The Advanced Metering Infrastructure (AMI) is one of the Smart Grid (SG) applications that used to upgrade the current power system by proposing a two-way communication system to connect the smart meter devices at homes with the electric control company. The design and deployment of an efficient routing protocol solution for AMI systems are considered to be a critical challenge due to the constrained resources of the smart meter nodes. IPv6 Routing Protocol for Low Power and Lossy Networks (RPL) was recently standardized by the IETF and originally designed to satisfy the routing requirements of lossy and low power networks like wireless sensors (WSN). We have two kinds of AMI applications, on one hand AMI based WSN and on the other hand AMI based PLC communication. In this paper, we proposed a real and simulated implementation of RPL behavior with proper modifications to support the AMI based WSN routing requirements. We evaluate RPL performance using 140 nodes from the wireless sensor testbed (IoT-LAB) and 1000 nodes using Cooja simulator measure RPL performance within medium and high-density networks. We adopted two routing metrics for path selection: First one is HOP Count (HC) and the second is Expected Transmission Unit (ETX) to evaluate RPL performance in terms of packet delivery ratio; network latency; control traffic overhead; and power consumption. Our results illustrate that routes with ETX calculations in low and medium network densities outperform routes using HC and the performance decreases as the network becomes dense. However, Cooja implementation results provides an average reasonable performance for AMI with high-density networks; still many RPL nodes suffering from high packet loss rates, network congestion and many retransmissions due to the selection of optimal paths with highly unreliable links.

In this paper, a Duty Cycling Centralized Hierarchical Protocol (DCCHP) has been proposed for wireless sensor networks. DCCHP is an energy efficient protocol that prolongs the lifetime of the network by applying a duty cycling mechanism named DCM that chooses the nodes that send unimportant data in a certain epoch to be candidates to be put to sleep. But if the proposed equations for choosing the cluster head nodes put any of them in a high priority it works in the active mode. When comparing DCCHP to the previously proposed LEACH-CS, LEACH-C protocols, using a simulation study, DCCHP in average extends the network lifetime 50% more than LEACH-CS and about 60% more than LEACH-C across a different number of nodes in the network scaled up to 1000 nodes. That is because DCCHP chooses the definite number of nodes of unimportant data to be switched to sleeping mode unlike LEACH-CS and unlike LEACH- C which keeps all nodes in active mode. Also an analytical study of energy consumption proves that DCCHP preserves energy consumption more than LEACH-CS and DCCHP. DCCHP has been proposed for applications with scarce resources.

In this paper, a Low-Energy Adaptive Clustering Hierarchy Centralized Sleeping Protocol (LEACH-CS) for wireless sensor networks has been proposed. LEACH-CS extends the lifetime of wireless sensor networks by proposing a mechanism that performs an intelligent choice of functioning nodes depending on the data sensed at the time being. If the data received from certain clusters appears insignificant in a period of time, these clusters are set to sleeping mode till the next data round. An algorithm named Intelligent Sleeping Mechanism (ISM) has been proposed for choice of nodes modes of functionality. When comparing LEACH-CS to the famous LEACH-C protocol through simulations, LEACH-CS succeeds in extending the lifetime of the network by on average 35% more than LEACH-C through network scaling and minimizing the end-to-end delay of data sending by an average 50% less than LEACH-C. LEACH-CS has been proposed for cultivation applications, where conditions may remain stable for a while and are not critical from onesecond to the other

The agricultural sector is still a major provider of many countries’ economies, but diseases that continuously infect plants represent continuous threats to agriculture and cause massive losses to the country’s economy. In this study, a lightweight convolutional neural network model called FL-ToLeD was proposed for tomato disease classification based on a soft attention mechanism with a depth-wise separable convolution layer. With a model size of 2.5 MB and 221,594 trainable parameters, FL-ToLeD achieved 99.5%, 99.10%, 99.04% for training, validation and testing accuracy respectively, and 99 % for each of precision, recall, and f1-score, it also achieved 99.90% for ROC-AUC with average inference time of 2.06924 μs. FL-ToLeD outperformed H. Ulutaş (2023) by 2.2% in terms of accuracy, precision, recall and f1-score. Additionally, it performed better than M. Agarwal (2023), Abbas (2021), and S. Verma (2020) in terms of accuracy, precision, recall, and f1-score by 8%, 2%, and 6%, respectively. It also outperformed Arshad (2023) by 4.77%, 8.92%, 35.18% and 5.11% in terms of accuracy, precision, recall and f1-score, respectively. Furthermore, FL-ToLeD is 90 times smaller than S. Verma (2020) and 2.5 times smaller than H. Ulutaş (2023) in terms of model size. All this makes FL-ToLeD more suitable for low-end devices in precision agriculture.

In this paper, a multilevel minimised delay clustering protocol (MMDCP) is proposed. MMDCP is proved to extend the lifetime of wireless sensor networks through levelling and through a better choice of cluster heads. MMDCP assigns the number of the lower level cluster heads and the leaf nodes in the network so as to minimise the end-to-end delay. When comparing MMDCP to LEACH-C, THCHP and Delay-Aware protocols; MMDCP succeeds in extending the lifetime of the network and in minimising the end-to-end delay and also in increasing throughput values. MMDCP also improves the structure of the network of delay-aware protocol. Two radio models are used in evaluation, the first order radio model and the discrete radio model. The obtained results are proved analytically and via simulation. These results make the proposed protocol a very good candidate for use in crises management applications like pre-expectation of landslides and early control of slum fires.