Search Results (47)

Open smart-hive datasets collected under commercial pollination conditions remain scarce and often lack homogeneous timestamps and synchronized event metadata. We present the decentralized AmoHive monitoring architecture and an open hourly IoT telemetry dataset collected from nine structurally identical solar-powered hives from 1 May to 31 August 2024 in the Kyiv region of Ukraine. Each hive operated as an autonomous sensing and GSM communication node without a local concentrator, allowing four instrumented colonies to be relocated to two sunflower fields without reconfiguring shared infrastructure. System operation was evaluated through temporal alignment, node-level coverage, missing-data runs, channel completeness, consistency of co-located external sensors, and a limited reconstruction check. All nodes produced records compatible with the common hourly grid. Observed coverage ranged from 76.6% to 95.8%, and missing-data runs were predominantly one to two hours. Co-located external-temperature channels tracked shared conditions consistently, whereas relative-humidity channels showed larger unit-specific differences. The released resource contains approximately 26.5 thousand hourly multichannel records, paired RAW and CLEAN layers, campaign metadata, a timestamped beekeeper-event workbook with an accompanying embedding script, and value-level provenance. The scientific contribution is a system-level field evaluation of a relocatable per-hive IoT topology coupled with a traceable dataset that connects physical deployment, node-specific data quality, and reproducible preprocessing. Full article

This study addresses the integration of a photovoltaic (PV) subsystem and a digital twin into the power supply system of bakery production. A four-level architecture is proposed, comprising a physical level, a data acquisition level, an analytical level implemented as a digital twin, and a control level. A low-power stand-alone PV installation that supplies sensors, telemetry units, controllers, and lighting is examined, and its daily operating cycle is analyzed. The PV output power varies from 10 W in the early morning to 300 W at midday, whereas the auxiliary load ranges from 120 to 160 W; the battery state of charge reaches 95–96% in the afternoon. Solar generation fully covers the auxiliary demand between 09:00 and 16:00 and supplies 77.0% of the daily auxiliary energy, with the remainder being provided by the battery storage (18.4%) and the external grid (4.6%). The proposed approach increases the transparency of energy processes and provides a basis for the intelligent management of the auxiliary energy infrastructure of bakery enterprises. Full article

Life cycle assessment (LCA) of photovoltaic systems rests largely on aggregated, time-invariant inventories. In Colombia, registered solar projects grew by 128.6% between 2018–2022 and 2022–2025, while environmental follow-up remains self-reported and semi-annual. We report IMPACT Energy.CO, a data infrastructure designed to enable dynamic LCA and installed in the production environment of the national hydrocarbons agency. It normalises heterogeneous telemetry onto a versioned vocabulary, hash-chains derived indicators and includes a headless openLCA connector. It was tested before the transfer and its telemetry path was exercised against a test instance only; no field telemetry has entered an inventory and no telemetry-to-openLCA run is evidenced, so the evidence supports an enabling proof of concept. Of 144 candidates, 32 indicators were screened; experts scored all 32 and communities 24. On fifteen shared social indicators, scored with non-equivalent instruments, the two rankings show no resolvable association ($\rho =-0.07$); in exploratory analysis the expert ranking is ordered by stakeholder category (Kendall’s ${\tau }_b=0.63$). Under an explicit criterion, energy and carbon payback time, ranked second and third by the experts, are the only screened environmental indicators an assessment engine cannot return as results. Re-scaling published values of the International Energy Agency Photovoltaic Power Systems Programme to Caribbean irradiance lowers the generation-normalised global warming potential of monocrystalline silicon modules by 32% (95% propagation interval 20–42%), and carbon payback varies three- to four-fold across official grid emission factors. Full article

Federated learning (FL) can support collaborative smart-grid monitoring without centralizing raw telemetry, but its value relative to local and centralized learning depends on both the operating regime and the learning model. This study evaluates that hypothesis in a physics-based AC power-flow simulation framework built on IEEE 14-, 39-, and 118-bus benchmark systems over 30-day horizons at 1 h resolution. The framework is a controlled simulation environment rather than a field-coupled or real-time digital twin. Twenty independent physical seeds were used to compare centralized XGBoost, local-only learning, FedAvg, SCAFFOLD, and a study-specific validation-blended personalized FedAvg, with pooled same-optimizer centralized linear/logistic controls used to isolate federation from model-family effects. Under nominal operation, centralized or personalized models were strongest; on IEEE 118, XGBoost achieved the lowest line-loading and power-loss MAEs (1.331 percentage points and 2.880 MW), while local-only and personalized learning achieved voltage-deviation MAEs of 0.000327 and 0.000330 p.u. Under IEEE 118 N-1 voltage-instability detection, centralized logistic gradient descent, FedAvg, and SCAFFOLD all achieved AUPRC values of approximately 0.993, demonstrating that much of the apparent XGBoost-to-FL gap was model-family-dependent. Under cross-attack transfer, SCAFFOLD retained small but statistically significant advantages over the matched centralized control. A targeted operational-threshold sensitivity analysis added 1500 refits across 15 threshold settings and 20 seeds; the qualitative separation between the federated and non-federated approaches remained stable, although the exact ordering among federated variants was metric- and threshold-dependent. Moderate telemetry noise, missingness, and bounded reporting delay caused at most 1.7% relative MAE degradation, whereas physical-regime changes produced substantially larger effects. The results support a regime-dependent and model-controlled interpretation of FL for supervisory smart-grid monitoring. Full article

Electric vehicle (EV) charging stations and vehicle-to-grid (V2G) systems depend on outbound Domain Name System (DNS) resolution for firmware retrieval, backend discovery, and fleet synchronization, making DNS tunneling an attractive covert command-and-control and data-exfiltration channel in charging infrastructure. Machine learning detectors trained on lexical and statistical DNS features achieve excellent in-distribution accuracy, yet they are rarely stress-tested against adaptive adversaries that deliberately reshape query characteristics toward benign traffic. This paper presents a station-independent evaluation framework and an adaptive-augmented, cyber-physical detection architecture for evasive DNS tunneling in EV charging and V2G networks. Using a 200-station synthetic dataset that couples 24 DNS features with 16 EV/Open Charge Point Protocol (OCPP)/V2G telemetry features and 14 cross-modal consistency features, we evaluate every detector over ten repeated grouped station-level splits and across three attack regimes: an adaptive-strength sweep (β = 0.25–0.95) of the interpolation mechanism used in training, a separately held-out constraint-aware adaptive mechanism excluded from all training and model selection, and multiplicative perturbation of the physical-anchor telemetry at relative scales of 5–20%. Under strong interpolation-based evasion at the training strength (β = 0.90), detectors relying on DNS evidence retain almost no detection capability at their original operating point (mean F1 = 0.041 ± 0.023), although part of their threshold-free ranking ability survives, and recalibrating the decision threshold alone does not repair the collapse. We propose a safe EV-anchored fusion detector that treats physical telemetry as a protected anchor, hardens a cross-modal branch with adaptive examples drawn only from training stations, and admits DNS evidence only through a bounded, validation-selected correction. Across the ten splits, the proposed detector sustains F1 = 0.909 ± 0.013 at β = 0.90 and F1 = 0.923 ± 0.016 under the held-out mechanism, retaining approximately 94–96% of its original F1 of 0.964 ± 0.006 at a false-positive rate near 5.5% (about 55 false alarms per 1000 benign windows), and it degrades gracefully (F1 ≥ 0.911) when the anchor telemetry is perturbed at up to 20% relative scale. The results indicate that anchoring detection in physical-side telemetry, with bounded and adaptively hardened cross-modal evidence, provides consistent performance across the evaluated repeated station partitions and is computationally feasible under the evaluated conditions. Full article

Accurate photovoltaic (PV) power forecasting is essential for renewable energy integration, dynamic reserve allocation, and generation scheduling. Unpredicted generation ramps induce substantial voltage and frequency deviations on grid-connected distribution networks. This paper provides an objective benchmark among three deep learning architectures: Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM). Telemetry spanning one year from an operational 175 kW plant in Reggane, Algeria, is evaluated across 72 h horizons ($\mathrm{H}=288$ steps at 15 min resolution) using a Direct Multi-Input Multi-Output framework under strict chronological splitting. The models are systematically evaluated across 1848 rolling 72 h forecast windows using a controlled benchmark protocol under daylight-only conditions ($\mathrm{GHI}>5{ \mathrm{W}/\mathrm{m}}^2$) against a Diurnal Smart Persistence baseline. Accuracy is assessed via daylight capacity-normalized MAE ($\mathrm{nMAE}$), $\mathrm{nRMSE}$, Diebold–Mariano tests ($\mathrm{h}=72$ lags), and ramp metrics across 34,840 events. The results demonstrate that deep architectures significantly outperform persistence ($\mathit{p}<0.001$). BiLSTM achieves superior overall accuracy ($\mathrm{nMAE}=2.84\%$, $\mathrm{nRMSE}=3.60\%$, ${\mathrm{R}}^2=0.985$, skill score = 79.37%) and the highest ramp fidelity (F1-Ramp = 0.965, $\mathrm{RME}=6.97 \mathrm{kW}$, yielding 54.95% ramp error reduction). Standard LSTM demonstrates competitive performance ($\mathrm{nMAE}=3.19\%$, skill score = 77.95%), whereas GRU exhibits higher deviations ($\mathrm{nMAE}=5.05\%$, skill score = 66.91%). Measured sub-millisecond latencies (0.07–0.11 ms/sample) confirm that computational overhead is negligible for 15 min dispatch, establishing BiLSTM as optimal for operational dispatch. Full article

Vehicle-to-grid (V2G) aggregators must commit energy and power that connected vehicles can actually deliver, yet they often observe only charger-side telemetry, and vehicle-reported state of charge (SOC) is optional or non-authoritative. This paper proposes an observability-aware framework for estimating tradeable V2G capacity: each session is classified by its measurement boundary, channels, sampling, latency, and setpoint control, then mapped to the battery through uncertain conversion paths. The estimator outputs conservative safe energy and safe power rather than absolute SOC, treats vehicle-reported values as noisy hints, and abstains when observability is insufficient. A reproducible synthetic study shows that regularization and a split-conformal margin bring the bound to the 95% target with a finite-sample guarantee under within-regime exchangeability, and that the required capacity haircut grows from about 2.6 through 4.3 to 6.5 SOC points as observability degrades. Coverage alone does not distinguish the method, since any conformalized predictor reaches the target; the observability-aware bound adds tradeable capacity at that coverage, and its advantage grows as telemetry degrades. End-to-end market deliverability is established only in synthesis: a laboratory proof of concept on one bidirectional charger with four production vehicles demonstrates AC-boundary telemetry ingestion and capability assignment, but measures realized throughput after the fact rather than a bound committed before dispatch. Full article

Active voltage control in distribution networks depends on a sensing–decision–actuation chain that must remain effective as feeder topology, inverter participation, and telemetry quality change. Most multi-agent reinforcement learning controllers retain feeder-specific observation and action interfaces, and their behavior under imperfect telemetry is rarely tested under whole-graph transfer. This paper proposes GRAS-AVC, which is a zero-shot graph actor–critic framework with a permutation-equivariant shared actor, variable-size twin graph critics, droop-residual actions, and deployment-time AC power-flow risk screening. The 322-bus target feeder contributes no replay, gradient updates, risk fitting, or checkpoint selection. On an independent third-year ten-day test, GRAS-AVC reduces violating bus–time pairs from 7.455% under droop control to 2.723% (63.5% relative reduction). Against a matched edge-conditioned Graph-TD3 backbone, the GRAS actor lowers pooled exposure from 9.239% to 4.027%; after identical screening, GRAS-AVC lowers it from 3.896% to 2.723% while triggering 15.89 percentage points less often. Across information-matched tests spanning reconstructed missing telemetry, graph-correlated errors, gross bad data, a one-step delay, compound stress, and 50 paired announced reconfigurations, the frozen system maintains 63.1–63.6% droop-relative reductions and improves bus–time exposure in every seed. A selector-model audit records no false acceptance across 40 exact-and-bounded-mismatch condition–seed evaluations. GRAS-AVC therefore couples topology-aware policy inference with auditable physical screening for scalable sensing-to-control operation in DER-rich distribution networks. Full article

Published quantum-streaming theory establishes quantum memory advantages for specific streaming problems; how a correlation-sensitive proxy model behaves under the structured dependence typical of sensor and telemetry streams, however, remains uncharted. We present a proxy-based diagnostic and hypothesis-generation framework for correlation-sensitive streaming analysis. Operational proxies for the refreshing time $\tau$ and repetition number r, introduced in this paper, are estimated on five synthetic non-IID regimes (IID, Markov switching, seasonal drift, burst repetition, and long-range dependence) and mapped onto a $(\tau ,r)$ sensitivity landscape—the paper’s central artifact. Three memory-bounded classical baselines (online SGD, averaged SGD, and Count-Min) supply empirical reference points; no quantum algorithm is implemented or simulated and all quantum curves are heuristic proxy estimates. Analytic and empirical refreshing-time estimates diverge by up to $125\times$ under long-range dependence (≈8× for Markov)—the two estimators answer different questions about temporal dependence. Using empirical $\tau$, the proxy model predicts a hypothesised proxy-favourable region under mild-to-moderate Markov correlation that closes as correlation strengthens: the mean curves cross at ${\rho }^{*}\approx 0.82$ under the operating constants ($C=2$, $\delta =0.05$; the crossing moves between ${\rho }^{*}\approx 0.38$ and beyond the sweep range across a C–$\delta$ grid, so only the ordinal reading is robust), and by $\rho =0.88$ the classical baseline exceeds the proxy estimate (Hodges–Lehmann difference $0.046$). Applied unchanged to two real NAB telemetry streams, the same estimators place NYC Taxi inside and Machine Temperature outside the hypothesised favourable region—an ordering that persists across all tested encoder resolutions—with imbalance-aware metrics guarding against majority-class artefacts. Ablations over the $\tau$ estimator, forward window, stream length, target function, and proxy constants preserve the regime ordering within each estimator family. Full article

Data centers can provide demand-side flexibility by coordinating computing workloads, cooling systems, and on-site energy resources. However, facility demand varies with information technology (IT) load and cooling operation, making a fixed power usage effectiveness (PUE) or a forecast independent of planned controls inconsistent with dispatch. This paper proposes a control-aware, multi-horizon PUE forecasting framework for coordinated data center demand-side management (DSM) and microgrid dispatch. The key idea of this control-aware approach is to forecast PUE using planned workload and cooling schedules as inputs. A power-consistent Temporal Fusion Transformer (PC-TFT) predicts quantiles of non-IT overhead power and rack inlet temperature from telemetry, weather forecasts, admitted requests, and candidate workload and cooling schedules. Facility power and PUE are derived from the algebraic power balance, ensuring consistency among IT, overhead, and facility power and PUE values no lower than 1. Empirical split conformal calibration and temporally dependent scenarios characterize forecast uncertainty. A trajectory-conditioned piecewise-affine control response map with a recursive thermal state links the forecasts to a risk-informed model predictive controller that coordinates workloads, cooling, photovoltaic generation, battery storage, and grid exchange. The proposed framework is validated through EnergyPlus simulations of a Shenzhen data center, coupled with workload and microgrid simulations. Forecasting performance is compared with persistence and matched-input neural baselines, while dispatch is benchmarked against deterministic and oracle controllers. The results demonstrate improved multi-horizon PUE forecasting accuracy and empirical interval calibration, lower operating cost and peak grid demand, higher renewable energy utilization, and fewer service quality violations. These findings indicate that control-aware, power-balance-constrained probabilistic PUE forecasts can provide a reliable basis for coordinated data center DSM and microgrid dispatch. Full article

Electric vehicle charging stations (EVCSs) are increasingly deployed as grid-interactive energy assets that combine power electronic converters, sensing devices, communication interfaces, photovoltaic (PV) generation, battery energy storage systems (BESS), and multiple charging ports. This complexity creates reliability challenges because abnormal behavior may originate from electrical, thermal, sensing, communication, port-level, or grid-side sources. This paper proposes a fault-aware decision-support framework for renewable-powered EVCSs using multi-source explainable learning. The framework integrates electrical, thermal, session/port, grid/PV/BESS, and communication/data-quality indicators into a unified health-monitoring representation. Supervised models diagnose known fault classes, anomaly-detection models flag unknown or anomalous events, and a source-level explainability layer supports candidate-source interpretation and maintenance-oriented risk mapping. A scenario-controlled EVCS benchmark is developed with PV generation, BESS operation, grid import, charging-port behavior, communication/data-quality indicators, and six injected fault/anomaly categories. An extended 180-day benchmark further assesses longer-horizon operation, seasonal/weather diversity, drift/ageing proxies, and event-level behavior. The strongest closed-set classifier, LightGBM with class weights, achieved 98.45% accuracy and 0.9792 macro-F1, while the Random Forest model used for explainability and decision-layer analysis achieved 97.35% accuracy and 0.9626 macro-F1. Full multi-source monitoring improved Random Forest macro-F1 from 0.6922 under electrical-only monitoring to 0.9626, demonstrating within the controlled benchmark the diagnostic value of heterogeneous EVCS observability. Open-set performance was source dependent: sensor/measurement and communication/data anomalies were more detectable, whereas thermal/cooling and port/session unknowns remained difficult at the selected threshold. Under nominal scenario-based response assumptions, unavailable port hours and unmet charging energy decreased by 49.01% and 38.33%, respectively, relative to reactive operation; sensitivity analysis showed that these outcomes depend on intervention effectiveness and response delay. These findings establish controlled-benchmark feasibility for explainable multi-source EVCS decision support. Field validation using charger telemetry, maintenance-confirmed labels, and operator-calibrated response policies remains necessary. Full article

Measuring the water table level is a critical factor in irrigated agriculture in arid regions, as it can significantly influence the exchange of water and nutrients with crops. This work presents the design, implementation, and field validation of an open-source, solar-powered IoT device for autonomous groundwater level monitoring, combining long-range low-power LoRa communication, a non-contact pressure-based level sensor using the trapped-air capillary method, and an efficient power management stage that seamlessly switches between solar and battery power. Unlike existing commercial leveloggers, which are costly and lack integrated wireless telemetry and solar-based autonomy, the proposed platform is presented as a fully open-source, low-cost alternative purpose-built for unattended deployment in areas without grid power or cellular coverage. The system was validated through a multi-day field trial and dedicated communication tests, demonstrating a stable power conversion efficiency of 84–90%, a five-day autonomous operation without any deep-discharge event, high linearity ($R^2$ = 0.9998) of the level module over a 0–2 m range with a resolution of approximately 1.94 mm per ADC count, and a reliable LoRa link of up to 8.51 km in an urban/suburban environment despite non-line-of-sight conditions. With an estimated hardware cost of approximately $100 USD per unit, the device represents a low-cost, low-maintenance tool capable of generating knowledge about water resources to optimize irrigation and crop management in the face of climate change. Full article

Green low-carbon data centers operate as coupled cyber-energy systems whose dispatch must coordinate renewable generation, grid exchange, battery storage, cooling load, flexible computing workload, carbon-intensity signals, and reliability constraints. This study develops and evaluates a safety-constrained deep reinforcement learning framework for source–load–storage coordinated operation of a grid-connected green data center. The operating problem is formulated as a constrained Markov decision process with state variables describing the IT load, deferrable workload backlog, renewable availability, electricity price, marginal carbon intensity, battery state of charge, server-room temperature, reserve margin, and calendar context. The action space covers grid import and export, renewable utilization, storage charge and discharge, workload shifting, and cooling control. The learning architecture combines a constrained actor–critic policy, adaptive Lagrangian safety critics, and a control barrier function (CBF)-based action shield that projects unsafe actions onto an explicitly defined operating set before plant execution. The shield is specified as a low-dimensional quadratic projection over state-dependent SOC, thermal, reserve, SLA, and grid-interface constraints, while cumulative risks are priced through Lagrangian safety budgets during policy training. The evaluation uses a controlled and auditable benchmark simulation with normalized public-data-compatible profiles, declared scenarios, random seeds, neural-network settings, and mechanism-matched baselines; it is not a telemetry-based verification or hardware certification of a deployed data center. Within this declared benchmark, the proposed safe DRL controller produces a simulated 13.1% emission reduction relative to the Rule-based controller, 95.8% renewable utilization, a normalized annual cost of 0.91, and fewer boundary contacts than the tested unconstrained, Lagrangian-only, and shield-only PPO variants. These percentages are simulator outputs relative to the stated benchmark and must not be interpreted as measured field savings. The results show how separating reward learning, cumulative safety pricing, and one-step engineering projection changes low-carbon dispatch within the specified model. Full article

Sparse point correspondence is a recurring signal-processing problem in sensing systems that reduce measurements to compact point observations, including image-control points, detected landmarks, star centroids, and target candidates. Many pipelines first estimate a global transform and only then infer point identities, an order that can be fragile when observations are sparse, partially overlapping, and contaminated by false or missing detections. This paper proposes Anchor Relative Topology (ART), a correspondence-first method that treats anchor-centered relative point layouts as the primary geometric signal. For each candidate anchor pair, ART removes translation by local centering, searches over a bounded rotation variable, evaluates a kernelized topology-consistency score, and recovers a partial one-to-one assignment with explicit unmatched-point handling. Two practical variants are reported: ART-RH increases the anchor-hypothesis budget to improve anchor recall, whereas ART-AD adapts the kernel width and angular grid from local structure. On a 1944-case synthetic benchmark, ART-RH achieves a mean F1 score of 0.7907, compared with 0.6965 for rigid CPD correspondence. Real sensor-derived protocols further show that ART remains effective on retinal image control points and provides useful identity recovery on telemetry-derived star-point cases under strong partial overlap. In the reported synthetic and real sparse-coordinate protocols, the ART variants achieve higher correspondence F1 than the evaluated classical coordinate-only baselines, while retaining an explicit runtime–accuracy trade-off. These results indicate that anchor-relative topology is useful when exact sparse correspondence identities are more important than a single global transform. Full article

This applied systems-integration study addresses the “Impedance Mismatch” inherent in multi-energy microgrids—namely, the conflict where disparate physical domains traditionally force the use of isolated or highly rigid Supervisory Control and Data Acquisition (SCADA) data silos. We present a scalable, open-source edge-to-cloud telemetry pipeline orchestrated entirely through a custom MING+React stack (Mosquitto, InfluxDB, Node-RED, Grafana). The core architectural contribution is a category-specific Canonical Data Model (CDM) that functions as a translation layer, effectively decoupling sensor hardware from ingestion logic. Coupled with an automated Null-Pruning middleware loop and Metadata Separation, this architecture maintains high input purity prior to time-series persistence. To validate the system, the middleware was subjected to a high-fidelity stochastic simulation utilizing a Strict Corridor Algorithm to mimic physical inertia across 12 distinct energy vectors. Simulation-based validation demonstrates that under simulated conditions, the pipeline maintains data integrity for valid telemetry packets, achieves high accuracy in pruning malformed data, and operates with low latency under concurrency. These findings demonstrate the feasibility of this applied architecture as a resilient, cross-domain research environment for modern Digital Learning Factories. Full article