No abstract

Natural ventilation is an effective passive control strategy to improve building energy efficiency, indoor thermal comfort and air quality. Near real-time model-based control of window openings for natural ventilation requires forecasts completed within a short time, typically seconds. However, widely-used physics-based simulation is time-consuming and entails high computation cost. This study is aimed at developing a Recurrent Neural Network (RNN) model for forecasting indoor temperature using seasonal window opening schedules and ambient conditions. The data-driven forecasting approach utilizes simulated indoor dry-bulb temperature (DBT) and relative humidity (RH) based on ambient parameters (DBT, RH, and wind speed and direction), time (time of day, day of year), building thermal parameters and window characteristics (location, opening size and type) to train the RNN model. The results show that the proposed RNN algorithm is effective in predicting indoor environmental conditions with considerable accuracy (R 2 = 0.956) and outperforms statistical methods by at least 20% in the same measure. Window opening area is highly correlated to the hourly change of indoor temperature. Prediction errors for indoor operative temperature are less than 1°C for 70% of the time and less than 2°C for 93% of the time. The speed and accuracy of a trained network illustrate the potential of the method for near-real time control of buildings and systems while maintaining occupant thermal comfort.

Passive cooling via natural ventilation through window openings is a low-carbon strategy to minimize cooling demand and to adapt to the rising ambient temperatures due to climate change. However, relying on the manual control of windows by occupants is not always optimal for maintaining indoor thermal comfort. In this study, a model-based approach using dynamic thermal simulation program EnergyPlus is used for the optimal control of window openings to maintain indoor thermal comfort. Based on the day-ahead weather forecast, the window opening schedule for the next 24 h is optimized through iteration. Results indicate that the proposed optimal control method significantly improves indoor thermal comfort than using some most commonly used manual control and automated control based on hourly set-point and outdoor temperatures.

This paper presents a smart energy management system for unlocking demand response in the UK residential sector. The approach comprises the estimation of one-hour energy demand and PV generation (supply) for scheduling the 24-h ahead demand profiles by shifting potential flexible loads. Real-time electrical demand is met by combining power supplies from PV, grid and batteries while minimizing consumer's cost of energy. The results show that the peak-to-average ratio is reduced by 22.9% with the cost saving of 34.6% for the selected day.

In this paper, we look at the key forecasting algorithms and optimization strategies for the building energy management and demand response management. By conducting a combined and critical review of forecast learning algorithms and optimization models/algorithms, current research gaps and future research directions and potential technical routes are identified. To be more specific, ensemble/hybrid machine learning algorithms and deep machine learning algorithms are promising in solving challenging energy forecasting problems while large-scale and distributed optimization algorithms are the future research directions for energy optimization in the context of smart buildings and smart grids.