Research framing
The paper identifies electricity load and consumption forecasting as important for planning. It considers the challenges of forecasting from historical information and weather conditions.
Co-authored research paper · 2020 / Project case study
Electricity Consumption Forecasting
Examining adaptive forecasting approaches
THE WORKFLOW
1Consumption data
2ANFIS modelling
3Forecast evaluation
Project overview
Project context & objective
This co-authored 2020 research project investigated the use of an Adaptive Neuro-Fuzzy Inference System (ANFIS) to predict electricity consumption. The publicly accessible paper considers historic consumption and weather-related variables when forecasting energy demand.
Energy-demand forecasts require organised inputs and clear evaluation of model behaviour. The study examined a neuro-fuzzy approach to consumption forecasting.
Electricity-demand prediction supports power-system planning and operations. Consumption depends on multiple conditions, including weather, and historical observations may not always be complete or reliable. The paper examines an adaptive approach to forecasting in that context.
Research publication
Prediction of Electricity Consumption using Adaptive Neuro-fuzzy Inference System (2020).
Authors: Sai Vikas Malladi, Sardar Maran P., and Venkat Sankalp Mandava.
The research explores electricity consumption forecasting using an adaptive neuro-fuzzy inference system (ANFIS), considering historical consumption and weather-related inputs. The available SSRN record identifies this as a publicly posted research paper; it does not independently establish peer-reviewed journal publication.
Methodology
From inputs to insights
The following stages explain the workflow and the technical decisions behind this project.
Input considerations
The abstract describes electricity-consumption records and weather data available online as sources for model assessment.
ANFIS methodology
The proposed approach uses an adaptive neuro-fuzzy inference system to predict future consumption from previous observations and weather parameters.
Published research record
The work was co-authored by Sai Vikas Malladi, Sardar Maran P. and Venkat Sankalp Mandava. SSRN records the paper as written in June 2020, posted in July 2020 and revised in August 2020.
Technology
Tools & methods
MATLABPythonANFIS
Deliverables
Project outputs & learning
A co-authored 2020 research paper examining electricity consumption forecasting using an adaptive neuro-fuzzy inference system.
What I learned
Model evaluation should distinguish exploratory research from validated operational deployment.
Key deliverables
- Co-authored paper: Prediction of Electricity Consumption using Adaptive Neuro-fuzzy Inference System
- Public SSRN and Academia.edu research records
- A documented forecasting approach combining previous usage with weather-related inputs
Transferable skills
Skills & practical relevance
Defining analytical requirements, evaluating model assumptions and translating forecasts into practical planning discussions.
- Defining forecasting inputs and assumptions
- Interpreting data dependencies
- Understanding evaluation and validation claims
- Documenting technical research for scrutiny
The abstract describes the approach as effective but does not support a numerical accuracy claim here. A public SSRN record alone does not verify peer-reviewed journal publication or production deployment.