Internet-of-Things Based Hardware-in-the-Loop Framework for Model-Predictive-Control of Smart Building Ventilation

Abstract

In this work, a Hardware-In-the-Loop (HIL) framework is introduced for the implementation and the assessment of predictive control approaches in smart buildings. The framework combines recent Internet of Things (IoT) and big data platforms together with machine-learning algorithms and MATLAB-based Model Predictive Control (MPC) programs in order to enable HIL simulations. As a case study, the MPC algorithm was deployed for control of a standalone ventilation system (VS). The objective is to maintain the indoor Carbon Dioxide (CO2) concentration at the standard comfort range while enhancing energy efficiency in the building. The proposed framework has been tested and deployed in a real-case scenario of the EEBLab test site. The MPC controller has been implemented on MATLAB/Simulink and deployed in a Raspberry Pi (RPi) hardware. Contextual data are collected using the deployed IoT/big data platform and injected into the MPC and LSTM machine learning models. Occupants’ numbers were first forecasted and then sent to the MPC to predict the optimal ventilation flow rates. The performance of the MPC control over the HIL framework has been assessed and compared to an ON/OFF strategy. Results show the usefulness of the proposed approach and its effectiveness in reducing energy consumption by approximately 16%, while maintaining good indoor air quality.

Design of a Meaningful Framework for Time Series Forecasting in Smart Buildings

“…[28] uses the EnergyPlus expert simulation software for HVAC control simulation, while [29] could access real HVAC control. The complexity of infrastructures for MPC, with humans in the loop [30], is concurrently becoming a main issue, as emphasized by [31,32]. The final step toward an industrial-scale AI solution will undoubtedly be to address this complexity in data by enabling the MPC to select relevant data and detect anomalies [33,34].…”

Sensing within Smart Buildings: A Survey

“…The data is fused to predict occupancy and improve energy efficiency [161] Occupancy sensing Accelerometer and gyroscope SVM The sensor data was fused and stored on Arduino Uno for different objects to identify different occupants in the smart home [50] Plug-load meters and PIR K-means clustering The sensor data was collected and transmitted from Raspberry Pi to an external server to estimate individual occupancy in office spaces [135] Temperature, humidity, light, and pressure xgboost, Random Forest (RF),DT, LightGBM, and Gradient Boosting Classifier (GBDT) Sensors data was collected using an Arduino board, and the board uploaded the data to an external server for visualization and enable accurate indoor location [46] Indoor positioning BLE beacons Trilateration algorithm The Beacons sensors transmit the BLE signals to estimate the occupant's position, Arduino Mega and the smartphone are used to track the position, and then the data was sent to an external server for analysis [18] Wearable wristband and smart phone Fuzzy logic and genetic algorithm Designed wristbands are used to receive the Received Signal Strength Index (RSSI) strength, and the corresponding MAC address is then sent to the cloud server, and then the server calculates and analyzes the received data for indoor positioning in an smart hospital environment [21] Temperature, light, PIR, and MQ-2 gas Proposed lighting control algorithm The sensor data was collected by the Arduino Mega board, the board controlled the lights in the house to reduce energy consumption [20] Building energy consumption CO2, temperature, and humidity Model predictive control (MPC), and long short-term memory (LSTM) Sensors data was collected and stored in a Raspberry pi. Then the data was sent to a remote ThingsBoard platform to control smart building ventilation predictively while enhancing energy efficiency [69] Temperature, humidity, CO2, and Wi-Fi probe k-nearest neighbors (kNN), SVM, artificial neural network(ANN) Sensor data is stored locally and WiFi data is sent to the cloud. The data is fused to predict occupancy and improve energy efficiency [161] CO2, temperature, and humidity Model predictive control (MPC), and long short-term memory (LSTM) Sensors data was collected and stored in a Raspberry pi.…”

“…The data is fused to predict occupancy and improve energy efficiency [161] CO2, temperature, and humidity Model predictive control (MPC), and long short-term memory (LSTM) Sensors data was collected and stored in a Raspberry pi. Then the data was sent to a remote ThingsBoard platform to control smart building ventilation predictively while enhancing energy efficiency [69] Building indoor environmental quality Particulate matter (PM), temperature, and humidity On-Off Control The sensor data was collected by the Arduino Pro Mini board and sent to a Raspberry Pi server for processing, and then the data was sent to the ESP8266 board to monitor and control the air quality in the building [169] Temperature, humidity, and gas sensor…”

Protocol for a distributed smart building solution using semi-physical simulation

“… 16 Kharbouch et al. 17 have used a hardware-in-the-loop framework, but it remains a hierarchical and centralized architecture. To address these issues, we propose the distributed smart building simulator (DSBS) protocol, which outlines the construction and operation of the fully distributed Honeycomb prototype that utilizes semi-physical simulation technology.…”