Search

Microgrids (MGs) have evolved as critical components of modern energy distribution networks, providing increased dependability, efficiency, and sustainability. Effective control strategies are essential for optimizing MG operation and maintaining stability in the face of changing environmental and load conditions. Traditional rule-based control systems are extensively used due to their interpretability and simplicity. However, these strategies frequently lack the flexibility for complex and changing system dynamics. This paper provides a novel method called hybrid intelligent control for adaptive MG that integrates basic rule-based control and deep learning techniques, including gated recurrent units (GRUs), basic recurrent neural networks (RNNs), and long short-term memory (LSTM). The main target of this hybrid approach is to improve MG management performance by combining the strengths of basic rule-based systems and deep learning techniques. These deep learning techniques readily enhance and adapt control decisions based on historical data and domain-specific rules, leading to increasing system efficiency, stability, and resilience in adaptive MG. Our results show that the proposed method optimizes MG operation, especially under demanding conditions such as variable renewable energy supply and unanticipated load fluctuations. This study investigates special RNN architectures and hyperparameter optimization techniques with the aim of predicting power consumption and generation within the adaptive MG system. Our promising results show the highest-performing models indicating high accuracy and efficiency in power prediction. The finest-performing model accomplishes an R2 value close to 1, representing a strong correlation between predicted and actual power values. Specifically, the best model achieved an R2 value of 0.999809, an MSE of 0.000002, and an MAE of 0.000831.

Switched model predictive control (S-MPC) and recurrent neural networks with long short-term memory (RNN-LSTM) are powerful control methods that have been extensively studied for the energy management of microgrids (MGs). These methods ease constraint satisfaction, computational demands, adaptability, and comprehensibility, but typically one method is chosen over the other. The S-MPC method dynamically selects optimal models and control strategies based on the system’s operating mode and performance objectives. On the other hand, integration of auto-regressive (AR) control with these powerful control methods improves the prediction accuracy and the adaptability of the system conditions. This paper compares the two control approaches and proposes a novel algorithm called switched auto-regressive neural control (S-ANC) that combines their respective strengths. Using a control formulation equivalent to S-MPC and the same controller model for learning, the results indicate that pure RNN-LSTM cannot provide constraint satisfaction. The novel S-ANC algorithm can satisfy constraints and deliver comparable performance to MPC, while enabling continuous learning. The results indicate that S-MPC optimization increases power flows within the MG, resulting in efficient utilization of energy resources. By merging the AR and LSTM, the model’s computational time decreased by nearly 47.2%. In addition, this study evaluated our predictive model’s accuracy: (i) the R-squared error was 0.951, indicating a strong predictive ability, and (ii) mean absolute error (MAE) and mean square error (MSE) values of 0.571 indicate accurate predictions, with minimal deviations from the actual values.

The energy sector is undergoing a paradigm shift among all the stages, from generation to the consumer end. The affordable, flexible, secure supply–demand balance due to an increase in renewable energy sources (RESs) penetration, technological advancements in monitoring and control, and the active nature of distribution system components have led to the development of microgrid (MG) energy systems. The intermittency and uncertainty of RES, as well as the controllable nature of MG components such as different types of energy generation sources, energy storage systems, electric vehicles, heating, and cooling systems are required to deploy efficient energy management systems (EMSs). Multi-agent systems (MASs) and model predictive control (MPC) approaches have been widely used in recent studies and have characteristics that address most of the EMS challenges. The advantages of these methods are due to the independent characteristics and nature of MAS, the predictive nature of MPC, and their ability to provide affordable, flexible, and secure MG operation. Therefore, for the first time, this state-of-the-art review presents a classification of the MG control and optimization methods, their objectives, and help in understanding the MG operational and EMS challenges from the perspective of the energy trilemma (flexibility, affordability, and security). The control and optimization architectures achievable with MAS and MPC methods predominantly identified and discussed. Furthermore, future research recommendations in MG-EMS in terms of energy trilemma associated with MAS, MPC methods, stability, resiliency, scalability improvements, and algorithm developments are presented to benefit the research community.

New advances in small-scale generation and consumption technologies have shifted conventional buildings’ functionality towards energy-efficient active buildings (ABs). Such developments drew the attention of researchers all around the world, resulting in a variety of publications, including several review papers. This study conducts a systematic literature review so as to analyse the concepts/factors enabling active participation of buildings in the energy networks. To do so, a relatively large number of publications devoted to the subject are identified, introducing the taxonomy of control and optimisation methods for the ABs. Then, a study selection methodology is proposed to nominate potential literature that has investigated the role of ABs in the energy networks. The modelling approaches in enabling flexible ABs are identified, while the potential challenges have been highlighted. Furthermore, the citation network of included papers is illustrated by Gephi software and analysed using “ForceAtlas2” and “Yifan Hu Proportional” algorithms so as to analyse the insights and possibilities for future developments. The survey results provide a clear answer to the research question around the potential flexibility that can be offered by ABs to the energy grids, and highlights possible prospective research plans, serving as a guide to research and industry.

Residential variable energy price schemes can be made more effective with the use of a demand response (DR) strategy along with smart appliances. Using DR, the electricity bill of participating customers/households can be minimised, while pursuing other aims such as demand-shifting and maximising consumption of locally generated renewable-electricity. In this article, a two-stage optimization method is used to implement a price-based implicit DR scheme. The model considers a range of novel smart devices/technologies/schemes, connected to smart-meters and a local DR-Controller. A case study with various decarbonisation scenarios is used to analyse the effects of deploying the proposed DR-scheme in households located in the west area of the Isle of Wight (Southern United Kingdom). There are approximately 15,000 households, of which 3000 are not connected to the gas-network. Using a distribution network model along with a load flow software-tool, the secondary voltages and apparent-power through transformers at the relevant substations are computed. The results show that in summer, participating households could export up to 6.4 MW of power, which is 10% of installed large-scale photovoltaics (PV) capacity on the island. Average carbon dioxide equivalent (CO2e) reductions of 7.1 ktons/annum and a reduction in combined energy/transport fuel-bills of 60%/annum could be achieved by participating households.