Electricity Demand and Energy Consumption Management System

TL;DR

This paper presents a system combining neural network-based demand forecasting and advanced simulation techniques to optimize electricity management in a smelter plant, reducing peak demand and improving energy planning.

Contribution

It introduces an integrated demand forecasting and simulation system tailored for industrial energy management, utilizing neural networks and advanced estimation methods.

Findings

Demand forecast error below 1%

Enhanced energy demand management and planning

Identification of energy consumption improvement opportunities

Abstract

This project describes the electricity demand and energy consumption management system and its application to Southern Peru smelter. It is composed of an hourly demand-forecasting module and of a simulation component for a plant electrical system. The first module was done using dynamic neural networks with backpropagation training algorithm; it is used to predict the electric power demanded every hour, with an error percentage below of 1%. This information allows efficient management of energy peak demands before this happen, distributing the raise of electric load to other hours or improving those equipments that increase the demand. The simulation module is based in advanced estimation techniques, such as: parametric estimation, neural network modeling, statistic regression and previously developed models, which simulates the electric behavior of the smelter plant. These modules facilitate electricity demand and consumption proper planning, because they allow knowing the behavior of the hourly demand and the consumption patterns of the plant, including the bill components, but also energy deficiencies and opportunities for improvement, based on analysis of information about equipments, processes and production plans, as well as maintenance programs. Finally the results of its application in Southern Peru smelter are presented.