← Back to Publications List

Intelligent Residential Demand Management via Bi-LSTM Forecasting and MPC-Based Optimization

Students & Supervisors

Student Authors
Raif Tanjim
Bachelor of Science in Electrical & Electronic Engineering, FE
Tanvir Ahmed
Bachelor of Science in Electrical & Electronic Engineering, FE
Abdullah Al Mujahid
Bachelor of Science in Electrical & Electronic Engineering, FE
Supervisors
Abu Shufian
Lecturer, Faculty, FE

Abstract

This study proposes a Bi-LSTM-enhanced MPC framework for residential DSM, integrating deep learning-based forecasting with optimization-driven control. Results demonstrate superior performance over conventional DSM: 25.13% peak reduction (11.48 kWh), 54.93% lower energy losses (46.17 kWh, 0.67% of total consumption), and 317.09 kWh shifted to off-peak periods without compromising user comfort. Sub-meter analysis identifies Water & AC as the primary DSM contributor, while robust seasonal performance confirms scalability and practical relevance.

Keywords

DSM Bi-LSTM MPC Load Forecasting Peak Load Reduction Smart Grid Integration.

Publication Details

  • Type of Publication:
  • Conference Name: IEEE Region 10 TENSYMP 2026
  • Date of Conference: 29/06/2026 - 29/06/2026
  • Venue: IEEE Malaysia Section, Penang, Malaysia
  • Organizer: IEEE Malaysia Section, Penang, Malaysia