arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Contact online >>
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv''s community? Learn more about arXivLabs.
Thank you for visiting nature . You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.
Despite two-way communication facilities and the advanced metering infrastructure (AMI), the optimal management capability of electrical energy among appliances and resources remains behind the rapid growth in power demand. Because of the modern lifestyle of consumers, the application of electrical appliances has increased dramatically. Therefore, it is estimated that global electricity demand will increase by 2.1 per year by 2040 (twice the rate of primary energy demand)1. Furthermore, the invention of several renewable energy sources (RES) aims to achieve sustainable electrical energy generation. Photovoltaic (PV) devices are the fastest-growing RES category with a growth rate of 60% whereas the growth rates of wind power and biofuels are 27% and 18%, respectively2.
Furthermore, the massive penetration of renewable resources and energy storage systems (ESS) is essential to mitigating electrical energy demand without a higher carbon emission volume. ESS technology can immediately transform and store electrical energy from the electrical power network and inject the electrical energy back according to the applied scheme or when the base units are unavailable for generation3. However, integration of ESS with proper management and resource scheduling is arduous. The home energy management system (HEMS)4 provides a possible solution by managing the energy consumption and PV generation with the integration of a battery ESS (BESS) that balances supply and demand cost-effectively.
However, accurate active demand (AD) and PV power generation forecasting are essential for precise scheduling of the BESS in leading continuous and secure power supply by avoiding blackouts. Because of the advancement in deep learning (DL) technology, numerous studies have been conducted on time-series forecasting (i.e., demand, generation, and price) using these techniques. In16, the authors used bidirectional long short-term memory (Bi-LSTM) for short-term PV power generation prediction. For ultra-short-term PV power prediction, an improved Bi-LSTM algorithm was proposed to increase performance when the prediction model inputs come from multiple PV output series17.
Toubeau et al.18 focused on multivariate predictive scenarios for multistep-ahead prediction. The authors in19 proposed a Bi-LSTM algorithm for different interval-ahead predictions in large-scale PV power plants. In20, a day-ahead peak demand forecasting was accomplished by applying a Bi-LSTM-based sequence to the sequence regression technique. Some recent studies also focused on this algorithm for predicting short-term wind speed21,22. However, previous studies16,17,18,19,20 only considered the operational constraints of the predictive model for improving performance parameters.
Stochastic optimization for HEMS was developed in the context of electrical energy allocation among the BESS, energy demand, and utility grid, which explicitly integrates probability distributions of trip duration and trip length. The optimization problem was formulated using time-varying electricity pricing and time-varying energy usage27. Moreover, a genetic harmony search algorithm was integrated with the home energy management controller to reduce electricity expense and enhance user comfort by considering real-time electricity pricing and critical peak pricing tariffs28.
From the aforementioned discussion, we may deduce that the existing studies utilized the PV-BESS energy completely on a daily basis owing to not considering the day-ahead constraints. However, if there is no PV generation and no energy stored in the BESS, existing studies fail to determine the optimal strategy for utilizing PV-BESS energy since the system requires power from the grid again, resulting in higher electricity bills due to exceeding the daily grid power allowance. Therefore, the proposed system presents an innovative approach for scheduling and optimization that incorporates day-ahead generation and consumption. The scheduling and optimization procedure was carried out in such a way that the BESS was able to keep energy for mitigating day-ahead energy demand.
This study proposes a novel scheme for a HEMS that optimally schedules and manages the PV-BESS for the customer in a dynamic environment. This study is the first (to the best of our knowledge) to simulate the integration of a predictive model with a control algorithm for optimal scheduling and maximizing the discharge amount by including dynamic tariffs. Significant contributions of this study are as follows:
In this study, we designed and developed a Bi-LSTM model for day-ahead energy consumption and generation forecasts (described in "Controlling mechanism" section). Training with the predictive model ensures consistent day-ahead forecasting performance by diminishing prediction errors.
This study proposes a heuristic strategy that considers the impact of predicted energy consumption and generation. The real-time scheduling and optimization technique is modeled in a specific interval by considering the energy demand and generation profile (described in "Simulation study" section).
The proposed system is evaluated under different scenarios of day-ahead power consumption and PV generation volume by the consumer, whereas existing studies focus only on the present-day scenario. The proposed system''s payback periods are also assessed.
This paper is organized as follows. "System modeling" section describes the modeling of the proposed system. "Controlling mechanism" section presents the control mechanism and operational constraints for the HEMS model. The simulation results and the corresponding discussion are presented in "Simulation study" section, and the conclusion is presented in "Conclusion" section.
Architecture of the proposed home mirogrid system.
Architecture of LSTM model.
Architecture of Bi-LSTM model.
The output response at t using a hidden vector derived from two LSTM layers is calculated as follows:
The day-ahead power generation and consumption is necessary for scheduling PV-BESS and optimizing the energy charging and discharging allowances. However, the following is a description of the procedure for determining day-ahead power generation and consumption:
Step 1: At first, zero/nan, and duplicate values from the historic data are removed/replaced through data cleaning process.
Step 3: The featured data are scaled by applying the data-scaling process.
Step 4: Initialization of the hyperparameters and designed the Bi-LSTM model.
Step 6: Finally, the real-time data is fed to the predictive model for determining day-ahead energy consumption and PV generation.
About Lome microgrid energy storage
As the photovoltaic (PV) industry continues to evolve, advancements in Lome microgrid energy storage have become critical to optimizing the utilization of renewable energy sources. From innovative battery technologies to intelligent energy management systems, these solutions are transforming the way we store and distribute solar-generated electricity.
When you're looking for the latest and most efficient Lome microgrid energy storage for your PV project, our website offers a comprehensive selection of cutting-edge products designed to meet your specific requirements. Whether you're a renewable energy developer, utility company, or commercial enterprise looking to reduce your carbon footprint, we have the solutions to help you harness the full potential of solar energy.
By interacting with our online customer service, you'll gain a deep understanding of the various Lome microgrid energy storage featured in our extensive catalog, such as high-efficiency storage batteries and intelligent energy management systems, and how they work together to provide a stable and reliable power supply for your PV projects.
