Purpose: Nigeria sits on massive renewable potential, yet clean power barely trickles into the national grid. This paper digs into why the transition keeps stalling despite the Electricity Act 2023 handing states the keys to their own power markets. Rather than celebrating the new legal framework, it examines the commercial and technical friction that is blocking developers from connecting to the grid. Methodology: This study used a qualitative policy review to examine Nigeria's renewable energy regulatory framework by reviewing key legal documents alongside relevant academic and industry publications. The selected materials, published mainly between 2023 and 2026, were examined through a structured narrative analysis to identify policy gaps affecting renewable energy policy readiness. Findings: The findings show that Nigeria has made important legal and policy progress, but implementation remains weak. The electricity market is fragmented, and renewable-energy developers continue to face challenges such as unclear federal-state coordination, limited grid capacity and flexibility, non-cost-reflective tariffs, and insufficient use of smart-grid, storage, and circular-economy technologies. The preliminary assessment produced a readiness score of 2.33 out of 6, suggesting that while policy ambition is evident, the conditions needed for effective market delivery are still inadequate. Unique Contribution to Theory, Practice and Policy: The six-pillar framework gives researchers a concrete diagnostic for measuring transition readiness beyond checkbox compliance. For industry players, it highlights exactly where projects get stuck between permitting chaos and unbankable contracts. For policymakers, the paper makes the case for binding federal-state coordination treaties, mandatory storage and digital standards, aggressive mini-grid scaling, and placing consumer affordability at the absolute center of market design rather than treating it as an afterthought.
MARBIYAT TAHIR GIDADO, BASHIRU ABDULGANIYU, MOHAMMED NASIR MUSA, Umaru Umaru
The increasing digitalization of smart grids has significantly improved the efficiency, reliability, and sustainability of modern power systems. However, the integration of advanced technologies, such as artificial intelligence, the Internet of Things, and cloud computing, has introduced new cybersecurity vulnerabilities that threaten critical energy infrastructure. This study presents a blockchain-enabled privacy-preserving Artificial intelligence framework designed to enhance cybersecurity in smart grid environments, with a particular focus on Northeast Nigeria as a case study. The framework integrates blockchain technology, federated learning, differential privacy, edge computing, and artificial intelligence (AI)-driven intrusion detection into a unified architecture to provide secure, intelligent, and privacy-aware protection for smart grid systems. The proposed framework was developed using the design science research methodology and evaluated through simulation and comparative performance analysis. The framework achieved excellent detection performance with an accuracy of 96.8%, precision of 95.9%, recall of 96.4%, and F1-score of 96.1%, significantly outperforming conventional centralized AI and blockchain-only approaches. The integration of federated learning and differential privacy effectively protected consumer information with a privacy leakage rate of only 2.7% while maintaining high model utility of 94.8%. The blockchain performance evaluation showed a transaction latency of 184.6 Ms, a throughput of 421.3 transactions per second, and efficient smart contract execution. The suitability of the framework for practical deployment with moderate resource requirements by computational assessment. The findings demonstrate that combining blockchain, privacy-preserving learning, and AI provides a comprehensive, scalable, and resilient cybersecurity solution for SGIs. This study contributes to the growing body of knowledge on smart grid cybersecurity and offers practical insights for utility providers, researchers, and policymakers seeking to strengthen the security and resilience of emerging smart grid systems, particularly in developing regions with infrastructural challenges.
A tokenised energy market settles payment against metered dispatch, but the meter reading is the prosumer's private information: a self-interested prosumer can report more energy than it supplied and be paid for the difference. The companion papers in this programme assume meter integrity — truthful reporting — and build settlement, participation, and delivery contracts on top of it. This paper derives the verification contract that makes the assumption hold. A prosumer dispatches a quantity it observes privately and reports a possibly inflated figure to the settlement layer; the grid-telemetry layer can audit a report at a cost, detecting a discrepancy with a probability that reflects sensor accuracy, and a detected misreport forfeits a posted verification stake. We treat the audit probability, the stake, and the sensor accuracy as the designer's instruments and characterise the verification that makes truthful reporting weakly dominant at minimum cost. The baseline assumes a margin-independent detection probability and one-sided audit error (false negatives possible, false positives excluded); both are stated and the general margin-dependent condition is given. First, truthful reporting is weakly dominant if and only if the expected forfeiture covers the largest gain from admissible over-reporting, αφB ≥ Pm̄ (strict under strict inequality), where α is the audit probability, φ the per-audit detection probability, B the stake, and m̄ the largest admissible over-report; with a one-unit maximum this is αφB ≥ P (Proposition 1). Second, along this deterrence frontier the audit probability is α = Pm̄/(φB), and once the stake is itself chosen against its capital carry the least-cost interior contract is B* = √(κPm̄/(ρφ)), α* = √(ρPm̄/(κφ)), total cost 2√(ρκPm̄/φ), all decreasing in detection accuracy, so accurate telemetry drives the audit rate, the stake, and the cost down together (Theorem 1). Third, sensor accuracy is itself a procurable instrument with a convex capital cost, and the cost-minimising accuracy equates marginal sensor capital cost to the marginal audit-opex saving, a capex–opex frontier between better meters and more auditing (Proposition 2). Fourth, the per-report enforcement αφB is exactly the meter-integrity guarantee the companion papers assume; truthful reporting is weakly dominant on the binding frontier and strict under an arbitrarily small slack, so the reported quantity equals the dispatched quantity, discharging that assumption from primitives and closing the stack at its base (Proposition 3). Full proofs are in the online appendix.
The increasing number of behind-the-meter distributed energy resources (DERs) is changing traditional distribution systems in a big way by adding new ways to control and monitor them. But the effectiveness and dependability of these systems depend heavily on the accuracy of the data (like measurements, control commands, etc.) that the prosumers, aggregators, and grid operators share with each other. In addition, traditional power systems rely entirely on trusted aggregators to gather data from these DERs. If these aggregators are hacked, the whole system could be at risk. In this paper, we respond to these concerns by suggesting a hierarchical blockchain-based framework that includes a distributed integrity auditing system for measuring DERs. By using hash functions and Merkle trees, a secure and lightweight blockchain-based hash aggregation protocol is made to make sure that behind-the-meter DERs' measurements are real. Also, an automated distributed sanity check of DERs' set points (control commands) is suggested to lower the risk of coordinated cyber attacks on a large number of DERs. The suggested framework is put into action and tested in a number of different situations to see how well it works and how safe it is. The results show that the framework can handle more work because it can cut its runtime and storage costs by about 47% and 44%, respectively.
Since the advent of smart contracts, security vulnerabilities have remained a persistent challenge, compromsing both the reliability of contract execution and the overall stability of the virtual currency market. Consequently... | Find, read and cite all the research you need on Tech Science Press
The hydropower fleet in Austria is ageing and needs to be modernised to adapt to changing conditions in national and international energy systems. The financial viability of hydropower repowering projects remains a challenge because of high investment costs and long payback periods. A part from additional revenuestreams, a Bitcoin mining operation has the potential to be used as a flexible demand source also for curtailment and grid stability services. This thesis provides quantitative evidence on whether a Bitcoin mining operation can serve as an additional revenue stream to improve the investment metrics of a hydro repowering project in Austria, using a dynamic investment calculation and sensitivity analysis.The results show that Bitcoin mining can improve the financial performance especially for run-of-river plants with higher full load hours. These positive effects are sensitive to the volatility of the Bitcoin price and the network hash rate, making long-term returns difficult to predict.
The rise of non-fungible tokens (NFTs) has increased the risk of fraud and market manipulation. This study introduces a method for detecting wash trading in the NFT marketplace using Graph Neural Networks (GNNs) applied to Ethereum blockchain transaction data. We constructed a heterogeneous graph, used Depth-First Search for labelling, and extracted graph features, including PageRank and degree centrality. We evaluate various classification models: Multilayer Perceptron (MLP), Graph Convolutional Neural Network (GCN), and Heterogeneous Graph Convolutional Neural Network (HeteroGCN). The results show that GNN models, particularly the feature-enhanced HeteroGCN, exhibit superior performance compared to featureless models and traditional tabular baselines. The key contribution of this study is that PageRank and Degree Centrality features significantly improve the accuracy of identifying transactions involved in market manipulation.
Bhabendu Kumar Mohanta, Ali Ismail Awad, Tarek Elsaka, Hamza Kheddar · 5 authors
Intelligent devices with embedded technology have proliferated dramatically over the past decade. The Internet of Things (IoT) has emerged as a transformational force, advancing traditional systems to previously unattainable levels of intelligence. Smart cities, transportation, healthcare, supply-chain management, agriculture, water management, and smart grid (SG) systems are among the industries where the IoT has found applications. These developments are demonstrated by the integration of IoT systems into SG networks, offering significant improvements in sustainability, dependability, and efficiency. Such systems use various IoT devices to continuously monitor the environment and transmit data for processing and analysis. Nonetheless, the growth of the IoT has introduced security vulnerabilities, including concerns about user identification, data integrity, and trust, especially in SG applications. This study aims to resolve several security challenges in IoT-enabled SG applications to support sustainability. The proposed scheme effectively tackles critical security requirements such as data integrity, user anonymity, distributed storage, trust management, and decentralized architecture. The security concerns addressed by blockchain technology include preserving data integrity, fostering trust, providing secure communication, and enabling effective monitoring. Smart contracts automate system processes and are effective in maintaining user trust. The experimental findings support the viability of the proposed system, demonstrating a computational cost of 3.150 ms and a communication overhead of 992 bits, both representing improvements over various existing solutions. Additionally, the deployment cost for the smart contract is found to be 5.64 USD with a writing cost of 2.89 USD, both of which are lower than the costs associated with comparable approaches.
Blockchain technologies have profoundly transformed information systems by providing decentralized infrastructures that enhance transparency, security, and traceability. Ethereum, in particular, supports smart contracts and facilitates the development of decentralized finance (DeFi), non-fungible tokens (NFTs), and Web3 applications. However, its openness also enables illicit activities, including fraud and money laundering, through anonymous wallets. Identifying wallets involved in large transfers or abnormal transactional patterns is therefore critical to ecosystem security. This study proposes an AI-based framework employing XGBoost, LightGBM, and CatBoost to detect suspicious Ethereum wallets, achieving test accuracies between 95.83% and 96.46%. The system provides near real-time predictions for individual or recent wallet addresses using a pre-trained XGBoost model. To improve interpretability, SHAP (SHapley Additive exPlanations) visualizations are integrated, highlighting the contribution of each feature. The results demonstrate the effectiveness of AI-driven methods in monitoring and securing Ethereum transactions against fraudulent activities.
This study delves into the vulnerability of the smart grid to infiltration by hackers and proposes methods to safeguard it by leveraging blockchain and artificial intelligence (AI). A categorization and analysis of cyberattacks against smart grids will be conducted, focusing on those targeting their communication layers. The main goal of the work is to address the challenges in this area by implementing novel detection and defense strategies. The authors categorize attacks on smart grid networks based on the communication classes they want to compromise. They propose novel taxonomies specifically designed to detect and implement defense strategies. The study investigates artificial intelligence and blockchain techniques to identify cyber-attacks that employ deceptive data injection. The study indicates that cyberattacks against smart grids are increasing in frequency and complexity. The paper proposes innovative strategies for defense, such as enhancing cybersecurity with artificial intelligence and blockchain technology. The research further enumerates several challenges, such as counterfeit topological data, imprecise data identification, and combining big data with blockchain technology. Given the increasing risks, the study emphasizes the crucial need for robust cybersecurity safeguards in smart grids. This work contributes to the protection of smart grid infrastructures by categorizing attacks, suggesting novel defenses, and exploring solutions integrating artificial intelligence and blockchain technology. Research should prioritize enhancing technology to maximize security and counter emerging attack methods. The intended audience of our paper comprises graduate-level academics and independent researchers.
Mubarak A. Khan, Md Mofijul Islam, Istiaq Ahmed, Md Masud Karim Rabbi · 10 authors
Peer-to-peer trading and the move to decentralized grids have reshaped the energy markets in the United States. Notwithstanding, such developments lead to new challenges, mainly regarding the safety and authenticity of energy trade. This study aimed to develop and build a secure, intelligent, and efficient energy transaction system for the decentralized US energy market. This research interlinks the technological prowess of blockchain and artificial intelligence (AI) in a novel way to solve long-standing challenges in the distributed energy market, specifically those of security, fraudulent behavior detection, and market reliability. The dataset for this research is comprised of more than 1.2 million anonymized energy transaction records from a simulated peer-to-peer (P2P) energy exchange network emulating real-life blockchain-based American microgrids, including those tested by LO3 Energy and Grid+ Labs. Each record contains detailed fields of transaction identifier, timestamp, energy volume (kWh), transaction type (buy/sell), unit price, prosumer/consumer identifier (hashed for privacy), smart meter readings, geolocation regions, and settlement confirmation status. The dataset also includes system-calculated behavior metrics of transaction rate, variability of energy production, and historical pricing patterns. The system architecture proposed involves the integration of two layers, namely a blockchain layer and artificial intelligence (AI) layer, each playing a unique but complementary function in energy transaction securing and market intelligence improvement. The machine learning models used in this research were specifically chosen for their established high performance in classification tasks, specifically in the identification of energy transaction fraud in decentralized markets. To guarantee the reliability and accuracy of the used machine learning models, an extensive battery of evaluation metrics was utilized. The plot demonstrates clearly that XG-Boost obtained the highest accuracy out of the three models, Random Forest was slightly lower, and conversely, Logistic Regression was the lowest of the three models. Integrating blockchain technology with AI can increase the transparency, security, and efficiency of the energy sector in the U.S. Blockchain's decentralized and immutable ledger can make energy transactions traceable and resistant to tampering, and it becomes extremely hard for malicious actors to manipulate prices or fake records. In the future, the integration of deep learning methodologies and real-time integration of data from the Internet of Things (IoT) holds promising implications for future improvements. Deep learning models like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) can detect strongly nonlinear patterns of fraud, which conventional models may not identify, particularly for the usage of multivariate time-series data from smart meters, sensors, and distributed energy resources.
The application of smart contracts in electric power systems is widespread. However, vulnerabilities in smart contracts can cause significant economic losses and require careful attention. Smart contracts in electric power systems have domain-specific characteristics that differ from traditional public blockchain applications. As a result, existing vulnerability detection tools cannot be directly applied to these systems. To address this challenge, we design a vulnerability detection tool called E-Guard specifically for smart contracts in electric power systems. E-Guard uses a tailored intermediate representation (IR) known as EIR, which provides control flow and data flow information more suited to the business logic of electric power systems than traditional static analysis tools. We identify and summarize three types of vulnerabilities unique to electric power systems based on expert knowledge. Experimental results show that E-Guard significantly outperforms traditional static analysis tools in detecting these three types of vulnerabilities. Additionally, the extra overhead generated by using EIR is minimal and negligible. This demonstrates that E-Guard is an effective and efficient tool for enhancing the security of smart contracts in electric power systems.
Smart grid technology is an amicable improvement of the conventional power grid characterized by improved communication, control, and computing technologies that enhance improved energy distribution. A smart grid is an improvement on the existing electric grid system that allow for more intelligent controlling of electricity from the generation point right down to the consumer. Consequently, the ICS (Industrial Control Systems) of smart grids have become more exposed to cyber risks resulting from enhanced network integration and digitalization. The complexity of smart grids with many DERs (Distributed Energy Resources), sensors, and systems make the security problem challenging. Reasons why decentralised smart grids have to be secure and more resilient mean that new approaches that can enable detection, prevention, and mitigations of cyber-attacks are desirable. Deep learning and smart grid cybersecurity based on decentralization has a bright outlook as it enables improving the detection of anomaly cases and potential threats and increasing the general level of resilience of the grid.Smart grids are a major evolution of conventional power grids that employ ICT (Information and Communication Technology) to optimize the delivery of electrical energy. Elements of smart grid include smart meters for consumers, automated distribution network, and communication network. Smart grids can be decentralised as it includes multiple DERs like solar power, wind mills or energy storage systems, that are usually integrated at the outskirts of the smart grid. Such decentralization adds more challenges to the grid's physical structure and also adds more vectors by which a cyber-threat can penetrate the network [1]. As such, cybersecurity emerged as a focal topic to protect the safe and reliable functioning of smart grids. It has also shown a commanding success in several contexts, which is due to the deep learning's inclusion capabilities of key features from accesses data [2]. A major advantage of deep learning is that models are able to detect the abnormal flow of traffic since they hold knowledge of normal traffic flow patterns [3]. Pattern recognition is another important factor; deep learning networks can recognize even complex pattern in a given data. However, deep learning models include scalability hence making them capable of analyzing a large quantity of data produced by, for instance, smart grids [4].The decentralized smart grids are the most vulnerable because of the localized architecture and large connections with IoT gadgets. The different systems that are used in smart girds are not homogenous and have different protocols and hence the weakness are provided [5]. Lack of computational capacity of many IoT devices due to resource constraints precludes such approaches and traditional security techniques cannot be implemented [6].Despite the potential of deep learning in smart grid cybersecurity, there are a number of issues before it. Concerning a few key points, it is important to mention data confidentiality as the training data can be considered sensitive. Another, there is an interpretability problem since, unlike traditional machine learning techniques, deep learning's models are considered 'black box' [7]. Another limitation of deep learning is that it demands massive computation, which may well not be readily feasible in low-power devices of smart grid [8]. There is also a big issue related to integration with legacy systems because such systems might be incompatible with deep learning solutions [9].Future research directions encompass the development of Smart grids which are decentralized and also experience a higher level of risk with relation to cybersecurity because of the deployment of several IoT devices. Table 1 summarizes robust deep learning approaches for smart grid cybersecurity, highlighting their advantages, challenges, and future directions. While these methods show high accuracy in detecting cyber threats (ranging from 92% to 99.5%), they face issues like high computational demands, vulnerability to adversarial attacks, and scalability concerns. Future research focuses on improving real-time integration, enhancing model interpretability, and developing more robust AI-driven cybersecurity frameworks.The most suitable solution for smart grid cybersecurity protection combines Federated Learning with Blockchain and Adversarial Deep Learning. With FL the grid nodes can participate in decentralized training processes without exchanging actual data which protects their information security and privacy. The combination of Blockchain technology and adversarial training creates an unalterable security framework which secures communication while building resistance against complex cyber threats. The implementation of this combined method becomes necessary because smart grids function through decentralized systems that connect many vulnerable IoT-enabled energy production networks to cyber security threats. Maximum security models become ineffective because they suffer from dimensional problems alongside privacy weaknesses and developing electronic strike threats. Through an integration of FL and Blockchain technology organizations achieve real-time threat detection with adaptive capabilities and lower IT overhead costs. Industrial security in the energy sector needs sophisticated AI-enabled solutions which must scale effectively to defend against infrastructure attacks and disruption of power supply. By utilizing this model organizations maintain autonomous cybersecurity operations which produce efficient proactive threat protection suitable for advanced smart grid systems against developing cyber attacks. Deep learning in the decentralised smart grid cybersecurity is a revolutionary way of handling the huge and dynamic risks. Based on the real-time data processing characteristic and the ability to recognize patterns of deep learning models, it is possible to improve the density of anomaly detection, threats' prediction, and systems' robustness. However, there are challenges that the use of deep learning in this area holds among them the fact that it calls for usage of a lot of computational power, data security issues, and the issues related with initiation and incorporation of integration of such complex technologies in the existing systems. To overcome these challenges new approaches, need to be created more efficiently, focus on to build effective privacy preservations, and integrate with other existing systems. For future work, the focus should be made on introducing new sophisticated and flexible frameworks of deep learning for the smart grid that will function in the given distributed environment. In this way, the industry can progress and advance towards building a smarter grid, that can address novel cyber threats and protect and enhance the reliability of the energy distribution systems.
Smart contracts on blockchain networks autonomously execute applications based on predefined conditions, making their security-critical due to the potential for significant financial losses from vulnerabilities. Current vulnerability detection algorithms commonly rely on expert-defined rules, which are prone to errors and insufficient for identifying complex vulnerability patterns . Given the immutability of smart contracts post-deployment, ensuring security before deployment is essential. This research presents Block-wise Abstract Syntax Tree based Federated Graph Neural Networks (BAST-FeGNN), a novel approach combining block-wise abstract syntax tree and Federated Graph Neural Networks (FeGNN) to detect code clones and multiclass vulnerabilities in Ethereum smart contracts. The BAST-FeGNN method operates in three stages: it first extracts security-related patterns from the base code using an abstract syntax tree; then, it constructs and normalizes a contract graph using FeGNN to capture critical nodes, analyze data and control flows. This integration of graph-based feature extraction with pattern matching allows precise detection of vulnerabilities like access control issues, reentrancy, and unchecked calls, as well as identifying code clones. Finally, the method pools these features for comprehensive vulnerability detection . BAST-FeGNN significantly enhances vulnerability detection accuracy and scalability, outperforming existing models with an accuracy of 95.35%, recall of 95.58%, F1-score of 95.80%, and precision of 96.10%, making it a robust solution for securing blockchain applications.
Dong Liu, Juan S. Giraldo, Peter Pálenský, Pedro P. Vergara
Model-free power flow calculation, driven by the rise of smart meter (SM) data and the lack of network topology, often relies on artificial intelligence neural networks (ANNs). However, training ANNs require vast amounts of SM data, posing privacy risks for households in distribution networks. To ensure customers' privacy during the SM data gathering and online sharing, we introduce a privacy preserving PF calculation framework, composed of two local strategies: a local randomisation strategy (LRS) and a local zero-knowledge proof (ZKP)-based data collection strategy. First, the LRS is used to achieve irreversible transformation and robust privacy protection for active and reactive power data, thereby ensuring that personal data remains confidential. Subsequently, the ZKP-based data collecting strategy is adopted to securely gather the training dataset for the ANN, enabling SMs to interact with the distribution system operator without revealing the actual voltage magnitude. Moreover, to mitigate the accuracy loss induced by the seasonal variations in load profiles, an incremental learning strategy is incorporated into the online application. The results across three datasets with varying measurement errors demonstrate that the proposed framework efficiently collects one month of SM data within one hour. Furthermore, it robustly maintains mean errors of 0.005 p.u. and 0.014 p.u. under multiple measurement errors and seasonal variations in load profiles, respectively.
Cryptocurrency has transformed finance and investment, with platforms like Uniswap facilitating billions of dollars in trades. However, malicious smart contracts and scam tokens have led to significant financial losses for decentralized finance (DeFi) users. Code analysis alone cannot detect rug pulls using social engineering tactics. To address this issue, machine learning algorithms can leverage the vast amount of transactional data stored on the blockchain, particularly time series data, to identify scam tokens. This study aims to determine the optimal timeframe for detecting rug pulls and highlights the importance of token volume and transaction count features. The findings suggest that shorter timeframes are sufficient for detecting rug pull tokens since most incidents occur soon after token creation. This research offers new insights into scam token classification and prevention and contributes to a broader understanding of this field. • Rug pull detection in Uniswap V3 is researched via on-chain indicators over time. • Many rug pulls occur during the first day after token creation. • Time windows close to rug pull events significantly influence the model's predictions.
Yunusa Ishaq, Ajuru Success Prince, Gbah Gonto Jean Claude, Togola Molobaly Di Bebe
Abstract: The transition to smart grids has revolutionized energy distribution, enabling more efficient and flexible power management through advanced communication and control systems. However, this interconnected structure makes smart grids vulnerable to cyberattacks, such as False Data Injection Attacks (FDIA), Distributed Denial of Service (DDoS) attacks, and data manipulation. These threats undermine the stability and reliability of the grid, and existing centralized security frameworks are often ill-equipped to address them due to their susceptibility to single points of failure and limited scalability. To overcome these challenges, this paper introduces a decentralized security framework that combines blockchain technology with machine learning (ML). The framework leverages blockchain to provide a transparent, immutable, and decentralized ledger, employing consensus mechanisms like Practical Byzantine Fault Tolerance (PBFT) or Proof of Authority (PoA) to ensure secure data validation. Alongside this, ML models, including Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNN), are used to detect anomalies in time-series data, such as FDIA, with high precision. Smart contracts embedded in the blockchain enable automated, real-time responses to threats, such as isolating compromised nodes or rerouting energy flows to maintain grid stability. Through simulations replicating real-world cyberattacks, the proposed framework demonstrated over 95% detection accuracy, a 30% reduction in response times, and enhanced computational efficiency with lower energy consumption. These results affirm the effectiveness of the framework as a scalable and resilient solution for modern smart grid security.
Oghenerume Augoye, Adekunle Adewoyin, Olugbenga Adediwin, Audu Joseph Audu
Artificial Intelligence (AI) is transforming energy financing by enhancing decision-making, optimizing investment portfolios, and improving risk assessment in sustainable infrastructure projects. This review explores the role of AI in energy financing, focusing on its applications in risk evaluation, credit scoring, investment optimization, and the development of climate-aligned financial strategies. AI-driven predictive analytics enable investors to assess the financial viability of renewable energy projects, identify high-impact opportunities, and optimize asset allocation. Additionally, AI-powered models enhance credit scoring for energy developers, facilitating access to funding for clean energy initiatives. The integration of AI with blockchain and smart contracts is also revolutionizing energy financing by ensuring transparency, reducing fraud, and automating financial transactions in sustainable projects. Furthermore, AI plays a crucial role in the management and monitoring of green bonds, improving impact assessment and ensuring accountability in climate finance. However, several challenges hinder AI-driven energy financing, including data limitations, regulatory gaps, cybersecurity risks, and potential biases in AI decision-making models. Ensuring data quality, developing ethical AI frameworks, and addressing cybersecurity concerns are essential for AI’s successful adoption in energy investment strategies. Future opportunities lie in AI-driven predictive analytics for emerging markets, enabling better financing mechanisms for off-grid and decentralized energy solutions. AI can also enhance public-private partnerships by optimizing investment structures and improving government funding allocation for renewable energy projects. As AI continues to evolve, it holds the potential to reshape energy financing, drive sustainable investments, and accelerate the transition to a low-carbon economy. This review underscores the need for collaborative efforts among policymakers, financial institutions, and technology providers to maximize AI’s potential in sustainable energy infrastructure financing while addressing its inherent challenges.
Ze Chang, Yunfei Cai, Xiao Fan Liu, Zhenping Xie · 6 authors
With the rapid development of blockchain technology, fraudulent activities have significantly increased, posing a major threat to the personal assets of blockchain users. The blockchain transaction network formed during user transactions can be represented as a graph consisting of nodes and edges, making it suitable for a graph data structure. Fraudulent nodes in the transaction network are referred to as anomalous nodes. In recent years, the mainstream method for detecting anomalous nodes in graphs has been the use of graph data mining techniques. However, anomalous nodes typically constitute only a small portion of the transaction network, known as the minority class, while the majority of nodes are normal nodes, referred to as the majority class. This discrepancy in sample sizes results in class imbalance data, where models tend to overfit the features of the majority class and neglect those of the minority class. This issue presents significant challenges for traditional graph data mining techniques. In this paper, we propose a novel graph neural network method to overcome class imbalance issues by improving the Graph Attention Network (GAT) and incorporating ensemble learning concepts. Our method combines GAT with a subtree attention mechanism and two ensemble learning methods: Bootstrap Aggregating (Bagging) and Categorical Boosting (CAT), called SGAT-BC. We conducted experiments on four real-world blockchain transaction datasets, and the results demonstrate that SGAT-BC outperforms existing baseline models.
• The article highlights the significance of smart grids in managing energy demand, addressing environmental issues, and ensuring energy security, emphasizing the need for blockchain technology and AI. • The study discusses data collection from smart city power consumption in a smart grid, utilizing techniques like Z-Score normalization and Spatial Temporal Correlation, and suggests blockchain technology for secure data transmission and storage. • The paper proposes a LSTM-RNN-ISSA for improved load forecasting accuracy and discusses the use of Blockchain-Based Smart Energy trading for effective communication in the smart grid. • Task-Oriented Communication facilitates real-time demand response, balancing electrical load and supply, outperforming existing approaches in smart city energy management. A smart grid (SG) is the financial benefit of a complicated and smart power system that can keep up with rising demand. It has to do with saving energy and being environmentally friendly. Growing populations and new technologies have caused a big rise in energy use, causing big problems for the environment and energy security. It is essential and significant to use blockchain technology and artificial intelligence (AI) to solve problems with power control. Data can be collected using a smart city in a power-consumed smart grid data and pre-process using a Z-Score normalization technique. It can extract features using a Spatial-Temporal Correlation (STC) to assess smart grid power usage within the context of a smart city using large-scale, high-dimensional data. Ensuring data integrity, privacy, and trust among grid applicants, transmit the data securely and reliably to a centralized or distributed cloud platform utilizing blockchain technology—a secure transmission and storage using Distributed Authentication and Authorization (DAA) protocol. To achieve precise load forecasting, a short-term recurrent neural network with an improved sparrow search algorithm (LSTM-RNN-ISSA) is incorporated. The smart grid may then record the projected results. Communication can be done on a smart grid with the users; the Blockchain-Based Smart Energy Trading with Adaptive Volt-VAR Optimization (BSET-AVVO) algorithm can be used for effective communication—a quick balancing electrical load and supply via a task-oriented communication mechanism in real-time demand response. Finally, our proposed method performs successfully better than the existing approaches.
Gary Hahn, Emilio C. Piesciorovsky, Raymond Borges Hink, Aaron Werth
• Faulted phases detection using backup method that is external to protective relay. • Validates integrity of input data using distributed ledger technology. • Tested using simulated faults in a realistic electrical substation test bed. Modern electrical grids have intelligent electronic devices (IEDs) such as protective relays that use internal logic to detect the types of electrical faults. The increasing integration of distributed energy sources and the resulting complexity of electrical grid communication architectures necessitates enhanced robustness of IEDs’ monitoring while maintaining security against potential cyber threats. In this study, a backup electrical faulted phase detection method with a distributed ledger technology (DLT) platform was implemented. Cyber Grid Guard software was developed to collect phase currents and voltages transmitted through IEC 61850 GOOSE messages, detect faulted phases from the IEDs using the GOOSE data, and validate the data by hashing them and storing them in the distributed ledger. In this way, the hashed data were run into an electrical faulted phase algorithm based on using a current threshold for detecting the faulted phases in the medium-voltage main feeder of an electrical substation. The detection of the electrical faulted phases was assessed in a real-time simulator with protective relays, meters, the software framework, and DLT in the loop. The proposed method provides secure and reliable backup detection external to the IEDs, and DLT validation enhances system security and trust.
The integration of smart contracts within water distribution networks presents a transformative approach to addressing challenges in water management. In this context, we propose a pioneering tool aimed at streamlining the design and implementation of smart contracts tailored specifically to smart water distribution networks. This tool allows stakeholders to input essential parameters such as water sources, distribution points, consumption patterns, and contractual stipulations. Through the utilization of predefined templates and adaptable contract logic, the tool automates critical processes including water allocation, usage monitoring, and penalty imposition based on predefined criteria. Furthermore, seamless integration with blockchain technology ensures the security and integrity of contract execution. By addressing scalability, compliance, and regulatory considerations, this tool represents a significant advancement in empowering stakeholders to optimize water management practices through the deployment of efficient and transparent smart contracts.