A multi-objective predictive energy management strategy for residential grid-connected PV-battery hybrid systems based on machine learning technique

Kumar, Sudhir; Tzou, Jong-Chyuan; Wu, Shang-Chen

doi:10.1016/j.enconman.2021.114103

Cited by 92 publications

(33 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inverter's power is turned off until the batteries have been recharged to a suitable level. [45,46].…”

Section: Discussionmentioning

confidence: 99%

“…This can be done only using variable speed operation with DFIG or PMSG where the rotor speed of the turbine can be adjusted at variable wind speed [9,[41][42][43][44][45]. Pitch angle control is usually used in large scale wind systems to fix the output power of the wind turbines at a specific limit, especially at high wind speed [28,46].…”

Section: Wind Turbine Characteristicsmentioning

confidence: 99%

See 1 more Smart Citation

Modelling, Design and Control of a Standalone Hybrid PV-Wind Micro-Grid System

Al-Quraan

Al-Qaisi

2021

Energies

View full text Add to dashboard Cite

The problem of electrical power delivery is a common problem, especially in remote areas where electrical networks are difficult to reach. One of the ways that is used to overcome this problem is the use of networks separated from the electrical system through which it is possible to supply electrical energy to remote areas. These networks are called standalone microgrid systems. In this paper, a standalone micro-grid system consisting of a Photovoltaic (PV) and Wind Energy Conversion System (WECS) based Permanent Magnet Synchronous Generator (PMSG) is being designed and controlled. Fuzzy logic-based Maximum Power Point Tracking (MPPT) is being applied to a boost converter to control and extract the maximum power available for the PV system. The control system is designed to deliver the required energy to a specific load, in all scenarios. The excess energy generated by the PV panel is used to charge the batteries when the energy generated by the PV panel exceeds the energy required by the load. When the electricity generated by the PV panels is insufficient to meet the load’s demands, the extra power is extracted from the charged batteries. In addition, the controller protects the battery banks in all conditions, including normal, overcharging, and overdischarging conditions. The controller should handle each case correctly. Under normal operation conditions (20% < State of Charge (SOC) < 80%), the controller functions as expected, regardless of the battery’s state of charge. When the SOC reaches 80%, a specific command is delivered, which shuts off the PV panel and the wind turbine. The PV panel and wind turbine cannot be connected until the SOC falls below a safe margin value of 75% in this controller. When the SOC goes below 20%, other commands are sent out to turn off the inverter and disconnect the loads. The electricity to the inverter is turned off until the batteries are charged again to a suitable value.

show abstract

“…The inverter's power is turned off until the batteries have been recharged to a suitable level. [45,46].…”

Section: Discussionmentioning

confidence: 99%

Section: Wind Turbine Characteristicsmentioning

confidence: 99%

Modelling, Design and Control of a Standalone Hybrid PV-Wind Micro-Grid System

Al-Quraan

Al-Qaisi

2021

Energies

View full text Add to dashboard Cite

show abstract

“…This model utilizes the previous time step (t À 1) values to predict the one-step-ahead (t + 1) values. 60 As the forecast time horizon increases, the accuracy of the model decreases. 61 By Equation ( 16), a simple persistence model can be defined.…”

Section: Persistence Vs Proposed 3 Models For Charging Profilementioning

confidence: 99%

Machinelearning‐basedapproach for useful capacity prediction ofsecond‐lifebatteries employing appropriate input selection

Bhatt

Ongsakul²,

Madhu

et al. 2021

Intl J of Energy Research

View full text Add to dashboard Cite

Electric vehicle-discarded second-life batteries still contain 80% of usable capacity and can serve as a low-cost alternative for microgrid storage applications where the battery storage capacity is flexible against transport applications. By accurately predicting the remaining useful capacity or state of health of these batteries, using the data from their first life operation, their costeffectiveness for microgrid energy management can be analyzed. For this purpose, three machine learning models are proposed here. The input parameters for the models are selected from the charging and discharging profiles of batteries, considering both the aging and regeneration phenomenon. Eight different input cases with and without K-fold (K = 10) cross-validation are used for training the proposed models. Based on the comparative analysis it is found that all the models trained with K-fold cross-validation, show minimum error as compared to without K-fold. The forecasting results from multiple approaches showed that the long short term memory model trained with battery discharging profile outperformed other models, quantified by multiple error indices, including root mean square error (0.009147), mean absolute error (0.005841), and R 2 (0.9713). The robustness of the model is validated with multiple battery datasets. Further, the study illustrates the importance of activation functions, in machine learning models used for forecasting.

show abstract

“…Therefore, the reliable prediction will reduce the deviations between the PV power plant's expected and generated power. The accuracy of predicting the PV output power is essential for several applications, such as Smart Grids (SGs), 8 load management, 9 the virtual power plant's reliability, 10 and the charging of electric vehicles. 11 Therefore, it is essential to predict the PV generation in the SG application at different time horizons.…”

Section: Introductionmentioning

confidence: 99%

An adaptive approach-based ensemble for 1 day-ahead production prediction of solar PV systems

Al‐Dahidi

Muhsen

Sari

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

The world is becoming more reliant on renewable energy sources to satisfy its growing energy demand. The primary disadvantage of such sources is their significant uncertainty in power production. As appropriate energy production planning and scheduling necessitate a solid and confident assessment of renewable power production, the necessity for developing reliable prediction models grows by the day. This paper proposes an adaptive approach-based ensemble for 1-day ahead production prediction of solar Photovoltaic (PV) systems. Different ensembles of Artificial Neural Networks (ANNs) prediction models are established, whose architectures (number of the ANNs that comprise the ensembles) and configurations (number of hidden nodes required by the ANNs models of the ensembles) change adaptively at each hour h, h∈ [1, 24] of a day, for accommodating the hour seasonality in the solar PV data and, thus, enhancing the 1 day-ahead predictions accuracy. The suggested approach is tested on a 264 kW solar PV system installed at Applied Science Private University, Jordan. Its prediction performance is evaluated, particularly for different weather conditions (seasons) experienced by the concerned PV system, using standard performance metrics. Results show the effectiveness of the suggested approach in predicting solar PV power production and its superiority compared to another prediction approach of the literature that uses single ANNs at each hour h of the day. Specifically, for 1-day ahead prediction, the obtained enhanced accuracy, on average, was around 8%–10% on the test “unseen” datasets.

show abstract

A multi-objective predictive energy management strategy for residential grid-connected PV-battery hybrid systems based on machine learning technique

Cited by 92 publications

References 33 publications

Modelling, Design and Control of a Standalone Hybrid PV-Wind Micro-Grid System

Modelling, Design and Control of a Standalone Hybrid PV-Wind Micro-Grid System

Machinelearning‐basedapproach for useful capacity prediction ofsecond‐lifebatteries employing appropriate input selection

An adaptive approach-based ensemble for 1 day-ahead production prediction of solar PV systems

Contact Info

Product

Resources

About