Battery lifetime remains a central constraint in scaling LoRaWAN deployments across diverse IoT applications. We propose a lightweight dilated causal Convolutional Neural Network (CNN) designed to forecast per-node energy consumption with high temporal fidelity. Unlike recurrent models, our approach captures both transient spikes and long-range patterns without sequential overhead, enabling efficient edge deployment. Trained on a 12-month NS-3 simulation dataset encompassing smart lighting, environmental monitoring, waste management, and agriculture, the model achieves 96.5% forecasting accuracy with mean absolute error below 0.3, improving over SARIMA and LSTM baselines by 55% and 32% respectively. We integrate this predictor into an end-to-end energy optimization pipeline where on-device inference executes every 15 minutes with under 5 ms overhead. Forecasts drive adaptive duty-cycling, transmission slotting, and data rate control, extending device lifetime by 20%, halving collision rates, and improving fairness by 15%. Real-world validation on ten STM32F407VG microcontrollers and a commercial RAK7258 gateway confirms practical feasibility: inference completes within 0.8 ms with 4.4 mW peak power draw and 95.6% packet delivery ratio. These results demonstrate the CNN's suitability for real-time, edge-centric forecasting and its potential for enabling sustainable, intelligent LoRaWAN networks.

ABSTRACT During the early phases of software system development, error detection can be challenging due to the complexity of both the requirements and the operating environments. This paper advocates for the utilization of formal modelling and verification throughout the first phases of systems development to promptly detect and correct errors. The formalism employed throughout is Event‐B, which is backed by the Rodin toolset. To conquer requirements complexity, the frameworks of set theory and first‐order logic are employed, which provide the necessary tools for formalizing and analysing the properties and behaviours associated with Event‐B. Also, we detail the way in which modelling may be used to achieve abstraction, as well as the way in which refinement can be used to manage complexity through layering. Furthermore, we emphasize the significance of model validation and verification in improving the precision of formal models and requirements in IoT communication systems. The model is exemplified using a Content‐Based Publish Subscribe System (CBPS), with a special emphasis on a fire alarm system as a motivating example.

The Internet of Things (IoT) comprises a group of interconnected devices that communicate through the internet, necessitating a robust infrastructure and security protocols. Within this ecosystem, the Content-based Publish-Subscribe (CBPS) messaging paradigm enables devices to subscribe to specific data or events. However, as the number of messages transmitted increases, ensuring reliable transmission and accurate event matching becomes a challenging task. To tackle this issue, this study proposes an Event-B formal model for verifying the correctness of IoT CBPS communication. The model aims to guarantee that messages are delivered to the intended devices while ensuring the appropriate use of context information for filtering messages. Furthermore, the model's consistency has been verified using Event-B tools.

Abstract The verification of the Cloud composite services’ correctness is challenging. In fact, multiple component services, derived from different Cloud providers with different service description languages and communication protocols, are involved in the composition which may raise incompatibility issues that in turn lead to a non-consistent composition. In this work, we propose a formal approach to model and verify Cloud composite services. Four verification levels are considered in this article; the structural, semantic, behavioral, and resource allocation levels. Therefore, we opted for the Event-B formal method that enables complex problems decomposition thanks to its refinement capabilities. The proposed approach has proven its efficiency for the modelling and verification of Cloud composite services. The proposed model comprises four abstract levels with respect to the four verification axes. A proof-based approach is applied to the model’s verification. We also succeeded in the validation of the model thanks to the model animation provided by the PROB tool. The use of formal methods provides a rigorous reasoning and mathematical proofs on the correction of the model which ensures the elaboration of correct-by-construction composite services.

With the emergence of Service Component Architecture (SCA), all interests were focused on representing this architecture in a formal way in order to be able to prevent the specifications failures. In this context, our recent works were interested in formalizing structural properties of the SCA specifications, particularly in defining structural compatibility between connected services. In fact, verifying structural compatibility is necessary but not sufficient. In this paper we intend to represent, in a first step, the SCA behavioral properties by means of Event-B invariants and events. In a second step, we established behavioral compatibility between services interacting together which is considered as a delicate task and has a great importance in guaranteeing reliable communication between services. The consistency and the validity of the obtained model have been proved by the Event-B dedicated tools.

Service Component Architecture (SCA) is a set of specifications which describe a model for building applications and systems using a Service-Oriented Architecture (SOA). However, SCA in its current form does not represent any formal definition. In addition, there is a growing interest for verification techniques which help to prevent SCA composition specification failure. In this context, we intend to propose an Event-B based approach so as to configure the SCA composition dynamically. We focus, particularly, on the correctional dynamic such as substituting faulty services and components. The consistency and the validity of the obtained model have been proved by the Event-B dedicated tools.