Prediction of Space Heating Consumption in District Heated Apartments

2013 ◽  
Author(s):  
D. Popescu ◽  
F. Ungureanu
Keyword(s):  
Neural Networks ◽  
Energy Demand ◽  
Space Heating ◽  
Prediction Methods ◽  
Analysis Method ◽  
End User ◽  
Simulation Tools ◽  
Heat Demand ◽  
Consumption Rates ◽  
Cluster Analysis Method

Enhancing energy efficiency from the producer to the end-users is a prioritized objective of European energy policies. The most difficult element to understand and to control is the last link, the consumer. Most simulation tools for the estimation of heat demand in buildings are based on the input parameters according to environmental conditions and the features of the materials and equipments. Studies have revealed that even if sophisticated programs are used, a gap between calculated and post occupancy space heating consumption rates occurs. Based on billing history, the present paper proposes a cluster analysis method to identify the grouping trends of habitants’ consumption. For modeling the heat consumption at end-user level and predicting the trends of energy demand, artificial neural networks (ANNs) technique was used. Unlike most prediction methods that have the entire building in view, the proposed technique can be applied to individual apartments situated in condominiums.

scholarly journals A Data-Driven Approach to Forecasting Heating and Cooling Energy Demand in an Office Building as an Alternative to Multi-Zone Dynamic Simulation

2021 ◽  
Vol 11 (4) ◽  
pp. 1356
Author(s):  
Xavier Godinho ◽  
Hermano Bernardo ◽  
João C. de Sousa ◽  
Filipe T. Oliveira
Keyword(s):  
Neural Networks ◽  
Dynamic Simulation ◽  
Energy Demand ◽  
Office Building ◽  
Data Driven ◽  
Support Vector ◽  
Simulation Tools ◽  
Heating And Cooling ◽  
Vector Machines ◽  
Cooling Energy Demand

Nowadays, as more data is now available from an increasing number of installed sensors, load forecasting applied to buildings is being increasingly explored. The amount and quality of resulting information can provide inputs for smarter decisions when managing and operating office buildings. In this article, the authors use two data-driven methods (artificial neural networks and support vector machines) to predict the heating and cooling energy demand in an office building located in Lisbon, Portugal. In the present case-study, these methods prove to be an accurate and appealing alternative to the use of accurate but time-consuming multi-zone dynamic simulation tools, which strongly depend on several parameters to be inserted and user expertise to calibrate the model. Artificial neural networks and support vector machines were developed and parametrized using historical data and different sets of exogenous variables to encounter the best performance combinations for both the heating and cooling periods of a year. In the case of support vector regression, a variation introduced simulated annealing to guide the search for different combinations of hyperparameters. After a feature selection stage for each individual method, the results for the different methods were compared, based on error metrics and distributions. The outputs of the study include the most suitable methodology for each season, and also the features (historical load records, but also exogenous features such as outdoor temperature, relative humidity or occupancy profile) that led to the most accurate models. Results clearly show there is a potential for faster, yet accurate machine-learning based forecasting methods to replace well-established, very accurate but time-consuming multi-zone dynamic simulation tools to forecast building energy consumption.

scholarly journals Detection of drought events in Greece using daily precipitation

2010 ◽  
Vol 41 (2) ◽  
pp. 126-133 ◽  
Author(s):  
N. Kalamaras ◽  
H. Michalopoulou ◽  
H. R. Byun
Keyword(s):  
Cluster Analysis ◽  
Hierarchical Cluster Analysis ◽  
Daily Precipitation ◽  
Hierarchical Cluster ◽  
Seasonal Distribution ◽  
Drought Severity ◽  
Severe Drought ◽  
Analysis Method ◽  
Cluster Analysis Method ◽  
Insight Into

In this study a method proposed by Byun & Wilhite, which estimates drought severity and duration using daily precipitation values, is applied to data from stations at different locations in Greece. Subsequently, a series of indices is calculated to facilitate the detection of drought events at these sites. The results provide insight into the trend of drought severity in the region. In addition, the seasonal distribution of days with moderate and severe drought is examined. Finally, the Hierarchical Cluster Analysis method is used to identify sites with similar drought features.

An environmental impact analysis method of machine-tool cutting units based on LCA

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Junli Shi ◽  
Junyu Hu ◽  
Mingyang Ma ◽  
Huaizhi Wang
Keyword(s):  
Environmental Impact ◽  
Machine Tool ◽  
Energy Demand ◽  
Impact Analysis ◽  
Primary Energy ◽  
Analysis Method ◽  
Environmental Impact Analysis ◽  
Content Type ◽  
Primary Energy Demand ◽  
Tool Cutting

Purpose The purpose of this paper is to present a method for the environmental impact analysis of machine-tool cutting, which enables the detailed analysis of inventory data on resource consumption and waste emissions, as well as the quantitative evaluation of environmental impact. Design/methodology/approach The proposed environmental impact analysis method is based on the life cycle assessment (LCA) methodology. In this method, the system boundary of the cutting unit is first defined, and inventory data on energy and material consumptions are analyzed. Subsequently, through classification, five important environmental impact categories are proposed, namely, primary energy demand, global warming potential, acidification potential, eutrophication potential and photochemical ozone creation potential. Finally, the environmental impact results are obtained through characterization and normalization. Findings This method is applied on a case study involving a machine-tool turning unit. Results show that primary energy demand and global warming potential exert the serious environmental impact in the turning unit. Suggestions for improving the environmental performance of the machine-tool turning are proposed. Originality/value The environmental impact analysis method is applicable to different machine tools and cutting-unit processes. Moreover, it can guide and support the development of green manufacturing by machinery manufacturers.

scholarly journals TEXT SENTIMENT ANALYSIS BASED ON CNNS AND SVM

2019 ◽  
Vol 7 (6) ◽  
pp. 77-83 ◽  
Author(s):  
Dr. C. Arunabala ◽  
P. Jwalitha ◽  
Soniya Nuthalapati
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Sentiment Analysis ◽  
Expressive Power ◽  
Sentiment Classification ◽  
Experimental Results ◽  
Analysis Method ◽  
Mapping Functions ◽  
Generalization Ability ◽  
Text Sentiment Analysis

The traditional text sentiment analysis method is mainly based on machine learning. However, its dependence on emotion dictionary construction and artificial design and extraction features makes the generalization ability limited. In contrast, depth models have more powerful expressive power, and can learn complex mapping functions from data to affective semantics better. In this paper, a Convolution Neural Networks (CNNs) model combined with SVM text sentiment analysis is proposed. The experimental results show that the proposed method improves the accuracy of text sentiment classification effectively compared with traditional CNN, and confirms the effectiveness of sentiment analysis based on CNNs and SVM

Sign in / Sign up

Export Citation Format

Share Document