Multi-objective optimization of HVAC system with an evolutionary computation algorithm

A data-mining approach for the optimization of a HVAC (heating, ventilation, and air conditioning) system is presented. A predictive model of the HVAC system is derived by data-mining algorithms, using a dataset collected from an experiment conducted at a research facility. To minimize the energy while maintaining the corresponding IAQ (indoor air quality) within a user-defined range, a multi-objective optimization model is developed. The solutions of this model are set points of the control system derived with an evolutionary computation algorithm. The controllable input variables — supply air temperature and supply air duct static pressure set points — are generated to reduce the energy use. The results produced by the evolutionary computation algorithm show that the control strategy saves energy by optimizing operations of an HVAC system.     

Energy saving in existing buildings by an intelligent use of interoperable ICTs

In this paper, we report a methodology, developed in the context of Smart Energy Efficient Middleware for Public Spaces European Project, aimed at exploiting ICT monitoring and control services to reduce energy usage and CO₂ footprint in existing buildings. The approach does not require significant construction work as it is based on commercial-off-the-shelf devices and, where present, it exploits and integrates existing building management systems with new sensors and actuator networks. To make this possible, the proposed approach leverages upon the following main contributions: (a) to develop an integrated building automation and control system, (b) to implement a middleware for the energy-efficient buildings domain, (c) to provide a multi-dimensional building information modelling-based visualisation, and (d) to raise people’s awareness about energy efficiency. The research approach adopted in the project started with the selection, as case studies, of representative test and reference rooms in modern and historical buildings chosen for having different requirements and constraints in term of sensing and control technologies. Then, according to the features of the selected rooms, the strategies to reduce the energy consumptions were defined, taking into account the potential savings related to lighting, heating, ventilation, and air conditioning (HVAC) systems and other device loads (PC, printers, etc.). The strategies include both the control of building services and devices and the monitoring of environmental conditions and energy consumption. In the paper, the energy savings estimated through simulation, for both HVAC and lighting, are presented to highlight the potential of the designed system. After the implementation of the system in the demonstrator, results will be compared with the monitored data.     

Application of neural networks to predict the steady state performance of a Run-Around Membrane Energy Exchanger

Modeling the performance characteristics of thermal systems has been a research interest for many decades with moisture transfer systems experiencing a resurgence over the last decade, especially in heating, ventilating, and air conditioning (HVAC) applications. In this study, a neural network (NN) model is developed to predict the heat and moisture transfer performances (i.e., the sensible and latent effectivenesses) of a novel HVAC energy exchanger called the Run-Around Membrane Energy Exchanger (RAMEE) which is able to transfer both heat and moisture between exhaust and supply air streams. The training data set for the NN model covers a wide range of design and operating parameters and is produced using an experimentally validated finite difference (FD) model. Two separate NNs (one for sensible and one for latent energy transfer) each with five inputs and one output, are selected to represent the RAMEE. The results from NN models are numerically and experimentally validated. The root mean squared error (RMSE) between the FD and NN models are 0.05 °C and 2 × 10^?5 kg_v/kg_a, indicating satisfactory agreement for energy exchange calculations. The paper reports the weights and biases to make the results of this study reproducible. These NN models are very fast and easy to use therefore, they might be used for design and for estimating the annual energy savings in different buildings which use the RAMEE in their HVAC system. Additionally, the NN models can be used with optimization algorithms to maximize energy savings and minimize life-cycle costs for a given system.     

Application of neural networks to predict the transient performance of a Run-Around Membrane Energy Exchanger for yearly non-stop operation

Application of soft computing methods (i.e. neural networks and genetic algorithms) for modeling and controlling the dynamic and transient behavior of systems has been increasing during the last decade. In this study, a neural network (NN) model is developed to predict the transient heat and moisture transfer performances (i.e., the sensible and latent effectivenesses) of a novel HVAC energy exchanger, called the Run-Around Membrane Energy Exchanger (RAMEE), which is able to transfer both heat and moisture between exhaust and supply air streams. The training data set for the NN model covers a wide range of outdoor conditions and system parameters and is produced using a Transient Numerical Model (TNM) that has been experimentally validated for some transient applications. Two separate NNs (one for sensible and one for latent energy transfer) each with 12 inputs and one output, are selected to represent the RAMEE. The ability of NN models to predict the performance of a given RAMEE design in different climates is numerically validated. The mean absolute difference (MAD) between the results of TNM and NN models for different locations are 0.5 °C for the sensible model and 0.2 g_v/kg_a for the latent model, which indicates satisfactory agreement for energy exchange calculations. These NN models are very fast and easy to use therefore, they might be used for design purposes or estimating the annual energy savings in different buildings with continuous operation and a RAMEE in their HVAC system.     

Intelligent soft-computing based modelling of naturally ventilated buildings

The paper presents recent results on the application of the soft computing methodology for modelling of the internal climate in office buildings. More specifically, a part of a recently completed naturally ventilated building is considered which comprises three neighbouring offices and one corridor within the Portland Building at the University of Portsmouth. The approach adopted uses fuzzy logic for modelling, neural networks for adaptation and genetic algorithms for optimisation of the fuzzy model. The fuzzy models are of the Takagi-Sugeno type and are built by subtractive clustering. As a result of the latter, the initial values of the antecedent non-linear membership functions and the consequent linear algebraic equations parameters are determined. A method of extensive search of fuzzy model structures is presented which fully explores the dynamics of the plant. The model parameters are further adjusted by a back-propagation training neural network and a real-valued genetic algorithm in order to obtain a better fit to the measured data. Results with real data are presented for two types of models, namely Regression Delay and Proportional Difference. These models are applied for predicting internal air temperatures.     

A data-driven approach for steam load prediction in buildings

Predicting building energy load is important in energy management. This load is often the result of steam heating and cooling of buildings. In this paper, a data-driven approach for the development of a daily steam load model is presented. Data-mining algorithms are used to select significant parameters used to develop models. A neural network (NN) ensemble with five MLPs (multi-layer perceptrons) performed best among all data-mining algorithms tested and therefore was selected to develop a predictive model. To meet the constraints of the existing energy management applications, Monte Carlo simulation is used to investigate uncertainty propagation of the model built by using weather forecast data. Based on the formulated model and weather forecasting data, future steam consumption is estimated. The latter allows optimal decisions to be made while managing fuel purchasing, scheduling the steam boiler, and building energy consumption.     

Anticipatory Control of Wind Turbines With Data-Driven Predictive Models

The concept of anticipatory control applied to wind turbines is presented. Anticipatory control is based on the model predictive control (MPC) approach. Unlike the MPC method, noncontrollable variables (such as wind speed) are directly considered in the dynamic equations presented in the paper to predict response variables, e.g., rotor speed and turbine power output. To determine future states of the power drive with the dynamic equations, a time series model was built for wind speed. The time series model was fused with the dynamic equations to predict the response variables over a certain prediction horizon. Based on these predictions, an optimization model was solved to find the optimal control settings to improve the power output without incurring large rotor speed changes. As both the dynamic equations and time series model were built by data mining algorithms, no gradient information is available. A modified evolutionary strategy algorithm was used to solve a nonlinear constrained optimization problem. The proposed approach has been tested on the data collected from a 1.5 MW wind turbine.      

Cooling output optimization of an air handling unit

A data-driven optimization approach for minimization of the cooling output of an air handling unit (AHU) is presented. The models used in this research are built with data mining algorithms. The performance of dynamic models build by four different data mining algorithms is studied. A model extracted by a neural network is selected for identifying the functional mapping between specific outputs and controllable and non-controllable inputs of the AHU. To minimize the cooling output while maintaining the corresponding thermal properties of the supply air within a certain range, a bi-objective optimization model is proposed. The evolutionary strategy algorithm is applied to solve the optimization problem with the optimal control settings obtained at each time stamp. The minimized AHU’s cooling output reduces the chiller’s load, which leads to energy savings.     

Short-Term Prediction of Wind Farm Power: A Data Mining Approach

This paper examines time series models for predicting the power of a wind farm at different time scales, i.e., 10-min and hour-long intervals. The time series models are built with data mining algorithms. Five different data mining algorithms have been tested on various wind farm datasets. Two of the five algorithms performed particularly well. The support vector machine regression algorithm provides accurate predictions of wind power and wind speed at 10-min intervals up to 1 h into the future, while the multilayer perceptron algorithm is accurate in predicting power over hour-long intervals up to 4 h ahead. Wind speed can be predicted fairly accurately based on its historical values; however, the power cannot be accurately determined given a power curve model and the predicted wind speed. Test computational results of all time series models and data mining algorithms are discussed. The tests were performed on data generated at a wind farm of 100 turbines. Suggestions for future research are provided.      

Development and optimization of artificial neural network algorithms for the prediction of building specific local temperature for HVAC control

This research accounts for the outcome of a major cloud-based smart dual fuel switching system (SDFSS) project, which is a dual-fuel integrated hybrid heating, ventilation, and air conditioning (HVAC) system in residential homes. The SDFSS was developed to enable optimized, flexible, and cost-effective switching between the natural gas furnace and electric air source heat pump (ASHP). In order to meet the optimal energy consumption requirements in the house and provide thermal comfort for the residents, various high-quality sensors and meters were installed to record multiple data points inside and outside the house. The performance of the system was monitored in the long term, which is a common practice in energy monitoring projects. Outdoor temperature data plays the most crucial role in operating HVAC systems and also is a key variable in the decision-making algorithm of the SDFSS controller. Therefore, this study introduces an innovative and unique approach to obtain the outdoor temperature that could potentially replace high precision sensors with a data-driven model utilizing weather station data at a time resolution of 2 minutes and 1 hour. In this work, a series of artificial neural network algorithms were developed, optimized, and implemented to predict the outdoor temperature with an average of 0.99 coefficient of correlation (R), 1.011 mean absolute error (MAE), and 1.315 root mean square error (RMSE). It has been demonstrated that the developed ANN is a reliable and powerful tool in predicting outdoor temperature. Thus, the proposed model is strongly suggested to be implemented as an alternative to temperature sensors in hybrid energy systems or similar systems requiring accurate ambient temperature measurements.     

System optimization for HVAC energy management using the robust evolutionary algorithm

For an installed centralized heating, ventilating and air conditioning (HVAC) system, appropriate energy management measures would achieve energy conservation targets through the optimal control and operation. The performance optimization of conventional HVAC systems may be handled by operation experience, but it may not cover different optimization scenarios and parameters in response to a variety of load and weather conditions. In this regard, it is common to apply the suitable simulation–optimization technique to model the system then determine the required operation parameters. The particular plant simulation models can be built up by either using the available simulation programs or a system of mathematical expressions. To handle the simulation models, iterations would be involved in the numerical solution methods. Since the gradient information is not easily available due to the complex nature of equations, the traditional gradient-based optimization methods are not applicable for this kind of system models. For the heuristic optimization methods, the continual search is commonly necessary, and the system function call is required for each search. The frequency of simulation function calls would then be a time-determining step, and an efficient optimization method is crucial, in order to find the solution through a number of function calls in a reasonable computational period. In this paper, the robust evolutionary algorithm (REA) is presented to tackle this nature of the HVAC simulation models. REA is based on one of the paradigms of evolutionary algorithm, evolution strategy, which is a stochastic population-based searching technique emphasized on mutation. The REA, which incorporates the Cauchy deterministic mutation, tournament selection and arithmetic recombination, would provide a synergetic effect for optimal search. The REA is effective to cope with the complex simulation models, as well as those represented by explicit mathematical expressions of HVAC engineering optimization problems.     

Towards zero carbon design in offices: Integrating smart facades,ventilation, and surface heating and cooling

This paper discusses an overall strategy for reducing energy demand in non-domestic buildings, mainly focusing on office developments. It considers four areas: reducing internal heat loads; addressing passive design through the building construction; using efficient and responsive HVAC systems and focusing on chilled (heated) surface systems; integrating renewable energy supply systems into the building design. The impact on energy use and carbon dioxide emissions will be discussed. The paper will draw from a range of design projects carried out in Europe, where this integrated approach has been applied, and then explore the benefits in relation to applications in the Middle East and China. Energy modeling results, to inform the design process will be presented, using energy simulation for three case study locations, in Zurich, the Chongqing and Abu Dhabi.     

Numerical study of a hybrid ventilation system for single family houses

The main objective of this study is to develop and test hybrid ventilation systems and control strategies that are suitable for residential buildings. Two ventilation systems were modelled: a mechanical extract ventilation system (called the reference system) and a hybrid low pressure ventilation system that can support two different types of demand control strategies (occupancy detection and CO₂ concentration). The newly developed models were assembled with the existing thermal models of the SIMBAD Building and HVAC Toolbox developed by the CSTB.A single family house located in Athens (Greece), Nice (France), Trappes (France) and finally Stockholm (Sweden) was considered as the case study. Yearly simulations were performed to assess the performance of the hybrid ventilation control strategies. The assessment criteria used are related to indoor air quality, thermal comfort, energy consumption and stability of control strategies. The results show that the low pressure ventilation system can improve the indoor air quality and reduce the fan energy consumption compared to the reference system while maintaining the same building energy consumption for heating.     

A transient ventilation demand model for air-conditioned offices

Ventilation to supply fresh air in an air-conditioned office consumes a considerable portion of energy in an air-conditioning system and affects the indoor-air quality (IAQ). The ventilation demand is primarily related to the occupant load. In this study, the ventilation demands due to occupant load variations were examined against certain IAQ objectives using the mass balance of carbon dioxide (CO₂) volume fractions in an air-conditioned office. In particular, this study proposed a transient ventilation demand model for occupant load, with the parameters determined from a year-round occupant load survey in Hong Kong. This model was applied to evaluate the performance of energy saving in different operating schedules of ventilation systems for typical office buildings in Hong Kong. The results showed that the energy consumption of a ventilation system would be correlated with the transient occupant load and its variations in the air-conditioned office. The ventilation system, with schedules taking account of the transient occupant loads, would offer a reduction in energy consumption up to 19% as compared with an operating schedule that assumed a steady occupant-load in the office during working hours. In both cases, the same IAQ objective was achieved.     

Progress and methodologies of lifecycle commissioning of HVAC systems to enhance building sustainability

Building energy consumption keeps rising in recent years due to growth in population, increasing demand for healthy, comfort and productive indoor environment, global climate changing, etc. Nowadays, the contribution from buildings toward global energy consumption is approximately 40%. Most of energy use in buildings is for the provision of heating, ventilation and air conditioning (HVAC). High-level performance of HVAC systems in building lifecycle is critical to building sustainability.As a quality-oriented process, commissioning has been recognized as a valid means to improve performance of buildings and HVAC systems in both energy and environment aspects and should be conducted regularly or continuously throughout the whole building lifecycle. At the same time, building automation systems (BAS) are now standard in most modern buildings. Besides automatic monitoring and control of building services systems, automatic commissioning is a new expectation on modern BAS to save labor, time and cost required by manual commissioning and improve the effectiveness of commissioning. This paper firstly takes a brief look at current situation of building commissioning in research and application world wide, and then summarizes state-of-the-art techniques for automatic commissioning of HVAC systems. It is concluded that, to maximize benefits from commissioning for enhancing building sustainability, more efforts should be made to develop automatic commissioning tools which can be integrated with modern BAS.     

Case study of data-oriented approach for building energy performance investigation

The key parameters that may influence building energy performance is studied by comparing the building energy data of college buildings in two different regions (the USA and China). By introducing data-orientated approach, a study of a set of on-campus building energy demand and consumption is conducted for cooling, heating and electricity. In addition, the heating, ventilation and air conditioning (HVAC) and lighting systems are studied in great detail. The breakdown analyses of the current energy consumption data are used to focus the investigation on critical issues. The analysis shows that the energy consumption of college buildings in the USA can be 3–5 times more than that of college buildings in China. The over-high energy consumption in campus buildings in the USA is mainly caused by operation schedule, system style, cooling and heating counteraction and sensor/actuator faults in the control systems, which also leads to the discussion of energy difference on the concept of “full control” or “local improvement” in building environment control. The study also indicates that the building energy efficiency can only be achieved by adjusting the demand according to natural conditions, encouraging green life behaviors, and developing relative technical solutions coordinated with the thrift culture and human behavior.     

Case study of data-oriented approach for building energy performance investigation

The key parameters that may influence building energy performance is studied by comparing the building energy data of college buildings in two different regions (the USA and China). By introducing data-orientated approach, a study of a set of on-campus building energy demand and consumption is conducted for cooling, heating and electricity. In addition, the heating, ventilation and air conditioning (HVAC) and lighting systems are studied in great detail. The breakdown analyses of the current energy consumption data are used to focus the investigation on critical issues. The analysis shows that the energy consumption of college buildings in the USA can be 3–5 times more than that of college buildings in China. The over-high energy consumption in campus buildings in the USA is mainly caused by operation schedule, system style, cooling and heating counteraction and sensor/actuator faults in the control systems, which also leads to the discussion of energy difference on the concept of “full control” or “local improvement” in building environment control. The study also indicates that the building energy efficiency can only be achieved by adjusting the demand according to natural conditions, encouraging green life behaviors, and developing relative technical solutions coordinated with the thrift culture and human behavior.     

Retro and on-going commissioning tool applied to an existing building: Operability and results of IPMVP

The new building thermal regulations, mainly published to reduce greenhouse gases emissions, leads to a continuous improvement of building envelopes. On the other hand, the technical performance of the air-conditioning plants, ensured by commissioning procedures, becomes a key point for the control of energy needs in buildings. The essential work of Annex 40 of the International Agency of the Energy reports on “Commissioning of Building HVAC systems for Improved Energy Performance”. In this annex, the test of the IPMVP, International Performance Measurement and Verification Protocol, which is a significant and commonly used tool, is carried out among many others. This paper aims to present and detail the methodology of the IPMVP application and the results of four different calculation options applied to an existing building equipped with an innovative HVAC device, where outdoor airflow rate is controlled by indoor CO₂ rate. This work provides a helpful advice to the energy service company to determine the most adequate option in terms of accuracy, cost and speed of execution according to the available parameters (measurements, software) and the energy saving measure.     

A model‐based fault detection and diagnosis strategy for HVAC systems

A strategy of fault detection and diagnosis (FDD) for HVAC sub‐systems at the system level is presented in this paper. In the strategy, performance indices (PIs) are proposed to indicate the health condition of different sub‐systems including cooling tower system, chiller system, secondary pump systems before heat exchangers, heat exchanger system and secondary pump system after heat exchangers. The regression models are used to estimate the PIs as benchmarks for comparison with monitored PIs. The online adaptive threshold determined by training data and monitored data is used to determine whether the PI residuals between the estimation and calculation or monitoring are in the normal working range. A dynamic simulation platform is used to simulate the faults of different sub‐systems and generate data for training and validation. The proposed FDD strategy is validated using the simulation data and proven to be effective in the FDD of heating, ventilating and air‐conditioning (HVAC) sub‐systems. Copyright © 2009 John Wiley & Sons, Ltd.     

Thermal energy storage in building integrated thermal systems: A review. Part 1. active storage systems

Energy consumed by heating, ventilation and air conditioning systems (HVAC) in buildings represents an important part of the global energy consumed in Europe. Thermal energy storage is considered as a promising technology to improve the energy efficiency of these systems, and if incorporated in the building envelope the energy demand can be reduced. Many studies are on applications of thermal energy storage in buildings, but few consider their integration in the building. The inclusion of thermal storage in a functional and constructive way could promote these systems in the commercial and residential building sector, as well as providing user-friendly tools to architects and engineers to help implementation at the design stage. The aim of this paper is to review and identify thermal storage building integrated systems and to classify them depending on the location of the thermal storage system.