**1. Introduction**

Optimal behaviour is one the most desired features of contemporary technological systems. Challenges like secure operation, energy efficiency, and reliable performance call for the optimised behaviour of any systems that operate and interact in our living environment. The challenge in achieving optimised performances resides in the uncertainty that qualifies the environment surrounding technical systems. Whatever model drives the systems' behaviour, it must be able to face unforeseen events, to manage the vagueness of the sensing apparatus and the errors of the control devices. Bayesian statistics is one of the theoretical backgrounds that support the construction of systems which are able to act effectively inside complex environments. Bayesian statistics is grounded on the fundamental premise that all uncertain‐ ties should be represented and measured by probabilities. Then, the laws of probabilities apply to produce probabilistic inferences about any quantity, or collection of quantities, of interest. Bayesian inference can provide predictions about probability values pertaining time series or can model parameters in terms of probability distributions that represent and summarize current uncertain knowledge and beliefs. Bayesian inference uses a kind of direct causal or model-based knowledge to provide the crucial robustness needed to make the optimised behaviour of technical systems feasible in the real world [1]. Once this kind of models have been built, then theoretically sound evidence propagation algorithms are used to update the belief set about the external environment and about the system performance, on the basis of acquired evidence. This is the fundamental mechanism that drives the construction and the operation of intelligent systems based on Bayesian inference. This chapter describes a sample engineering application of this approach on a large scale. It concerns the design and the development of an intelligent building energy management system (smart BEMS) that is able

© 2014 The Author(s). Licensee InTech. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

to optimise the operation of the mechanical air supply systems of the Passeig De Gracia metro station in Barcelona. To the purpose of this application, predictive models were developed to support the optimal control of environmental conditions in the station, which was necessary due to the many interacting variables of the domain.

that serve the optimal control are obtained through model simulation of the building future states, the implementation of MPC requires the development of integrated models capable of predicting the near future behaviour of the controlled environment under specific conditions, so that the optimal solution can be sought through scenario analysis [13, 14]. Adaptive and predictive control strategies would follow from these considerations. The development of domain models that are able to drive the MPC of a complex set of systems, like the ones operating in a metro station, is not a trivial task. For example, on one side MPC models must provide accurate predictions of future states but, on the other side, they must be computa‐ tionally light in order to provide predictions in a time frame compatible with the monitoring time constraints. Furthermore, MPC models must interoperate with real sensor/actuator networks that usually, for cost reasons, cannot be larger than few tenths of devices and whose deployment is constrained by a number of external factors. Nevertheless, the model accuracy must be granted despite the reduced representation of the physical model and the suboptimal selection of the parameter set. The fulfilment of such competing requirements compels the definition of a modelling framework that, by guiding the MPC modeller through a set of methodological steps, will contribute to design accurate and robust models, which are sufficiently light to be embedded in real control systems. The Bayesian inference approach, and its computational counterpart Bayesian Networks, provide the means to manage the

Bayesian Networks for Supporting Model Based Predictive Control of Smart Buildings

http://dx.doi.org/10.5772/58470

5

This chapter will outline the Bayesian Network approach that was followed to develop the environmental model used to design the line 3 of "Passeig De Gracia" (PdG-L3) metro station energy control system and the main features of the hybrid modelling solution undertaken to fulfil its functional requirements. A metro station is a very complex system. It involves, among others, multi-storey underground spaces having multifaceted thermal behaviour, e.g., intricate air exchange dynamics with the outside, heat conduction with the surrounding soil and high variable internal gains due to travelling passengers and trains. Furthermore, a metro station is usually serviced by various equipment involving cooling, ventilation, safety and security, lighting, vertical transportation and horizontal passenger transfer, gates and selling machines, information and auxiliary systems. The research illustrated in this paper is one of the results of the SEAM4US project funded under EU grant n. FP7-2011-NMP-ENV-ENERGY-ICT-EeB-285408. The objective of the SEAM4US research is to develop an advanced control system for the PdG metro station in Barcelona capable of dynamically adjusting the internal environ‐ ment in optimal way, based on forecasts regarding the external environment, in order to

As mentioned in the Introduction, the Bayesian networks developed in this chapter were used to provide forecasts about the future state of the PdG-L3 in Barcelona, given the knowledge about their current state, in order to support the application of a Model based Predictive

Control (MPC) approach. In fact, MPC is an enhancement of adaptive control.

requirements set that compels the development of MPC models.

guarantee energy efficiency, comfort and comply with regulations.

**2. Literature review about MPC control**

Building Energy Management Systems (BEMSs) are control systems installed in buildings for managing the building's mechanical and electrical equipment, such as ventilation, lighting, fire and security systems [2]. BEMSs consist of hardware and software components. The hardware set-up of a BEMS is typically made up of sensor-actuator networks that accurately monitor the indoor-outdoor environment and the building plants state. The software side of a BEMS consists of a number of functional layers that implement standard management functionalities like plant status monitoring, alarm management, demand driven plant management, reporting, etc. The hardware side of the commercial BEMS technology is at present a rather mature field. A number of initiatives and associations both at industrial and public level (e.g. European Building Automation and Controls Association-EU.BAC) are cooperating to develop open communication and seamless integration standards such as BACnet, KNX, LonWorks [3], and DALI [4]. The software side of commercial BEMSs is being standardised as well. Standard EN15232 provides a structured list of controls, building automation and technical building management functions that make an impact on the energy performances of buildings. Firstly, it provides a method to define the minimum requirements concerning the building automation and the building management policies, differentiated according to the level of complexity of buildings; secondly, it provides detailed methods to assess the impact of these policies on the energy performance of any given building. Never‐ theless, EN15232 methods are limited to relatively simplified applications, ranging from simple homeostatic control to demand-driven and time-scheduled policies. The implementa‐ tion of optimised control policies that encompass the complex weather and end-user dynamics in the energy management of buildings is still missing. The analysis of standard BEMS applications suggests that only a fraction of the available BEMS energy saving potential of each specific building is utilized by the implemented management policies, thus missing significant opportunities for reducing operating costs through better supervisory controls. Frequently, plant and building set-points follow prescribed schedules and are not optimized in response to changing dynamic conditions, including weather, internal loads, occupancy patterns, etc. Nonetheless, there are significant opportunities for optimizing control set points and modes of operation in response to dynamic forcing functions and utility rate incentives. A number of studies [5-8] have shown potential savings for optimized controls in the range of 10% to 40% of the overall cooling cost.

Model Predictive Control (MPC) [9-11] may be used to enhance BEMSs so that they can improve their control performances getting close to optimal behaviour. MPC is an advanced control technique [12] that uses the predictions of future building status, obtained by means of a model of the building's dynamics, in order to solve the problem of determining the optimal control policies. The purpose of building management is to guarantee comfort at minimum operational cost. The MPC integrated approach to building management guarantees perform‐ ance over the full range of conditions which are likely to be encountered. Since the predictions that serve the optimal control are obtained through model simulation of the building future states, the implementation of MPC requires the development of integrated models capable of predicting the near future behaviour of the controlled environment under specific conditions, so that the optimal solution can be sought through scenario analysis [13, 14]. Adaptive and predictive control strategies would follow from these considerations. The development of domain models that are able to drive the MPC of a complex set of systems, like the ones operating in a metro station, is not a trivial task. For example, on one side MPC models must provide accurate predictions of future states but, on the other side, they must be computa‐ tionally light in order to provide predictions in a time frame compatible with the monitoring time constraints. Furthermore, MPC models must interoperate with real sensor/actuator networks that usually, for cost reasons, cannot be larger than few tenths of devices and whose deployment is constrained by a number of external factors. Nevertheless, the model accuracy must be granted despite the reduced representation of the physical model and the suboptimal selection of the parameter set. The fulfilment of such competing requirements compels the definition of a modelling framework that, by guiding the MPC modeller through a set of methodological steps, will contribute to design accurate and robust models, which are sufficiently light to be embedded in real control systems. The Bayesian inference approach, and its computational counterpart Bayesian Networks, provide the means to manage the requirements set that compels the development of MPC models.

This chapter will outline the Bayesian Network approach that was followed to develop the environmental model used to design the line 3 of "Passeig De Gracia" (PdG-L3) metro station energy control system and the main features of the hybrid modelling solution undertaken to fulfil its functional requirements. A metro station is a very complex system. It involves, among others, multi-storey underground spaces having multifaceted thermal behaviour, e.g., intricate air exchange dynamics with the outside, heat conduction with the surrounding soil and high variable internal gains due to travelling passengers and trains. Furthermore, a metro station is usually serviced by various equipment involving cooling, ventilation, safety and security, lighting, vertical transportation and horizontal passenger transfer, gates and selling machines, information and auxiliary systems. The research illustrated in this paper is one of the results of the SEAM4US project funded under EU grant n. FP7-2011-NMP-ENV-ENERGY-ICT-EeB-285408. The objective of the SEAM4US research is to develop an advanced control system for the PdG metro station in Barcelona capable of dynamically adjusting the internal environ‐ ment in optimal way, based on forecasts regarding the external environment, in order to guarantee energy efficiency, comfort and comply with regulations.
