Showing papers by "Kishore Bingi published in 2023"

Machine Learning Prediction Based Adaptive Duty Cycle MAC Protocol for Solar Energy Harvesting Wireless Sensor Networks

Abstract: The dynamic nature of energy harvesting rate, arising because of ever changing weather conditions, raises new concerns in energy harvesting based wireless sensor networks (EH-WSNs). Therefore, this drives the development of energy aware EH solutions. Formerly, many Medium Access Control (MAC) protocols have been developed for EH-WSNs. However, optimizing MAC protocol performance by incorporating predicted future energy intake is relatively new in EH-WSNs. Furthermore, existing MAC protocols do not fully harness the high harvested energy to perform aggressively despite the availability of sufficient energy resources. Therefore, a prediction-based adaptive duty cycle (PADC) MAC protocol has been proposed, called PADC-MAC, that incorporates current and future harvested energy information using the mathematical formulation to improve network performance. Furthermore, a machine learning model, namely nonlinear autoregressive (NAR) neural network, is employed that achieves good prediction accuracy under dynamic harvesting scenarios. As a result, it enables the receiver node to perform aggressively better when there is sufficient inflow of incoming harvesting energy. In addition, PADC-MAC uses a self-adaptation technique that reduces energy consumption. The performance of PADC-MAC is evaluated using GreenCastalia in terms of packet delay, network throughput, packet delivery ratio, energy consumption per bit, receiver energy consumption, and total network energy consumption using realistic harvesting data for 96 consecutive hours under dynamic solar harvesting conditions. The simulation results show that PADC-MAC provides lower average packet delay of the highest priority packets and all packets, energy consumption per bit, and total energy consumption by more than 10.7%, 7.8%, 81%, and 76.4%, respectively when compared to three state-of-the-art protocols for EH-WSNs.

Novel Architecture for Transactive Energy Management Systems with Various Market Clearing Strategies

Abstract: The recent advancements in demand-side management techniques add significant benefits to the distribution systems. One such technique is transactive energy management systems (TEMS) which motivate the energy end-users to take part in local energy trading. The end-users can effectively increase the monetary benefits by trading the surplus generation/demand within the local energy market (LEM). The LEM operator frames a viable market clearing strategy to fix the market clearing price to enhance the monetary benefits of all the market players. In this study, LEM architecture with different market clearing strategies is proposed for TEMS to ensure profitable power transactions between the neighboring end-users. An optimal energy management algorithm is also proposed for time scheduling the operation of flexible loads and batteries, considering dynamics in end-users’ behavior, variations in utility parameters, and the intermittent nature of renewable power generation. Further, an optimal load scheduling algorithm is developed at the end-users’ premises to improve the profits in the LEM. Correspondingly, the trading strategies are extended to increase market reliability by penalizing participants for their abnormal activities in energy trading. The proposed framework is validated with different case studies considering ten residential participants in a locality.

A Novel Hybrid Harris Hawk-Arithmetic Optimization Algorithm for Industrial Wireless Mesh Networks

Abstract: A novel hybrid Harris Hawk-Arithmetic Optimization Algorithm (HHAOA) for optimizing the Industrial Wireless Mesh Networks (WMNs) and real-time pressure process control was proposed in this research article. The proposed algorithm uses inspiration from Harris Hawk Optimization and the Arithmetic Optimization Algorithm to improve position relocation problems, premature convergence, and the poor accuracy the existing techniques face. The HHAOA algorithm was evaluated on various benchmark functions and compared with other optimization algorithms, namely Arithmetic Optimization Algorithm, Moth Flame Optimization, Sine Cosine Algorithm, Grey Wolf Optimization, and Harris Hawk Optimization. The proposed algorithm was also applied to a real-world industrial wireless mesh network simulation and experimentation on the real-time pressure process control system. All the results demonstrate that the HHAOA algorithm outperforms different algorithms regarding mean, standard deviation, convergence speed, accuracy, and robustness and improves client router connectivity and network congestion with a 31.7% reduction in Wireless Mesh Network routers. In the real-time pressure process, the HHAOA optimized Fractional-order Predictive PI (FOPPI) Controller produced a robust and smoother control signal leading to minimal peak overshoot and an average of a 53.244% faster settling. Based on the results, the algorithm enhanced the efficiency and reliability of industrial wireless networks and real-time pressure process control systems, which are critical for industrial automation and control applications.