Abstract

Radio frequency identification (RFID) is an automatic identification technique that facilitates data exchange and transmission between a reader and a tag using radio frequency waves. In large-scale environments, it is observed that RFID devices are susceptible to signal collision. This collision can occur between many entities, such as tags, readers, and the between readers and tags. Furthermore, the limited range of identification associated with it leads to increased expenses in terms of deployment. Hence, the primary concerns in organizations revolve around the elimination of RFID collision and the reduction of deployment costs.

This study introduces a hybrid BIRCH Chaotic Particle Swarm Optimization (BCPSO) algorithm that seeks to optimize four contradictory objective functions (maximizing tag coverage, minimizing readers interference, reducing power transmission consumption, and minimizing the variance of load balancing). The MATLAB R2020a package and the computer hardware specifications of Intel Core i5-1135G7 with 8.00 GB of RAM and CPU of 2.40GHz were used.

The proposed hybrid BIRCH Chaotic Particle Swarm Optimization (BCPSO) algorithm improves the coverage of tags by 100% with the fewest readers while avoiding interference. It also improves load balancing in three different cases with respect to the number of tags: case1 when the number of tags is 30 by 99.89%, 99.98%, 99.97% and 99.9%; case2 when the number of tags is 50 by 80.18%, 43.94%, 50.15%, and 70.39%; case3 when the number of tags is 100 by 63.47%, 23.90%, 51.67%, and 86.83% according to the comparison results between the proposed (BCPSO) algorithm and the (PSO, PS2O, VNPSO- RNP, and CSP-RNP) algorithms in [67], respectively. We also compared the proposed hybrid BCPSO algorithm with the HPSO-RNP algorithm in [17] and, the comparison results demonstrate that the proposed hybrid (BCPSO) algorithm improves the power transmission consumption in case2 when the number of tags is 50 by 54.60%, and 45.66% and case3 when the number of tags is 100 by 49.24%, and 42.58%, respectively.

Hydrogen Fuel Cells (FCs) are a type of renewable energy source that is gaining global interest as a sustainable energy choice for clean energy sources. A big challenge is to achieve optimum FC efficiency in the presence of multiple factors that impact the cell's performance, such as pressure, temperature, humidity, and supplied current, which results in a nonlinear dynamic behavior in the system's generation. Thus, control and monitoring of a FC are essential to improving global efficiency, hydrogen and air utilization, and achieving consistent and accurate power response, which contributes to optimizing its efficiency, safety, cost, and durability. In this work, a new development of a predictive voltage neural controller and remote monitoring for the nonlinear proton exchange membrane fuel cell (PEMFC) system is implemented in real-time. The major purpose of this work is to precisely and rapidly determine the appropriate hydrogen partial pressure (PH2) control action with a minimum number of step-ahead predictions (one step). This optimal control action improves the fuel cell's nonlinear performance under varying load currents, preventing damage to the fuel cell membrane and thereby prolonging the fuel cell’s lifetime. Moreover, another purpose is to enables the remote monitoring of the nonlinear PEMFC system response based on the Internet of Things (IoT). The proposed predictive voltage controller consists of three sub-controllers. The first one is the numerical feed-forward controller (NFFC), which is used to decide the steady-state PH2 control action depending on the desired voltage. The second sub-controller is a feedback neural controller that uses a multi-layer perceptron (MLP) neural network structure and a back-propagation learning algorithm to generate the hydrogen partial pressure feedback control action to track the desired output voltage of the fuel cell during transient conditions. The third sub-controller is the predictive control law equation, which is based on the modified Elman recurrent neural network (MERNN) as an identifier for the PEMFC model and the multi-objective performance index (Mean Square Error). From the simulation results using the MATLAB program, the proposed controller has the capability to generate a precisely and quickly timed response to the PH2 control action without any saturation state in order to minimize the tracking voltage error and eliminate oscillation in the output voltage of the FC. The suggested predictive control strategy's numerical simulation results are then verified by comparing them with those of other types of controllers in terms of the minimum number of steps ahead prediction (reducing from 10 to 1 step), enhancement of the tracking voltage error by 81.8% compared with a predictive neural controller, and improvement of the tracking voltage error by 87.5% compared with an inverse neural controller. Moreover, the oscillation effect in the output voltage is completely eliminated, resulting in a response without any overshoot. The Laboratory Virtual Instrument Engineering Workbench (LabVIEW) package is used to demonstrate the real-time performance of the proposed predictive voltage neural controller applied to the 150-watt PROTIUM PEMFC, which will be used to generate the appropriate amount of PH2 control action that will enter the fuel cell for stabilizing the desired output voltage. The IoT based on the Message Queuing Telemetry Transport (MQTT) protocol and a Raspberry Pi 4 acting as a local server are the building blocks upon which the monitoring component of the proposed system is implemented in order to monitor the desired output voltage, the fuel cell output voltage, and PH2. The Raspberry Pi collects the necessary fuel cell data and sends it to the Node-RED dashboard for monitoring. According to the simulation and the experimental results obtained using the proposed predictive neural controller on PROTIUM PEMFC, the proposed controller can generate an accurate, prompt, and timely reaction to the PH2 control action to reduce the tracking voltage error and to get rid of fuel cell output voltage oscillation. The proposed experimental work was compared to the simulation findings to confirm its effectiveness in terms of effectively tracking the desired output voltage, providing a fast response, and achieving the optimal partial pressure of hydrogen. However, in the simulation findings, a voltage error of 0.01 volts was observed without any oscillation. On the other hand, the experimental results indicate a slightly higher voltage error of approximately 0.1 volts, accompanied by oscillations of around ± 0.1 volts.