Load Forecasting Techniques - Brief

1. AJAY BHATNAGAR, NRLDC
Load Forecasting Techniques
&
Scheduling
POSOCO - NRLDC

2. lOAD FORECASTING IS USED by
POwER COMPANIES TO
ANTICIPATE THE AMOUNT OF
POwER NEEDED TO SUPPly THE
DEMAND.

3. JURISDICTION OF LOAD DESPATCH CENTERS
NLDC:
Apex body to ensure integrated
operation of National Power System
RLDC:
Apex body to ensure integrated
operation of power system in the
concerned region
SLDC:
Apex body to ensure integrated
operation of power system in a state
POSOCO - NRLDC

4. PECULIARITIES OF REGIONAL GRIDS
SOUTHERN
REGION
WESTERN
REGION
EASTERN
REGION
NORTHERN
REGION NORTH-
EASTERN
REGION
REGIONAL
GRIDS
Deficit Region
Snow fed – run-of –the –river hydro
Highly weather sensitive load
Adverse weather conditions: Fog & Dust
Storm
Very low load
High hydro potential
Evacuation problems
Industrial load and agricultural load
Low load
High coal reserves
Pit head base load plants
High load (40% agricultural load)
Monsoon dependent hydro
CHICKEN-NECK
POSOCO - NRLDC

5. POSOCO - NRLDC
lOAD FORECASTING

6. What is Load forecasting
POSOCO - NRLDC
Load forecasting is sort of planning & It is
said that “To work with plan is to work with
accuracy”.
Load forecasting is used by power
companies to anticipate the amount of
power needed to supply the demand.

7. LOAD FORECASTING
• The first crucial step for any planning study
• Forecasting refers to the prediction of the load behaviour 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
POSOCO - NRLDC

8. NATURE OF LOADS
Load characteristics:
• Demand factor
• Load factor
• Diversity factor
• Utilization factor
• Power factor
• Higher the values of load factor and diversity factor, lower will be the
overall cost per unit generated.
• Higher the diversity factor of the loads, the fixed charges due to
capital investment will be reduced.
POSOCO - NRLDC
loadConnected
demandMax
factorDemand
.

demandMax
demandAvg
factorLoad
.
.

stationpowerofdemandMax
demandsindividualofSum
factorDiversity
.
.max

stationpowerofcapacityRated
stationpowerondemandMax
factornUtilisatio
.


9. TYPES OF LOADS
Five broad categories:
• Domestic
• Demand factor: 70-100%
• Diversity factor: 1.2-1.3
• Load factor: 10-15%
• Commercial
• Demand factor: 90-100%
• Diversity factor: 1.1-1.2
• Load factor: 25-30%
• Industrial
• Small-scale: 0-20 kW
• Medium-scale: 20-100 kW
• Large-scale: 100 kW and above
• Demand factor: 70-80%
• Load factor: 60-65%
POSOCO - NRLDC

10. TYPES OF LOADS
• Agricultural
• Demand factor: 90-100%
• Diversity factor: 1-1.5
• Load factor: 15-25%
• Other loads
• Street lights, bulk supplies, traction etc.
Commercial and agricultural loads are characterized by
seasonal variations.
Industrial loads are base loads and are little weather
dependent.
POSOCO - NRLDC

11. DEMAND ESTIMATION
AS PER
IEGC PROVISIONS
POSOCO - NRLDC

12. DEMAND ESTIMATION
 Demand estimation for operational purposes is to be done on a
daily/weekly/monthly basis. The mechanism and facilities at SLDCs shall
be created to facilitate on-line estimation of demand for daily operational
use for each 15 minutes block.
 The monthly estimated demand by the SLDC shall be provided to RLDC
and RPC
 The SLDC shall take into account the Wind Energy forecasting to meet
the active and reactive power requirement.
 In order to facilitate estimation of Total Transfer Capability / Available
Transfer Capability on three month ahead basis , the SLDC shall furnish
estimated demand and availability data to RLDCs.

13. DEMAND-SIDE MANAGEMENT
 Grouping of Loads by SLDC without overlapping between different Groups
as given below
 Loads for scheduled power cuts/load shedding
 Loads for unscheduled load shedding
 Loads to be shed through under frequency relays/df/dt relays
 Loads to be shed under any System Protection Scheme identified at the
RPC level.

14. TECHNIQUES
OF
lOAD FORECASTING

15. FACTORS AFFECTING LOAD FORECASTING
• Time factors such as:
• Hours of the day (day/night)
• Day of the week (week day/weekend)
• Time of the year (season)
• Weather conditions (temperature and humidity)
• Class of customers (residential, commercial, industrial,
agricultural, public, etc.)
• Special events (TV programmes, public holidays, etc.)
• Population
• Economic indicators (per capita income, Gross National
Product (GNP), Gross Domestic Product (GDP), etc.)
• Trends in using new technologies
• Electricity price
POSOCO - NRLDC

16. FORECASTING METHODOLOGY
• Forecasting: systematic procedure for quantitatively
defining future loads.
• Classification depending on the time period:
• Short term
• Intermediate
• Long term
• Forecast will imply an intermediate-range forecast
• Planning for the addition of new generation, transmission and
distribution facilities must begin 4-10 years in advance of the
actual in-service date.
POSOCO - NRLDC

17. FORECASTING TECHNIQUES
POSOCO - NRLDC
 Three broad categories based on:
• Extrapolation
– Time series method
– Use historical data as the basis of estimating future
outcomes.
• Correlation
– Econometric forecasting method
– identify the underlying factors that might influence the
variable that is being forecast.
• Combination of both

18. EXTRAPOLATION
• Based on curve fitting to previous data available.
• With the trend curve obtained from curve fitted load can
be forecasted at any future point.
• Simple method and reliable in some cases.
• Deterministic extrapolation:
• Errors in data available and errors in curve fitting are not
accounted.
• Probabilistic extrapolation
• Accuracy of the forecast available is tested using statistical
measures such as mean and variance.
POSOCO - NRLDC

19. CORRELATION
• Relates system loads to various demographic and
economic factors.
• Knowledge about the interrelationship between nature of
load growth and other measurable factors.
• Forecasting demographic and economic factors is a
difficult task.
• No forecasting method is effective in all situations.
• Designer must have good judgment and experience to
make a forecasting method effective.
POSOCO - NRLDC

20. IMPACT OF WEATHER IN LOAD FORECASTING
• Weather causes variations in domestic load, public
lighting, commercial loads etc.
• Main weather variables that affect the power
consumption are:
• Temperature
• Cloud cover
• Visibility
• precipitation
• First two factors affect the heating/cooling loads
• Others affect lighting loads
POSOCO - NRLDC

21. IMPACT OF WEATHER IN LOAD FORECASTING
• Average temperature is the most significant weather
dependent factor that influences load variations.
• Temperature and load are not linearly related.
• Non-linearity is further complicated by the influence of
• Humidity
• Extended periods of extreme heat or cold spells
• In load forecast models proper temperature ranges and
representative average temperatures which cover all
regions of the area served by the electric utility should be
selected.
POSOCO - NRLDC

22. IMPACT OF WEATHER IN LOAD FORECASTING
• Cloud cover is measured in terms of:
• height of cloud cover
• Thickness
• Cloud amount
• Time of occurrence and duration before crossing over a
population area.
• Visibility measurements are made in terms of
meters/kilometers with fog indication.
• To determine impact of weather variables on load
demand, it is essential to analyze data concerning
different weather variables through the cross-section of
area served by utility and calculate weighted averages
for incorporation in the modeling.
POSOCO - NRLDC

23. ENERGY FORECASTING
• To arrive at a total energy forecast, the forecasts for
residential, commercial and industrial customers are
forecasted separately and then combined.
POSOCO - NRLDC

24. RESIDENTIAL SALES FORECAST
• Population method
• Residential energy requirements are dependent on:
• Residential customers
• Population per customer
• Per capita energy consumption
• To forecast these factors:
• Simple curve fitting
• Regression analysis
• Multiplying the three factors gives the forecast of residential
sales.
POSOCO - NRLDC

25. RESIDENTIAL SALES FORECAST
• Synthetic method
• Detailed look at each customer
• Major factors are:
• Saturation level of major appliances
• Average energy consumption per appliance
• Residential customers
• Forecast these factors using extrapolation.
• Multiplying the three factors gives the forecast of residential
sales.
POSOCO - NRLDC

26. COMMERCIAL SALES FORECAST
• Commercial establishments are service oriented.
• Growth patterns are related closely to growth patterns in
residential sales.
• Method 1:
• Extrapolate historical commercial sales which is frequently
available.
• Method 2:
• Extrapolate the ratio of commercial to residential sales into
the future.
• Multiply this forecast by residential sales forecast.
POSOCO - NRLDC

27. INDUSTRIAL SALES FORECAST
• Industrial sales are very closely tied to the overall
economy.
• Economy is unpredictable over selected periods
• Method 1:
• Multiply forecasted production levels by forecasted energy
consumption per unit of production.
• Method 2:
• Multiply forecasted number of industrial workers by forecasted
energy consumption per worker.
POSOCO - NRLDC

28. PEAK LOAD FORECASTING
• Extrapolate historical demand data
• Weather conditions can be included
• Basic approach for weekly peak demand forecast is:
1. Determine seasonal weather load model.
2. Separate historical weather-sensitive and non-weather
sensitive components of weekly peak demand using
weather load model.
3. Forecast mean and variance of non-weather-sensitive
component of demand.
4. Extrapolate weather load model and forecast mean and
variance of weather sensitive component.
5. Determine mean, variance and density function of total
weekly forecast.
6. Calculate density function of monthly/annual forecast.
POSOCO - NRLDC

29. WEATHER LOAD MODEL
• Plot a scatter diagram of daily peaks versus an appropriate
weather variables.
• Dry-bulb temperature and humidity
• Using curve fitting three line segments can be defined in the example
POSOCO - NRLDC
sw
www
sss
TTTif0
TTifTTk
TTifTTkw



)(
)(
Parameters of the model:
• Slopes: ks and kw
• Threshold temperatures:
Ts and Tw

30. SEPARATING WEATHER-SENSITIVE AND NON-
WEATHER SENSITIVE COMPONENTS
• From the weather load model
• Weather-sensitive (WS) component of weekly peak load demand
data is calculated from the weekly peak coincident dry-bulb
temperatures.
• Non-weather-sensitive (NWS) component of peak demand is
obtained by subtracting the first component from historical data.
• NWS component is used in step-3, of basic approach for weekly
peak demand forecast , to forecast the mean and variance of the
NWS component of future weekly peak demands.
POSOCO - NRLDC

31. TOTAL FORECAST
POSOCO - NRLDC

32. LOAD FORECASTING CATEGORIES
Load Forecasting Categories
 Short-term load forecasting
 One hour ~ One week
 Control and schedule power system in everyday
operations
 Medium-term and Long-term load forecasting
 One week ~ longer than one year
 Determine capacity of generation, transmission,
distribution systems, type of facilities required in
transmission expansion planning, development of
power system infrastructure, etc.
POSOCO - NRLDC

33. LOAD FORECASTING METHODS
 Parametric methods
 Regression method
 Time series
 Similar day Approach
 Autoregressive Moving Average (ARMA)
 Spectral expansion technique (Fourier Series)
 State equations
 Artificial intelligence methods
 Artificial neural networks
 Fuzzy logic
 Expert systems
POSOCO - NRLDC

34. INFLUENCE – WEATHER, TIME & TYPE
Electric load has an obvious correlation to weather. The most
important variables responsible in load changes are:
 Dry and wet bulb temperature
 Dew point
 Humidity
 Wind Speed / Wind Direction
 Sky Cover
 Sunshine
In the forecasting model, we should also consider time factors
such as:
 The day of the week
 The hour of the day
 Holidays
Electric utilities usually serve different types of customers such as
residential, commercial, and industrial. The following graphs
show the load behavior in the above classes by showing the
amount of peak load per customer, and the total energy.
POSOCO - NRLDC

35. SCHEDUlING
AS PER
IEGC PROVISIONS
POSOCO - NRLDC

36. SCHEDULING RESPONSIBILITY
RLDC has Scheduling Responsibility for
 a) Central Generating Stations (excluding stations where full Share is
allocated to host state),
 b) Ultra-Mega power projects
 c) If a generating station is connected only to the ISTS, (except for
Central Generating Stations where full Share is allocated to one State)
 d) If a generating station is connected to both ISTS and the State
network and if the state has 50% Share of power or less ( of the
generating capacity put into commercial operation)
POSOCO - NRLDC

37. SCHEDULING RESPONSIBILITY
SLDC has Scheduling Responsibility for
 a) Generating station which is connected only to the State transmission
network
 b) Central Generating Station whose full Share is allocated to host state.
 c) If a generating station is connected both to ISTS and the State network
and if the state has more than 50% Share of power (of the generating
capacity put into commercial operation)
 d) Generating station supplying power to any state other than host state
POSOCO - NRLDC

38. SCHEDULING RESPONSIBILITY
NLDC shall be responsible for
 scheduling and despatch of electricity over inter-regional links in
accordance with the grid code specified by Central Commission in
coordination with Regional Load Despatch Centers.
 NLDC shall be responsible for coordination with Regional Load
Despatch Centers for the energy accounting of inter-regional exchange
of power.
 NLDC shall also be responsible for coordination for trans-national
exchange of power.
 NLDC shall develop a procedure for scheduling of collective transaction
through Power Exchanges, scheduling of inter-regional power exchanges
including HVDC setting responsibility and power exchanges of the
country with other countries.
POSOCO - NRLDC

39. SCHEDULING PROCEDURE
POSOCO - NRLDC

40. TIME LINE OF SCHEDULE
By 09.00 hrs. ISGSs shall advise NRLDC the Station-wise MW and MWh
capabilities
By 10.00 Hrs. NRLDC shall advise the States / Beneficiaries the Station wise MW
& MWh entitlements.
By 1500 hrs. SLDCs/ Beneficiaries shall communicate the Station-wise
requisitions and details of bilateral exchanges to NRLDC.
By 1800 hrs. NRLDC shall convey the ex-power plant despatch schedule to each
ISGS and net drawal schedule to each State / Beneficiary. The
details of unrequisitioned surpluses shall also be intimated.
By 2200 hrs.* ISGSs / States / Beneficiaries shall inform the modifications, if any,
for incorporating in the final schedule
By 2300 hrs. NRLDC shall issue the final despatch and drawal schedule.
* Since issuing the final despatch and drawal schedule is a critical activity and
considerable time is involved in its preparation and carrying out requisite
moderation, if any, it has been agreed to complete this activity by 2100 hrs.
POSOCO - NRLDC

41. COMPOSITE TIMELINE
Availability
Declaration
Entitlements
S
L
D
C
Requisition &
Bilateral Agreements
Injection Schedule Drawal Schedule
Revision in DC Revision in Requisition
Final
Injection Schedule
Final
Drawal Schedule
09:00
10:00
15:00
18:00
22:00
23:00
R
L
D
C
I
S
G
S
Time
Revisions during
Current day
Revisions during
Current day
0 to 24
hours
Collective
Transactions (PX)
POSOCO - NRLDC

42. SPECIAL REQUIREMENT OF SOLAR / WIND
5.2
(u) Special requirements for Solar/ wind generators
System operator (SLDC/ RLDC) shall make all efforts to evacuate the
available solar and wind power and treat as a must-run station. However,
System operator may instruct the solar /wind generator to back down
generation on consideration of grid security or safety of any equipment or
personnel is endangered and Solar/ wind generator shall comply with the
same. For this, Data Acquisition System facility shall be provided for
transfer of information to concerned SLDC and RLDC
(i) SLDC/RLDC may direct a wind farm to curtail its VAr drawl/injection in
case the security of grid or safety of any equipment or personnel is
endangered.
(ii) During the wind generator start-up, the wind generator shall ensure that
the reactive power drawl (inrush currents incase of induction generators)
shall not affect the grid performance.
POSOCO - NRLDC

43. DEVIATIONS FROM SCHEDULE - UI
POSOCO - NRLDC

44. POSOCO - NRLDC