Diversification Of Energy Sources Research Articles

Enhancing Load Frequency Control of Interconnected Power System Using Hybrid PSO-AHA Optimizer

The integration of nonconventional energy sources such as solar, wind, and fuel cells into electrical power networks introduces significant challenges in maintaining frequency stability and consistent tie-line power flows. These fluctuations can adversely affect the quality and reliability of power supplied to consumers. This paper addresses this issue by proposing a Proportional–Integral–Derivative (PID) controller optimized through a hybrid Particle Swarm Optimization–Artificial Hummingbird Algorithm (PSO-AHA) approach. The PID controller is tuned using the Integral Time Absolute Error (ITAE) as a fitness function to enhance control performance. The PSO-AHA-PID controller’s effectiveness is evaluated in two networks: a two-area thermal tie-line interconnected power system (IPS) and a one-area multi-source power network incorporating thermal, solar, wind, and fuel cell sources. Comparative analyses under various operational conditions, including parameter variations and load changes, demonstrate the superior performance of the PSO-AHA-PID controller over the conventional PSO-PID controller. Statistical results indicate that in the one-area multi-source network, the PSO-AHA-PID controller achieves a 76.6% reduction in overshoot, an 88.9% reduction in undershoot, and a 97.5% reduction in settling time compared to the PSO-PID controller. In the dual-area system, the PSO-AHA-PID controller reduces the overshoot by 75.2%, reduces the undershoot by 85.7%, and improves the fall time by 71.6%. These improvements provide a robust and reliable solution for enhancing the stability of interconnected power systems in the presence of diverse and variable energy sources.

Comparative genomic analysis of an emerging Pseudomonadaceae member, Thiopseudomonas alkaliphila.

Thiopseudomonas alkaliphila, an organism recently classified within the Pseudomonadaceae family, has been detected in diverse sources such as human tissues, animal guts, industrial fermenters, and decomposition environments, suggesting a diverse ecological role. However, a large knowledge gap exists in how T. alkaliphila functions. In this comparative genomic analysis, adaptations indicative of habitat specificity among strains and genomic similarity to known opportunistic pathogens are revealed. Genomic investigation reveals a core metabolic utilization of multiple oxidative and non-oxidative catabolic pathways, suggesting adaptability to varied environments and carbon sources. The genomic repertoire of T. alkaliphila includes secondary metabolites, such as antimicrobials and siderophores, indicative of its involvement in microbial competition and resource acquisition. Additionally, the presence of transposases, prophages, plasmids, and Clustered Regularly Interspaced Short Palindromic Repeats-Cas systems in T. alkaliphila genomes suggests mechanisms for horizontal gene transfer and defense against viral predation. This comprehensive genomic analysis expands our understanding on the ecological functions, community interactions, and potential virulence of T. alkaliphila, while emphasizing its adaptability and diverse capabilities across environmental and host-associated ecosystems.IMPORTANCEAs the microbial world continues to be explored, new organisms will emerge with beneficial and/or pathogenetic impact. Thiopseudomonas alkaliphila is a species originally isolated from clinical human tissue and fluid samples but has not been attributed to disease. Since its classification, T. alkaliphila has been found in animal guts, animal waste, decomposing remains, and biogas fermentation reactors. This is the first study to provide an in-depth view of the metabolic potential of publicly available genomes belonging to this species through a comparative genomics and draft pangenome calculation approach. It was found that T. alkaliphila is metabolically versatile and likely adapts to diverse energy sources and environments, which may make it useful for bioremediation and in industrial settings. A range of virulence factors and antibiotic resistances were also detected, suggesting T. alkaliphila may operate as an undescribed opportunistic pathogen.

Investigating and predicting the role of photovoltaic, wind, and hydrogen energies in sustainable global energy evolution

The global shift toward next-generation energy systems is propelled by the urgent need to combat climate change and the dwindling supply of fossil fuels. This review explores the intricate challenges and opportunities for transitioning to sustainable renewable energy sources such as solar, wind, and hydrogen. This transition economically challenges traditional energy sectors while fostering new industries, promoting job growth, and sustainable economic development. The transition to renewable energy demands social equity, ensuring universal access to affordable energy, and considering community impact. The environmental benefits include a significant reduction in greenhouse gas emissions and a lesser ecological footprint. This study highlights the rapid growth of the global wind power market, which is projected to increase from $112.23 billion in 2022 to $278.43 billion by 2030, with a compound annual growth rate of 13.67%. In addition, the demand for hydrogen is expected to increase, significantly impacting the market with potential cost reductions and making it a critical renewable energy source owing to its affordability and zero emissions. By 2028, renewables are predicted to account for 42% of global electricity generation, with significant contributions from wind and solar photovoltaic (PV) technology, particularly in China, the European Union, the United States, and India. These developments signify a global commitment to diversifying energy sources, reducing emissions, and moving toward cleaner and more sustainable energy solutions. This review offers stakeholders the insights required to smoothly transition to sustainable energy, setting the stage for a resilient future.

Comparison of different drivers on energy systems investment dynamics to achieve the energy transition goals

The signing of the Paris Agreement represents a consensus on limiting the increase of the average global temperature compared to the preindustrial period. The European Union has set an ambitious goal of achieving climate neutrality by 2050. By 2030, the European Commission's REPowerEU plan aims to accelerate the processes of increasing the share of renewable energy sources, improving energy efficiency, reducing energy use, and, at the same time, diversifying energy sources and increasing electricity connectivity between member states.In order to achieve the stated goals, future energy systems will be based on renewable energy sources, which are characterized by production variability. Such systems require flexibilization technologies that ensure security and stability of supply. In this study, an analysis of how different fuel and technology costs, as well as policy targets, influence the pace of the energy transition dynamic was made on the case study of Croatia, as there was no such previous investigation. Therefore, the goal of the research is to identify the most prominent driver to achieve energy transition targets in Croatia, with an emphasis on the required flexibilization technologies. The investigation has been implemented in the energy planning tool H2RES, a detailed open-source long-term optimization model in a five-year step model based on scenario analysis of different RES and CO2 targets, technology costs, and fuel prices. The results reveal a need for an ambitious energy policy if the goal is to achieve full energy system decarbonization. Currently, high carbon prices and lower technology costs won't be enough to lead the energy transition, without legislative support.

Planning framework for establishment of hydrogen hubs incorporating the path towards net-zero-driven policies

Hydrogen hubs are emerging as strategic solutions to meet governmental emission reduction targets. A critical aspect of hydrogen hub design involves diversifying end uses, encompassing mobility, backup/storage, heating and cooling provision, onsite electricity generation, and grid energy supply. This paper introduces a comprehensive hydrogen hub model catering to these varied applications. Additionally, a novel multi-stage planning framework is proposed to assist hub operators in making informed decisions regarding the integration of diverse renewable energy sources and infrastructure. This framework addresses varying demands efficiently and economically. Moreover, to align with governmental emission reduction policies leading to net-zero targets, a proactive strategy is suggested. Through zoning for commercial, residential, educational, and healthcare sectors, the Sydney hydrogen hub is envisioned under two scenarios: business-as-usual and towards-net-zero design. Notably, CO2 emissions are projected to decrease from 18.3 ktonnes in the former to 4.7 ktonnes in the latter scenario.

Socioeconomic challenges and opportunities in renewable energy transition

The global transition to renewable energy is a multifaceted endeavor that entails profound socioeconomic transformations. This study aimed to explore the socioeconomic challenges and opportunities inherent in this transition. By leveraging a comprehensive review of existing literature and case studies, this research provides insights into the economic, social, technological, and policy dimensions of renewable energy adoption. The study employed a mixed-methods approach, combining qualitative analysis of policy frameworks with quantitative assessment of economic impacts. Key findings indicate that while renewable energy technologies, such as solar and wind, are increasingly cost-competitive, high initial capital costs and long payback periods remain significant barriers. Social and cultural resistance also poses challenges, particularly in communities with strong ties to traditional energy sources. Policy inconsistencies and regulatory uncertainties further complicate the adoption of renewable energy technologies. Conversely, the study highlights numerous opportunities. Renewable energy deployment can drive substantial job creation, stimulate local economies, and enhance energy security by diversifying energy sources. Technological advancements in energy storage and smart grids are crucial for integrating renewable energy into existing systems, thereby ensuring reliability and stability. Effective policy frameworks, such as feed-in tariffs and carbon pricing, are essential for fostering investment and innovation in the renewable energy sector. The study concludes that a holistic approach, integrating economic incentives, social engagement, and robust policy frameworks, is vital for overcoming challenges and maximizing the benefits of renewable energy. Recommendations for future research include exploring innovative financial instruments, advancing energy storage technologies, and enhancing public engagement to increase social acceptance of renewable energy projects. Keywords: Renewable Energy, Socioeconomic Challenges, Energy Policy, Technological Innovation, Energy Transition, Sustainable Development.

Multi-Agent Reinforcement Learning Optimization Framework for On-Grid Electric Vehicle Charging from Base Transceiver Stations Using Renewable Energy and Storage Systems

Rapid growth in a number of developing nations’ mobile telecommunications sectors presents network operators with difficulties such as poor service quality and congestion, mostly because these locations lack a dependable and reasonably priced electrical source. In order to provide a sustainable and reasonably priced energy alternative for the developing world, this study provides a detailed examination of the core ideas behind renewable energy technology (RET). A multi-agent-based small-scaled smart base transceiver station (BTS) site reinforcement strategy is presented to manage energy resources by boosting resilience so to supply power to essential loads in peak demand periods by leveraging demand-side management (DSM). Diverse energy sources are combined to create interconnected BTS sites, which enable energy sharing to balance fluctuations by establishing a market that promotes economical energy. A MATLAB simulation model was developed to assess the effectiveness of the proposed system by using real load data and fast electric vehicle charging loads from five different base transceiver stations (BTSs) located throughout Pakistan’s southern area. In this proposed study, the base transceiver station (BTS) sites can share their energy through a multi-agent-based system. From the results, it is observed that, after optimization, the base transceiver station (BTS) sites trade their energy with the grid at rate of 0.08 USD/kWh and with other sites at a rate of 0.04 USD/kWh. Therefore, grid dependency is decreased by 44.3% and carbon emissions are reduced by 71.4% after the optimization of the base transceiver station (BTS) sites.

A review of control strategies for optimized microgrid operations

AbstractMicrogrids (MGs) have emerged as a promising solution for providing reliable and sustainable electricity, particularly in underserved communities and remote areas. Integrating diverse renewable energy sources into the grid has further emphasized the need for effective management and sophisticated control strategies. This review explores the crucial role of control strategies in optimizing MG operations and ensuring efficient utilization of distributed energy resources, storage systems, networks, and loads. To maximize energy source utilization and overall system performance, various control strategies are implemented, including demand response, energy storage management, data management, and generation‐load management. Employing artificial intelligence (AI) and optimization techniques further enhances these strategies, leading to improved energy management and performance in MGs. The review delves into the control strategies and their architectures, and highlights the significant contributions of AI and emerging technologies in advancing MG energy management.

National-level resilience: Innovative framework for Energy-Water-Food nexus evaluation

The escalating demand for energy, water, and food (EWF) resources, alongside external stressors such as climate change, is placing significant strain on national systems. Therefore, this study introduces a novel framework for assessing the resilience of interconnected EWF systems at a national level. The framework utilizes a hybrid approach of network systems modeling and optimization models, integrating sectoral and dependency impacts to offer a comprehensive perspective on the interconnected resilience of EWF components. Applied to Qatar's EWF nexus, the framework revealed significant interdependencies, particularly between water and energy components, that led to cascading failures and challenged nexus resilience. Under single failure scenarios, unmet demands for energy and water ranged from 9 to 59 GWh and 97,000 to 359,000 m3, respectively, with resilience indices from 0.86 to 0.99. In double failure scenarios, significantly higher unmet demands caused the resilience index to drop to 0.43. Due to limited freshwater availability, the food sector is highly vulnerable to groundwater supply disruptions, resulting in an 85.6 % reduction in total crop production under extreme scenarios. Furthermore, the study highlighted resilience-enhancement strategies, such as utilizing treated wastewater for agricultural, industrial, and commercial activities and diversifying energy sources to reduce the risk of cascading failures, which increased the nexus's resilience by 17 %. The proposed framework serves as an essential tool for identifying critical components within the EWF nexus and planning strategies to enhance both operational and structural resilience.

A Comprehensive Review on the Role of Artificial Intelligence in Power System Stability, Control, and Protection: Insights and Future Directions

This review comprehensively examines the burgeoning field of intelligent techniques to enhance power systems’ stability, control, and protection. As global energy demands increase and renewable energy sources become more integrated, maintaining the stability and reliability of both conventional power systems and smart grids is crucial. Traditional methods are increasingly insufficient for handling today’s power grids’ complex, dynamic nature. This paper discusses the adoption of advanced intelligence methods, including artificial intelligence (AI), deep learning (DL), machine learning (ML), metaheuristic optimization algorithms, and other AI techniques such as fuzzy logic, reinforcement learning, and model predictive control to address these challenges. It underscores the critical importance of power system stability and the new challenges of integrating diverse energy sources. The paper reviews various intelligent methods used in power system analysis, emphasizing their roles in predictive maintenance, fault detection, real-time control, and monitoring. It details extensive research on the capabilities of AI and ML algorithms to enhance the precision and efficiency of protection systems, showing their effectiveness in accurately identifying and resolving faults. Additionally, it explores the potential of fuzzy logic in decision-making under uncertainty, reinforcement learning for dynamic stability control, and the integration of IoT and big data analytics for real-time system monitoring and optimization. Case studies from the literature are presented, offering valuable insights into practical applications. The review concludes by identifying current limitations and suggesting areas for future research, highlighting the need for more robust, flexible, and scalable intelligent systems in the power sector. This paper is a valuable resource for researchers, engineers, and policymakers, providing a detailed understanding of the current and future potential of intelligent techniques in power system stability, control, and protection.

Examining public private partnership investment in energy towards achieving sustainable development goal 7 for ASEAN region

The gradual progress in aligning financial flows with the adoption of clean technologies reveals a persistent funding gap, signaling a global misallocation of capital. Addressing this challenge necessitates political leadership and robust policies to counteract the insecurities impeding the redirection of financial flows. This study investigates into the impact of energy-related public–private partnership investments (PPPIE) and macro-environmental variables on the attainment of Sustainable Development Goal 7 (SDG7) across Association of Southeast Asian Nations (ASEAN) member countries from 1999 to 2021. Employing the Dynamac command technique, we conduct autoregressive distribution lag analysis and the Bounds Cointegration Test to evaluate ASEAN’s efforts in achieving SDG7. Results indicate that a ten-year exogenous shock to the GDP growth rate initially causes a temporary decline in both GDP and PPPIE, albeit not statistically significant. However, in the long run, the shock becomes statistically significant, correlating with a negative decline in the GDP growth rate. This underscores the negative impact of external factors like the COVID-19 pandemic on the economic growth of ASEAN member countries. Specifically, a percentage increase in PPPIE leads to an 8.3% reduction in the GDP growth rate, revealing a detrimental and unsustainable impact on the economy. This signifies that energy investments in the ASEAN region, are predominantly unsustainable and adversely impact economic growth. Moreover, these energy investments contribute to a significant 52.6% increase in greenhouse gas emissions, indicating a substantial setback in the region’s progress towards meeting SDG7’s clean energy objectives by 2030. This suggests the present state of PPPIE does not align with sustainable clean energy goals of the region. Therefore, recommendations should include diversifying energy sources and investment strategies to enhance sustainable clean energy. Also, policymakers and researchers should reassess the terms and conditions of PPPIE, refining frameworks for private sector involvement to align with long-term economic sustainability goals.

Optimized integration of renewable energy sources using seven-level converter controlled by ANFIS-CS-GWO

The global energy landscape is undergoing a significant transformation, driven by the need to reduce greenhouse gas emissions, enhance energy security, and provide sustainable and clean power solutions. Renewable energy sources (RES) such as Solar Photovoltaic (SPV), wind, fuel cells, and tidal power play a crucial role in this transition due to their abundant availability and low environmental impact. However, integrating these diverse energy sources into power systems requires advanced control strategies to ensure stability, efficiency, and reliability. Existing systems, however, face significant challenges such as unstable voltage profiles, prolonged fault settling time (FST), and high total harmonic distortion (THD), which compromise their efficiency and reliability. To overcome these limitations, a novel methodology is proposed, integrating Solar PV (SPV), wind, fuel cell, and tidal energy sources into a seven-level converter (SLC) system, which is named as Four Level RES based SLC (FLRES-SLC) system. This system is managed by an Adaptive Neuro-Fuzzy Inference System (ANFIS), fine-tuned by Cuckoo Search adopted Grey Wolf Optimizer (CS-GWO). This hybrid control strategy ensures a robust voltage profile, significantly reduces FST, and lowers THD, thereby markedly improving the overall performance of the converter system. The innovative approach offers a reliable and efficient solution for modern power systems, enhancing their integration with diverse RES and ensuring high-quality power delivery.

Intelligent optimal sitting and sizing of distributed resources in presence of renewable energy and fuel cells based on reliability and emission factors

As the integration of renewable energy sources—such as wind, solar, and fuel cells—into power systems increases, challenges related to system reliability and cost efficiency become paramount. This paper examines the reliability of a standard power network composed of diverse energy sources including wind turbines, solar panels, fuel cells, batteries, and diesel generators. This paper proposes a novel hybrid optimization approach utilizing a Grey Wolf Optimizer combined with another advanced algorithm to minimize the total cost of energy production, inclusive of emission penalties for CO2, NO2, and SO2. The proposed approach is tested on IEEE 57-bus and IEEE 118-bus systems, demonstrating significant improvements over existing algorithms. Quantitative results show that our method reduces the total cost by up to 18 % and enhances system reliability by reducing voltage deviations in various scenarios by 12 %. The paper also provides insights into the optimal sizing and placement of wind turbines, photovoltaics, diesel generators, and fuel cells under different emission constraints (15000, 25000, and 45000 kg), further emphasizing the flexibility and effectiveness of our method in addressing environmental and economic challenges in modern power systems.

A hierarchical optimization approach to maximize hosting capacity for electric vehicles and renewable energy sources through demand response and transmission expansion planning

Within the scope of sustainable development, integrating electric vehicles (EVs) and renewable energy sources (RESs) into power grids offers a number of benefits. These include reducing greenhouse gas emissions, diversifying energy sources, and promoting the use of green energy. Although the literature on hosting capacity (HC) models has grown, there is still a noticeable gap in the discussion of models that successfully handle transmission expansion planning (TEP), demand response (DR), and HC objectives simultaneously. Combining TEP, DR, and HC objectives in one model optimizes resource use, enhances grid stability, supports renewable and EV integration, and aligns with regulatory and market demands, resulting in a more efficient, reliable, and sustainable power system. This research presents an innovative two-layer HC model, including considerations for TEP and DR. The model determines the highest degree of load shifting appropriate for incorporation into power networks in the first layer. Meanwhile, the second layer focuses on augmenting the RES and EVs’ hosting capability and modernizing the network infrastructure. System operators can choose the best scenario to increase the penetration level of EVs and RESs with the aid of the proposed model. The proposed model, which is formulated as a multi-objective mixed-integer nonlinear optimization problem, uses a hierarchical optimization technique to identify effective solutions by combining the particle swarm optimization algorithm and the crayfish optimizer. When compared to traditional methods, the results obtained from implementing the proposed hierarchical optimization algorithm on the Garver network and the IEEE 24-bus system indicated how effective it is at solving the presented HC model. The case studies demonstrated that integrating DR into the HC problem reduced peak load by 10.4–23.25%. The findings also highlighted that DR did not impact the total energy consumed by EVs throughout the day, but it did reshape the timing of EV charging, creating more opportunities for integration during periods of high demand. Implementing DR reduced the number of projects needed and, in some cases, led to cost savings of up to 12.3%.

Ensuring energy security: situating the Bay of Bengal in cooperative architecture narrative

ABSTRACT In today’s world, the concept of security is incomplete without the concept of energy security. Unless a country has access to uninterrupted flow of energy resources, its massive stockpile of weapons and ammunition is unlikely to keep it safe. Therefore, contemporary security studies include concerns about energy security as one of the key components of non-traditional security issues. Ensuring free access to energy for all – is a top priority in the BIMSTEC region. Trans-border cooperation can help diversify energy sources, reduce average supply costs, and meet peak demands as the gap between supply and demand grows in BIMSTEC countries. The paper examines the current energy scenario in BIMSTEC, evaluates the scope of cross-border energy trade in the region. Energy security and maritime security are intertwined with each other in today’s world. The paper also addresses the broader geopolitical, geostrategic, and geoeconomic aspects of the Bay of Bengal, illustrating how maritime security is integral to ensuring energy security in the region.

Business Models on the Energy Market in the Era of a Low-Emission Economy

In the energy market, we observe a dynamic development of innovative business models that take into account various aspects related to the direction of zero-emission economic growth. Companies are intensifying their efforts in utilizing renewable energy sources, implementing significant photovoltaic projects, and advancing technologies related to wind and hydrodynamic energy. Within this trend, microgrids become a crucial element, enabling efficient management of local energy sources. Contemporary energy companies also focus on innovative digital technologies, harnessing the potential of the Internet of Things (IoT) and artificial intelligence (AI). These tools allow for precise monitoring and optimization of energy consumption, resulting in increased operational efficiency. The expansion of subscription-based energy services encompasses not only traditional energy deliveries but also new aspects, such as intelligent management of home energy installations or the provision of advisory services on energy conservation. This approach emphasizes the customer as a partner in sustainable energy usage. Hybrid energy models, integrating diverse energy sources, constitute a key element in the transformation of the sector. The combination of photovoltaic, wind, and traditional power plants allows for flexible adaptation to changing conditions and maintains stability in the energy supply. In the face of a changing energy landscape, companies consistently strive for sustainable practices, implementing strategies that not only reduce their carbon footprint but also contribute to improving efficiency, ecology, and the decentralization of the energy system. Adapting to these dynamic changes becomes not only a challenge but also an opportunity to create a more sustainable energy future. The objective of this research is to analyze key business models in the energy market and identify their impact on operational efficiency and market competitiveness. The main results indicate significant improvements in energy management and sustainability through the adoption of these models.

Energy from waste biomass: an LCA study on a biofuel cell at early design stage.

Diversifying energy sources and managing waste biomass are two pressing contemporary issues. The new technology proposed in this study aims to address both by converting waste biomass into energy and fertilizer through the use of a biofuel cell (BFC). The purpose of this study is to assess the environmental impacts associated with this innovative technology through a Life Cycle Assessment (LCA). To achieve the goal, the production and use of the cell were modelled, considering both laboratory-scale operations and industrial-scale approximations. The study explored alternative scenarios, such as sensitivity analyses involving different acids and bases, renewable energy sources, and heat recovery. Comparisons with conventional biomass waste treatments (anaerobic digestion and composting) demonstrated that the BFC technology remains competitive. To further improve the BFC's environmental footprint, efforts should focus on reducing energy requirements and enhancing nutrient recovery during scale-up. These insights are crucial for advancing sustainable waste treatment technologies and maximizing the potential of discarded biomass in an environmentally friendly manner.

Predicting energy source diversification in emerging Asia: The role of global supply chain pressure

This study investigates energy diversification trends in six Emerging Asian countries from 1998 to 2021 while exploring the predicting effects of the global supply chain pressure, total investment, innovation, economic growth, and globalisation on energy diversification. This study considers the Kernel-Based Regularized Least Squares (KRLS) estimations and prediction models (Adam and Stochastic Gradient Descent optimisers). The impacts of global supply chain pressure and total investment on energy diversification are positive. Innovation also emerges as crucial factor to enhance energy diversification. Deeper integration into the global economy (globalisation) and economic growth strengthen energy diversification. The study underscores the importance of tailored policies, advocating for investments in innovation, targeted total investment, and inclusive growth strategies to address energy diversification in emerging Asian countries.

Hydrogen-fueled microgrid energy management: Novel EMS approach for efficiency and reliability

Effective energy management within microgrids is crucial, especially given system uncertainties. This study presents a novel Energy Management System (EMS) designed for microgrids with diverse energy sources, notably hydrogen and fuel cells. The EMS integrates artificial intelligence algorithms to predict and adapt to rapid changes, enhancing energy resource efficiency and minimizing wastage. Responsive in nature, the EMS enhances efficiency, reliability, and cost reduction in microgrid energy, dynamically responding to varying conditions for improved stability and environmental protection. Employing a random pattern approach, the EMS focuses on operational efficiency and reliability in supplying electrical and thermal loads. Addressing uncertainties in the electricity market and renewable production, a stochastic framework with scenario generation enables operation in grid-connected and island modes. Enhanced optimization through an improved particle swarm algorithm ensures cost-effectiveness and system reliability in dynamic environmental conditions. This research pioneers innovative microgrid energy management, emphasizing hydrogen and fuel cell technologies to elevate efficiency and performance reliability.

Energy management based on safe multi-agent reinforcement learning for smart buildings in distribution networks

The rapid urbanization and increasing use of distributed renewable energy resources have imposed a significant burden on power networks. Smart buildings equipped with artificial intelligence technology can play a pivotal role in energy management, ultimately enhancing energy efficiency and voltage quality. However, ensuring voltage stability within large-scale smart building systems presents challenges due to the coexistence of diverse energy sources and the fluctuating nature of renewable energy. This paper proposes a safe multi-energy management framework achieved by online decentralized execution and centralized training for large scale smart buildings in distribution networks. The energy management problem is formulated as a safety-augmented Markov decision process, presenting intractability for dynamic programming due to its extensive continuous state space. To solve this issue and improve the convergence speed and training process stability, a safety-augmented constrained multi-agent reinforcement learning algorithm based on reward extrapolation is proposed. In this algorithm, hazard values are introduced to enhance non-safe multi-agent reinforcement learning algorithms and meet safety constraints. A novel reward network is designed by imitating expert underlying intentions to ensure the rationality of the reward function for multi-objective tasks. Additionally, the loss function for estimating the Q-network is redesigned during training process to guarantee effective convergence. Theoretical analysis is conducted to provide the convergence guarantee. Numerical case studies based on actual data are performed to validate the effectiveness and scalability of our approach, showing that smart buildings can achieve superior energy management performance while ensuring voltage safety for distribution networks. The source code of the proposed algorithm is available at https://github.com/SYiyun/CMARL-EX.