Big data: the key to energy efficiency in smart buildings

Abstract

Due to the high impact that energy consumption by buildings has at global scale, energy-efficient buildings to reduce CO 2 emissions and energy consumption are needed. In this work we present a novel approach to energy saving in buildings through the identification of the relevant parameters and the application of Soft Computing techniques to generate predictive models of energy consumption in buildings. Using such models it is possible to define strategies for optimizing the day-today energy consumption of buildings. To verify the feasibility of this proposal, we apply our approach to a reference building for which we have contextual data from a complete year of monitoring. First, we characterize the building in terms of its contextual features

A comprehensive review of big data analytics throughout product lifecycle to support sustainable smart manufacturing: A framework, challenges and future research directions

“…By analyzing the data on a number of process parameters, those which have significant impacts upon energy consumption can be identified to establish a predictive model for the reduction of energy consumption. That model can be used to define strategies for optimizing the day-to-day energy consumption of manufacturing enterprises (Moreno et al, 2016). Because energy waste problems (e.g.…”

Drivers and Challenges Associated With the Implementation of Big Data Within U.K. Facilities Management Sector: An Exploratory Factor Analysis Approach

“…However, the conventional BMS's isolated communication protocols and static rules are unable to respond to real-time building conditions [39], as the data processing technique is primarily based on SQL database or even spreadsheets statistics which is pretty primitive, inefficient, resource-demanding and costly [40] [41] and not intended for analytics [42]. The building services could be improved by developing more accurate context using recent IoT and BD technologies [43] [44]. Especially, IoT-enabled smart networks capable of integrating dynamic control strategies and new efficient and effective algorithms to deal with large influx of data, hold the promise of improved system reliability, greater energy efficiency, and lower costs for consumers [39] [40] [25].…”

“…The situation gets exacerbated by the fact that these data source systems created by different vendors do not speak the same language. Therefore, the FM industry has long been troubled with interoperability issues between its diverse systems [58], each with its distinct communication protocol creating large quantities of data posing integration challenges [43]. Another major obstacle for the widespread use of data analytics in buildings is that the data tags in existing BMSs are nonstandard and unintuitive descriptors for the sensors and actuators; they are often arbitrarily determined by each controls technician or company and thus, their format can vary drastically from one building to another [42].…”

Heating and Hot Water Industrial Prediction System for Residential District

“…The aim is to detect the humans presence to increase the prediction.The models used the piloting and the predictions often remain the property of the projects partners [2]. We can cite the intrusive model [3] [4]. The neural networks are widely used to this purpose and manage these.…”