Although the EVRP (Electric Vehicle routing problem) has promising results on the environmental scale, its implementation has proved challenging. The difficulty of the EVRP resides in the limited driving range of the electric vehicles, combined with the significant charging time. While the charging cost is less than the cost of fuel, this charge time adds to the overall travel time and may overlap with customers’ time windows. All these factors increased the computational time exponentially and resulted in the need to overlook some constraints such as traffic congestion, road conditions, weather impact on energy consumption, and driving style, to name a few, in order to speed up execution time. While this method proved effective in accelerating the process of the EVRP, it did, however, render the approach unrealistic, as it steered far from real-life settings and made the approach unpredictable when facing dynamic and changing parameters. In this paper, we try to remedy this issue by proposing an approach in which we try to replicate real-life parameters such as heterogenous fleets, energy consumption, and infrastructure data. The objective of our approach was to minimize the total travel time, travel distance, energy consumed, and the number of vehicles deployed. To solve this problem, we propose a three-stages approach, in which the first stage consists of a newly developed dispatching approach where customers are assigned to vehicles. The second stage uses the genetic algorithm to find a set of optimal paths, and, finally, in the third stage, charging stations are inserted in the selected paths. Upon testing our approach on Solomon’s instances, our approach proved effective in finding optimal solutions in a reasonable time for five- to fifteen-customer datasets. However, when trying to solve larger datasets, the approach was slowed down by the extreme number of constraints it had to satisfy.

Aware of the nefarious effects of excessive exploitation of natural resources and the greenhouse gases emissions linked to building sector, the concept of smart buildings emerged, referring to a building that uses clean energy efficiently. This requires intelligent control systems to manage the use of residential energy consuming devices, namely the HVAC (Heating, Ventilation, Air-conditioning) system. This system consumes up to 50% of the total energy used by a building. In this paper, we introduce a RL (Reinforcement Learning) and MPC-LSTM (Model Predictive Control-Long-Short Term Memory) hybrid control system that combines DNNs (Deep Neural Networks), through RL, with LSTM’s long-short memory technique and MPC’s control characteristics. The goal of our model is to maintain thermal comfort of residents while optimizing energy consumption. Consequently, to train and test our model, we generate our own dataset using a building model of a corporate building in Casablanca, Morocco, combined with weather data of the same city. Simulations confirm the robustness of our model as it outperforms basic control methods in terms of thermal comfort and energy consumption especially during summer. Compared to conventional methods, our approach resulted in a 45.4% and 70.9% reduction in energy consumption, in winter and summer, respectively. Our approach also resulted in 26 less comfort violations during winter. On the other hand, during summer, our approach found a compromise between energy consumption and comfort with no more than 2.5 °C above ideal temperature limit.

This paper describes the benchmark dataset for the electric vehicle routing problem with time windows. It is designed to facilitate the large-scale and reproducible evaluation of routing approaches under diverse charging scenarios. It is an extension of the Homberger 1000-customer vehicle-routing benchmark dataset through the incorporation of computationally derived charging-station data. For the 60 base instances included in the dataset, charging-station locations are randomly generated within the customer-coordinate bounds, and two variants are provided, resulting in 120 benchmark problems used in the validation and baseline analyses. A normalized local customer-density score is derived for each station. It is used to determine charging rates and log-normal parameters for prices and waiting times. Two variants are included in the dataset. Variant A maintains the original customer time-window constraints, while Variant B relaxes customer due dates based on the distance from the depot, subject to the depot closing time. The dataset is complemented by instance files, station attributes, parameters, and scripts. It also includes the results of feasibility tests, baseline solver tests, difficulty analyses, and sensitivity tests. These results show that the benchmark includes both easier and harder instance classes under different charging settings. Overall, the dataset is intended to support its use as a reproducible benchmark.