---
title: "Short-term load forecasting method"
subject: "Power Plant Design"
chapter: 2
key: "semester_8/power_plant_design:short-term-load-forecasting"
source: https://www.bctengineer.com/q/semester_8/power_plant_design/short-term-load-forecasting
site: BCT Engineering
---

# Short-term load forecasting method

Power Plant Design · Chapter 2: Integrated System Planning in Design Approach

- Asked in: 2082 Shrawan, 4 marks
- Video: [Short-Term Electric Load Forecasting using ANN in MATLAB](https://www.youtube.com/watch?v=UfTK8i3Zd5s) — SunTech Engineering Solutions
- Answer checked by Claude Opus 5.5 (high effort) on 2026-10-14
- Page: https://www.bctengineer.com/q/semester_8/power_plant_design/short-term-load-forecasting
- Whole chapter: https://www.bctengineer.com/md/semester_8/power_plant_design/chapter-2

## Question

Discuss a suitable method for a short-term load forecasting.

## Short answer

Short-term load forecasting uses multiple linear regression with temperature, load at the same hour yesterday and last week, and day-type indicators, or artificial neural networks. Coefficients are estimated by least squares, forecasts checked by MAPE, and models updated daily; good accuracy is 1–3% error.

## Answer

**Short-term load forecasting (STLF)** predicts the load for the next hour to one week, mainly for unit commitment, economic dispatch and reserve scheduling. A widely used method is the **time-series (similar-day / regression) method**, and modern utilities also use **artificial neural networks (ANN)**.

#### Multiple linear regression method (suitable and simple)
The hourly load is modelled as a function of the variables that affect it:

$$
L(t) = a_0 + a_1 T(t) + a_2 L(t-24) + a_3 L(t-168) + a_4 D(t) + e(t)
$$

where $T$ = forecast temperature, $L(t-24)$ = load at the same hour yesterday, $L(t-168)$ = load at the same hour last week, $D$ = day-type indicator (working day/holiday), $e$ = error.

#### Steps
1. **Collect data:** past hourly load (2–3 years), weather data, calendar (weekends, festivals like Dashain/Tihar).
2. **Clean data:** remove load-shedding periods and abnormal values.
3. **Select variables:** find those strongly correlated with load.
4. **Estimate coefficients** $a_0 \dots a_4$ by least squares.
5. **Forecast** using next day's weather forecast and day type.
6. **Check accuracy** using Mean Absolute Percentage Error (MAPE); good STLF gives about 1–3% error.
7. **Update** the model daily with new data.

#### Alternative
An **ANN** takes the same inputs (past loads, temperature, hour, day type), learns the nonlinear relation from history, and usually gives lower error than regression, especially for holidays and weather changes.

## Check yourself

The answer's key points as multiple-choice questions, with the correct option and why.

1. Short-term load forecasting covers what period and purpose?
   A. 10-25 years for plant planning
   B. Next hour to one week for unit commitment, dispatch and reserve scheduling
   C. One year for tariff
   D. Only monthly energy sales
   Answer: B. STLF predicts load from an hour to a week for operational scheduling. (Key point: STLF horizon and use)

2. Which variables appear in the multiple linear regression model?
   A. Line length and conductor size
   B. Fuel price and discount rate
   C. Only population
   D. Temperature, load 24 h ago, load 168 h ago and day-type
   Answer: D. L(t) uses T(t), L(t-24), L(t-168) and D(t), plus an error term. (Key point: Regression variables)

3. How are the regression coefficients a0...a4 found?
   A. By least squares from past data
   B. By guessing
   C. From transformer ratings
   D. By the largest observed load
   Answer: A. Coefficients are estimated by least squares on 2-3 years of hourly data. (Key point: Coefficient estimation)

4. How is forecast accuracy checked?
   A. Load factor
   B. Mean Absolute Percentage Error (MAPE), about 1-3% for good STLF
   C. LOLP
   D. Power factor
   Answer: B. MAPE compares forecast to actual load; 1-3% is good. (Key point: Accuracy check)

## Related in Power Plant Design

- [Need for accurate load forecasting](https://www.bctengineer.com/question.md?key=semester_8%2Fpower_plant_design%3Aload-forecasting-importance) — Power Plant Design, chapter 2, asked 2×
- [Generation expansion planning and load forecasting](https://www.bctengineer.com/question.md?key=semester_8%2Fpower_plant_design%3Ageneration-expansion-load-forecast) — Power Plant Design, chapter 2
- [Accurate load forecasting and system security](https://www.bctengineer.com/question.md?key=semester_8%2Fpower_plant_design%3Aload-forecasting-benefits-security) — Power Plant Design, chapter 2
- [Intelligent methods for load forecasting](https://www.bctengineer.com/question.md?key=semester_8%2Fpower_plant_design%3Aintelligent-load-forecasting) — Power Plant Design, chapter 2

## Related in other subjects

- [Demand forecasting steps at load center](https://www.bctengineer.com/question.md?key=semester_8%2Ftransmission_and_distribution_system_design%3Ademand-forecast-load-center-steps) — Transmission and Distribution System Design, chapter 6
- [Methods of load forecasting](https://www.bctengineer.com/question.md?key=semester_8%2Ftransmission_and_distribution_system_design%3Aload-forecasting-methods) — Transmission and Distribution System Design, chapter 6
- [Small area forecasting with load growth curve](https://www.bctengineer.com/question.md?key=semester_8%2Ftransmission_and_distribution_system_design%3Asmall-area-load-growth-curve) — Transmission and Distribution System Design, chapter 6
- [Small area load forecasting method](https://www.bctengineer.com/question.md?key=semester_8%2Ftransmission_and_distribution_system_design%3Asmall-area-forecasting-method) — Transmission and Distribution System Design, chapter 6