Search

The Electricity Demand Prediction (EDP) and Generation Expansion Planning (GEP) make a real-world planning problem more optimal. In this study, the EDP problem has been solved using the optimizatio...

A power system planning must involve the Electricity demand forecasting (EDF) and Generation expansion planning (GEP) for better operation. The optimal plan should consider both qualitative and quantitative factors such as error, cost and reliability of the power system. In this study, EDF and GEP problem have been solved till the year 2030 for Tamil Nadu, an Indian state. The formulation of EDF problem has been modeled based on the input variables such as population, Gross State domestic product (GSDP) and per capita income, and has been solved using Genetic algorithm (GA), Artificial immune system (AIS) and Differential evolution (DE). While analyzing the results of EDF problem, DE provides optimal result with Minimum mean absolute percentage error (MAPE). Continually, short term (6-year) and long term (12-year) GEP problem have been solved using DE by considering minimization of cost and environmental effects as the main objectives. To achieve these objectives, Renewable Energy Sources (RES) have been integrated in different penetration levels such as 0–10%, 10–20%, 20–30%, 30–40%, and 40–50% on GEP problem and its impacts have been investigated. The results of DE have been validated with Dynamic Programing (DP). The outcomes of the study have assisted the power system planners while decision making in introducing Renewable Energy Sources (RES) on a real-world power system.

This paper aims to apply the Differential evolution (DE) to forecast the electricity demand for Tamil Nadu based on population, Gross State Domestic Product (GSDP), and Per Capita Income (PCI). The linear and nonlinear models have been applied to forecast electricity demand. The actual data is partially used to attain the best values of the weighting parameters (years from 1980 to 2005) and the remaining data are used for testing the models (years from 2006 to 2017). Three scenarios have been considered (high, average, and low growth) to forecast the electricity demand for Tamil Nadu till the year 2030. Mean Absolute Percentage Error (MAPE) is the estimation key. The results have been validated with the National Electricity Plan (NEP) of India.

This research study presents the prediction of energy demand for India using Artificial Immune System (AIS) based on the input variables such as population, per capita Gross Domestic Product (PC-GDP), per capita Gross Domestic Income (PC-GDI) used during the model development. The Artificial Immune System-Energy Demand (AIS-ED) model is developed based on the available past year data. Two forms of the AIS-ED models are developed and also three different scenarios such that high growth, low growth and trend line are used to predict future energy demand of India. Mean Absolute Percentage Error (MAPE) is validating the performance of the model. The obtained AIS-ED results are compared with the 18th Electricity Power Survey of India.

This study deals with estimation of electricity demand for India using Genetic Algorithm (GA) based on economic indicators. The economic indicators are population, per capita gross domestic product (GDP), import and export. The Genetic Algorithm-Electricity Demand (GA-ED) model is developed based on past data, and different scenarios (low, high growth and trend line) are used to predict electricity demand. Two forms of the GA-ED models are developed to estimate electricity demand. Mean Absolute Percentage Error (MAPE) is used as an evaluation criterion to choose the best-fit GA-ED model and it is used for future electricity demand prediction. The GA-ED results are compared with the prediction of 18th Electricity Power Survey of India. The GD-ED model estimates electricity demand until 2025.