Evangelos Spiliotis

Decision Support for Intelligent Energy Management in Buildings Using the Thermal Comfort Model

The main objective of this paper is to present a transparent Decision Support System (DSS) for the energy managers of buildings, which can assist them in setting indoor temperature set point, based on the feedback received by the occupants. Within the proposed DSS, the Thermal Comfort Validator (TCV) tool is introduced, a fully responsive and cross-platform web-app which exploits the Predicted Mean Vote comfort theory by considering real-time feedback of the occupants. The TCV facilitates the detection of the range of accepted temperature inside a building, by correlating “real” with “predicted” thermal comfort, to overcome the limits of the standardized approaches. The proposed system can reveal an important potential for achieving energy savings by means of dynamic event driven data collection and processing, while ensuring high levels of comfort.

Statistical and Machine Learning forecasting methods: Concerns and ways forward

Machine Learning (ML) methods have been proposed in the academic literature as alternatives to statistical ones for time series forecasting. Yet, scant evidence is available about their relative performance in terms of accuracy and computational requirements. The purpose of this paper is to evaluate such performance across multiple forecasting horizons using a large subset of 1045 monthly time series used in the M3 Competition. After comparing the post-sample accuracy of popular ML methods with that of eight traditional statistical ones, we found that the former are dominated across both accuracy measures used and for all forecasting horizons examined. Moreover, we observed that their computational requirements are considerably greater than those of statistical methods. The paper discusses the results, explains why the accuracy of ML models is below that of statistical ones and proposes some possible ways forward. The empirical results found in our research stress the need for objective and unbiased ways to test the performance of forecasting methods that can be achieved through sizable and open competitions allowing meaningful comparisons and definite conclusions.

OPTIMUS decision support tools: Transforming multidisciplinary data to energy management action plans

Making Smart Energy Cities (SEC) a reality requires an intelligent and integrated assessment and consideration of various data sets, as well as relevant intelligent systems in a transparent and accessible manner. The scope of this paper is to present an innovative package of decision support tools (entitled “OPTIMUS”) for energy managers and energy consultancies, in order to make cities more energy efficient and sustainable. OPTIMUS package includes the Smart City Energy Assessment Framework (SCEAF) Tool, the Tracker Tool and the Decision Support System (DSS). The purpose is to optimize the energy use in main citys buildings (municipal, office, educational and entertainment buildings, buildings for sports facilities, etc.), taking into consideration their interaction with energy systems, such as renewable energy production, smart district heating and cooling grids through CHP (Combined Heat and Power) and other energy sources.

Integrating a decision support system with smart grid infrastructures and ICT solutions towards energy cost reduction: An action plan to optimally schedule the operation of heating and electricity systems

Smart grid technology has recently attracted a lot of attention since it enables the effective use of widespread energy sources and supports that way actions towards energy optimization and cost reduction. The benefits of adopting and promoting such a technology becomes even more promising given the advances in the field of renewable energy and Information and Communications Technology (ICT), which allow managing the energy sources available according to the respective demand in a smart and environmental friendly way. The main scope of this paper is to present an action plan in order to schedule the operation of heating and electricity systems towards energy cost optimization by taking advantage of smart grid and ICT infrastructures. The action plan, which has been developed to operate within a Decision Support System, is currently tested in the University Campus of Savona (Italy) in order to indicate the usefulness of the solution in a real life application.

A Framework to Assess the Behavior and Performance of a City Towards Energy Optimization

A Smart City Energy Assessment Framework (SCEAF) is introduced to evaluate the performance and behavior of a city towards energy optimization, taking into consideration multiple characteristics. The SCEAF aims to provide to city authorities a systematic and independent evaluation means of the actions taken towards energy efficiency in parallel with the transition to become a “Smart City”. The framework consists of indicators that are structured on three major assessment axes (1) Political Field of Action, (2) Energy & Environmental Profile, (3) Related Infrastructures-Energy & ICT. The framework can be designed generally for the whole activities spectrum of a city, but it can also be customized per sector, providing more focused information.

Forecasting electrical consumption of commercial buildings using energy performance indicators

This paper presents a methodology for predicting electrical consumption in energy-intensive commercial buildings through a range of energy performance indicators. Specifically, the most representative indicators per energy end use of the building (lighting, kitchen, refrigerators, etc.) are defined and appropriate time series forecasting methods are applied at its time series to predict future energy performance of the whole building. In order to determine the accuracy of the methodology, a fast-food restaurant in Cyprus was selected and the electrical consumption was measured over a winter month. Then, the methodology was applied for multiple forecasting horizons and electrical consumption predictions were compared with the actual consumption. The results indicated a relatively satisfactory performance of the methodology for all the horizons tested, revealing at the same time that the length of the forecasting period has a significant impact on the accuracy of the predicted energy consumption of buildings.

A framework for integrating user experience in action plan evaluation through social media: Transforming user generated content into knowledge to optimise energy use in buildings

This paper introduces a methodological approach for evaluating the thermal comfort of building users, captured through social media, in order to evaluate and accordingly adjust energy management action plans. A framework for performing sentiment analysis of messages is developed and a pilot case is presented for optimally scheduling the temperature set-point adjustment of a municipal building, based on user thermal comfort criteria retrieved from social data.