Artificial neural network decision support tool for assessment of the energy performance and the refurbishment actions for the non-residential building stock in Southern Italy

Highlights

• Energy audits of 151 existing public building located in Southern Italy.

• Creation and implementation of an organised energy audit database.

• Artificial Neural Network to develop a decision support tool for the assessment of the energy performance.

• Energy and economic evaluation of the best refurbishment actions.

Abstract

The public buildings sector represents one of the most intensive items of EU energy consumption; the application of retrofit solutions in existing buildings is a crucial way to reduce its impact. To facilitate the knowledge of the energy performance of existing non-residential buildings and the choice of the more adequate actions, Public Administrations (PA) should have the availability of proper tools. Within the Italian project “POI 2007-13”, a database and a decision support tool, for easy use, even to a non-technical user, have been developed. A large set of data, obtained from the energy audits of 151 existing public buildings located in four regions of South Italy have been analysed, elaborated, and organised in a database. This was used to identify the best architectures of two ANNs and to train them. The first ANN provides the actual energy performance of any building; the second ANN assesses key economic indicators. A decision support tool, based on the use of these ANNs is conceived for a fast prediction of the energy performance of buildings and for a first selection of energy retrofit actions that can be applied.

Introduction

In order to achieve the goals of Europe 2020, many energy saving actions have to be adopted by Member States [1]. In this framework, the public buildings sector is responsible for a large part of European Union energy consumption [2], [3]. Its average yearly specific primary energy demand is very high, about 220 kWh/m²y [4]. Thus, effective actions for its reduction conducted by public administrations are necessary in order to reduce greenhouse gas emissions and CO₂-decommissioning of the European economy. Today, existing energy saving regulations are strongly restrictive on new buildings, meanwhile the international debate is focused on the definition and application of Net Zero Energy Building targeting existing buildings [5], [6], [7] as a new worldwide challenge [8].

The escalation of energy costs and impacts of energy consumption on the environment have compelled government agencies and researchers to develop tools and retrofit measures to conserve energy in existing buildings. On the demand-side, a multi-country effort under the International Energy Agency has led to the gathering, evaluation and documentation of the largest collection of energy retrofit measures for commercial, residential and industrial buildings [9]. Since the public building sector, including schools, have a key role in relation to energy saving for the whole community, they are considered as one of the starting points for energy efficiency. In addition to energy consumption reduction obligatory in new constructions, it is broadly accepted that a drastic decrease in energy consumption is needed in existing educational buildings. A large scientific literature investigates strategies for energy efficient building retrofits. Series of procedures have been used in different studies, according to the local climate and the construction style [10]. Concerning Italy, the Istitituto Nazionale di Statistica (ISTAT) has estimated that the current school building stock amounts to 50,157 national schools with 49% nursery schools, 35% primary schools, and 16% first-level secondary schools [11]. Generally, Italian public building stock is characterised by inadequate envelopes and low performance HVAC systems. A detailed analysis among geographical areas is necessary to understand where to focus maintenance and refurbishment actions and their relative funding. In other words, a detailed knowledge about the state-of-the-art is a useful approach to help local PA in defining and adopting not only energy saving actions for new constructions but also effective and retrofit measures for the current estate [12], [13], [14].

In literature, various modelling techniques for estimating the energy consumption of buildings have been developed. Some predictive tools use recorded and/or generated energy consumption data along with statistical methods such as regression methods, artificial neural networks (ANN), or decision trees, to forecast the energy consumption of building [15], [16]. Others, including EnergyPlus, DOE and TRNSYS, use more fundamental approaches such as the mass and heat balance technique to simulate the building thermal loads. Currently, in Italy many local and international research teams are involved in collecting data of energy consumption of the public building stock, aiming to identify the best energy retrofit actions and to reduce national CO2 emissions. In this paper, the authors describes a methodology to determine, for local PA, a decision support tool on the energy efficiency evaluation of an existing building and the selection of the best energy efficiency solutions. After an accurate energy audit of the existing school-buildings stock it was possible to develop an accurate energy database that represent the base of the training of a specific ANN and the development of a decision support tool.