Machine learning models have proven to be reliable methods in the forecasting of energy use in commercial and office buildings. However, little research has been done on energy forecasting in dwellings, mainly due to the difficulty of obtaining household level data while keeping the privacy of inhabitants in mind. Gaining insight into the energy consumption in the near future can be helpful in balancing the grid and insights in how to reduce the energy consumption can be received. In collaboration with OPSCHALER, a measurement campaign on the influence of housing characteristics on energy costs and comfort, several machine learning models were compared on forecasting performance and the computational time needed. Nine months of data containing the mean gas consumption of 52 dwellings on a one hour resolution was used for this research. The first 6 months were used for training, whereas the last 3 months were used to evaluate the models. The results showed that the Deep Neural Network (DNN) performed best with a 50.1 % Mean Absolute Percentage Error (MAPE) on a one hour resolution. When comparing daily and weekly resolutions, the Multivariate Linear Regression (MVLR) outperformed other models, with a 20.1 % and 17.0 % MAPE, respectively. The models were programmed in Python.
Abstract-In response to increasing environmental problems and consciousness in relation to urbanization, more and more cities are trying to become eco-cities. We can question, however, whether these cities can be considered as sustainable cities. The eco-city concept usually includes criteria regarding energy and water consumption, transport, waste management, amount of green spaces, etc. However, food consumed in the cities is usually marginally taken into account. Moreover, implementation strategies necessary to successfully make a transition to sustainability are rarely mentioned. The goals of this paper are twofold. First, we will ask attention for urban agriculture and include food in the eco-city equation. Second, we will argue that eco-cities should not be considered as project but operated as a process.
Purpose -The aim of the present study was to characterize the main project delivery methods that are used for the renovation of social housing, and to analyse the advantages and disadvantages of their application for energy renovations in order to assist social housing organisations in making an informed decision on the choice of a project delivery method that suits their organizational context. Design/methodology/approach -The study is based on a literature review, five case studies of renovation processes by five social housing organizations in four EU countries, a questionnaire completed by 36 social housing organizations from eight EU countries, and a series of 14 interviews with energy renovation experts from ten EU countries. Findings -Four main project delivery methods were identified: iterative minor renovations, design-bid-build, design-build and design-build-maintain. Design-build-maintain has the maximum potential to deliver energy savings because it facilitates collaboration between the various actors and promotes their commitment to achieving project goals.Research limitations/implications -The presented data is not meant to be representative for a country or the sector as a whole, but aims to indicate the main characteristics of the current energy renovations carried out by European social housing organizations. Practical implications -Social housing organizations are provided with useful information about the advantages and disadvantages of different project delivery methods for energy renovation projects, assisting them to choose the option that suits their organizational context. Originality/value -This study fills a knowledge gap about the project delivery methods currently used in social housing energy renovations and their potential for energy renovations.
The renovation of existing building stock is seen as one the most practical ways to achieve the high energy savings targets for the built environment defined by European authorities. In France, the Grenelle environmental legislation addresses the need to renovate the building stock and specifically stresses the key role of social housing organisations. In recent years, French procurement rules have been modified in order to allow social housing organisations to make use of integrated contracts such as Design-Build-Maintain. These contracts have a greater potential to deliver energy savings in renovation projects than do traditional project delivery methods, like Design-bid-Build. This is because they facilitate collaboration between the various actors and boost their commitment to the achievement of project goals. In order to evaluate the estimated potential of such contracts to achieve energy savings, two renovation projects (carried out by two French social housing organisations) were analysed from their inception until the end of construction work. The analysis is based on written tender documents, technical evaluation reports, observations of the negotiation phase (in one of the cases) and interviews with the main actors involved. Findings show that Design-Build-Maintain contracts do indeed offer substantial energy savings. Both projects achieved higher energy targets than those initially required. Furthermore, the energy results are guaranteed by the contractor, through a system of bonuses and penalties. Other results demonstrate that, compared to previous Design-bid-Build renovation projects, these projects were completed in less time (from project inception to completion of the work) and at virtually the same cost. There has also been a substantial improvement in cooperation between the actors involved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.