Micro-grid can improve greenhouse gas emissions and reduce operational costs. To forecast both energy generation load demand, time series prediction has been a key tool in real-time control optimization. Developing an adequate predictive model is difficult when there lack of historical data. Moreover, hyperparameters have tangible impact on the performance machine learning models. Bearing these considerations mind, this paper develops BiLO-Auto-TSF/ML framework that automates optimal design...

An increasing number of distributed generators will penetrate into the distribution power system in future smart grid, thus a centralized control strategy cannot effectively optimize loss problem real-time. This paper examines idea fully optimal flow (OPF) approach, based on alternating direction multiplier method, to loss. The objectives are not only obtain minimization loss, but also analyze effect communication time-delay optimization performance. Both synchronous and asynchronous...

Abstract Grid-connected microgrids comprising renewable energy, energy storage systems and local load, play a vital role in decreasing the consumption of fossil diesel greenhouse gas emissions. A distribution power network connecting several can promote more potent reliable operations to enhance security privacy system. However, operation control for multi-microgrid system is big challenge. To design system, an intelligent multi-microgrids management method proposed based on preference-based...

Isolated microgrids powered by renewable energy sources, battery storage, and backup diesel generators need appropriate demand response to utilize available reduce consumption efficiently. However, real-time demand-side management has become a significant challenge due the communication time-delay issue. In this paper, distributed model-free strategy is proposed manage of Electric Water Heater (EWH) units. The artificial intelligence technology based on Reinforcement Learning (RL) adopted...

Sensor technology has become increasingly prevalent in various domains of human life. However, the collected data often contains missing values to varying degrees. Moreover, obtaining sufficient historical data, particularly for smart grid forecasting isolated networks, is challenging. These deficiencies can negatively impact accuracy deep-learning models, consequently affecting operational performance microgrids. To address these challenges, this article introduces a multioutput learning...

High penetration of Distributed Generations (DGs) will have impact on the development power systems. Due to uncertainty DG output, it becomes extremely difficult control system voltage profile. This paper proposes a coordinated decentralized method, together with self-excited inverter, that can level by reactive injection/absorption. The time-delay introduced communications among DGs is considered validate proposed approach. Simulation results show coodinated approach sensitive in 33-bus...

More and more distributed generators (DGs) will penetrate into the distribution power system in future. Therefore, voltage fluctuation becomes a challenging essential issue for future smart grids. In this paper coordinated decentralized control method based on optimal flow (OPF) algorithm, alternating direction multiplier (ADMM), is proposed which does not require any center. Meanwhile, communication queueing theory ADMM also presented. Simulation results show that approach sensitive to...

Significant advancements have been witnessed in the global development and deployment of smart grid systems recent years. The strategic integration advanced artificial intelligence (AI) technologies holds potential to propel these grids toward a future characterized by enhanced intelligence, efficiency, sustainability. Within realm grids, insulators assume critical role. However, they pose persistent challenge terms effective defect monitoring. To alleviate this dilemma, This article...

In the face of global climate challenges, energy conservation and demand response have become crucial. Electric water heaters (EWHs), with their excellent heat storage capacity, are an ideal choice for household response. However, individual households often relatively small variable hot demands, they may struggle to respond promptly fluctuations in electricity prices. To address this challenge, we developed a small-scale community model, which includes centralized supply center, group...

In recent years, extreme weather events (EWE) have occurred frequently on a global scale, introducing uncertainty into the energy scheduling of microgrids and increasing challenges associated with their operation. To address management optimization problem in under EWE, this paper presents generic framework based Meta-Reinforcement Learning (Meta-RL). Initially, various operational scenarios are modeled as series correlated Markov Decision Processes (MDPs), incorporating time-varying...