On-line learning of indoor temperature forecasting models towards energy efficiency

Zamora-Martínez, Francisco; Romeu, Pablo; Botella-Rocamora, Paloma; Pardo, Juan

doi:10.1016/j.enbuild.2014.04.034

Cited by 117 publications

(52 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Temperature forecasting is a portion of weather forecasting; other portions include the probability of precipitation forecasting, barometric pressure forecasting, wind power forecasting, etc. One point needs to be noted; temperature forecasting models need to be adapted to different applicable environments, for example, some models are used to forecasting indoor temperature [3,4], some models are used for large-scale temperature forecasting [5,6], and some models are used in specific environment [7,8]. With the rapid development of machine learning, more and more machine learning methods have been applied to weather forecasting, such as support vector machine (SVM) [9,10], genetic algorithms [11], and neural networks [12][13][14].…”

Section: Related Workmentioning

confidence: 99%

Temperature Forecasting via Convolutional Recurrent Neural Networks Based on Time-Series Data

Zhang

Dong

2020

Complexity

View full text Add to dashboard Cite

Today, artificial intelligence and deep neural networks have been successfully used in many applications that have fundamentally changed people’s lives in many areas. However, very limited research has been done in the meteorology area, where meteorological forecasts still rely on simulations via extensive computing resources. In this paper, we propose an approach to using the neural network to forecast the future temperature according to the past temperature values. Specifically, we design a convolutional recurrent neural network (CRNN) model that is composed of convolution neural network (CNN) portion and recurrent neural network (RNN) portion. The model can learn the time correlation and space correlation of temperature changes from historical data through neural networks. To evaluate the proposed CRNN model, we use the daily temperature data of mainland China from 1952 to 2018 as training data. The results show that our model can predict future temperature with an error around 0.907°C.

show abstract

Section: Related Workmentioning

confidence: 99%

Temperature Forecasting via Convolutional Recurrent Neural Networks Based on Time-Series Data

Zhang

Dong

2020

Complexity

View full text Add to dashboard Cite

show abstract

“…Evaporative cooling [41] Active thermal storage [42] Heat recovery [37,43,44] Radiative heating/cooling [45] Variable air volume (VAV)/variable coolant volume [46,47] DWH Solar water heating (SWH) -Flat plate collectors -Vacuum tube collectors [9,14,32,35,48] Solar heat pump system [37,49] Combined cooling/heating and power (CCHP) [37,50] LIGHTING Light-emitting diodes (LED) [51] Use of daylight [52] HOUSEHOLD EQUIPMENT Efficient appliances [9,32,53] Domotics/Monitoring/Automation [17,30,54] WATER CYCLE Greywater recycling [11,30] Use of rainwater [11] After analyzing the regulations of the countries being studied (Colombia and Spain), it is clear that the implementation of a certain technology in the architectural process must pass through a legal and regulatory filter. It is for this reason that an updated review of the energy efficiency legislation and renewable energies regulations in both Colombia [55] and Spain [56] was carried out, these countries being the location of SDLAC15 and the field of work of the authors of the article, respectively, which could be assimilated to Latin America vs. Europe.…”

Section: Solar Energymentioning

confidence: 99%

Solar Decathlon Latin America and Caribbean: Comfort and the Balance between Passive and Active Design

2019

View full text Add to dashboard Cite

This article contains an overall analysis of the results obtained by the four highest scoring teams in the Solar Decathlon Latin America and Caribbean 2015 collegiate sustainable habitat competition. Considering that the prototypes developed were based on energy self-sufficiency when operational, it was considered necessary to propose this analysis based on the degree of suitability of each of these models based on their different performances from the perspective of comfort conditions. It was observed that the design of the prototypes did not manage to properly adjust the relationship between passive and active conditioning elements based on the location’s conditions. Accordingly, this article concludes that a balance of the two aforementioned conditioning modes recorded better results based on the measurements taken.

show abstract

“…Consider a monitoring system in a home which records temperature and relative humidity and sends them over a noisy communication channel to a central hub [36]. The data from the hub is used to control an HVAC system.…”

Section: Correlation Between Random Variablesmentioning

confidence: 99%

“…The Bayesian network for this program is shown in Figure 12. t and h are used in the hub for further computations such as controlling an HVAC system [36]. This adds another node, M to the Bayesian network as shown in Figure 12.…”

Section: Incorrect Inference Call Leading To Loss Of Dependence Informentioning

confidence: 99%

Debugging probabilistic programs

Nandi

Grossman

Sampson

et al. 2017

Proceedings of the 1st ACM SIGPLAN International Workshop on Machine Learning and Programming Languages

View full text Add to dashboard Cite

Many applications compute with estimated and uncertain data. While advances in probabilistic programming help developers build such applications, debugging them remains extremely challenging. New types of errors in probabilistic programs include 1) ignoring dependencies and correlation between random variables and in training data, 2) poorly chosen inference hyper-parameters, and 3) incorrect statistical models. A partial solution to prevent these errors in some languages forbids developers from explicitly invoking inference. While this prevents some dependence errors, it limits composition and control over inference, and does not guarantee absence of other types of errors. This paper presents the FLEXI programming model which supports constructs for invoking inference in the language and reusing the results in other statistical computations. We define a novel formalism for inference with a Decorated Bayesian Network and present a tool, DePP, that analyzes this representation to identify the above errors. We evaluate DePP on a range of prototypical examples to show how it helps developers to detect errors. CCS Concepts • Software and its engineering → Syntax; Error handling and recovery; • Mathematics of computing → Maximum likelihood estimation

show abstract

On-line learning of indoor temperature forecasting models towards energy efficiency

Cited by 117 publications

References 20 publications

Temperature Forecasting via Convolutional Recurrent Neural Networks Based on Time-Series Data

Temperature Forecasting via Convolutional Recurrent Neural Networks Based on Time-Series Data

Solar Decathlon Latin America and Caribbean: Comfort and the Balance between Passive and Active Design

Debugging probabilistic programs

Contact Info

Product

Resources

About