LOAD FORECASTING USING ANN UNDER THE GUIDANCE OF PROF. G.N.GOYAL NEHA CHOURE (04) AVI AGRAWAL (110) SUMIT PARKHADE (118) HITESH CHAUDHARI (126) DEPARTMENT OF ELECTRICAL ENGINEERING SHRI RAMDEOBABA COLLEGE OF ENGINEERING & MANAGEMENT

WHAT IS LOAD FORECASTING? Electric load forecasting is the process used to forecast future electric load, given historical load, weather information along with current and forecasted weather information. Load forecasting plays a key role in helping an electric utility to make important decisions on power, load switching, voltage control, network reconfiguration, infrastructure development, purchasing and generating electric power.

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.

Load forecasting helps an electric utility to make important decisions including decisions on purchasing and generating electric power, load switching, and infrastructure development. However, with the deregulation of the energy industries, load forecasting is even more important. Load forecasting can be divided into three categories. Short term load forecasting which from are usually one hour to one week period. Short term load forecasting can help to estimate load flows and to make decisions that can prevent overloading. Medium load forecasting which are usually from a week to one year, and Long term load forecasting which are longer than a year Approximately nine categories of load forecasting techniques has been reported in the literature

WHY LOAD FORECASTING Proper planning of power system is a very important part of power systems operation. Load forecasts are an important factor for planning in the long, short and medium term. Accurate models for electric power load forecasting are essential to the operation and planning of a utility company.

Load forecasting helps an electric utility to make important decisions including decisions on purchasing and generating electric power, load switching, and infrastructure development. Load forecasts are extremely important for energy suppliers, ISOs, financial institutions, and other participants in electric energy generation, transmission, distribution, and markets

METHODS OF FORECASTING Statistical model-based learning Artificial Neural Network(ANN) Method Expert systems Method Fuzzy logic Method Regression methods. Time series

WHAT IS ANN? A neural network is a machine that is designed to model the way in which the brain performs a particular task. The network is implemented by using electronic components or is simulated in software on a digital computer. It is composed of a large number of highly interconnected processing elements (neurons) working in unison to solve specific problems.

A neural network is a massively parallel distributed processor made up of simple processing units, which has a natural propensity for storing experimental knowledge and making it available for use. There are two different types of layers: 1.Single layer ANN 2.Multi-layer ANN

Different layers may perform different kinds of transformations on their inputs. Signals travel from the first (input), to the last (output) layer, possibly after traversing the layers multiple times. The original goal of the neural network approach was to solve problems in the same way that a human brain would.

WHY DO WE USE NEURAL NETWORKS Neural networks, with their remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. Benefits: 1. Adaptive learning: An ability to learn how to do tasks based on the data given for training or initial experience.

2. Self-Organization: An ANN can create its own organization or representation of the information it receives during learning time. 3. Real Time Operation: ANN computations may be carried out in parallel, and special hardware devices are being designed and manufactured which take advantage of this capability.

ANN LOAD FORECASTING MODEL The developed forecasting model, which considers temperature and humidity as input data, is shown in Fig. 1. Fig.1 The proposed ANN Model

Since the load demand does not depend only on temperature and humidity and in order to account for other factors, the input data are fed to the neural network with historical load data for training and comparing for future load forecasting. Neural network elements might be arranged in different number of layers between the input and output; however, in practice, the number of used layers is relatively small.

TYPES OF ANN Feed forward Network Recurrent Neural Network Regulatory feedback Network Radial Basis Function

ADVANTAGES A neural network can perform tasks in which a linear program cannot perform. When an element of the neural network fails, it can continue without any problem by their parallel nature. A neural network does not need to be reprogrammed as it learns itself. It can be implemented in an easy way without any problem.

As adaptive, intelligent systems, neural networks are robust and excel at solving complex problems. It can be implemented in any applications without any risk. It generalizes knowledge to produce adequate responses to unknown situations.

APPLICATION Artificial neural network applications have been used in the field of solar energy for modelling and design of a solar steam generating plant. They are useful in system modelling, such as in implementing complex mapping and system identification. ANN are used for the estimation of heating-loads of buildings, parabolic-trough collector’s intercept factor and local concentration ratio.

ANN are used in diverse applications in control, robotics, pattern recognition, forecasting, medicine, power systems, manufacturing, optimization and signal processing. They are able to handle noisy and incomplete data and also able to deal with non-linear problems. The use of ANN in ventilating, air conditioning, heating, Load Forecasting and control of power generation system.

DATA COLLECTED All data are collected from Mankapur substation of 4 feeders(Ambajhari-1 & 2,Hingna-1, Uppalwadi) for the months of June, July and August. The following parameters are- Maximum Voltage Minimum Voltage Maximum Current Minimum Current MWH Meter Reading MWH consumption Temperature

ELECTRICAL PARAMETERS FOR THE MONTH OF JUNE MONTH:JUNE S.No.DateTime 132kV Ambajhari-I132kV Ambajhari-II VoltageCurrent MWH Meter Reading MWH VoltageCurrent MWH Meter Reading MWH MaxMinMaxMinMaxMinMaxMin : : : : : : : : : : : : : : : : : : : : : : : : NA : : : : : :

132kV Hingna-I132kV Uppalwadi VoltageCurrent MWH Meter Reading MWH VoltageCurrent MWH Meter ReadingMWH MaxMinMaxMinMaxMinMaxMin

ELECTRICAL PARAMETERS FOR THE MONTH OF JULY MONTH:JULY S.No.DateTime 132kV Ambajhari-I132kV Ambajhari-II VoltageCurrent MWH Meter Reading MWH VoltageCurrent MWH Meter Reading MWH MaxMinMaxMinMaxMinMaxMin : : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : NA : : :

132kV Hingna-I132kV Uppalwadi VoltageCurrent MWH Meter Reading MWH VoltageCurrent MWH Meter ReadingMWH MaxMinMaxMinMaxMinMaxMin

ELECTRICAL PARAMETERS FOR THE MONTH OF AUGUST MONTH:AUGUST S.No.DateTime 132kV Ambajhari-I132kV Ambajhari-II VoltageCurrent MWH Meter Reading MWH VoltageCurrent MWH Meter Reading MWH MaxMinMaxMinMaxMinMaxMin : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : :

132kV Hingna-I132kV Uppalwadi VoltageCurrent MWH Meter Reading MWH VoltageCurrent MWH Meter ReadingMWH MaxMinMaxMinMaxMinMaxMin

LOAD FORECASTING USING ANN Short-term power load forecasting is used to provide utility company management with future information about electric load demand in order to assist them in running more economical and reliable day-to-day operations. A broad spectrum of factors affect the system’s load level such as trend effects, cyclic-time effects, and weather effects, random effects like human activities, load management and thunderstorms.

Thus the load profile is dynamic in nature with temporal, seasonal and annual variations. In our project we developed a system that predicted 24 hour at a time load demand. As inputs we took the past 24 load and the day of the week. Input to the ANN are past loads and the output of the ANN is the load forecast for a next day.

The inputs were fed into our Artificial Neural Network (ANN) and after sufficient training were used to predict the load demand for the next week. A schematic model of our system is shown in Fig 5.1. The inputs given are: 1.Hourly load demand for the full day. 2.Day of the week. 3.Min/Max/ Average daily temperature. The output obtained was the predicted hourly load demand for the next day.

The flow chart is shown below

The ANN was implemented using MATLAB 15. The training algorithm was used which is an adaptive learning algorithm using the epoch method of training. The number of epochs while training was set at 50,000 by which point the network was sufficiently trained.

IMPLEMENTATION Gathering and arranging the data in MS Excel spreadsheet. Tagging the data into groups. Analyse the data. MATLAB simulation of data using ANN.

CONCLUSION The historical data of 3 months collected from Mankapur substation and physical parameters like temperature and humidity are used for analysis and this data is used in MATLAB simulation using ANN for further analysis. FUTURE WORK Using this data and MATLAB simulation using ANN, we can analyse the electrical parameters of next month and this can be used in generating station for required generation of power and the effect of temperature and pressure can be determined.

REFERENCES Mohan B. Tasre,Prashant P. Bedekar and Vilas N. Ghate,"Daily Peak Load Forecasting Using ANN",IEEE Trans.,8-10 December Mohammad Ghomi, Mahdi Goodarzi, Mahmood Goodarzi, “Peak Load Forecasting of Electric Utilities for West province of Iran by using Neural Network without weather Information”,IEEE Trans.,12th International Conference on Computer Modelling and Simulation 2010,Oct 2010.

THANK YOU