The reliability of AI generative models is typically measured by output correctness, yet in practice it depends on the effort required to verify those outputs. We argue that current evaluation metrics overlook a critical failure mode: Verification-Cost Errors (VCEs), defined as incorrect input-output pairs that a declared fraction of the verifier population fails to identify within the verification budget available in a given deployment context. Unlike standard notions of "hallucination", VCEs are defined operationally, by the failure of correct identification within budget rather than by any property of the output itself. Plausibility and authoritative presentation are hypothesised contributors to that failure, not defining conditions. To capture this asymmetry, we introduce the notion of verification cost relative to a deployment budget as an operational dimension that current evaluation does not routinely capture. The quantity is presented as a conceptual instrument rather than a finalized metric. Evidence from code generation and multi-modal document understanding shows that high benchmark accuracy can mask significant verification effort in practice. We therefore take the position that correctness alone is insufficient as a measure of reliability. AI evaluation should explicitly account for verification cost, reflecting whether errors can be detected under realistic resource constraints.
Residential photovoltaic generation and household demand are temporally mismatched, affecting grid dependence and local storage use. This study formulates a 24 h mixed-integer linear programming model for a grid-connected residential prosumer with rooftop PV, a stationary behind-the-meter battery, and an electric vehicle capable of vehicle-to-home operation. Four configurations are compared under common external inputs: no storage, battery only, V2H only, and a hybrid battery–V2H system. The model resolves the main power routes, enforces charging, discharging, and cyclic state-of-charge constraints, allows grid charging, and excludes storage-to-grid export. PV generation is reduced, and residential demand is increased through a prescribed deviation-scaling parameter evaluated at five levels for clear-day and synthetic partly cloudy profiles. Numerical consistency is checked using an independent no-storage calculation and equation residuals. At ρ = 0.3 under the clear-day profile, the hybrid configuration reduces daily operating cost from USD 26.113 to USD 17.807, increases PV self-consumption from 69.684% to 89.121%, lowers utility purchase from 106.380 to 88.700 kWh/day, and reduces export from 36.170 to 12.980 kWh/day. Under the partly cloudy profile, all storage-based configurations reach 100% PV self-consumption and zero export, while the hybrid case retains the lowest operating cost. The results are conditional on the adopted capacities, continuous EV connection, tariff structure, and exclusion of degradation and investment costs.
Safety-critical sectors such as power transmission and autonomous mobility are not replacing their deterministic controllers; they are adding artificial intelligence (AI) layers to existing systems to gain additional, sustainable business value. This approach increases the socio-technical complexity, creating pressure for a structured means to compare benefits, oversight effort and risk over time. In this descriptive study, we introduce Epistemic Gain G, a scalar derived from the Delta - eta - zeta model that links foresight gains to human oversight and system friction. Within this framework, G > 0 is treated as a necessary condition for epistemically sustainable scaling. We then formulate a conjectured governance-level Law of Diminishing Returns that holds up to a Scaling Failure Threshold, beyond which marginal upgrades begin to destroy value. Drawing on recent empirical studies, we further sketch the Delta - eta - zeta model and show how G can be displayed in software development lifecycle dashboards. This paper extends the earlier IEEE AI & times;B 2025 conference paper in three main directions: (i) provide the theoretical foundation of the M-Vector and formalize it as the explicit epistemic state M(t) underpinning the Delta - eta - zeta model; (ii) introducing semantic instability phi and epistemic drift xi as properties inspired by causal representation learning, used here as an AI-safety and governance lens; and (iii) identifying canonical regions of M-space for deterministic, vital, symbolic, sub-symbolic and generative AI systems. The overarching aim is to formalize the theoretical basis of G and its time-variant machine form, enabling it to serve as a governance indicator for when to scale, optimize, or pause AI deployments.
Green hydrogen is increasingly discussed as an energy carrier that can link electricity, gas, heat, and transport sectors. However, many existing reviews address this topic from separate viewpoints, such as hydrogen production technologies, Artificial Intelligence (AI) applications, or system integration, with less attention to how policy and market conditions affect deployment. This review brings these related aspects together in one structured discussion. The paper first reviews the hydrogen supply chain, including production, storage, transport, and utilization. It then discusses an integrated multi-energy architecture in which hydrogen interacts with electricity, natural gas, heat, and cooling networks. Policy instruments in five major economies, including the European Union, the United States, China, Japan, and India, are compared. The review also summarizes the main barriers to large-scale deployment, including high production costs, limited infrastructure, technological challenges, regulatory uncertainty, and supply-chain constraints. In addition, the current market structure and selected large-scale hydrogen projects planned in the United States are reviewed. The paper also examines the role of artificial intelligence in green hydrogen systems. AI applications are grouped into four main stages of the hydrogen value chain: forecasting renewable energy generation, improving electrolyzer design and operation, optimizing storage and distribution, and supporting system-level techno-economic assessment. Recent Machine Learning (ML) studies are compared based on their methods and their contributions to operation and planning. Overall, this review highlights the role of AI in enabling green hydrogen integration within multi-energy systems.
Peer-to-peer (P2P) energy trading combines local energy resources, market coordination, data-driven decisions, and transaction management. This review examines how machine learning (ML) and blockchain are used across these functions and separates market and ledger processes from physical electricity delivery. A structured review procedure was applied to a corpus of 52 peer-reviewed journal articles, including the core P2P energy-trading evidence and a limited number of closely related contextual studies, supplemented by 10 non-journal or foundational sources, using defined search families, screening criteria, and qualitative synthesis. The literature is organized by the functional role of ML and compared across architecture, market operation, trust, consensus, privacy, and implementation. The consensus discussion considers practical Byzantine fault tolerance, Istanbul Byzantine fault tolerance, proof-of-authority, and application-oriented Byzantine-fault-tolerance variants, while the privacy discussion distinguishes federated learning, differential privacy, zero-knowledge proofs, and secure multiparty computation. Two deterministic MATLAB examples are included only for illustration. In the five-prosumer forecasting example, regression reduced mean absolute error (MAE) from 0.4240 to 0.2219 kWh and the hourly grid-import mismatch from 30.3529 to 7.9029 kWh. In the 10-peer workflow, five trades settled 7.7587 kWh, corresponding to 59.35% of the horizon-level surplus–deficit denominator defined in the simulation. These examples do not validate feeder feasibility, consensus performance, cryptographic security, or deployment readiness.
