Smart Grid Technologies Research Articles

Cyber-secure energy and flexibility scheduling of interconnected local energy networks with introducing an XGBoost-assisted false data detection and correction method

The growing penetration of renewable energy resources (RERs) and the ever-increasing implementation of information and communication technologies in smart grids necessitate the utilization of fast and safe operation methods. These schemes should be able to cope with the intermittency of uncertain RERs and fully explore the capabilities of new technologies while considering the vulnerabilities as a result of digitalization. Here, the integrity of the energy and flexibility scheduling and trading heavily depends on the security of the cyber-physical system. Local energy networks (LENs) are introduced to easily incorporate and utilize distributed energy resources, improving electrical power reliability and efficiency. This study develops a cyber-secure energy and flexibility scheduling platform for interconnected local energy networks. Hence, it introduces a novel false data detection and correction method based on the XGBoost machine learning method and investigates the performance of the proposed algorithm in the context of an interconnected local energy network and the corresponding energy and flexibility transactions. In this regard, this paper initially presents a bilevel energy and flexibility scheduling problem for interconnected local energy networks (ILENs) considering cyber-attacks (BLEFSCAILEN), which tries to satisfy the energy and flexibility requirements of the ILEN guaranteeing a resilient decision against false data injection cyber-attacks. Within the proposed BLEFSCAILEN a bi-level multi-objective optimization problem is defined where the operator of ILEN optimizes both energy and flexibility trading among LENs in the upper level to maximize its revenue. In the proposed structure, the operator of each LEN is situated at the lower level and tries to minimize the scheduling cost and simultaneously maximize the local flexibility index. Furthermore, in order to evaluate and improve the proposed system’s cyber-security, a false data injection attack is constructed using the Gaussian probability distribution function. Herein, the scheduling of ILEN is optimized considering vulnerabilities of electricity consumption data as a consequence of cyber-attack. Finally, the novel XGBoost-assisted deviation bound-based false data detection/correction (XGBFDD) algorithm is suggested to mitigate the above-mentioned cyber-attack and attain near real-world conditions. Simulation results demonstrate that the proposed false data detection/correction strategy exhibits a maximum accuracy of 91.67 precent in mitigating the attack effects. This is because the acquired post-correction results exhibit minor deviations in comparison to the original optimization output that is calculated with the pre-attack consumption data.

A Hybrid Physical Co-Simulation Smart Grid Testbed for Testing and Impact Analysis of Cyber-Attacks on Power Systems: Framework and Attack Scenarios

With the deployment of numerous innovative smart grid technologies in modern power systems, more real-time communication and control are required due to the complexity and proliferation of grid-connected systems, making a power system a typical cyber-physical system (CPS). However, these systems are also exposed to new cyber vulnerabilities. Therefore, understanding the intricate interplay between the cyber and physical domains and the potential effects on the power system of successful attacks is essential. For cybersecurity experimentation and impact analysis, developing a comprehensive testbed is needed. This paper presents a state-of-the-art Hybrid Physical Co-simulation SG testbed at FIU developed for in-depth studies on the impact of communication system latency and failures, physical events, and cyber-attacks on the grid. The Hybrid SGTB is designed to take full advantage of the benefits of both co-simulation-based and physical-based testbeds. Based on this testbed, various attack strategies are tested, including man-in-the-middle (MitM), denial-of-service (DoS), data manipulation (DM), and setting tampering (change) on various power system topologies to analyze their impacts on grid stability, power flow, and protection reliability. Our research, which is based on extensive testing on several testbeds, shows that using hybrid testbeds is justified as both practical and effective.

An analysis of barriers to the implementation of smart grid technology in Pakistan

The share of renewables in the energy mix of Pakistan has gradually been increasing over the past few years, and the generated electricity is sufficient to cater to consumer electricity demands. However, almost one-third of the population still lacks electricity because of inefficiencies in transmission and distribution systems. To address this, the government introduced smart grid projects that were ineffective. Therefore, for the successful implementation of the Smart grid technology in Pakistan, it is important to know the barriers to implementing the technology in Pakistan and determine their interrelationship with each other. This research aims to identify Pakistan-specific smart grid implementation barriers through a mixed-methods approach involving a literature review and expert surveys based on the Delphi method to identify barriers and determine their interlinkages. Nine barriers are identified: state monopoly, lack of public awareness, lack of relevant regulations and policies, organizational barriers, financial constraints, market uncertainty, a dearth of technical human resources, lack of modernized grid infrastructure, and data management issues. This is followed by developing a hierarchical model in consultation with Pakistan's Energy sector experts using the Interpretive Structural Modeling (ISM) method. The driving and dependence powers of the identified barriers are determined by using MICMAC analysis. The result shows that the nine barriers are interlinked at five hierarchical levels. These are: ‘state monopoly’, and ‘lack of public awareness (level five)’, ‘lack of relevant regulations and policies (level four)’, ‘organizational barriers (level-three)’, ‘market uncertainty and financial barriers (level-two)’, and ‘lack of modernized grid infrastructure’, ‘a dearth of technical human resources’, and ‘data management issues (level-one)’. From this, we draw the conclusion that since the barriers with high driving power are influencing those with less driving power, the identified barriers may be addressed sequentially starting from level-five for the successful implementation of the Smart grid technology in Pakistan. The existing literature on the Smart Grid Implementation barriers in Pakistan lacks a determination of the interlinkages between barriers. Therefore, the findings of this research will help the energy sector stakeholders in Pakistan understand the nature of the barriers hindering smart grid technology implementation and enable them to devise effective energy policies while simultaneously adopting intelligent implementation and operational strategies. Insights reported in this study could also be useful for policymakers and stakeholders from other developing countries with socioeconomic and political contexts similar to Pakistan. Further investigations on the findings of this study may be performed using the Analytical Hierarchical Process method to quantify the weights of barriers identified in this research, and Structural Equation Modeling may be used to check the validity of the hierarchical model developed in this study.

A Case Study on Smart Grid Technologies with Renewable Energy for Central Parts of Hamburg

Globally, efforts are made to balance energy demands and supplies while reducing CO2 emissions. Germany, in its transition to renewable energies, faces challenges in regulating its energy supply. This study investigates the impact of various technologies, including energy storage solutions, peak shaving, and virtual buffers in a smart energy grid on a large scale. Real-time energy supply and demand data are collected from the Port of Hamburg and HafenCity in Germany to analyze the characteristics of different technologies such as load shifting of reefer containers and private electric vehicles’ energy, as well as pumped hydro storage. Through simulations, we assess the usability of renewable energies in a smart grid with versatile energy demands and determine the effects of peak shaving, storage solutions, and virtual buffers on uncertain energy supply. Our case study reveals that integrating smart grid technologies can reduce the overproduction of renewable energies needed to prevent blackouts from 95% to 65% at the HafenCity and the Port of Hamburg. Notably, large, reliable, and predictable energy consumers like the Port of Hamburg play a vital role in managing the uncontrollable nature of renewables, resulting in up to 31% cost savings for new infrastructure.

Demand side management using a novel archimedes optimization algorithm in a smart grid environment

Demand side management (DSM) is a smart grid technology that enables consumers to make decisions about their energy use, lowers energy suppliers’ peak hour demand, and changes the load profile. Demand Side Management (DSM) is regarded as the most significant method used in a Smart Grid (SG), as it helps consumers produce accurate information about their electrical energy usage and assists the utility in reducing peak load demand and reshaping the demand curve. By effectively utilising storage with Renewable Energy Systems (RES), DSM seeks to reduce peak demand, electricity costs, and emission rates. In this paper, we have proposed a load-shifting method for the DSM with a large number of controllable devices. The load-shifting issue has been handled hourly, throughout the course of a 24-hour day, in order to reduce the peak demand, lower the power cost, and minimise the Peak to Average load Ratio (PAR). The Archimedes Optimization (AO) method has been utilised in residential loads in SG to achieve the goal of load shifting by minimising of the problem to the DSM. The simulation findings demonstrate that the suggested demand side management technique generates significant cost savings while lowering the smart grid’s peak load demand.

An Overview of Short-Term Load Forecasting for Electricity Systems Operational Planning: Machine Learning Methods and the Brazilian Experience

The advent of smart grid technologies has facilitated the integration of new and intermittent renewable forms of electricity generation in power systems. Advancements are driving transformations in the context of energy planning and operations in many countries around the world, particularly impacting short-term horizons. Therefore, one of the primary challenges in this environment is to accurately provide forecasting of the short-term load demand. This is a critical task for creating supply strategies, system reliability decisions, and price formation in electricity power markets. In this context, nonlinear models, such as Neural Networks and Support Vector Machines, have gained popularity over the years due to advancements in mathematical techniques as well as improved computational capacity. The academic literature highlights various approaches to improve the accuracy of these machine learning models, including data segmentation by similar patterns, input variable selection, forecasting from hierarchical data, and net load forecasts. In Brazil, the national independent system operator improved the operation planning in the short term through the DESSEM model, which uses short-term load forecast models for planning the day-ahead operation of the system. Consequently, this study provides a comprehensive review of various methods used for short-term load forecasting, with a particular focus on those based on machine learning strategies, and discusses the Brazilian Experience.

A REVIEW ON INTEGRATION OF ELECTRIC VEHICLES AND OPTIMAL POWER MANAGEMENT STRATEGY FOR SUSTAINABLE DEVELOPMENT

The integration of electric vehicles (EVs) into our transportation system is a pivotal step towards sustainable development. EVs are gaining traction as a cleaner and more energy-efficient alternative to traditional internal combustion engine vehicles. Their adoption holds the promise of reducing greenhouse gas emissions and decreasing our reliance on fossil fuels, contributing significantly to environmental sustainability .One of the critical aspects of effective EV integration is the development and implementation of optimal power management strategies. These strategies play a pivotal role in ensuring that the charging and discharging of EV batteries are not only efficient but also seamlessly integrated with the existing power grid infrastructure. An optimal power management system takes into consideration factors such as load balancing, peak demand management, and the integration of renewable energy sources, making it a key component of a sustainable and resilient energy ecosystem. By efficiently scheduling when and how EVs charge or discharge, these strategies can reduce the strain on the electrical grid during peak periods, lower electricity costs, and minimize the carbon footprint associated with charging. Moreover, they can contribute to grid stability and reliability, making the entire energy system more sustainable. This research explores the synergistic potential of EVs and smart grid technologies, aiming to create a harmonious relationship between transportation and energy systems. Key Words: Electric Vehicles, Sustainable Development, Optimal Power Management, greenhouse gas emissions, fossil fuels, clean environment, smart grid technology.

The smart grid archipelago: Infrastructures of networked (dis)connectivity in Amman

This article examines the fragmented connections of Jordan’s smart grid, building on scholarship that questions how smart infrastructures reshape governance, sociospatial exclusion, and the fabric of urban life. Jordan’s ambitious smart energy program is often held up as a global model by investors, as it catalyzed over US$4 billion in private investment for new renewable and smart energy development. Yet smart energy transition is experienced in powerfully uneven ways, as distributed solar installations and smart grid technologies radically remake the spaces of urban life. Rooted in sixteen months of ethnographic fieldwork, this article traces the vertical materialization of the smart grid from the ground up, from in-home smart meters through the evolving interconnections that they enact. I argue that (post)colonial property relations engender an archipelagic landscape of (dis)connectivity that redistributes the benefits and burdens of digitalization. Drawing from Glissant’s archipelagic thought, I examine (dis)connection and urban fragmentation as a form of relation that links enduring (post)colonial relations to contemporary projects of smart development. In the (post)colonial world, as smart infrastructures are built into the conduits of uneven property relations, they come to incorporate not only capitalist logics but also racialized logics and historically contingent relations of exclusion and differentiation.

Smart Grid Study As Solution To The Challenges Of Electricity Transmission And Distribution In North Sulawesi

Electricity delivery in North Sulawesi faces many problems, such as inadequate supply, unreliable infrastructure, ineffective power transfer, and inadequate integration of renewable sources. This research is a literature study that provides a logical description in accordance with the study objectives. The results of this study show that Smart Grid Technology is considered a feasible solution to overcome the problem. Smart Grid can revolutionize the power grid in this region by monitoring and controlling superior power transmission by combining contemporary information and communication technology with conventional energy infrastructure. As this research shows, Smart Grid solutions can improve the efficiency and reliability of electric power transmission and distribution in North Sulawesi.

Optimization-based optimal energy management system for smart home in smart grid

The introduction of advanced technologies has led to an unprecedented rise in automated appliances in the housing sector. Building new administrative structures to satisfy electrical needs has grown more crucial to ensure the safety of residential devices. One of the approaches to achieve this is Demand Side Management (DSM), a key component of both micro-grid and Smart Grid technology. DSM can be accomplished by carefully controlling requirements while upholding the trust of clients. Most of the DS Management which has been covered in the research is aimed at helping households manage their power plan. The innovative HBA+DMO technique inherits Honey Badger Optimization (HBA) and Dwarf Mongoose Optimization (DMO) for executing the DSM program. The groundwork for the proposed framework implemented in this investigation is provided by the Critical-Peak-Price (CPP) and Real-Time-Price (RTP) payment processes. Two operational instances (60 min and 12 min) are being taken into consideration to evaluate client requirements and behavior over the suggested strategy. In accordance with the results from simulations, the suggested strategy arranges the devices in the best possible way, leading to fewer energy expenses while maintaining user comfort (UC). Customers sometimes pay a premium as a result of gadget waiting periods in order to gain the most comfort. As equipment is turned on in response to user comfort, the amount of time spent waiting during an unscheduled situation is close to zero. Tools for lowering energy expenditures and consumption for buildings, communities, or enterprises are frequently provided through energy management software. The three main uses of the energy data that EMS collects are reporting, monitoring, and engagement. The computational time of the proposed approach is (∼213.42). Future testing involving different conditions and control methods for study into HRES microgrid infrastructure may be done on the medium of the experiment bench.

Enabling An Efficient Smart Grid Infrastructure Through IOT Integration

In the ever-evolving landscape of energy management, the marriage of Smart Grid technology with the Internet of Things (IOT) emerges as a ground breaking paradigm. This visionary approach revolutionizes how we harness and distribute electricity. Imagine a grid that not only delivers power but also communicates dynamically with its components. Smart sensors and advanced computing work in tandem to provide real-time insights, ensuring optimal performance even in times of high demand. Beyond efficiency, this Smart Grid paves the way for seamless integration of renewable energy sources, transforming intermittent energy flows into a stable, sustainable resource. It empowers consumers, offering them personalized insights into their energy consumption patterns, and encouraging informed choices for a greener tomorrow. Yet, this innovation demands diligence in security. Robust protocols fortify against cyber threats, guaranteeing the integrity of critical infrastructure. Moreover, data privacy is held sacrosanct, with transparent handling practices in place. In essence, the Smart Grid with IOT is a catalyst for a more sustainable and efficient energy future. It not only economizes energy usage but also opens doors to a new era of renewable energy integration. With the right safeguards, this transformative technology promises a brighter, greener, and more connected world.

Do technology standards induce innovation in environmental technologies when coordination is important?

A next generation of innovation in enabling and complementary green energy technologies is needed to further accelerate the decarbonization of electricity systems. Few studies have investigated the policy determinants of innovation in this sector to glean insights on how governments may support the development and deployment of these technologies. Policies that were successful at supporting the first wave of renewables innovation may not be sufficient to produce similar results in the next wave of green innovation since those face higher coordination challenges. Using the case of smart grid technology, we investigate the effects of interoperability standards, an instrument that may facilitate coordination through establishing common technological frameworks, on inventive activity. Using firm-level analysis, we find that on average standards decrease firms' patenting activity. We further find that this negative effect is driven by firms with high patenting intensity, whereas standards enable the entry of new firms into the field. We further find suggestive evidence that standards improve innovation quality.

Novel Radio Resource Allocation Scheme in 5G and Future Sharing Network via Multi-Dimensional Collaboration

Radio resource allocation schemes are critical to enhance user experience and spectrum efficiency. In the context of fifth-generation (5G) and future networks, co-construction and sharing among multiple telecom operators, which effectively mitigate challenges stemming from resource scarcity, energy consumption, and network construction costs, also attract wide attention. Therefore, optimal resource allocation techniques in sharing networks should be explored. Current resource allocation schemes primarily optimize for load balancing, single-user throughput, and fairness of multi-user whole network throughput, with minimal consideration for network-level user experience. Moreover, existing approaches predominantly concentrate on specific resource domains, seldom considering holistic collaboration across all domains, which limits the user experience of the whole network. This paper introduces an innovative resource allocation method grounded in the Shannon theorem, incorporating time-frequency-spatial domain multi-dimensional collaboration. More importantly, by constructing an optimization model, we strive to attain optimal network-level user experience. Furthermore, we provide a smart grid technology based on the Artificial Intelligence (AI) method to predict inter-frequency information, including Received Signal Reference Power (RSRP), beam ID, and spectral efficiency, which are modeled as air interface utilization, channel bandwidth, and signal-to-noise ratio, respectively, providing input for the optimization algorithm, which seeks to achieve the optimal time-frequency-space resource allocation scheme. Extensive experimentation validates the effectiveness and superiority of our proposed methodology.

Enhancing energy efficiency with smart grid technology: a fusion of TCN, BiGRU, and attention mechanism

Introduction: Smart Grid (SG) as an intelligent system has become a key element in the efficient operation of the electrical grid. With the continuous increase in global energy demand and escalating environmental concerns, the importance of energy conservation and sustainable energy sources has become increasingly prominent. Especially in energy-intensive sectors such as large-scale buildings, energy supply and management face challenges. These structures require a significant amount of energy supply at specific times, but may encounter energy wastage issues at other times.Method: Smart Grid technology establishes a network that can transmit both electricity and data. By making full use of this data, intelligent decision-making is achieved, optimizing grid operations. Therefore, the application of Smart Grid technology to energy conservation has attracted attention and become a research focus. This study utilizes the TCN-BiGRU model, leveraging spatiotemporal sequence data and incorporating an attention mechanism to predict future energy consumption.Results: The research results indicate that the integration of Smart Grid technology, TCN, BiGRU, and the attention mechanism contributes to accurately and stably predicting energy consumption demands. This approach helps optimize energy scheduling, enhance energy utilization efficiency, and realize more intelligent, efficient, and sustainable energy management and utilization strategies.Discussion: This study provides an innovative solution for applying Smart Grid technology to energy conservation in large-scale buildings. This approach holds the potential to improve the efficiency of energy supply and management, promote sustainable energy utilization, and address the growing global energy demand and environmental issues.

Some features of the systems for monitoring and diagnostic hydro units technical condition with considering smart grid technology

Recently, hydro units are used in maneuverable modes, which leads to an increase in the load on all elements of hydro units. It can lead to unpredictable failure of their components and even failures in the operation of the hydroelectric power plant. Therefore, the use of diagnostic systems is appropriate for solving such problems. The most promising non-destructive diagnostic systems are vibration diagnosis systems. However, the effectiveness of their use depends on the diagnosis algorithms, which depend on the features and functioning of the diagnosed unit of the power unit. In this work, some models of vibration signals of hydraulic units and features of the construction of vibration diagnostics systems of hydrogenerator units are considered

Cooperative Voltage-Balancing Control for Medium-Voltage Electric–Spring System Based on Diode-Clamped Converter and Dual Active Bridges

Electric spring (ES) is an emerging smart grid technology for stabilizing the voltage and frequency in a power network. Being fast demand-side-management technology, ES has recently been extended to the medium-voltage (MV) level in an AC-DC power conversion system that connects the distribution line of 6.6/11/22 kV to a DC grid of 800 V. To interface with the MV power grid, a diode-clamped converter (DCC) and multiple dual active bridges (DABs) can be employed to construct the MV-ES system. The balance of the capacitor voltages is crucial for DCCs, and thereby also for the MV-ES system. Conventional voltage-balancing approaches for DCCs generally compromise the quality of the grid-side voltage and current, which is undesirable especially in high-voltage high-power occasions. In this paper, a voltage-balancing control solution is proposed for the MV-ES system via cooperation of the DCC and DABs. By taking advantage of the DABs in voltage balancing, the DCC can adopt simple modulation and ensure grid-friendly voltage and current injection into the grid. The proposed voltage-balancing solution is verified using simulations in a five-level system and with practical experiments for a three-level system.

Robust Integrated Energy Management of a Smart Home Considering Discomfort Degree-Day

This article implements an integrated electrical and thermal energy management of a smart home in real time, taking into account the residents' comfort conditions. The smart home can benefit from a multi-carrier energy system. The energy resources include electrical network, photovoltaic generating unit and storage unit, as well as a hybrid water heating system supplied from solar irradiation and natural gas network. Additionally, electrical and thermal loads are categorized into three types: i)time flexible, ii) power flexible and iii) fixed loads. Taking advantage of smart grid technology, an energy management system receives required economic, technical, and climatic information in real-time, and decides the energy schedules time by time. The integrated energy management problem is formulated to optimize economic and discomfort metrics. A novel metric of discomfort degree-day is proposed to measure the residents' dissatisfaction with the indoor temperature, which considers both magnitude and duration of deviation from a desired temperature in a day. Additionally, the uncertainties in solar irradiation and outdoor temperature are presented by uncertainty sets, and handled through a robust optimization model. The out-of-sample results through a realistic case study indicate that a more robust schedule of energy resources and loads (e.g., ranging from 20% to 100% robustness) is obtained with negligible change (e.g., < 1%) in the operation cost, but at the expense of 48.82% and 58.97% increment of dissatisfaction under the uncertainty sets with the confidence levels of 0.6 and 0.8, respectively.

Step towards secure and reliable smart grids in Industry 5.0: A federated learning assisted hybrid deep learning model for electricity theft detection using smart meters

The integration of Smart Grid technology and conceptual Industry 5.0 has paved the way for advanced energy management systems that enhance efficiency and revolutionized the parallel integration of power sources in a sustainable manner. However, this digitization has opened a new stream of the threat and opportunities of electricity theft posing a significant challenge to the security and reliability of Smart Grid networks. In this paper, we propose a secure and reliable theft detection technique using deep federated learning (FL) mechanism. The technique leverages the collaborative power of FL to train a Convolutional Gated Recurrent Unit (ConvGRU) model on distributed data sources without compromising data privacy. The training deep learning model backbone consists of a ConvGRU model that combines convolutional and gated recurrent units to capture spatial and temporal patterns in electricity consumption data. An improvised preprocessing mechanism and hyperparameter tuning is done to facilitate FL mechanism. The halving randomized search algorithm is used for hyperparameters tuning of the ConvGRU model. The impact of hyperparameters involved in the ConvGRU model such as number of layers, filters, kernel size, activation function, pooling, GRU layers, hidden state dimension, learning rate, and the dropout rate is elaborated. The proposed technique achieves promising results, with high accuracy, precision, recall, and F1 score, demonstrating its efficacy in detecting electricity theft in Smart Grid networks. Comparative analysis with existing techniques reveal the superior performance of the deep FL-based ConvGRU model. The findings highlight the potential of this approach in enhancing the security and efficiency of Smart Grid systems while preserving data privacy.

Key technologies of active distribution networks control

Active Distribution Networks (ADNs) are modern and intelligent power distribution systems that integrate renewable energy sources and advanced control technologies to provide reliable, secure, and efficient electricity supply. The traditional power distribution networks are designed to deliver electricity in a one-way flow from the transmission system to the customers. In contrast, ADN enables two-way power flow between the distribution network and customers, allowing them to become active participants in the electricity system. The key technology behind ADN includes advanced metering infrastructure (AMI), Distribution Automation (DA), and energy storage systems (ESS). AMI provides real-time data on electricity consumption, generation, and distribution, enabling efficient load management and demand response. Other key technologies of ADN include renewable energy sources such as solar photovoltaic (PV), Wind turbines and small-scale hydroelectricity. These sources are connected to the distribution network through power electronic interfaces that convert the DC output of the renewable sources into AC for distribution. Smart grid technologies such as microgrids, virtual power plants, and energy management systems are also integrated into ADN to improve grid stability and resilience. ADNs have the potential to transform the electricity system by enabling more efficient, sustainable, and reliable energy systems that can better serve the needs of consumers and society. Thus, ADN is expected to become a critical technology in achieving a cleaner and more sustainable energy future.

Optimizing electric vehicle charging schedules and energy management in smart grids using an integrated GA-GRU-RL approach

Introduction: Smart grid technology is a crucial direction for the future development of power systems, with electric vehicles, especially new energy vehicles, serving as important carriers for smart grids. However, the main challenge faced by smart grids is the efficient scheduling of electric vehicle charging and effective energy management within the grid.Methods: To address this issue, we propose a novel approach for intelligent grid electric vehicle charging scheduling and energy management, integrating three powerful technologies: Genetic Algorithm (GA), Gated Recurrent Unit (GRU) neural network, and Reinforcement Learning (RL) algorithm. This integrated approach enables global search, sequence prediction, and intelligent decision-making to optimize electric vehicle charging scheduling and energy management. Firstly, the Genetic Algorithm optimizes electric vehicle charging demands while minimizing peak grid loads. Secondly, the GRU model accurately predicts electric vehicle charging demands and grid load conditions, facilitating the optimization of electric vehicle charging schedules. Lastly, the Reinforcement Learning algorithm focuses on energy management, aiming to minimize grid energy costs while meeting electric vehicle charging demands.Results and discussion: Experimental results demonstrate that the method achieves prediction accuracy and recall rates of 97.56% and 95.17%, respectively, with parameters (M) and triggers (G) at 210.04 M and 115.65G, significantly outperforming traditional models. The approach significantly reduces peak grid loads and energy costs while ensuring the fulfilment of electric vehicle charging demands and promoting the adoption of green energy in smart city environments.