Pavlos Nikolaidis

Despite growing renewable energy integration, curtailments persist, causing reverse power flows, congestion and operational issues, such as instability and frequency deviations. Battery energy storage can mitigate these impacts by rapidly absorbing and supplying power. This study targets isolated, high‑PV grids where HV/MV utility substations experience midday exports (reverse power flows) and proposes to nearly zero each substation’s daily net demand, by optimally charging/discharging distributed Battery Energy Storage Systems (BESS). We develop a hybrid heuristic–convex framework coupling Linear Programming dispatch with a Genetic Algorithm for parameter tuning and an AI (Deep Neural Networks) component to support decisions under variable net‑load conditions. The approach is validated on the Cyprus power system using 30‑min net‑load real data from transmission/distribution substations. Results show that substations equipped with BESS can markedly reduce energy imported from the transmission grid and excess PV energy exported back to the network during midday, by about ~60% and up to ~90%, respectively. The analysis also indicates that the increased local self‑consumption within the substations leads to the reduction in both minimum and peak conventional generation requirements. This is achieved by lowering average ramp rates by ~16% and contributing to a smoother system residual‑load profile (“duck curve”). These outcomes are particularly valuable for isolated systems like Cyprus that rely on imported fossil fuels and fluctuating domestic renewables.

Accurate short-term forecasting of photovoltaic power generation is vital for the operational stability of isolated energy systems, especially in regions with increasing renewable energy penetration. This study presents a novel AI-based forecasting framework applied to the island of Cyprus. Using machine learning methods, particularly regression trees, the proposed approach evaluates the impact of key environmental variables on PV performance, with an emphasis on atmospheric dust transport and air composition variability. A distinguishing feature of this work is the integration of cross-continental dust events and diverse atmospheric parameters into a structured forecasting model. A new clustering methodology is introduced to classify these inputs and analyze their correlation with PV output, enabling improved feature selection for model training. Importantly, all input parameters are sourced from publicly accessible, internet-based platforms, facilitating wide reproducibility and operational application. The obtained results demonstrate that incorporating dust deposition and air composition features significantly enhances forecasting accuracy, particularly during severe dust episodes. This research not only fills a notable gap in the PV forecasting literature but also provides a scalable model for other dust-prone regions transitioning to high levels of solar energy integration.

Global efforts aiming to shift towards renewable energy and smart grid configurations require accurate unit commitment schedules to guarantee power balance and ensure feasible operation under different complex constraints. Intelligent systems utilizing hybrid and high-level techniques have arisen as promising solutions to provide optimum exploration–exploitation trade-offs at the expense of computational complexity. To ameliorate this requirement, which is extremely expensive in non-interconnected renewable systems, radically different approaches based on enhanced priority schemes and Boolean encoding/decoding have to take place. This compilation encompasses various mappings that convert multi-valued clausal forms into Boolean expressions with equivalent satisfiability. Avoiding any need to introduce prior parameter settings, the solution utilizes state-of-the-art advancements in the field of artificial intelligence models, namely Boolean mapping. It allows for the efficient identification of the optimal configuration of a non-convex system with binary and discontinuous dynamics in the fewest possible trials, providing impressive performance. In this way, Boolean mapping becomes capable of providing global optimum solutions to unit commitment utilizing fully tractable procedures without deteriorating the computational time. The results, considering a non-interconnected power system, show that the proposed model based on artificial intelligence presents advantageous performance in terms of generating cost and complexity. This is particularly important in isolated networks, where even a-not-so great deviation between production and consumption may reflect as a major disturbance in terms of frequency and voltage.

With the fast expansion of intermittent renewable energy sources in the upcoming smart grids, simple and accurate day-ahead systems for residual load forecasts are urgently needed. Machine learning strategies can facilitate towards drastic cost minimizations in terms of operating-reserves avoidance to compensate the mismatches between the actual and forecasted values. In this study, a multi-input/multi-output model is developed based on artificial neural networks to map the relationship between different predictor inputs, including time indices, weather variables, human activity parameters, and energy price indicators, and target outputs such as wind and photovoltaic generation. While the information flows in only one direction (from the predictor nodes through the hidden layers to the target node), benchmark training algorithms are employed and assessed under different case studies. The model is evaluated under both parametric and non-parametric formulations, namely neural networks and Gaussian process regression. Essential improvements are achieved by enhancing the number of embedded predictors, while superior performance is observed by using Bayesian regularization mechanisms. In terms of mean-error indices and determination coefficient, this opens the pathway towards minimization via Bayesian inference-based approaches in the presence of increased and highly stochastic renewable inputs.

Solar energy, derived from the inexhaustible energy of the sun, has emerged as a promising solution to mitigate the environmental challenges posed by fossil fuel consumption and global climate change. This work explores the underlying principles of solar energy exploitation, focusing on energy collection technologies as the primary means of solar energy conversion. The physics of the state-of-the-art mechanisms, the photovoltaic effect, and the advancements that have driven the transformation of solar energy into a viable and sustainable alternative energy source are also examined. Through a comprehensive review of relevant literature and pioneering research, this study highlights the immense potential of solar energy and its role in shaping a cleaner, greener future. Towards de-carbonization, the various exploitation technologies are divided into direct and indirect in order to optimize resource utilization. Accounting for the most important advantages presented, solar-based utilization processes are perhaps the only ones that provide access to energy for all to satisfy their vital needs. As nations continue to embrace solar energy and invest in its development, we move closer to achieving a more sustainable and environmentally friendly world for generations to come.

Renewable energy sources are constantly increasing in the modern power systems. Due to their intermittent and uncertain potential, increased spinning reserve requirements are needed to conserve the reliability. On the other hand, each action towards efficiency improvement and cost reduction contradicts the participation of variable resources in the energy mix, requiring more accurate tools for optimal unit commitment. By increasing the renewable contribution, not only does the overall system inertia decrease with the decreasing conventional generation, but more generators that are expensive are also introduced. This work provides a radically different approach towards a tractable optimization task based on the framework of Lagrange relaxation and variational Bayes. Following a dual formulation of reliability and cost, the Lagrange multipliers are accelerated via a machine learning mechanism, namely, variational Bayesian inference. The novelty in the proposed approach stems from the employed acquisition function and the effect of the Gaussian process. The obtained results show great improvements compared with the Lagrange relaxation alternative, which can reach over USD 1 M in production cost credits at the least number of function evaluations. The proposed hybrid method promises global solutions relying on a proper acquisition function that is able to move towards regions with minimum objective value and maximum uncertainty.

Renewable resources provide viable and advantageous solutions up to a certain integration share. At higher penetration levels, they violate the conventional generation constraints, leading to decentralized uncertainty with respect to bi-directional power flows. This generates an increasing need for smart tools able to predict their output with high accuracy, based on easily accessible input data for forecasting. Based on actual data with respect to load demand and wind power generation, this work presents a realization of decision trees that target on a continuous response, also known as regression trees. Utilizing the speed and direction of wind, the ambient temperature, relative humidity, renewable capacity and renewable energy source curtailment as predictors in distribution networks of different regions, the proposed configuration is able to predict the generated power with high accuracy. According to the obtained results under distinguished scenarios, the inclusion of temperature and humidity to the predictive list greatly improves the accuracy in terms of mean square error, root mean square error and mean absolute range normalized error, whereas the renewable availability offer no relevant changes. However, in the forthcoming de-carbonized power systems, the impact of curtailed energy will play an important role in expert forecasting systems where the input/output association must be modelled with high resolution.

Global efforts towards de-carbonization give rise to remarkable energy challenges, which include renewable energy penetration increase and intermediate energy carriers for a sustainable transition. In order to reduce the dependence on fossil fuels, alternative sources are considered by commodities to satisfy their increasing electricity demand, as a consequence of a rise in population and the quantity of residential appliances in forthcoming years. The near-term trends appear to be in fuel and emission reduction techniques through the integration of carbon capture and storage and more efficient energy carriers, exploiting alternative energy sources, such as natural gas and hydrogen. Formulating both the fuel consumption and emission released, the obtained experimental results showed that the total production cost can be reduced by making use of natural gas for the transition towards 2035’s targets. Maximum profits will be achieved with hydrogen as the only fuel in modern power plants by 2050. In this way, the lowest electricity production can be achieved as well as the elimination of carbon dioxide emissions. Since the integration of renewable energy resources in the sectors of electricity, heating/cooling and transportation will continuously be increased, alternative feedstocks can serve as primary inputs and contribute to production cost profits, improved utilization factors and further environmental achievements.

Hydrogen constitutes the only carbon-free fuel that can be used for energy conversion, producing water as the only by-product. With water being one of the most abundant and inexhaustible raw materials in the world, and the required electricity input being provided by renewable resources, the produced hydrogen via water electrolysis constitutes a green pathway towards sustainability. In this work, a hybrid PV power-to-hydrogen, storage and fuel cell system is proposed to satisfy the domestic load of a residential building. Identifying alkaline as a mandatory electrolysis technology, the performance of alkaline electrolysis cells is assessed considering the inclusion of a two-switch buck-boost converter. Following a comprehensive formulation with respect to each distinguished system component, the balance condition at DC and AC buses is determined. The proposed configuration is evaluated, taking into account PV systems of different ratings, namely 3 kW, 5 kW and 7 kW. Based on actual data relating to both PV generation and domestic load for the year 2020, the obtained results from the annual simulations are compared with feed-in tariff and net-metering schemes. According to the results, PV capacity firming is achieved, creating great opportunities for autonomy enhancement, not only for electricity, but also in other energy sectors.

Under the constraints of fossil‐fuel reserves depletion and climate change, the expansion of intermittent renewable generation creates a lot of power integration issues which undeniably disturb the overall system stability. Optimally planned, electricity storage systems are capable of managing the variability and uncertainty of renewable energy sources, guaranteeing power balance and ensuring feasible and economical operation. Here, the outcomes derived by a Genetic algorithm‐driven priority list approach is provided, which effectively quantifies the impact of intermittent renewable energy sources on total production cost and the benefits of electricity storage. The experimental evaluation on three benchmark scenarios shows that cost improvements exist in terms of thermal generation improvement, lower renewable generation curtailment and load shedding avoidance cost. Zinc‐air battery offers the highest net present value at relatively low PV penetration levels. Increased penetration levels favour Li‐ion batteries followed by Pb‐acid and Vanadium‐redox flow batteries. In general, the viability of each storage device depends on the renewable penetration level, promoting the technologies with lower capital costs at limited shares, whereas at higher contribution frameworks systems with higher performance features become preferable.