Forecasting Heating Consumption in Buildings: A Scalable Full-Stack Distributed Engine

Abstract

Predicting power demand of building heating systems is a challenging task due to the high variability of their energy profiles. Power demand is characterized by different heating cycles including sequences of various transient and steady-state phases. To effectively perform the predictive task by exploiting the huge amount of fine-grained energy-related data collected through Internet of Things (IoT) devices, innovative and scalable solutions should be devised. This paper presents PHi-CiB, a scalable full-stack distributed engine, addressing all tasks from energy-related data collection, to their integration, storage, analysis, and modeling. Heterogeneous data measurements (e.g., power consumption in buildings, meteorological conditions) are collected through multiple hardware (e.g., IoT devices) and software (e.g., web services) entities. Such data are integrated and analyzed to predict the average power demand of each building for different time horizons. First, the transient and steady-state phases characterizing the heating cycle of each building are automatically identified; then the power-level forecasting is performed for each phase. To this aim, PHi-CiB relies on a pipeline of three algorithms: the Exponentially Weighted Moving Average, the Multivariate Adaptive Regression Spline, and the Linear Regression with Stochastic Gradient Descent. PHi-CiB’s current implementation exploits Apache Spark and MongoDB and supports parallel and scalable processing and analytical tasks. Experimental results, performed on energy-related data collected in a real-world system show the effectiveness of PHi-CiB in predicting heating power consumption of buildings with a limited prediction error and an optimal horizontal scalability.

A Cloud-to-Edge Approach to Support Predictive Analytics in Robotics Industry

“…By bringing micro-services to the place where data is captured and stored instead of moving these large quantities of data to one central processing node, unnecessary data transport can be significantly reduced. In [9] a scalable full-stack distributed engine tailored to energy data collection and forecasting in the smart-city context enabling the integration of the heterogeneous data measurements gathered from real-world systems and the forecasting of average power demand. Moreover, related to fog computing, in [10] the authors introduce a new architecture enabling on-demand computation to offload the computation in the cloud architecture, reducing unnecessary network overhead, by properly selecting the most effective edge devices as computation delegates.…”

A Non-Linear Autoregressive Model for Indoor Air-Temperature Predictions in Smart Buildings

“…For example, in [37], authors proposed an overall framework for energy consumption prediction in buildings, comparing three different machine learning algorithms based on deep extreme learning machine, adaptive neuro-fuzzy inference and artificial neural networks. More recently, in [38], authors presented a big-data platform for predicting and characterizing energy consumption of building connected to district heating system, exploiting multi-regression method between power consumption and environmental conditions. However, a general limitation of the works of [37,38] is that they do not provide any prediction of internal temperature conditions of the building.…”

Exploiting Scalable Machine-Learning Distributed Frameworks to Forecast Power Consumption of Buildings

“…Similarly, research efforts have been devoted to characterizing energy consumption at a large scale [34,35] as well as energy efficiency based on real consumption data [6] or estimated data [36,37]. The study presented in [34] exploits a NoSQL technology to support the collection, storing and analysis of large volumes of energy-related data.…”

“…Differently from the previously-mentioned research papers [6,34,35,39,40], the current work presents an engine based on scalable machine learning approaches to forecast fine-grained power consumption. The previously-cited works focus on diverse targets and proposed different analytics approaches.…”

“…Specifically, the target of [34,39] is the characterization of the power consumption and the focus of [6] is the energy efficiency characterization, to define a building ranking, whereas the present paper targets the predicting of sliding-windows power consumption. Furthermore, the methodologies proposed in [6,34] exploit the map-reduce paradigm, while this work exploits the more advanced and high-performing Apache Spark framework; and the approach proposed in [35] does not include the forecasting data mining techniques exploited by the currently proposed methodology.…”