An ANN-GA Semantic Rule-Based System to Reduce the Gap Between Predicted and Actual Energy Consumption in Buildings

Abstract

This paper addresses the endemic problem of the gap between predicted and actual energy performance in public buildings. A system engineering approach is used to characterize energy performance factoring in building intrinsic properties, occupancy patterns, environmental conditions, as well as available control variables and their respective ranges. Due to the lack of historical data, a theoretical simulation model is considered. A semantic mapping process is proposed using principle component analysis (PCA) and multi regression analysis (MRA) to determine the governing (i.e., most sensitive) variables to reduce the energy gap with a (near) real-time capability. Further, an artificial neural network (ANN) is developed to learn the patterns of this semantic mapping, and is used as the cost function of a genetic algorithm (GA)-based optimization tool to generate optimized energy saving rules factoring in multiple objectives and constraints. Finally, a novel rule evaluation process is developed to evaluate the generated energy saving rules, their boundaries, and underpinning variables. The proposed solution has been tested on both a simulation platform and a pilot building-a care home in the Netherlands. Validation results suggest an average 25% energy reduction while meeting occupants' comfort conditions. Note to Practioners-This study presents a novel semantic rule generation process using GA and ANN with the objective to reduce the gap between predicted and actual energy consumption in public buildings. Due to the absence of historical energy consumption data, a theoretical simulation approach is used that takes into account a wide range of factors, including building fabric, occupancy patterns, and environmental conditions. Energy sensitive variables are then identified using PCA and MRA. These sensitive variables as well as available control variables (set points) are used to train an ANN to learn energy consumption patterns and behavior within the considered buildings. This trained network is then used as a cost function engine (predictor) for a GA-based optimization process to generate the optimized energy saving rules. Finally, a novel rule evaluation process is devised and implemented to assess energy saving rules quality and boundaries. All generated rules have been tested on both the proposed simulation environment and real buildings. Validation results suggest an average 25% energy reduction.

A Smart Forecasting Approach to District Energy Management

“…Moreover, this configuration cannot be generalised in some parameter. However, Yuce et al [23] stated that trainlm based training function performs the best in electricity management problems; and that other configurations do not seem to have similar performance.…”

Optimizing Energy Efficiency in Operating Built Environment Assets through Building Information Modeling: A Case Study

“…Although according to some thermal regulations the energy consumption of a building is expected to not exceed a given limit, the real energy performance is usually lower. One means to reduce the gap between prediction and reality is to improve the entire process, from the early design phase to the operation phase [8,9]. Practitioners who use BIM during the design phase, the construction phase or the maintenance phase will contribute to improving the quality of the building's performance.…”

“…BIM has a number of socio-technological advantages not only at the technological level, but also the process level, and can complement the way that architectural design artefacts are created, but also can profoundly change the collaborative process associated with the act of building. As the construction industry is facing increased pressure from regulations calling for significant gains in energy efficiency, increased economic pressure and competition, and a dramatic evolution of working culture and practices, BIM can represent a gamechanging factor that would support the transition to more energy and cost-efficient practices [6][7][8][9].…”

District heating and cooling optimization and enhancement – Towards integration of renewables, storage and smart grid

“…Globally, buildings account for 40% of total energy used and contribute towards 30% of the total CO 2 emissions [1] and [2]. Buildings are the largest consumer of energy in the European Union, accounting for up to 40% of the total energy consumption and approximately 36% of the greenhouse gas emissions [3].…”