The Industrial Internet of Things (IIoT) has revolutionized industrial automation, enabling real-time monitoring and intelligent decision-making. However, the increasing connectivity of IIoT devices exposes them to cyber threats, necessitating robust Intrusion Detection Systems (IDS). Traditional centralized IDS solutions face concerns regarding sharing of sensitive data, high computational costs, and communication overhead. Federated Learning (FL) provides a privacypreserving alternative to such centralized systems. However, existing FL-based IDS frameworks may face challenges such as high resource consumption and privacy threats such as gradient leakage from shared updates. To address these challenges, we propose Robust Optimization for Encrypted Federated Learning (ROCHE), a lightweight FL-based IDS optimized for IIoT, ensures data privacy and efficiency. ROCHE uses low-degree polynomial approximations to replace complex activation functions, reducing computational load without significantly impacting accuracy. An adaptive quantization mechanism is utilized to reduce bandwidth consumption while ensuring accurate model convergence. To preserve data privacy during model aggregation, ROCHE integrates symmetric homomorphic encryption, enabling secure model updates while maintaining resilience to user dropout. Comprehensive security analysis and experiments demonstrate that ROCHE outperforms state-of-the-art frameworks. Compared to MiTFed, ROCHE reduces computational overhead by 11% and lowers communication cost by 16%, demonstrating its efficiency in optimizing resource utilization while maintaining robust privacy preservation in FL based IDS. Additionally, ROCHE maintains an average accuracy of over 90% across multiple attack types. Deployment in a cloud-based IIoT environment demonstrates its feasibility, establishing ROCHE as a scalable and efficient IDS for IIoT security.

Wireless Sensor Networks (WSNs) provide noteworthy advantages over conventional methods for various real-time applications, i.e., healthcare, temperature sensing, smart homes, homeland security, and environmental monitoring. However, limited resources, short life-time network constraints, and security vulnerabilities are the challenging issues in the era of WSNs. Besides, WSNs performance is susceptible to network anomalies, particularly to misdirection attacks. The above-mentioned issues pose our attentions to produce a security-aware application. In this work, therefore, we present a Reinforcement Learning (RL) algorithm for Misdirection Attack Detection and Prevention (RL-MADP) in WSNs. In our proposed approach, other than the flat architecture configuration for WSN, Markov Decision Process (MDP) from RL is considered. Where, each sensor node is fully aware of its environment. It is an online method and incurs minimal computation cost, and performs load-balancing with higher residual energy to prolong the network lifetime.

The 5th generation (5G) of communication networks will facilitate innovative and emerging services and applications having lower latency requirements, increased energy efficiency and reliability. These characteristics of 5G make it capable to act as a potential underlying network for smart city services such as for implementation of demand response in smart grids. More specifically, in terms of demand response, these low latency networks are used for the explicit exchange of messages between utility companies and customers for pricing mechanisms. According to the time to use (ToU) pricing scheme, consumers are offered a specific electricity price for each time interval i.e., off-peak, on-peak and mid-peak blocks. Unlike high energy consumers (HECs), low energy consumers (LECs) are not the reason of high peaks (on-peaks) formation; however, they pay higher rates to the utility during on-peak hours because of one price for all rule. Here, one price for all makes ToU an unjustified pricing scheme. This issue is discussed in this study and a fair pricing scheme is proposed to remove undue financial burden from LECs. The proposed fair pricing scheme (FPS) is based on energy consumption of each category customer. LECs and HECs pay the electricity bill exactly according to their electricity consumption and no one has to bear the financial load of others. Simulation results show that LECs are able to save up to 11.0075% of their total electricity bill. HECs has to pay the penalty of high energy consumption whereas, the utility company is not affected by the implementation of the proposed fair pricing scheme.

Data collection and transmission are the fundamental operations of WSNs. The performance of WSNs relies upon these essential tasks because data gathering directly affects the efficiency and lifetime of WSNs. This paper presents a data volume based data collection technique using Mobile Data Collector (MDC). In this technique, the MDC uses data volume information to plan visits to the nodes. The MDC visits only those nodes which have generated data while the rests of the nodes are ignored. This scheme is validated with the help of simulations, and the results are compared with existing renowned techniques. The results show that the proposed scheme is energy efficient.