The document discusses load forecasting techniques used in Rajasthan, India. It provides background on why load forecasting is needed, an overview of power supply and demand in Rajasthan, and describes short-term load forecasting methods like neural networks used to predict load 15 minutes to a week in advance. Traditional techniques like regression and exponential smoothing are discussed along with modified methods. The results are used for generation and infrastructure planning, and both advantages like improved insight and disadvantages like inaccuracies are noted.
2. INDEX
1. What is load forecasting.
2. Why do we need load forecasting.
3. Power supply position in Rajasthan.
4. Demand requirement of Rajasthan.
5. Short-term load forecasting in Rajasthan.
6. Methodologies for load forecasting.
7. Interpretation of forecast results.
8. Planning scenario.
9. Advantages and disadvantages.
10. Conclusion.
3. LOAD FORCASTING
The first crucial step for any planning study.
Forecasting refers to the prediction of the load behavior for the future.
Words such as, demand and consumption are also used instead of electric load.
Energy (MWh, kWh) and power (MW,kW) are the two basic parameters of a load.
By load, we mean the power.
Demand forecast
To determine capacity of generation, transmission and distribution required .
Energy forecast
To determine the type of generation facilities required.
4. Why do we need load forecasting?
Load forecasting is a technique used by power
companies to predict the power or energy needed to
balance the supply and load demand at all the
times. It is mandatory for proper functioning of
electrical industry.
5. POWER SUPPLY POSITION IN RAJASTHAN
Power supply position in Rajasthan. Rajasthan got benefit of about
2339 MW (Excluding RES) from the power projects commissioned
during 11th Plan with 434 MW from Central sector stations, 1290
MW from State Sector stations, 540 MW from private sector
stations and 75 MW from Mundra UMPP.
Maximum peak demand in Rajasthan attained so far was 10,047
MW during last year (2018-19) which was also met almost in full.
Similarly, the energy availability was 58042 MUs against the
requirement of 58202 Mus.
6. DEMAND REQUIREMENT OF RAJASTHAN
The present energy requirement of Rajasthan is of the order of 58.9 BU per year.
The introduction of 24X7 supply across the State is likely to increase the electricity
consumption substantially in the State.
The demand can be classified in three broad categories.
(a) Demand on account of 24X 7 power supply to already electrified households.
(b) Demand on account of 24X7 power supply to already electrified other than
domestic category.
(c) Demand from electrification of unelectrified households.
7. SHORT-TERM LOAD FORECASTING IN RAJASTHAN
1) Short-term load forecasting is an important component in the power system
load forecast, it is very important to unit optimum combination, economic
scheduling, optimum current of dispatching department.
2) When using neural network to predict electric power load, front neural network
can predict with more precision fitting high linking and non-linear relation of
shining upon between inputting and outputting from complicated sample data
through studying.
8. CONTINUED….
The proposed models are tested for
prediction of load demand of Rajasthan
region of India, from fifteen minutes to
one week ahead for particular time of
the day of year 2015. Rajasthan region
has a typical load curve as it has a land
area of 342,239 km2 and population of
68 million, with acute climatic
conditions.
9. CLASSIFICATION OF DEMAND FORECASTING TECHNIQUES
1. Traditional Forecasting Techniques
(a) Regression Method
(b) Multiple Regression
(c) Exponential smoothing
2. Modified Traditional Techniques
(a) Adaptive Demand Forecasting
(b) Stochastic Time Series
10. Methodologies for Load Forecasting
The ability to accurately forecast load is vitally important for
the electric industry in a deregulated economy. Load
forecasting has many applications including energy
purchasing and generation, load switching, contract
evaluation, and infrastructure development. A large variety of
methods have been developed for and applied to load
forecasting.
11.
12.
13. Interpretation of forecast results
The results developed using the forecast methodologies are inclusive of additional
demand i.e. Open Access & Captive, Railways, Electric vehicles, expected
infrastructure plans, Master Plan of cities, Latent demand, Housing schemes, Metro
etc.
In a future scenario, electricity demand forecasting without baseline correction may
lead to shortfall in reserve capacities.
14. Planning scenario
Gas based stations has been accorded a higher priority than coal based stations
to derive the additional coal capacities which will be required. For gas, the
committed capacity additions up to FY22 as per final NEP(National Electricity
Plan)’18 has been considered. Also, as per the results of the final NEP’18, there
would be no capacity additions from FY22 onwards. Starting from FY17, a PLF of
21% has been considered which is expected to remain constant till FY32. In case
availability of gas improves, the PLF( plant load factor ) is expected to go up.
15. Advantages of forecasting
1) You’ll gain valuable insight.
2) You’ll learn from past mistakes.
3) It can decrease costs.
16. Disadvantages of forecasting
1) Forecasts are never 100% accurate.
2) It can be time-consuming and resource-intensive.
3) The model itself result in its defective prediction effect
and thus inability to meet the actual forecasting
requirement.
17. load and generation forecast, is the actual output of the models
and is a very valuable outcome for consumers, generators,
prosumers and aggregators to optimize the energy
management of consumers connected at the Low Voltage (LV)
level of secondary substations (SSs).
CONCLUSION