• Growing offshore wind farms need efficient inspection; exploring digital solutions. • Framework: UAV dock and recharge on USV, addressing power issues. • 45-min UAV flight needs 90-min charge, affecting inspection scheduling. • Optimisation model and Bees metaheuristic optimise USV routes and UAV schedules. The increasing size and scope of offshore wind farms drive the need for industry to reduce costs through more efficient daily operations, including inspection. Most recently, Unmanned vehicles have been investigated in conjunction with digital platform technologies to improve the efficiency and safety of inspection tasks. In this paper, we propose an Unmanned Aerial Vehicles (UAVs) swarm-Unmanned Surface Vessels (USVs) framework that combines automated USVs with a swarm of UAVs for the inspection of wind farms, addressing the insufficient power of UAVs to sustain flight and communication throughout the entire mission. Once the UAV’s battery is depleted, no signals are transmitted, and the communications become intermittent. The automated USVs carry the docking recharging station for the UAV swarm to be recharged on the USVs. Furthermore, the fact that a 45-minute UAV operation requires a 90-minute charging time complicates the scheduling task of maintaining the inspection as a continuous process. This sophisticated inspection framework requires an efficient USV routing and UAV swarm scheduling for the inspection of wind farms. We have developed a deterministic optimisation model and a multi-stage Bees metaheuristic to generate the optimal USV routes to transport the UAV swarms to the wind farm and schedule them to operate the inspection of the wind turbines. We evaluate the proposed algorithm’s performance by comparing the solutions generated with Gurobi optimisation software, adapted Genetic Algorithm (GA), adapted Particle Swarm Optimisation (PSO) and adapted Combinatorial Bees Algorithm (CBA), demonstrating improvements in the solution quality of up to 1.79%, 2.58%, 3.07% and 1.93% respectively. Note that the study does not address the actual inspection procedure or real-world deployment challenges.

The study proposes using five benchmark machine-learning models alongside XGBoost, applied for the first time to an existing case study to predict the success of suicide of terrorist attacks. Utilizing data from the Global Terrorism Database (GTD), the study evaluates model effectiveness to aid decision-making for emergency responders and policymakers. Employing explainable Artificial Intelligence (XAI) models like SHAP ensures transparent decision-making processes. XGBoost performed best for accuracy and performance, while LightGBM excelled in explainability, with SHAP providing global and local insights into their decision-making. The primary goal is to enhance user comprehension and facilitate informed decision-making in critical scenarios, prioritizing transparency, and trustworthiness.

This paper presents the first published application of multiple existing machine learning methods to a subset of features taken from the Profiles of Individual Radicalization in the United States (PIRUS) database to predict the feature ‘violent’. The best-performing model in terms of accuracy is the Hist Gradient Boosting model, with an accuracy of 89.06%, which is an improvement of more than 2.5% compared to the benchmark application. Permutation Feature Importance (PFI) and the explanation framework SHAP were then applied to explain the model predictions. Using both of these techniques together allows for a holistic view of both the model's inner workings and the impact of the features on the results.

This paper proposes tackling the difficult course timetabling problem using a multi-agent approach. The proposed design seeks to deal with the problem using a distributed solution environment in which a mediator agent coordinates various timetabling agents that cooperate to improve a common global solution. Initial timetables provided to the multi-agent system are generated using several hybrid heuristics that combine graph colouring heuristics and local search in different ways. The hybrid heuristics are capable of generating feasible timetables for all instances of the two sets of benchmark problems used here. We discuss how these initialisation hybrid heuristics can be incorporated into the proposed multi-agent approach in order to conduct distributed timetabling. This preliminary work serves as a solid basis towards the design of an effective multi-agent distributed timetabling system.

In recent years, hyper-heuristics have emerged as a new search methodology that is motivated by the goal of increasing the level of generality of meta-heuristics. In this paper, we aim at investigating the role of cooperative decision making in the selection process of low level heuristics. We propose a novel cooperative distributed hyper-heuristic framework. The cooperative distributed hyper-heuristic framework is an agent-based system composed of a Hyper-Heuristic Agent (HHA) and a number of Low Level Heuristic Agents (LLHA). The HHA is in charge of the selection of the low level heuristic to apply at a decision point in the search process. The LLHAs search synchronously through the same solution space, starting from the same solution and using different low level heuristics. We conducted several experiments, using the permutation flow shop benchmark instances, to investigate the performance of the developed cooperative distributed hyper-heuristic approaches.

This paper considers the problem of grid scheduling in which different jobs are assigned to different processors, and a scheduling algorithm is devised, using tabu search, to find optimal solutions in order to maximize the number of scheduled jobs. However, inherent in the nature of the application, the processing times of jobs are not precise but are estimates that vary between minimal values, in case of premature failure of jobs, to maximal values as specified 'a priori' by well-experienced users. Fuzzy methodology becomes instrumental in this application as it allows the use of fuzzy sets to represent the processing times of jobs, modelling their uncertainty. This work presents the implementation of a tabu search algorithm to create good schedules and explores the robustness of the schedule when processing times do vary by assessing its performance in both fuzzy and crisp modes. Finally, the impact of changing the shapes of fuzzy completion times and the average job length on the schedule performance is discussed.

This paper describes an intelligent distributed monitoring architecture for flexible manufacturing systems (FMS) based on the multi-agent paradigm. The proposed approach models the FMS by a society of cognitive agents, which monitor a set of heterogeneous resources. These agents have sufficient knowledge for the decision-making and they co-operate together in order to achieve the FMS monitoring functions. The originality of this approach resides in the total distribution of the monitoring functions over the agents and the co-operation of these agents by the contract net protocol for the real-time supervision. These characteristics improve flexibility, extensibility, real-time running, autonomy, fast reaction to faults, and development cost. Experimental results developed in simulation show the feasibility and the potentialities of the proposed multi-agent architecture for distributed monitoring where concepts such us flexibility, co-ordination, reactivity and integration are involved.

Deals with a multi-agent architecture and a negotiation protocol for the dynamic scheduling of flexible manufacturing systems. The originality of the multi-agent architecture resides in the existence of task agents and resource agents. The multi-contract net protocol proposed, is an innovation with regard to the contract-net protocol due to the way that it makes it possible to negotiate several tasks concurrently, in real time and with more optimal results taking into account uncertainty and conflict situations in the scheduling of operations. The paper, also, stresses the efficiency and the optimality of the distributed implementation.

Describes an intelligent real time cell control architecture for flexible manufacturing systems. This architecture is based on the multi-agent concept of the distributed artificial intelligence. We propose an actor architecture. This multi-agent prototype system involves the following functions: scheduling, dispatching, monitoring and error handling. A new contract protocol for dynamic scheduling is presented. The purpose of this protocol is to dynamically assign operations to the resources of the manufacturing system in order to accomplish the proposed tasks. This protocol is able to deal with exceptions.