Integrating AI and Multi-objective Optimization for Enhanced Microgrid Energy Management Using Quadratic Programming

Developing Hybrid Demand Response Technique for Energy Management in Microgrid Based on Pelican Optimization Algorithm

This paper presents a stochastic optimization framework for microgrid (MG) energy management, integrating electric bicycle (E-Bike) and electric vehicle (EV) charging stations with a green certificate market (GCM) to enhance sustainability and economic efficiency. Uncertainties in renewable energy generation (solar and wind) and load demand are modeled using the Two-Point Estimation Method (TPEM), enabling robust handling of variability. A novel metaheuristic algorithm, Mountaineering Team-Based Optimization (MTBO), is developed to solve a three-objective optimization problem: minimizing operational costs, minimizing emissions, and maximizing GCM revenue. MTBO is benchmarked against particle swarm optimization, achieving a 21.6% reduction in operational costs and a 13.12% reduction in emissions in deterministic scenarios. Three cases are analyzed: (I) no mobile storage, (II) deterministic mobile storage, and (III) stochastic management. In case II, integrating mobile storage (EVs and E-Bikes) with V2G capabilities reduces operational costs by 18.6% and emissions by 10.9% compared to case I. Case III, incorporating stochastic management, further lowers costs by 1.5% and by 19.8% relative to case I, but increases demand response costs by 7.5% and reduces GCM revenue by 38.9% due to renewable fluctuations. These results highlight the practical benefits of combining E-Bike and EV mobile storage with GCM trading in microgrids, demonstrating MTBO's superior exploration and exploitation capabilities for high-dimensional, uncertainty-aware energy scheduling.

A hybrid method for simultaneous optimization of DG capacity and operational strategy in microgrids considering uncertainty in electricity price forecasting

The increasing integration of distributed renewable energy sources (RES), energy storage systems (ESS), electric vehicle (EV) charging stations, and demand response (DR) mechanisms has significantly enhanced microgrid deployment. However, the operational complexity and vulnerability of islanded microgrids to disruptions, especially during renewable energy fluctuations, pose critical challenges. Existing approaches primarily focus on minimizing operational costs or emissions but fail to simultaneously address load curtailment, voltage stability, and resilience under uncertain conditions. In this paper, we propose a novel resilience-oriented energy and load management framework for island microgrids, integrating a multi-objective optimization function that explicitly minimizes load curtailment, energy losses, voltage deviations, emissions, and energy procurement costs while maximizing the utilization of renewable energy sources. Unlike conventional models that separately optimize demand-side management (DSM), distributed generation (DG), EV charging/discharging, and ESS scheduling, our approach incorporates a coordinated control strategy that jointly optimizes these elements alongside reactive power compensation devices such as capacitors and shunt reactors. To effectively solve this high-dimensional, nonlinear problem, we employ the Multi-objective Moth Flame Algorithm (MOMFA), an enhanced metaheuristic evolutionary algorithm designed to handle complex trade-offs between cost, reliability, and resilience. The superiority of MOMFA over conventional optimization techniques such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Grey Wolf Optimization (GWO) is validated through simulations on a realistic 33-node microgrid under various renewable energy outage scenarios. The results demonstrate that the proposed framework achieves a 60% reduction in voltage deviation, an 81% decrease in energy losses, and an 86% reduction in CO₂ emissions, while ensuring zero load curtailment, even under severe outage conditions. The proposed method offers a scalable, real-time implementable solution for microgrid operators seeking to enhance resilience against renewable energy intermittency and optimize energy utilization. This work significantly advances state-of-the-art microgrid energy management by providing a holistic, multi-objective, and resilience-driven optimization strategy.

Implementation of a multistage predictive energy management strategy considering electric vehicles using a novel hybrid optimization technique

Optimizing power systems and microgrids: A novel multi-objective model for energy hubs with innovative algorithmic optimization

Today, the use of renewable energy is increasing rapidly due to the reduction of pollution and the optimal use of available energy. Microgrids (MGs) are used as systems to control and exploit various resources and loads. Due to the connection of different resources in MGs, control and operation of this system are complex and important. In this paper, the optimal utilization of MGs is presented by considering various parameters including production sources, different loads and energy storage. In this paper for energy management in systems with various MGs, we aim to apply the multi-objective optimization algorithm to obtain the optimal energy management in MG, while simultaneously satisfying pollution and economic objectives. The multi-objective particle swarm optimization (MOPSO) method and non-dominated sorting genetic algorithm (NSGA-II) are used to solve the problem and their results are compared. Various factors are considered in the cost function including operation cost, losses, pollution and other operation characteristics. Using multi-objective optimization functions considering cost functions and various constraints ensures optimal operation of the MG. Simulation results verify various models and effectiveness of the proposed methods. Simulation results show that using NSGA-II for scheduling DG resources gives more optimal results in terms of reducing operation cost and losses such that considering operation cost and pollution cost using NSGA-II reduces operation cost and losses by 10% and 4%, respectively.

Multi-Energy Microgrids (ME-MGs) represent an integrated and advanced energy system, playing a vital role in delivering optimal and sustainable energy solutions in modern societies. These systems combine various energy sources, such as electricity, heat, and storage systems, to ensure efficient resource management and operation. One of the primary challenges in managing ME-MGs is reducing operational costs and emissions while addressing uncertainties. This study investigates the optimization and energy management (EM) in ME-MGs through the application of the Multi-Objective Walrus Optimization Algorithm (MOWaOA) combined with fuzzy decision-making techniques. The main objective of the research is to minimize operational costs and emissions in the face of uncertain conditions. To achieve this goal, multiple scenarios were analyzed, including EM without considering demand response and electric vehicles, EM with the inclusion of these factors, and EM under uncertain conditions. The results demonstrated that integrating electric vehicles and demand response into microgrid EM led to a 15.6% reduction in operational costs and a 12.8% decrease in emissions compared to scenarios where these factors were excluded. Furthermore, when uncertainties were accounted for, operational costs increased by 2.1% and emissions rose by 1.2%. This increase emphasizes the significance of employing more precise management techniques and advanced strategies to effectively address uncertainties in ME-MGs.

Microgrids offer enhanced resilience and efficiency but require sophisticated energy management systems (EMS) to balance conflicting objectives like cost minimization, renewable energy utilization, and component longevity, especially under uncertainty. Traditional optimization methods often rely on precise forecasts and may struggle with real-time adaptation and complex trade-offs like battery degradation. This research aimed to develop a deep reinforcement learning (DRL) based EMS for optimizing microgrid operation considering operational cost, battery degradation, and renewable generation uncertainty. A deep Q-network (DQN) based reinforcement learning agent was trained to manage energy flows within a simulated microgrid comprising solar PV, battery storage, controllable loads, and a grid connection. The reward function incorporated operational costs, battery degradation, and renewable utilization objectives, with the agent learning control policies through environment interaction. The DRL-based EMS demonstrated effective adaptive control, achieving a 12.01% reduction in overall operational costs compared to the model predictive control benchmark. The DRL agent implicitly learned strategies that reduced battery degradation by 8.19% while increasing renewable energy utilization by 10.39%. Most notably, the approach maintained robust performance under uncertainty, with only 8.9% cost increase under severe forecast errors compared to 21.5% for conventional methods. This study demonstrates the efficacy of DRL for adaptive multi-objective microgrid energy management, successfully balancing economic operation, battery health preservation, and renewable energy integration under uncertainty.

This paper explores the economic viability of renewable energy microgrids in remote regions, focusing on their potential to provide reliable and sustainable energy solutions. Renewable energy microgrids, which integrate sources such as solar and wind power with advanced energy storage, offer a promising alternative to traditional energy systems, particularly for regions that lack access to conventional power grids. Remote regions often face significant challenges in accessing reliable and affordable energy. The dependence on diesel generators leads to high operational costs and environmental concerns. Renewable energy microgrids present an innovative solution to these issues by harnessing locally available renewable resources, reducing greenhouse gas emissions, and providing consistent energy supply. The assessment involves analyzing initial capital investment and operational costs, comparing the economic performance of renewable microgrids against conventional energy systems, evaluating environmental and social benefits, and reviewing government policies, incentives, and regulatory frameworks that impact the deployment of microgrids. Data is gathered from case studies, existing projects, academic research, and industry reports to develop economic models and scenarios for analysis. While the initial setup cost for renewable microgrids is relatively high, advancements in technology and increased production scale are driving costs down. Significant savings are achieved over time through reduced fuel and maintenance expenses compared to diesel generators. Microgrids can achieve a favorable return on investment (ROI) within 5-10 years, contingent upon local conditions and system scale. Adoption of renewable microgrids leads to substantial reductions in greenhouse gas emissions, supporting global climate goals. Improved energy reliability enhances the quality of life, supports economic development, and promotes social welfare in remote communities. Effective policies, subsidies, and incentives are crucial for reducing financial barriers and encouraging investment in renewable microgrids. Establishing clear and supportive regulatory environments is essential for the successful integration and scalability of microgrid systems. Despite the promising outlook, several challenges remain. The significant upfront investment required for microgrid infrastructure is a major hurdle. The lack of technical skills for installation, operation, and maintenance in remote regions can hinder successful deployment. Additionally, variability in local renewable resources like solar and wind can affect the reliability and performance of microgrids. To overcome these challenges, it is recommended to focus on reducing costs through technological advancements and enhancing local capacity through training and education. Developing policies and incentives that support renewable energy projects and reduce financial barriers is also essential. Engaging local communities in the planning and implementation process ensures the systems meet their needs and gain local support. Renewable energy microgrids are economically viable and environmentally sustainable solutions for providing reliable energy in remote regions. Despite initial cost challenges, the long-term benefits, including operational savings, emission reductions, and enhanced energy access, make them a compelling option. With strategic investments, supportive policies, and community involvement, renewable microgrids can significantly transform energy access and drive sustainable development in remote areas. Keywords: Economic Viability, Microgrinds, Sustainability, Energy, Nigeria.

Escalating energy demands and climate change challenges necessitate the adaptation of renewable-based microgrid systems in the energy sector. The proposed work employs a robust Multi Agent System (MAS) technique to achieve efficient and automated control of the hybrid microgrid operation. The hybrid microgrid system incorporates Renewable Energy Sources (RES), a diesel generator, and a battery storage system. The operation of the hybrid microgrid consists of three distinct modes: islanded, transition to grid, and grid-oriented mode. The system’s performance is optimized by considering factors like climatic patterns, energy costs, connected source characteristics, and load demand. Different climatic scenarios are assessed for each mode of operation, where the best, extreme sunny, extreme cloudy, and worst climate conditions are considered for islanded mode; sunny and cloudy scenarios are considered for transition to grid mode as well as grid-feed and grid-tied modes are considered for grid-oriented operation of the microgrid. The simulation studies are performed using the MATLAB/Simulink R2021a environment. Furthermore, Particle Swarm Optimization (PSO) is implemented to optimize power allocation within the microgrid and enhance its cost-effectiveness. The optimization results demonstrate efficient utilization of available energy sources along with effective energy management facilitated by the MAS control system. The results emphasize the importance of adopting a MAS approach for achieving smart energy management through comprehensive analysis and integrating decentralized energy management techniques for optimal accommodation of distributed energy resources in hybrid microgrids

In smart grid concept, microgrid defines the new paradigm for distributed energy resource integration. A micro-grid can be operated in parallel with the conventional grid or isolated mode, is one of the key enabling components of a smart grid. The dynamics of the system, due to the penetration of highly intermittent and unpredictable distributed energy resources changes. Thus, the control strategies become difficult and for improving the performance of the existing system an advanced energy management is required. The microgrid energy management should be capable of balancing supply and demand at every instant and also ensure further requirements like flexibility, reliability, fault tolerance and reduction in operation costs, etc. In this paper, a multi agent based energy management system is proposed and simulated with and without the agent based management for 24-hour real time scenario to analyze the performance of the proposed scheme. The simulation results show the effectiveness of the proposed system in the presence of different events occurred in the system.

In the last years the microgrid are emerged as the key component able to increase the efficiency, reliability, and sustainability of traditional electrical infrastructures. Micro distribution systems aggregate small, modular renewable power source, distributed storage and local loads as autonomous entities that can exchange power with the traditional electricity if operating in connected mode. A prime task in microgrid operation is the dynamic balance of local supply and power demand due to the intermittent nature of renewable energy resource and the variability of load demand during the day. However the power transfer among each microgrid and the main grid is always associated with a cost due to the loss of power over the distribution line. In this paper, a multi-agent systems (MAS) for the optimal coordination of multiple distributed energy resources is presented. The agents, associated with each microgrid, implement a cooperative strategy to minimise the power loss over the distribution lines and to maximise the economic income by sharing the surplus of the generated power between the microgrids belonging to the same coalition. The simulation results show the effectiveness of the proposed control strategy demonstrating that the MGs payoff increases up to 30% when microgrids cooperate to gain the power balance.

In recent years, the power system has been evolved into micro grids, which are little pockets of self-contained entities. Different distributed, interconnected generation units, loads, and energy storage units make up a typical microgrid system. The increased energy efficiency of these units on micro grids is gaining popularity Day-by-Day. Because of their stochastic behavior, renewable generation causes an imbalance in the power system, which needs microgrid energy management. An efficient energy management system for a small-scale Hybrid Wind-Solar- Battery based microgrid is proposed in this paper. The wind and solar energy conversion systems and battery storage system have been developed along with power electronic converters, control algorithms and controllers to test the operation of hybrid microgrid. The power balance is maintained by an energy management system for the variations of renewable energy power generation and also for the load demand variations. In this system, for reliable and stable operation of a microgrid with multiple DGs, coordinated control of energy management system is proposed. The control algorithms of microgrid system are verified by Matlab Simulation.

In this article, we suggest a micro-grid methodology based on renewable energy sources (RES) in order to make more efficient use of renewable energy sources and use less energy from the traditional power grid. Off-grid, RES likes solar (generated by a photovoltaic panel) and wind can be stored in a battery and utilised to power loads. As an additional measure, a Fuzzy logic-based energy-saving method has been applied. Microgrids are used to integrate these systems in a decentralised fashion, and they provide a suite of technology solutions that facilitate communication between end users and dispersed power plants. This raises the question of how best to administer these systems. In order to guarantee that both the generating and distribution systems produce energy at low operating costs, energy management in microgrids is described as a data and monitoring network that allows the required functions. In this study, we discuss the difficulties associated with using RES and managing a microgrid. Voltage and frequency variations result from the dynamic nature of DG systems. Unpredictable dynamics result from the load's unknowability. As a result of this nonlinear dynamic, there are observable changes to the microgrid's operation. In this study, we test the efficiency of the microgrid in a variety of settings. We compare the PI controller's performance on the MATLAB/Simulink platform to that of a Fuzzy logic-based controller with various levels of complexity.