The difficulty and manual nature of procuring human evaluators for ranking the quality of images affected by various types of degradations, and of those cleaned up by developed algorithms, has lead to the widespread adoption of automated metrics, like the Peak Signal-to-Noise Ratio (PSNR) and the Structural Similarity Index Metric (SSIM). However, disparities between rankings given by these metrics and those given by human evaluators have encouraged the development of improved image quality assessment (IQA) metrics that are a better fit for this purpose. These methods have been previously used solely for quality assessments and not as objectives in the training of neural networks for high-level vision tasks, despite the potential improvements that may come about by directly optimizing for desired metrics. This paper examines the adequacy of ten recent IQA metrics, compared with standard loss functions, within two trained dehazing neural networks, with observed broad improvement in their performance.
The rapid growth of prosumer photovoltaic installations has introduced significant supply–demand imbalances in modern power grids, motivating the development of energy management systems that can coordinate distributed resources without sacrificing local control responsiveness. This paper presents qToggleEMS, a distributed architecture that combines cloud-resident receding-horizon planning with edge-resident bounded-override control for prosumer sites equipped with photovoltaic generation, battery storage, and grid interconnection. The contribution is positioned at the systems-engineering level: a documented partitioning of responsibilities between a cloud planner (forecasting, price-aware scheduling) and an edge controller (sub-second actuation, autonomous fallback) that preserves planning quality while remaining operational under cloud–edge disconnection. The cloud component, powerHub, is implemented as a set of microservices communicating via MQTT and TimescaleDB; the edge component runs qToggleOS on an ARM single-board computer and accesses inverters directly via Modbus RTU, bypassing manufacturer-provided cloud APIs. The system was deployed at a commercial prosumer site for approximately two months using the prosumer-oriented optimization strategy. Compared with a within-period counterfactual baseline (the cost the site would have incurred under its previous flat-tariff contract), monthly energy costs decreased by 14–15%. An analytical projection of the producer-oriented strategy using historical day-ahead prices from OPCOM PZU suggests a revenue uplift of approximately 23%, pending field validation.
Photovoltaic inverters are the devices that actually change solar output on the distribution network, yet reviews of virtual power plants often treat them as abstract units that can simply be dispatched. This review therefore starts from the device. A solar system is controllable only when three things are true together: the inverter can change its behaviour, there is a way to send that change, and someone is allowed to send it. On the way up from the device, grid codes, communication choices, the path used to reach the inverter, and market rules each remove part of what the nameplate suggests. Four results follow from this view. First, inverters with the same rated power do not behave in the same way, and reactive-power support shortens inverter life. Second, standards agree on what a function means but not on how it is written in the message, so the cost of adding devices grows with the number of manufacturers. Third, choosing between a manufacturer cloud and a local controller is mainly a choice about who can still give orders when the link fails. Fourth, changing output when the network needs it keeps much more solar energy than a fixed capacity limit, but it does not replace network upgrades, the loss is not shared evenly, and a saved kilowatt-hour is not the same thing as avoided emissions. Overall, the tightest limits are interoperability, different national rules, reactive power that is required but not paid, and cybersecurity duties that are weaker than the control duties.