Smart Home Energy Consumption Forecasting: An Engineering

Approach with IoT and Al-Biruni Earth Radius Optimized LSTM

Networks

M. El-Said 1,*

1 Electrical Engineering Department, Faculty of Engineering, Mansoura University, Mansoura 35516, Egypt

Delta Higher Institute of Engineering and Technology, Mansoura 35111, Egypt

Received: May 08, 2026 Revised: June 30, 2026 Accepted: August 30, 2026 ⋆ Corresponding author

ABSTRACT

With the growing complexity of energy consumption patterns, accurate forecasting is required to maximize the

benefits of demand-side management, which relies on precise forecasting and optimization. To respond to this

challenge, this research suggests a new forecasting method by integrating the Al-Biruni Earth Radius (BER)

optimization algorithm with the Long Short-Term Memory (LSTM) network within an Internet of Things (IoT)-based

framework. The BER-optimized LSTM model processes real-time IoT sensor data, such as energy usage patterns

and weather conditions, to enhance energy usage predictions. Time-series clustering addresses data uncertainty and

noise, providing a probabilistic load forecast at both the household and aggregated levels. Extensive evaluation of the

model’s performance demonstrates substantial predictive accuracy, achieving a root mean squared error (RMSE) of

0.007146, surpassing conventional forecasting methods. These findings corroborate that BER optimization, coupled

with the use of LSTM networks, provides a suitable tool for smart home energy forecasting, which, in turn, can

facilitate improved energy management, demand-side optimization, and innovative grid applications in the evolving

energy market.

Keywords: Al-Biruni Earth Radius Load Forecasting IoT Long Short-Term Memory Weather Conditions

1. INTRODUCTION

Modern electrical systems are comprised of generation, transmission,

distribution, and end-use consumption. Their reliable

operation depends upon the continuous balancing of

supply and demand, yet the rapid pace of urbanization, industrialization,

and the integration of renewable energy sources

have complicated the task of forecasting electricity requirements,

creating a pressing need for advanced, data-driven

predictive techniques [1]. The emergence of smart grids and

the diversified energy mix further amplify the complexity of

energy management, underscoring the necessity for accurate,

adaptable forecasting solutions [2].

As electricity demand grows, so do the challenges associated

with energy planning, grid operations, and resource

allocation. Accurate forecasting empowers stakeholders to

anticipate fluctuations in demand, mitigate risks, and deploy

timely interventions. Traditional approaches, which rely on

statistical analysis of historical consumption data [3], are

increasingly insufficient for capturing the full spectrum of

demand variability. In contrast, probabilistic forecasting offers

a richer, more nuanced perspective on future demand,

supporting robust risk management and enabling efficient

resource allocation.

Electricity consumption is affected by a broad array of fac-