Transferable Adaptive Differential Evolution for Many-Task Optimization

The evolutionary multitask optimization (EMTO) algorithm is a promising approach to solve many-task optimization problems (MaTOPs), in which similarity measurement and knowledge transfer (KT) are two key issues. Many existing EMTO algorithms estimate the similarity of population distribution to select a set of similar tasks and then perform KT by simply mixing individuals among the selected tasks. However, these methods may be less effective when the global optima of the tasks greatly differ from each other. Therefore, this article proposes to consider a new kind of similarity, namely, shift invariance, between tasks. The shift invariance is defined that the two tasks are similar after linear shift transformation on both the search space and the objective space. To identify and utilize the shift invariance between tasks, a two-stage transferable adaptive differential evolution (TRADE) algorithm is proposed. In the first evolution stage, a task representation strategy is proposed to represent each task by a vector that embeds the evolution information. Then, a task grouping strategy is proposed to group the similar (i.e., shift invariant) tasks into the same group while the dissimilar tasks into different groups. In the second evolution stage, a novel successful evolution experience transfer method is proposed to adaptively utilize the suitable parameters by transferring successful parameters among similar tasks within the same group. Comprehensive experiments are carried out on two representative MaTOP benchmarks with a total of 16 instances and a real-world application. The comparative results show that the proposed TRADE is superior to some state-of-the-art EMTO algorithms and single-task optimization algorithms.

Data-driven multi-objective optimization for electric vehicle charging infrastructure

This paper presents a data-driven methodology combining simulation and multi-objective optimization to efficiently implement transportation policy commitments, using as a case study the electric vehicle (EV) charging infrastructure in Newcastle upon Tyne, United Kingdom. The methodology leverages a baseline simulation model developed by our industry partner, Arup Group Limited, to estimate EV demand and quantities from 2020 to 2050. Four future energy scenarios are considered, and a multi-objective optimization approach is employed to determine the optimal types, locations, and quantities of charging points, along with the corresponding total capital and operational expenditures and charging point operating hours. Quantitatively, the variations of the portions of different types of charging points for the four scenarios are relatively small and within 3% range of the total number of charging points. The optimal solutions put priority on the slower charging points, with faster charging points having smaller portions each around 10%-13%.

Enhanced QoS Routing Protocol for an Unmanned Ground Vehicle, Based on the ACO Approach

Improving models for managing the networks of firefighting unmanned ground vehicles in crowded areas, as a recommendation system (RS), represented a difficult challenge. This challenge comes from the peculiarities of these types of networks. These networks are distinguished by the network coverage area size, frequent network connection failures, and quick network structure changes. The research aims to improve the communication network of self-driving firefighting unmanned ground vehicles by determining the best routing track to the desired fire area. The suggested new model intends to improve the RS regarding the optimum tracking route for firefighting unmanned ground vehicles by employing the ant colony optimization technique. This optimization method represents one of the swarm theories utilized in vehicles ad-hoc networks and social networks. According to the results, the proposed model can enhance the navigation of self-driving firefighting unmanned ground vehicles towards the fire region, allowing firefighting unmanned ground vehicles to take the shortest routes possible, while avoiding closed roads and traffic accidents. This study aids in the control and management of ad-hoc vehicle networks, vehicles of everything, and the internet of things.