Search

Abstract Microgrids have emerged as a promising solution for enhancing energy sustainability and resilience in localized energy distribution systems. Efficient energy management and accurate load forecasting are one of the critical aspects for improving the operation of microgrids. Various approaches for energy prediction and load forecasting using statistical models are discussed in the literature. In this work, a novel energy management framework that incorporates machine learning (ML) techniques is presented for an accurate prediction of solar and wind energy generation. The anticipated approach also emphasizes time series-based load forecasting in microgrids with precise estimation of State of Charge (SoC) of battery. A unique feature of the proposed framework is that utilizes historical load data and employs time series analysis coupled with different ML models to forecast the load demand in a commercial microgrids scenario. In this work, Long Short-Term Memory (LSTM) and Linear Regression (LR) models are employed for an experimental analysis to study the proposed framework under three different cases, such as (i) prediction of energy generation, (ii) load demand forecasting and, (iii) prediction of SoC of battery. The results show that the Random Forest (RF) and LSTM models performs well for energy prediction and load forecasting respectively. On the other hand, the Artificial Neural Network (ANN) model exhibited superior accuracy in terms of SoC estimation. Further, in this work, a Graphical User Interface (GUI) is developed for evaluating the efficacy of the proposed energy management framework.

Microgrids have emerged as a promising solution for enhancing energy sustainability and resilience in localized energy distribution systems. Efficient energy management and accurate load forecasting are one of the critical aspects for improving the operation of microgrids. Various approaches for energy prediction and load forecasting using statistical models are discussed in the literature. In this work, a novel energy management framework that incorporates machine learning (ML) techniques is presented for an accurate prediction of solar and wind energy generation. The anticipated approach also emphasizes time series-based load forecasting in microgrids with precise estimation of State of Charge (SoC) of battery. A unique feature of the proposed framework is that utilizes historical load data and employs time series analysis coupled with different ML models to forecast the load demand in a commercial microgrids scenario. In this work, Long Short-Term Memory (LSTM) and Linear Regression (LR) models are employed for an experimental analysis to study the proposed framework under three different cases, such as (i) prediction of energy generation, (ii) load demand forecasting and, (iii) prediction of SoC of battery. The results show that the Random Forest (RF) and LSTM models performs well for energy prediction and load forecasting respectively. On the other hand, the Artificial Neural Network (ANN) model exhibited superior accuracy in terms of SoC estimation. Further, in this work, a Graphical User Interface (GUI) is developed for evaluating the efficacy of the proposed energy management framework. Article Highlights: Design of ML based framework for energy management system for commercial micro grids. Precise estimation of major sources of microgrids such as wind, solar and SoC of battery. A comparative study on various ML models with ANN model. An evaluation study for the efficiency of the proposed energy management framework by using real-time data incorporated GUI. [ABSTRACT FROM AUTHOR]

This research puts forward the modeling of a Hydrogen Fuel Cell Electric Vehicle (HFCEV) and its validation, in comparison with battery electrical vehicle (BEV) based on a postal vehicle and its subsystems. The main investigation parameters are the amount of hydrogen consumed, and the change in the state of charging of the battery. For the profile of the same speed route, an HFCEV model and a BEV model, consisting of multiple subsystems, were developed, and simulated in the MATLAB® Simulink environment. We make use of various sources of drive cycles to obtain our outcomes such as the New European Diving Cycle (NEDC). By running simulations for different stages, we are able to generate simulation results. The discrepancies in the graphs and the visual demonstrations guided us to variable conclusions on how different factors affect an electric vehicle’s performance and efficiency. The simulation result shows that the (BEV) is 30% more effective for NEDC drive cycle comparing with (HFCEV).

This paper discusses emissions from plug-in hybrid vehicles under various driving scenarios and reports experimental data obtained under laboratory and real-world conditions. Two European plug-in hybrid passenger cars were tested using the two test types in use in the EU (chassis dynamometer and on-road), with some modifications. The best-case and near-worst-case battery states of charge were used for testing. Behavior in terms of CO2 emissions, regulated emissions, and unregulated emissions was characterized and analyzed. Differences were generally much greater for on-road testing, especially for urban driving, during which the potential for purely electrical propulsion of the vehicle is greatest. The long distances covered by current EU legislative test procedures limit the impacts of some effects. Regardless of the traction battery's state of charge, regulated emissions were well below the applicable EU limits under all driving conditions--for example, combined emissions of reactive nitrogen compounds (nitrogen oxides, ammonia, and nitrous oxide) were consistently < 10 mg/km when tested under laboratory conditions. The two vehicles tested showed that the state of the battery had a large impact on the proportion of electrical propulsion and the resulting CO2 emissions, but differences in regulated pollutants decrease with increasing distance and are generally relatively limited for longer journeys, which include non-urban driving. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles, also known as UAVs, play an increasingly important part in daily life. However, the ever-increasing number of UAVs pose an ever-increasing threat to the transportation infrastructure. Despite their precision and general efficiency, infrastructural-scale Unmanned Aerial Systems (UASs) have a disadvantage regarding their capability of being implanted in the ecosystem. There are several reasons for this, but the primary bottleneck is that their systems are not transparent to society and have very complicated processes. As a result, the authors decided to investigate the functional properties of UASs and make improvements to those properties. Throughout the study, the authors' primary focus was on analysis, which boosts productivity and ensures a significant level of safety for routine flights. The amount of power that a UAV uses depends on several variables, including the amount of power that its individual components require, the temperature of its surroundings, and the condition of the battery that it is powered by. Therefore, critical parameters and interdependencies are taken into account in the risk assessment strategy for energy-efficient Unmanned Aerial Vehicles (UAVs). In the case of UAVs, the algorithm performs a risk calculation before take-off to estimate the amount of risk that can be associated with the given flight time when using the provided battery. On the one hand, several instances of the pre-take-off state and how its parameters interact are investigated. On the other hand, they demonstrate the calculation of the risk while in flight, which is based on actual flight data. [ABSTRACT FROM AUTHOR]

Aiming at the existing single-motor agricultural tractors, which often have a mismatch between power and working conditions and a poor operation effect under different tillage modes, this paper designs a torque allocation strategy for agricultural electric tractors under different tillage modes. Firstly, the torque is divided into basic and compensating, and a calculation model is established. Then, the Particle Swarm Optimization algorithm is used to find the optimal demand torque position, and fuzzy control rules allocate the motor torque in combination with the battery SOC. Finally, the strategy's effectiveness in different tillage modes is verified by MATLAB/Simulink simulation and bench test. The test results show that the strategy can distribute the motor torque stably according to the load torque change and pedal opening under three PTO transitions and the plowing and rotary tillage modes. The main and speed control motors respond in about 3 s with good real-time performance. The drive wheel torque can reach 1600 N·m during plowing and rotating operation. The PTO torque can reach 60 N·m during the rotating process. The maximum torque of the output shaft can reach 150 N·m with good plowing performance. During all operations, the SOC of the battery shows a steady linear decrease, and the battery discharge has stability. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles, also known as UAVs, play an increasingly important part in daily life. However, the ever-increasing number of UAVs pose an ever-increasing threat to the transportation infrastructure. Despite their precision and general efficiency, infrastructural-scale Unmanned Aerial Systems (UASs) have a disadvantage regarding their capability of being implanted in the ecosystem. There are several reasons for this, but the primary bottleneck is that their systems are not transparent to society and have very complicated processes. As a result, the authors decided to investigate the functional properties of UASs and make improvements to those properties. Throughout the study, the authors’ primary focus was on analysis, which boosts productivity and ensures a significant level of safety for routine flights. The amount of power that a UAV uses depends on several variables, including the amount of power that its individual components require, the temperature of its surroundings, and the condition of the battery that it is powered by. Therefore, critical parameters and interdependencies are taken into account in the risk assessment strategy for energy-efficient Unmanned Aerial Vehicles (UAVs). In the case of UAVs, the algorithm performs a risk calculation before take-off to estimate the amount of risk that can be associated with the given flight time when using the provided battery. On the one hand, several instances of the pre-take-off state and how its parameters interact are investigated. On the other hand, they demonstrate the calculation of the risk while in flight, which is based on actual flight data.

Data-Driven approaches for State of Charge (SOC) prediction have been developed considerably in recent years. However, determining the appropriate training dataset is still a challenge for model development and validation due to the considerably varieties of lithium-ion batteries in terms of material, types of battery cells, and operation conditions. This work focuses on optimization of the training data set by using simple measurable data sets, which is important for the accuracy of predictions, reduction of training time, and application to online estimation. It is found that a randomly generated data set can be effectively used for the training data set, which is not necessarily the same format as conventional predefined battery testing protocols, such as constant current cycling, Highway Fuel Economy Cycle, and Urban Dynamometer Driving Schedule. The randomly generated data can be successfully applied to various dynamic battery operating conditions. For the ML algorithm, XGBoost is used, along with Random Forest, Artificial Neural Network, and a reduced-order physical battery model for comparison. The XGBoost method with the optimal training data set shows excellent performance for SOC prediction with the fastest learning time within 1 s, a short running time of 0.03 s, and accurate results with a 0.358% Mean Absolute Percentage Error, which is outstanding compared to other Data-Driven approaches and the physics-based model.

Aiming at the existing single-motor agricultural tractors, which often have a mismatch between power and working conditions and a poor operation effect under different tillage modes, this paper designs a torque allocation strategy for agricultural electric tractors under different tillage modes. Firstly, the torque is divided into basic and compensating, and a calculation model is established. Then, the Particle Swarm Optimization algorithm is used to find the optimal demand torque position, and fuzzy control rules allocate the motor torque in combination with the battery SOC. Finally, the strategy’s effectiveness in different tillage modes is verified by MATLAB/Simulink simulation and bench test. The test results show that the strategy can distribute the motor torque stably according to the load torque change and pedal opening under three PTO transitions and the plowing and rotary tillage modes. The main and speed control motors respond in about 3 s with good real-time performance. The drive wheel torque can reach 1600 N·m during plowing and rotating operation. The PTO torque can reach 60 N·m during the rotating process. The maximum torque of the output shaft can reach 150 N·m with good plowing performance. During all operations, the SOC of the battery shows a steady linear decrease, and the battery discharge has stability.

Here, a distributed generation system (DGS) is proposed that allows the different distributed energy resources to operate in coordination with others to provide the electricity in rural areas. Two individual controls are used in the DGS: (i) solar maximum power point tracking (MPPT) and the battery protection control, and (ii) voltage source converter (VSC) control. The proposed VSC control algorithm is based on an improved generalised filter algorithm for power quality improvement of the DGS. This control strategy effectively regulates the active power flow and provides the harmonics mitigation, reactive power compensation, and load balancing in the DGS with low steady‐state error and fast dynamic response under high impulsive noise with DC‐offset component. The solar MPPT control is designed on the basis of battery state of charge (SOC). In this control, the solar PV array operates in limited power point tracking (LPPT) after the storage battery surpasses the maximum SOC limit. In LPPT control, the solar PV MPPT operates in the voltage source operating region of PV array characteristic, thereby, reducing the power generation and avoids the overcharging of the storage battery. The proposed DGS performance is validated through test results under dynamics and steady‐state conditions. [ABSTRACT FROM AUTHOR]

In this study, the influence on fuel economy testing of gasoline-powered vehicles is evaluated for various test conditions (e.g., laboratory temperature, soaking time, cooling fan, battery charge state, and driving mode tracking). It showed a difference in fuel economy results of approximately 3 % between low (88 %) and high (99 %) battery state of charge conditions because the alternator saving function has a positive effect on fuel economy. Fuel economy testing with laboratory temperature changes gave a slight reduction at 21 °C and slight increase at 29 °C. The cooling fan changes had an almost negligible effect on fuel consumption. The largest fuel economy result varied by 5.2 % in the soft, standard, and rough driving conditions. [ABSTRACT FROM AUTHOR]

A common problem in solar farms is to predict when accumulators stop working optimally and start losing efficiency. This paper proposes and describes how to use Bayesian networks together with expert systems to predict this moment by using a telecontrol multiagent system for monitoring solar farms with distributed sensors, which was developed in a previous work. To this end, a Bayesian network model and its implementation are proposed. The resulting system meets the requirements of telecontrol systems (reliability, flexibility, and response time), yields a solution for the prediction of lifespan batteries, and provides the multiagent system with autonomous intelligent capabilities and integrated learning.

This paper addresses different techniques for modelling electrochemical energy storage (ES) devices in insular power network applications supported on real data. The first contribution is a comprehensive performance study between a set of competing electrochemical energy storage technologies: Lithium-ion (Li-ion), Nickel–Cadmium (NiCd), Nickel–Metal Hydride (NiMH) and Lead Acid (PbA) batteries. As a second contribution, several key engineering parameters with regards to the PbA battery-based storage solution are examined, such as cell charge distribution, cell string configuration and battery capacity fade. Finally, as a third contribution, an ES system operating criterion is discussed and proposed to manage the inherent rapid aging of the batteries due to their cycling activity. The simulation results are supported on real data from two non-interconnected power grids, namely Crete (Greece) and São Miguel (Portugal) Islands, for demonstration and validation purposes. [ABSTRACT FROM AUTHOR]

An Electrical Vehicle (EV) has the advantage of being friendly with environment but it does not have the same performance as a current conventional vehicle. This work proposes a strategy to improve the EV autonomy. At first, an EV model that combines lead acid batteries and a DC motor is described. The individual mathematical model for each component is developed in MATLAB. Moreover, the control speed strategy using fuzzy logic is applied to the system to produce a maximum speed reference of an EV under different states of charge of the battery and acceleration. Then, a proportional integral control adjusts the speed strategy. When the vehicle is subjected to different scenarios, the simulation realized in MATLAB/Simulink will show good efficiency. [ABSTRACT FROM AUTHOR]

In this paper an overloading prevention of a private customer power distribution transformer (PDT) in an island in Portugal through the means of a new smart electric vehicle (EV) charging scheduler is proposed. The aim of this paper is to assess the repercussion of the penetration of additional power to restore the full level of EV battery state of charge (SoC) on dielectric oil deterioration of the PDT of a private industry client. This will allow EVs to charge while their owners are at work at three different working shifts during the day. In addition, the system is part of an isolated electric grid in a Portuguese Island. A transformer thermal model is utilised in this paper to assess hot-spot temperature by having the information of the load ratio. The data used for the main inputs of the model are the private industry client daily load profile, PDT parameters, the characteristics of the factory and EV parameters. This paper demonstrates that the proposed solution allows avoiding the overloading of the PDT, thus mitigating the loss-of-life, while charging all the EVs plugged-in at the beginning of each working shift. [ABSTRACT FROM AUTHOR]

Up to date, model and parameter uncertainties are generally overlooked by majority of researchers in the field of battery diagnostics and prognostics. As a consequence, accuracy of the battery performance estimation is dominated by the model fidelity and may vary from cell-to-cell. This paper proposes a systematic framework to quantify battery model and parameter uncertainties for more effective battery performance estimation. Such a framework is generally applicable for estimating various battery performances of interest (e.g. state of charge (SOC), capacity, and power capability). Case studies for battery SOC estimation are conducted to demonstrate the effectiveness of the proposed framework.

In electric vehicle, rechargeable battery served as energy source for all its system operation which include electric motor for propulsion system and also other auxiliary components. Therefore, it becomes an important issue to be tackled in EV technology in order to enhance the battery energy capacity for long range operation. In general public view, people tend to be very concern in purchasing the electric car. One of the concerns lies on the question of how far they can travel with only battery for their car propulsion means. Therefore, this study tries to investigate the relation between battery types and the range anxiety faces by electric car makers. The investigations reveals that, Li-ion as the battery with high energy density cover more area or distance travel. [ABSTRACT FROM AUTHOR]

A common problem in solar farms is to predict when accumulators stop working optimally and start losing efficiency. This paper proposes and describes how to use Bayesian networks together with expert systems to predict this moment by using a telecontrol multiagent system for monitoring solar farms with distributed sensors, which was developed in a previous work. To this end, a Bayesian network model and its implementation are proposed. The resulting system meets the requirements of telecontrol systems (reliability, flexibility, and response time), yields a solution for the prediction of lifespan batteries, and provides the multiagent system with autonomous intelligent capabilities and integrated learning. [ABSTRACT FROM AUTHOR]