Limited Battery Capacity Research Articles

Silencing eavesdroppers: SVM unveiling physical layer threats

Frothy Disturbance Intrusion Detection Systems (FIDS) can help detect and prevent security attacks using the Support Vector Machine (SVM) algorithm. Recognizing the importance of FIDS in protecting various domains linked to the internet, focus lies on adapting traditional intrusion detection methods for the landscape, which faces challenges such as resource constraints and limited memory and battery capacity. This study entails the creation of a lightweight attack detection technique that utilizes a supervised machine learning-based FIDS using the SVM algorithm. Simulations are used to demonstrate the usefulness of the proposed SVM-based FIDS classifier, which employs a combination of two or three complex features and achieves satisfactory classification accuracy and detection time. This strategy has the ability to enhance application security by effectively addressing the particular.

Stretchable and biodegradable plant-based redox-diffusion batteries.

The redox-diffusion (RD) battery concept introduces an environmentally friendly solution for stretchable batteries in autonomous wearable electronics. By utilising plant-based redox-active biomolecules and cellulose fibers for the electrode scaffold, separator membrane, and current collector, along with a biodegradable elastomer encapsulation, the battery design overcomes the reliance on unsustainable transition metal-based active materials and non-biodegradable elastomers used in existing stretchable batteries. Importantly, it addresses the drawback of limited attainable battery capacity, where increasing the active material loading often leads to thicker and stiffer electrodes with poor mechanical properties. The concept decouples the active material loading from the mechanical structure of the electrode, enabling high mass loadings, while retaining a skin-like young's modulus and stretchability. A stretchable ion-selective membrane facilitates the RD process, allowing two separate redox couples, while preventing crossovers. This results in a high-capacity battery cell that is both electrochemically and mechanically stable, engineered from sustainable plant-based materials. Notably, the battery components are biodegradable at the end of their life, addressing concerns of e-waste and resource depletion.

An electric vehicle routing model with charging stations consideration for sustainable logistics

PurposeRecently, electric vehicles have been widely used in the cold chain logistics sector to reduce the effects of excessive energy consumption and to support environmental friendliness. Considering the limited battery capacity of electric vehicles, it is vital to optimize battery charging during the distribution process.Design/methodology/approachThis study establishes an electric vehicle routing model for cold chain logistics with charging stations, which will integrate multiple distribution centers to achieve sustainable logistics. The suggested optimization model aimed at minimizing the overall cost of cold chain logistics, which incorporates fixed, damage, refrigeration, penalty, queuing, energy and carbon emission costs. In addition, the proposed model takes into accounts factors such as time-varying speed, time-varying electricity price, energy consumption and queuing at the charging station. In the proposed model, a hybrid crow search algorithm (CSA), which combines opposition-based learning (OBL) and taboo search (TS), is developed for optimization purposes. To evaluate the model, algorithms and model experiments are conducted based on a real case in Chongqing, China.FindingsThe result of algorithm experiments illustrate that hybrid CSA is effective in terms of both solution quality and speed compared to genetic algorithm (GA) and particle swarm optimization (PSO). In addition, the model experiments highlight the benefits of joint distribution over individual distribution in reducing costs and carbon emissions.Research limitations/implicationsThe optimization model of cold chain logistics routes based on electric vehicles provides a reference for managers to develop distribution plans, which contributes to the development of sustainable logistics.Originality/valueIn prior studies, many scholars have conducted related research on the subject of cold chain logistics vehicle routing problems and electric vehicle routing problems separately, but few have merged the above two subjects. In response, this study innovatively designs an electric vehicle routing model for cold chain logistics with consideration of time-varying speeds, time-varying electricity prices, energy consumption and queues at charging stations to make it consistent with the real world.

Climate systems of urban electric buses

This article considers the climate systems of urban electric buses from different manufacturers, as well as presents and compares their characteristics and diagrams. Climate systems with two vapor compression refrigeration machines, a dependent evaporator of the driver’s cabin, and a chiller-fan coil circuit are analyzed, the existing domestic microclimate system for an electric bus is considered, and the advantages and disadvantages of these systems are presented. The influence of the features of electric buses, such as the limited battery capacity and absence of an internal combustion engine as a heat source, on the concept and design features of their microclimate systems is shown. The features of climate systems for electric buses intended for operation in the territory of the Russian Federation are considered, including the following technical requirements of organizations operating city electric buses: dual-zone climate control, i.e., separately for the passenger salon and driver’s cabin, and the possibility of using an auxiliary heater operating by burning diesel fuel only at ambient temperatures below 0 ℃ and at relatively low ambient temperatures during the cold season. The review conducted in this article aims to identify ways to further improve the climate systems of urban electric buses and demonstrate the various criteria when comparing them and assessing their efficiency.

DRL-Based Computation Offloading and Resource Allocation in Green MEC-Enabled Maritime-IoT Networks

The maritime Internet of Things (MIoT), a maritime version of the Internet of Things (IoT), is envisioned as a promising solution that can provide ubiquitous connectivity over land and sea. Due to the rapid development of maritime activities and the maritime economy, there is a growing demand for computing-intensive and latency-sensitive maritime applications requiring various energy consumption, communication, and computation resources, posing a significant challenge to MIoT devices due to their limited computational ability and battery capacity. Mobile Edge Computing (MEC), which can handle computation tasks at the network’s edge more efficiently and with less latency, is emerging as a paradigm for fulfilling the ever-increasing demands of MIoT applications. However, the exponential increase in the number of MIoT devices has increased the system’s energy consumption, resulting in increased greenhouse gas emissions and a negative impact on the environment. As a result, it is vital for MIoT networks to take traditional energy usage minimization into account. The integration of renewable energy-harvesting capabilities into base stations or MIoT devices possesses the potential to reduce grid energy consumption and carbon emissions. However, making an effective decision regarding task offloading and resource allocation is crucial for maximizing the utilization of the system’s potential resources and minimizing carbon emissions. In this paper, we first propose a green MEC-enabled maritime IoT network architecture to flexibly provide computing-intensive and latency-sensitive applications for MIoT users. Based on the architecture, we formulate the joint task offloading and resource allocation problem by optimizing the total system execution efficiency (including the total size of completed tasks, task execution latency, and the system’s carbon emissions) and then propose a deep-deterministic-policy-gradient-based joint optimization strategy to solve the problem, eventually obtaining an effective resolution through continuous action space learning in the changing environment. Finally, simulation results confirm that our proposal can yield good performance in system execution efficiency compared to other benchmarks; that is, it can significantly reduce the system’s carbon emissions and tasks’ delay and improve the total size of completed tasks.

Efficient Multi-UAV Assisted Data Gathering Schemes for Maximizing the Operation Time of Wireless Sensor Networks in Precision Farming

Measurement data from wireless sensors deployed in large agricultural areas could be used to help the automation of precision farming activities like irrigation management, fertilization, etc. The widespread use of sensors with limited battery capacity in precision farming largely depends on data collection methods that reduce the energy consumption of transmitting measurement data and prolong the battery run time. In this paper, we investigate joint clustering and multi-UAV-assisted data-gathering schemes to save the energy consumption of sensors. We establish a theoretical lower bound for the energy consumption of sensors to transport data to cluster heads and prove that the energy consumption of sensors approaches the theoretical lower bound if clusters are balanced regarding energy consumption. Therefore, the essential step of proposed heuristic multi-UAV schemes, called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Gathering data Assisted by Multi-UAV with a BAlanced Clustering</i> (GAMBAC), is to find balanced or near-balanced clusters concerning energy consumption. For sensor networks with a small number of nodes our heuristic algorithms give results close to the ones obtained by the reference solution. Numerical results show that the GAMBAC schemes extend network lifetime and requires less energy to support a specific number of collection rounds than the best existing approach. Numerical results show that the GAMBAC schemes extend network lifetime and requires less energy to support a specific number of collection rounds than the best existing approach. Therefore, the GAMBAC algorithms could enhance the reliable data collection of sensor networks for precision farming.

High Performance Rotating Triboelectric Nanogenerator with Coaxial Rolling Charge Pump Strategy.

With the development of society and the advancement of technology, the emergence of the Internet of Things (IoT) has changed people's lifestyles and raised the demand for energy to a new level. However, there are some drawbacks in terms of energy supply for IoT sensors, such as limited battery capacity and limitations in replacement and maintenance. Therefore, it has become urgent to develop a sustainable green energy source (wind energy) using the surrounding environment. Meanwhile, triboelectric nanogenerators (TENGs) with advantages such as flexible structure, low manufacturing cost, and environmental friendliness provide enormous potential for constructing self-powered sensing systems. In this work, we present a novel coaxial rolling charge pump TENG (CR-TENG) based on wind energy to enhance the output performance and durability. The rolling friction charge pump TENG directly injects positive and negative charges into the main TENG, which is more wear-resistant compared to sliding friction, and greatly increases the charge density and output power. In addition, the charge pumping part and the main TENG adopt the coaxial design, reducing the complexity of the structural design. On comparing the output performance of the CR-TENG under the initial state, rectifier bridge supplemental charge strategy, and charge pump supplemental charge strategy, results shown that the output voltage performance of the CR-TENG can be improved by 5800% under the charge pump supplemental charge strategy. Moreover, the output performance of the CR-TENG remains stable after 72,000 cycles. The output power of the CR-TENG can reach 1.21 mW with a load resistance of 3 × 107 Ω. And the CR-TENG can charge a 0.1 μF capacitor to 5 V in just 1.6 s. This work provides new insights for the rotary durable high output charge pump compensating a triboelectric nanogenerator and demonstrates the important potential of harvesting environmental energy to supply intelligent IoT nodes.

Powering Implanted Devices Wirelessly Using Spider-Web Coil

Implantable biomedical (IBM) systems and biomedical sensors can improve life quality, identify sickness, monitor biological signs, and replace the function of malfunctioning organs. However, these devices compel continuous battery power, which can be limited by the battery's capacity and lifetime, reducing the device's effectiveness. The wireless power transfer (WPT) technique, specifically magnetic resonator coupling (MRC), was utilized to address the limited battery capacity of IBMs. By using WPT–MRC, the device can obtain power wirelessly, thereby reducing the need for frequent battery replacements and increasing the device's potential. In this research, spider-web coil (S-WC) based MRC–WPT was conceived and carried out experimentally to enhance low-power IBM's rechargeable battery usage time. The presented S-WC–MRC–WPT design uses series–parallel (S–P) configuration to power the IBM. Both transmitter and receiver coils exhibit an operating oscillation frequency of 6.78 MHz. The paper reports on experiments performed in the laboratory to assess the performance of the proposed design in terms of output DC at three different resistive loads and transmission distances with alignment conditions among the receiver and the transmitter coils. Various transfer distances ranging from 10 to 100 mm were investigated to analyze the DC output current (Idc). Specifically, under a 30 V voltage source (VS) and a transfer distance of 20 mm, the DC output current was observed to be 330, 321, and 313 mA at resistive loads of 50, 100, and 150 Ω, respectively.

Joint trajectory design and spectrum allocation for unmanned aerial vehicle task efficiency

AbstractIn unmanned aerial vehicle (UAV)‐assisted wireless sensor networks (WSNs), UAVs are employed to collect sensing data from each sensor node (SN). Because of limited battery capacity, shortening the time of data collection by the UAV is necessary. Notably, the task completion time is related to UAV trajectory and spectrum allocation. In this paper, joint trajectory design and spectrum allocation is studied to minimize the task completion time of UAVs while ensuring the target upload data amount for each SN. The cases that all SNs are located within the communication range of a UAV is explored first; the formulated problem is non‐convex and difficult to solve directly. Hence, an iterative algorithm based on block coordinate descent and successive convex approximation is proposed to decompose and transformed the original problem into two convex optimizations. Furthermore, the proposed algorithm is applied to the general case that all SNs are widely distributed by leveraging the spiral algorithm and traveling salesman problem technique. Simulation results show that the proposed algorithm can effectively reduce the task time of UAV compared to other benchmark algorithms.

Efficient self-driving control for lead vehicle following in a mixed traffic environment

Autonomous control for vehicles is rapidly developed since it not only improves the mixed traffic flow but also decreases the traffic accidents and the energy consumption. Especially self-driving technology has been attention since it progressively plays an important role in prompting comport driving condition as well as safety. In addition, eco-driving strategy is considered as the energy efficient driving technology of electric vehicles (EVs) since the eco-driving can increase the fuel economy of the limited power capacity of battery. This research introduces an energy efficient EVs control strategy with Model predictive control (MPC) and deep neural networks (DNN). MPC and DNN are combined to solve the optimal problem that is to minimize battery consumption and maximize the energy efficiency during self-driving. The estimated vehicle state information by DNN and the ratio of power consumption at the previous state are fed into the next state information of the MPC controller. Thus, the controller can optimize the energy consumption ratio with respect to the state values such as the vehicle state and the battery state of charge. The hybrid control algorithm was evaluated using PGDrive which is a virtual vehicle driving environment, and simulation results showed that the MPC controller with DNN can efficiently reduce the battery consumption and increase the energy efficient up to 1.7%.

Battery-powered automated guided vehicles scheduling problem in automated container terminals for minimizing energy consumption

Battery-Powered Automated Guided Vehicles (B-AGVs) are important equipment used to transfer containers between the seaside and the landside in automated container terminals. Due to their limited battery capacity, the B-AGVs require battery recovery when their battery reaches the threshold. However, the processing capacity of electrical battery swapping stations is limited, it is crucial to avoid congestion in swapping station. Considering that the scheduling problem of B-AGV in the terminal is time intensive, this paper proposes a set partitioning method based on breadth-first and depth-first search to solve the established mixed integer programming model. Combined with the operational characteristics of the terminal, this paper adopts the flexible pooling strategy to effectively matches the inbound and outbound containers to form dual-cycle operation of B-AGVs, which can reduce the computational complexity and thus improving the solution efficiency. In addition, the record-to-record travel algorithm is applied to improve the quality of the solution. Finally, the effectiveness of the proposed model and solution method is evaluated through numerical experiments. Besides, the applicability of the flexible pooling strategy to different container terminals is studied, and the impact of the number of B-AGVs and the capacity of swapping stations on the energy consumption of B-AGVs is investigated, and some managerial insights are given accordingly.

Soft Actor–Critic-Based Computation Offloading in Multiuser MEC-Enabled IoT—A Lifetime Maximization Perspective

This paper studies the network lifetime optimization problem in a multi-user mobile edge computing (MEC)-enabled Internet of things (IoT) system comprising an access point (AP), a MEC server, and a set of K mobile devices (MDs) with limited battery capacity. Considering the residual battery energy at the MDs, stochastic task arrivals, and time-varying wireless fading channels, a soft actor-critic (SAC)-based deep reinforcement learning (DRL) lifetime maximization, called DeepLM, is proposed to jointly optimize the task splitting ratio, the local CPU-cycle frequencies at the MDs, the bandwidth allocation, and the CPU-cycle frequency allocation at the MEC server subject to the task queuing backlogs constraint, the bandwidth constraint, and maximum CPU-cycle frequency constraints at the MDs and the MEC server. Our results reveal that DeepLM enjoys a fast convergence rate and a small oscillation amplitude. We also compare the performance of DeepLM with three benchmark offloading schemes, namely, fully edge computing (FEC), fully local computing (FLC), and random computation offloading (RCO). DeepLM increases the network lifetime by 496% and 229% compared to the FLC and RCO schemes. Interestingly, it achieves such a colossal lifetime improvement when its non-backlog probability is 0.99, while that of FEC, FLC, and RCO is 0.69, 0.53, and 0.25, respectively, showing a significant performance gain of 30%, 46%, and 74%.

An Enhanced Backtracking Search Algorithm for the Flight Planning of a Multi-Drones-Assisted Commercial Parcel Delivery System

Using drones to carry out commercial parcel delivery can significantly promote the transformation and upgrading of the logistics industry thanks to the saving of human labor source, which is becoming a new component of intelligent transportation systems. However, the flight distance of drones is often constrained due to the limited battery capacity. To address this challenge, this paper designs a multi-drones-assisted commercial parcel delivery system, which supports long-distance delivery by a generalized service network (GSN). Each node of the GSN is equipped with charging piles to provide a charging service for drones. Given the limited number of charging piles at each node and the limited battery capacity of a drone, to ensure the efficient operation of the system, the flight planning problem of drones is converted into a large-scale optimization problem by a priority-based encoding mechanism. To solve this problem, an enhanced backtracking search algorithm (EBSA) is reported, which is inspired by the characteristics of the considered flight planning problem and the weak ability of the backtracking search algorithm to escape from a local optimum. The core components of EBSA are the designed comprehensive learning mechanism and local escape operator. Experimental results prove the validity of the improved strategies and the excellent performance of EBSA on the considered flight planning problem.

Aeroacoustic and aerodynamic measurements of a ducted propeller

The flexibility and wide range of possible applications in both civilian and military areas make unmanned aerial vehicles (UAVs) an object of continuous research. An important focus of such work is the propulsion system and ways of improving its efficiency. A ducted propeller is a common solution to increase the thrust and power efficiency of the propulsion system, which is especially beneficial for UAVs driven by electric motors due to their limited battery capacity; however, noise created by UAVs can not only annoy the public but may also reduce its acoustic stealth. Hence, the aim of this paper is to describe a test rig that can take aeroacoustic and aerodynamic measurements of both ducted and open propellers and present some initial experimental results. Both aeroacoustic and aerodynamic measurements were taken in an anechoic chamber with an arc of 6 ½ in. microphones to record noise level from different directions. The APC 12 × 8 propeller was used together with the SunnySky x2820 brushless motor.

Incentive Mechanism and Resource Allocation for Collaborative Task Offloading in Energy-Efficient Mobile Edge Computing

We investigate a mobile edge computing (MEC) system that supports collaborative task offloading, allowing busy users to offload their tasks to the server and idle users, or perform them locally. However, executing computing tasks consumes device energy, making idle users unwilling to perform other users' tasks due to limited battery capacity. Additionally, the components of the total energy expenditure of the MEC system supporting collaborative task offloading are complex, necessitating appropriate resource allocation and offloading strategies to minimize the system's total energy consumption. To address these challenges, we propose a computing resource sharing auction (CRSA) algorithm to motivate idle users to participate in task offloading. Then, we establish a non-convex mixed-integer nonlinear programming (MINLP) problem to minimize the total energy consumed by the system. By utilizing the McCormick and continuous relaxation (CR) approaches, we develop a low-complexity resource allocation algorithm. Finally, the numerical results demonstrate the effectiveness of the proposed mechanism and resource allocation algorithm.

Secure and Energy-Based STEERA Routing Protocol for Wireless Sensor Networks

In wireless sensor networks (WSN), the multifunctional low-power sensor nodes are linked to base stations and are highly responsible for sensing various information. However, maintaining the network’s lifespan is a major issue because of limited battery capacity and node failures. Thus, the proposed study introduced a new Scalable Trust-based Energy Efficient Routing Algorithm (STEERA) with Adaptive Grasshopper Algorithm (AGA) to enhance the network lifespan. At first, the trust values (Tv) are generated for each node to eliminate the malicious node with the help of penalty factor and volatilization. To make efficient routing process, the nodes are formed into cluster groups. A suitable cluster head is selected for each cluster to mitigate the energy consumption problem through the AGA approach by optimizing the parameters like Tv, distance and residual energy. Finally, the data packets are effectively transmitted through a multi-hop routing process by selecting an appropriate path and satisfying certain parameters through Fire Hawks Optimization (FHO). To simulate the proposed techniques, NS2 software is employed, and the performance is measured over various metrics like energy consumption, residual energy, the lifespan of a network, packet loss ratio and average end-to-end delay. The performance analysis shows that the proposed protocol design has obtained higher results than conventional routing protocols.

Automated Guided Vehicle (AGV) Scheduling in Automated Container Terminals (ACTs) Focusing on Battery Swapping and Speed Control

Because they are environmentally friendly and safe, automated guided vehicles (AGVs) are increasingly used in newly constructed automated container terminals. However, their scheduling strategy is constrained by their limited battery capacity. When batteries reach their charging threshold, the AGVs need to be returned to battery-swapping stations. Moreover, the movement speed of AGVs has a significant impact on their energy consumption and operating times. Therefore, in this paper, a speed control strategy that considers the traffic environment of the terminal is proposed from the perspective of energy conservation and emission reduction. In addition, the charging capacity of the terminal is discretized to model its limited handling capacity to avoid congestion in the battery-swapping stations. To minimize the costs of delays and carbon emissions of AGV operations, a mixed integer programming model is established. It optimizes the efficiency and carbon emissions of the operations by assigning and prioritizing container transportation and AGV battery-swapping tasks. An improved genetic algorithm-based approach is designed where a better initial solution is obtained through a greedy strategy, while simulated annealing is adopted for population selection to prevent the algorithm from falling into local optima. Furthermore, an adaptive adjustment strategy for crossover and mutation probabilities is adopted to improve the algorithm’s convergence. Finally, a series of numerical experiments is conducted to verify the efficiency of the proposed method. The experimental results indicate that considering the variability of AGV speed can more accurately characterize their energy consumption, and increasing the number of AGVs and enhancing the battery-swapping capacity can effectively reduce the costs of delays and carbon emissions.

A double-adaptive general variable neighborhood search for an unmanned electric vehicle routing and scheduling problem in green manufacturing systems

In recent years, more and more manufacturing factories have employed unmanned electric vehicles (UEVs) to perform the materials delivery, and efficient routing and scheduling approaches are required to improve the delivery efficiency. However, most of existing papers studied the routing problem of fuel vehicles or the drones. This paper investigates the optimization of UEVs delivery routes and charging strategies. Due to the limited payload capacity and battery capacity, the UEV must return to the depot multiple times to load the materials and go to the recharging station during the route to charge, and thus the problem is modeled as a multi-trip UEV routing and scheduling problem, which assigns the recharging station to the UEV’s route and optimizes a set of UEV’s trips. The investigated problem is firstly formulated as a mixed integer programming model. Then, considering the routing and scheduling challenges, we develop an efficient double-adaptive variable neighborhood search (DA-GVNS), which incorporates the general variable neighborhood search with a new adaptive mechanism, for this problem. The experimental results on the test and benchmark instances highlight that the DA-GVNS outperforms other existing algorithms. Furthermore, sensitivity analyses are conducted to study the impact of model’s characteristics on the optimality and complexity of solutions. Finally, a case study is proposed to present how the developed approach works for a manufacturing factory. This paper can offer decision-makers a valuable approach to construct a high-quality routing and scheduling scheme for the UEV delivery while providing potential managerial insights for implementing efficient green manufacturing systems.

A Long-Distance First Matching Algorithm for Charging Scheduling in Wireless Rechargeable Sensor Networks

In large wireless rechargeable sensor networks (WRSNs), the limited battery capacity of sensor nodes and finite network lifetime are commonly considered as performance bottlenecks. Previous works have employed wireless mobile vehicles (vehicles) to charge sensor nodes (nodes), but they face limitations in terms of low speed and offroad terrain. The rapid development of wireless charging drones (drones) brings a new perspective on charging nodes; nevertheless, their use is limited by small capacity batteries and cannot cover large regions alone. Most existing works consider the charging of nodes only with vehicles or drones. However, these solutions may not be robust enough, as some nodes’ energy will have run out before vehicles’ or drones’ arrival. Considering the merits and demerits of vehicles and drones comprehensively, we propose a novel WRSN model whose charging system integrates one vehicle, multiple drones and one base station together. Moreover, a charging strategy named long-distance first matching (LDFM) algorithm to schedule the vehicle and multiple drones collaboratively is proposed. In the proposed scheme, drones that are carried by the vehicle start from the base station. According to distance and deadline of nodes with charging requests, LDFM prioritizes nodes with the longest matching distance for allocation to drones. As a result, the proposed scheme aims to minimize the moving distance of charging scheduling of the WCV on premise of satisfying charging requests with the cooperation of WCVs and drones. Our proposed scheme is thus designed to maximize the efficiency of drone usage and shares the charging burden of the vehicle, which makes WRSNs work well in large and complex terrain regions, such as a hill, natural disaster areas or war zones. Simulation results confirm that our proposed scheme outperforms hybrid scheme in previous work with respect to total number of charging nodes and network energy consumption. Especially with heavy traffic load, the proposed scheme can charge more than 10% additional nodes compared to the hybrid. Moreover, the proposed scheme achieves a reduction of over 50% in the moving distance compared to the hybrid.

Personalized Velocity and Energy Prediction for Electric Vehicles With Road Features in Consideration

Electric vehicles (EVs) seem to be an eminent alternative for ground transportation. Yet, human drivers may suffer from EV’s range anxiety, which is engendered by EV’s limited battery capacity and sparse charging stations, particularly in rural areas. A reliable prediction of EV battery energy consumption for the intended route before traveling can alleviate this feeling of unease. Fundamentally, an accurate speed trajectory forecast lays the foundation for a dependable energy consumption prediction. This paper originates a data-driven paradigm to predict an EV’s speed considering various road features and individuals’ driving characteristics. Two modified Transformer neural networks, which outperform the traditional recurrent neural networks, are exploited to extract information from input features and predict vehicular acceleration or velocity profile. Additionally, a novel energy consumption model is suggested to pioneeringly take the tire slip ratio into account and utilize a neural-network-predicted powertrain efficiency map. By design, the proposed algorithm can offer EV speed and energy consumption estimations prior to the start of a trip. Experimental data collected in real-world EV test drives on four different routes are employed to validate the method. Compared to a baseline approach, the proposed scheme yields a superior accuracy on both velocity and energy consumption predictions for EVs.