Predictive control of multizone heating,ventilation and air-conditioning systems in non-residential buildings

In France, buildings account for a large part of the energy consumption and carbon emissions. Both are mainly due to heating, ventilation and air-conditioning (HVAC) systems. Because older, oversized or poorly maintained systems may be using more energy and costing more to operate than necessary, new management approaches are needed. In addition, energy efficiency can be improved in central heating and cooling systems by introducing zoned operation. So, the present work deals with the predictive control of multizone HVAC systems in non-residential buildings. First, a real non-residential building located in Perpignan (south of France) has been modelled using the EnergyPlus software. We used the predicted mean vote (PMV) index as a thermal comfort indicator and developed low-order ANN-based models to be used as controller's internal models. A genetic algorithm allowed the optimization problem to be solved. In order to appraise the proposed management strategy, it has been compared to basic scheduling techniques. Using the proposed strategy, the operation of all the HVAC subsystems is optimized by computing the right time to turn them on and off, in both heating and cooling modes. Energy consumption is minimized and thermal comfort requirements are met. So, the simulation results highlight the pertinence of a predicitive approach for multizone HVAC systems management.     

Decentralized predictive thermal control for buildings

This paper studies the problem of decentralized control design for thermal control in buildings, to achieve a satisfactory trade-off between underlying performance and robustness objectives. An output-feedback, model predictive framework is used for decentralized control which is based on a reduced order system representation. It entails the use of decentralized extended state observers to address the issue of unavailability of all states and disturbances. The decision on control architecture selection is based on an agglomerative clustering methodology developed previously [22]. The potential use of the proposed control design methodology is demonstrated in simulation on a multi-zone building, which quantifies the tradeoffs in performance and robustness with respect to the degree of decentralization.     

A federated learning approach for thermal comfort management

Existing thermal comfort prediction approaches by machine learning models have been achieving great success based on large datasets in sustainable Industry 4.0 environment. However, the industrial Internet of Things (IoT) environment generates small-scale datasets where each dataset may contain lots of worker’s private data. The latter is challenging the current prediction approaches as small datasets running a large number of iterations can result in overfitting. Moreover, worker’s privacy has been a public concern throughout recent years. Therefore, there must be a trade-off between developing accurate thermal comfort prediction models and worker’s privacy-preserving. To tackle this challenge, we present a privacy-preserving machine learning technique, federated learning (FL), where an FL-based neural network algorithm (Fed-NN) is proposed for thermal comfort prediction. Fed-NN departs from current centralized machine learning approaches where a universal learning model is updated through a secured parameter aggregation process in place of sharing raw data among different industrial IoT environments. Besides, we designed a branch selection protocol to solve the problem of communication overhead in federating learning. Experimental studies on a real dataset reveal the robustness, accuracy, and stability of our algorithm in comparison to other machine learning algorithms while taking privacy into consideration.     

Thermal comfort control using a non-linear MPC strategy: A real case of study in a bioclimatic building

The aim to maintain thermal comfort conditions in confined environments may require complex regulation procedures and the proper management of an HVAC (heating, ventilation and air conditioning) system. This problem is being widely analyzed, since it has a direct effect on users’ productivity, and an indirect effect on energy saving. This paper presents a hierarchical thermal comfort control system with two layers. The upper layer includes a non-linear model predictive controller that allows to obtain a high thermal comfort level by optimizing the use of an HVAC system in order to reduce, as much as possible, the energy consumption. On the other hand, the lower layer is formed by a PID (proportional, integrative and derivative) controller with anti-windup function which is in charge of reach the setpoints calculated by the non-linear model predictive controller. In order to probe the effectiveness of the proposed control system, suitable real results obtained in a bioclimatic building are included and commented.     

Model reduction and model predictive control of energy-efficient buildings for electrical heating load shifting

In France, buildings account for a significant portion of the electricity consumption (around 68%), due to an important use of electrical heating systems. This results in high peak load in winter and causes tensions on the production-consumption balance. In view of reducing such fluctuations, advanced control systems (including the Model Predictive Control framework) have been developed to shift heating load while maintaining indoor comfort and taking advantage of the building thermal mass. In this paper, a framework for developing optimisation-based control strategies to shift the heating load in buildings is introduced. The balanced truncation method and a time-continuous optimisation method were used to develop a real-time control of the heating power. These two methods are well suited for control problems and yield precise results. The novelty of the approach is to use reduced models derived from advanced building simulation software. A simulation case study demonstrates the controller performance in the synthesis of a predictive model-based optimal energy management strategy for a single-zone test building of the “INCAS” platform built in Le Bourget-du-Lac, France, by the National Solar Energy Institute (INES). The controller exhibits excellent performance, reaching between 6 and 13% cost reduction, and can easily be applied in real-time.     

Stochastic model predictive control for remanufacturing system management

Uncertainties in the quality, quantity, and operational time of used products pose a challenge to the management of remanufacturing systems. In addition, it becomes a necessity to optimize the operation of the remanufacturing system to balance the quality of products, remanufacturing efficiency, and service level. In this study, a stochastic discrete-time dynamical model is proposed to represent a remanufacturing system, where the relationship between the market satisfaction, inventory status, and operational actions is explicitly modeled. This includes production and inventory planning, resource allocation and acquisition. To handle uncertainties, a stochastic model predictive control approach is proposed to plan the actions that optimize the remanufacturing efficiency. Our results in the simulation examples show that: (a) without supplies, the remanufacturing system has better stability and robustness than a conventional manufacturing system with the same initial stocks; and (b) with insufficient initial stocks, the remanufacturing system demands fewer and more gradual supplies, thereby keeping the system stable. Finally, a sensitivity analysis is conducted for testing the performance of the remanufacturing system. By changing the operational action capacity, different state equilibria are discovered, which correspond to distinct system response characteristics. The study reveals notable managerial insights and effects of product commonality, demand patterns, and operational actions scheduling on the efficiency of the remanufacturing system.     

Artificial neural networks for predicting indoor temperature using roof passive cooling techniques in buildings in different climatic conditions

Three passive cooling methods (e.g. roof pond, reflective roof cooling and using insulation over the roof) have been experimentally evaluated using an experimental test structure. The objective of this work is to train an artificial neural network (ANN) to learn and predict the indoor temperature of room with the different experimental data. Different training algorithms (traingd, traingdm, traingdx, trainrp, traincgp, traincgf, traincgb, trainscg, trainbfg, trainoss, trainlm, and trainbr) were used to create an ANN model. This study is helpful in finding the thermal comfort of building by applying different passive cooling techniques. The data presented as input were outside temperature, relative humidity, solar intensity and wind speed. The network output was indoor temperature. The advantages of this approach are (i) the speed of calculation, (ii) the simplicity, (iii) adaptive learning from examples and thus gradually improve its performance, (iv) self-organization and (vi) real time operation. Results proved highly satisfactory and provided enough confidence for the process to be extended to a larger solution space for which there is uneconomical and time consuming way of calculating the solution.     

Developing a robust model predictive control architecture through regional knowledge analysis of artificial neural networks

Chemical processes are nonlinear. Model based control schemes such as model predictive control are highly related to the accuracy of the process model. For a highly nonlinear chemical system, it is clear to implement a nonlinear empirical model, such as artificial neural network model, should be superior to a linear model such as dynamic matrix model. However, unlike linear systems, the accuracy of a nonlinear empirical model strongly depends on its original data or training data based on how the model is built up. A regional-knowledge index is proposed in this study and applied in the analysis of dynamic artificial neural network models in process control. New input patterns that imply extrapolations and thus unreliable prediction by an artificial neural network model can be recognized from a significant decrease in the regional-knowledge index. To tackle the extrapolation problem and assure stability of the control system, we propose to run a neural adaptive controller in parallel with a model predictive control. A coordinator weights the outputs of these two controllers to make the final control decision. The present state of the controlled process and the model fitness to the present input pattern determine the weightings of the controller's output. The proposed analysis method and the modified model predictive control architecture have been applied to a neutralization process and excellent control performance is observed in this highly nonlinear system.     

A multiple model approach for predictive control of nonlinear hybrid systems

This paper presents modeling and control of nonlinear hybrid systems using multiple linearized models. Each linearized model is a local representation of all locations of the hybrid system. These models are then combined using Bayes theorem to describe the nonlinear hybrid system. The multiple models, which consist of continuous as well as discrete variables, are used for synthesis of a model predictive control (MPC) law. The discrete-time equivalent of the model predicts the hybrid system behavior over the prediction horizon. The MPC formulation takes on a similar form as that used for control of a continuous variable system. Although implementation of the control law requires solution of an online mixed integer nonlinear program, the optimization problem has a fixed structure with certain computational advantages. We demonstrate performance and computational efficiency of the modeling and control scheme using simulations on a benchmark three-spherical tank system and a hydraulic process plant.     

Artificial neural network models for indoor temperature prediction: investigations in two buildings

The problem how to identify prediction models of the indoor climate in buildings is discussed. Identification experiments have been carried out in two buildings and different models, such as linear ARX-, ARMAX- and BJ-models as well as non-linear artificial neural network models (ANN-models) of different orders, have been identified based on these experiments. In the models, many different input signals have been used, such as the outdoor and indoor temperature, heating power, wall temperatures, ventilation flow rate, time of day and sun radiation. For both buildings, it is shown that ANN-models give more accurate temperature predictions than linear models. For the first building, it is shown that a non-linear combination of sun radiation and time of day is important when predicting the indoor temperature. For the second building, it is shown that the indoor temperature is non-linearly dependent on the ventilation flow rate.     

Predictive and interactive controllers for solar absorption cooling systems in buildings

A predictive control approach is proposed for a solar powered hot water storage (SHWS) system which interacts with a simple thermal building control. The primary objective of this first controller is to optimize the use of the solar energy in order to ensure the cooling requirement of the building. The main difficulties are related to the presence of safety constraints and the nonlinearity as well as the hybrid nature of the system. The resulting optimization problem is simplified using various relaxations. The second controller is dedicated to the control of the building temperature. Using a model of the building thermal behavior, it sends its predicted operating profile to the SHWS controller. The performances of these two interacting controllers are illustrated by various simulations on a TRNSYS model of the building and its subsystems.     

Learning-based tuning of supervisory model predictive control for drinking water networks

This paper presents a constrained Model Predictive Control (MPC) strategy enriched with soft-control techniques as neural networks and fuzzy logic, to incorporate self-tuning capabilities and reliability aspects for the management of drinking water networks (DWNs). The control system architecture consists in a multilayer controller with three hierarchical layers: learning and planning layer, supervision and adaptation layer, and feedback control layer. Results of applying the proposed approach to the Barcelona DWN show that the quasi-explicit nature of the proposed adaptive predictive controller leads to improve the computational time, especially when the complexity of the problem structure can vary while tuning the receding horizons.     

Variational Bayesian learning of nonlinear hidden state-space models for model predictive control

This paper studies the identification and model predictive control in nonlinear hidden state-space models. Nonlinearities are modelled with neural networks and system identification is done with variational Bayesian learning. In addition to the robustness of control, the stochastic approach allows for various control schemes, including combinations of direct and indirect controls, as well as using probabilistic inference for control. We study the noise-robustness, speed, and accuracy of three different control schemes as well as the effect of changing horizon lengths and initialisation methods using a simulated cart–pole system. The simulations indicate that the proposed method is able to find a representation of the system state that makes control easier especially under high noise.     

Separated design of robust model predictive control for LPV systems with periodic disturbance

To eliminate the steady-state error of systems with periodic disturbance, the repetitive control (RC) is a useful approach. For practical applications, the controller is designed to both steer system output to a given set-point (or track a given reference signal) and reject periodic disturbance. The learning procedure of RC and the control action to steer system output to a set-point may influence each other and prolong the convergence time RC. In order to reduce this interaction, this paper proposes a separated design approach. A linear parameter varying (LPV) system is considered. A repetitive predictive control (RPC) and a robust model predictive control (RMPC) are separately designed, respectively, corresponding to reject the periodic disturbance and steer system output to the set-point. The convergence of the proposed RPC sub-controller is derived. The numerical examples show that the proposed design is effective.     

Review of control strategies for improving the energy flexibility provided by heat pump systems in buildings

The present work constitutes a review of the existing literature on supervisory control for improving the energy flexibility provided by heat pumps in buildings. A distinction was drawn between rule-based controls (RBC) and model predictive controls (MPC), given the clear differences in their concept and complexity. For both kinds, the different objectives claimed by these strategies have been reviewed, as well as the control inputs, disturbances and constraints. Notably in MPC, the monetary objective (reduction of the energy costs) has been the most utilized in the literature, therefore the authors advocate for the further study of other objectives related to energy flexibility. Further than the control strategies themselves, the different thermal storage options (necessary to activate the flexibility) have also been reviewed, the built-in thermal mass seeming more cost-effective than water buffer tanks in this regard. Based on these conclusions, recommendations for further research topics are drawn.     

Power management for a DC MicroGrid integrating renewables and storages

A power management controller for a DC MicroGrid containing renewable energy sources, storage elements and loads is presented. The controller ensures power balance and grid stability even when some devices are not controllable in terms of their power output, and environmental conditions and load vary in time. Power balance and desired voltage level for the DC MicroGrid are considered as constraints for the controller. Simulations and an experimental setup are implemented to show the effectiveness of the proposed control action.     

Feedback and feedforward control in the context of model predictive control with application to the management of type 1 diabetes mellitus

A unified formulation of feedback and feedforward control is given in the context of model predictive control. The ideas are illustrated by the management of type 1 diabetes mellitus although the general principles apply, mutatis mutandis, to other scenarios and problems.     

ILC strategy for progress improvement of economic performance in industrial model predictive control systems

A novel approach to progress improvement of the economic performance in model predictive control (MPC) systems is developed. The conventional LQG based economic performance design provides an estimation which cannot be done by the controller while the proposed approach can develop the design performance achievable by the controller. Its optimal performance is achieved by solving economic performance design (EPD) problem and optimizing the MPC performance iteratively in contrast to the original EPD which has nonlinear LQG curve relationship. Based on the current operating data from MPC, EPD is transformed into a linear programming problem. With the iterative learning control (ILC) strategy, EPD is solved at each trial to update the tuning parameter and the designed condition; then MPC is conducted in the condition guided by EPD. The ILC strategy is proposed to adjust the tuning parameter based on the sensitivity analysis. The convergence of EPD by the proposed ILC has also been proved. The strategy can be applied to industry processes to keep enhancing the performance and to obtain the achievable optimal EPD. The performance of the proposed method is illustrated via an SISO numerical system as well as an MIMO industry process.     

Connection of nonlinear model predictive controllers for smooth task switching in autonomous driving

Motion planning, decision making, and control are vital functions in autonomous driving for accomplishing the desired driving task while considering passenger comfort, road infrastructure, and surrounding traffic participants. Model predictive control (MPC) is a promising method for simultaneously realizing these functions. However, formulating a single MPC that can run through all driving scenarios is difficult, and previous research has often been conducted to design an MPC for a specific driving task. To extend the availability of MPC for all driving tasks, smooth switching between different MPCs designed for each driving task must be addressed. One of the difficulties in switching between MPCs is guiding the state to a feasible set of optimization problems after switching. In this paper, we present a new framework to realize the smooth connection of MPCs, that is, to reduce the optimization infeasibility at the time of MPC switching. In our proposed method, two general nonlinear MPCs with different state spaces, cost functions, constraints, and formulations can be systematically switched via automatically generated intermediate-MPCs without requiring any particular alterations. This can help reduce the system complexity of the hybrid MPC system.     

Simulation-based optimization of process control policies for inventory management in supply chains

A simulation-based optimization framework involving simultaneous perturbation stochastic approximation (SPSA) is presented as a means for optimally specifying parameters of internal model control (IMC) and model predictive control (MPC)-based decision policies for inventory management in supply chains under conditions involving supply and demand uncertainty. The effective use of the SPSA technique serves to enhance the performance and functionality of this class of decision algorithms and is illustrated with case studies involving the simultaneous optimization of controller tuning parameters and safety stock levels for supply chain networks inspired from semiconductor manufacturing. The results of the case studies demonstrate that safety stock levels can be significantly reduced and financial benefits achieved while maintaining satisfactory operating performance in the supply chain.