5. Life Style Changes
6. Power Tariffs
NEED FOR SHORT-TERM LOAD FORECASTING
• Electric industry needs to predict load consumption in the short
term:
• Economic scheduling of generation capacity
• Security analysis
• Final price in deregulated markets
• Efficient Power Procurement
• Selling of Excess Power
• Network Planning
• Demand Side Management
• Fuel Mix Selection
• Renewable Planning, etc
ARTIFICIAL NEURAL NETWORKS
A neural network is a concept in computation for many
applications: pattern recognition, system identification,
cognitive modeling, etc., which is used to get the
mathematical model and the concept that is similar to the
structure and operation of the brain. It consists of a
number of simple processing units ‘cells’ or ‘nodes’
connected together into a layered net-like structure. When
a given set of cells (the inputs) are stimulated, the signals
are passed through the network from node to node and
finally exit the network through another set of simplified
nodes (the outputs). The computational elements or nodes
in the hidden and output layers are generally nonlinear.
ANN-BASED FORECASTING SYSTEMS
Two main architectures: one output node or several
output nodes.
One output node:
Next hour’s load; next day’s peak; next day’s integral load.
Forecast load profile: repeatedly forecasting one hourly load at a time; or
using a system with 24 ANNs in parallel, one for each hour of the day.
Several output nodes:
24 nodes to forecast the load profile.
TOPOLOGIES OF ANN
Input data sources for STLF
Historical Load & Weather Real time
weather data Forecast data base
Measured load
STLF
EMS Information
display
RESULT
CONCLUSION
It can be concluded that the STLF is important for power
system planning in order to ensure a secure, reliable and
cost effective operation of a power system whilst sustaining
an inexpensive energy supply to the customers.
The results have also shown that the ANN with stationary
output provides more accurate results of STLF compared to
the ANN with non-stationary output.
THANK
YOU
