This paper presents the Reasoning-based, Explainable and Adaptive Contextual Tool for Smart Energy Management (REACTS). The tool enables the automatic management of energy resources in smart buildings, promoting transparent decision-making to foster user trust and support sustainability goals. It integrates Artificial Intelligence (AI) techniques, including machine learning models such as Multilayer Perceptrons, Random Forests, K-nearest Neighbors, and Support Vector Machines, to forecast energy usage and classify contextual states. Reinforcement Learning is employed to dynamically select and update forecasting models based on their historical performance. Semantic reasoning is used to represent domain knowledge through ontologies and rule-based inference, enabling context-aware decisions that adapt to user preferences and environmental conditions. Control actions are computed periodically using real-time sensor data enriched with semantic annotations. To ensure interpretability, REACTS employs Explainable AI methods, specifically SHapley Additive exPlanations, to generate feature-attribution-based justifications tailored to user profiles in both visual and textual formats. The system also incorporates green computing strategies, triggering model retraining only when performance degradation is detected, and scheduling updates during periods of lower energy or computational demand. REACTS is deployed in a real office building, operating continuously and demonstrating how contextual reasoning and explainability can enhance the reliability and sustainability of smart energy systems.

This paper presents the Adaptive Decision Support for Electricity Markets Negotiations (AiD-EM) system. AiD-EM is a multi-agent system that provides decision support to market players by incorporating multiple sub-(agent-based) systems, directed to the decision support of specific problems. These sub-systems make use of different artificial intelligence methodologies, such as machine learning and evolutionary computation, to enable players adaptation in the planning phase and in actual negotiations in auction-based markets and bilateral negotiations.

This paper presents the Adaptive Decision Support for Electricity Markets Negotiations (AiD-EM) system. AiD-EM is a multi-agent system that provides decision support to market players by incorporating multiple sub-(agent-based) systems, directed to the decision support of specific problems. These sub-systems make use of different artificial intelligence methodologies, such as machine learning and evolutionary computing, to enable players adaptation in the planning phase and in actual negotiations in auction-based markets and bilateral negotiations. AiD-EM demonstration is enabled by its connection to MASCEM (Multi-Agent Simulator of Competitive Electricity Markets).

Entropy models the added information associated to data uncertainty, proving that stochasticity is not purely random. This paper explores the potential improvement of machine learning methodologies through the incorporation of entropy analysis in the learning process. A multi-layer perceptron is applied to identify patterns in previous forecasting errors achieved by a machine learning methodology. The proposed learning approach is adaptive to the training data through a re-training process that includes only the most recent and relevant data, thus excluding misleading information from the training process. The learnt error patterns are then combined with the original forecasting results in order to improve forecasting accuracy, using the Rényi entropy to determine the amount in which the original forecasted value should be adapted considering the learnt error patterns. The proposed approach is combined with eleven different machine learning methodologies, and applied to the forecasting of electricity market prices using real data from the Iberian electricity market operator – OMIE. Results show that through the identification of patterns in the forecasting error, the proposed methodology is able to improve the learning algorithms’ forecasting accuracy and reduce the variability of their forecasting errors.

Power systems are showing a dynamic evolution in the last few years, caused in part by the adoption of smart grid technologies. The integration of new elements that represent a source of uncertainty, such as renewables generation, electric vehicles, variable loads and electricity markets, poses a higher degree of complexity causing that traditional mathematical formulations struggle in finding efficient solutions to problems in the smart grid context. In some situations, where traditional approaches fail, computational intelligence has demonstrated being a very powerful tool for solving optimization problems. In this paper, we analyze the application of Differential Evolution (DE) to address an energy resource management problem under uncertain environments. We perform a systematic parameter tuning to determine the best set of parameters of four state-of-the-art DE strategies. Having knowledge of the sensitivity of DE to the parameter selection, self-adaptive parameter control DE algorithms are also implemented, showing that competitive results can be achieved without the application of parameter tuning methodologies. Finally, a new hybrid-adaptive DE algorithm, HyDE, which uses a new “DE/target - to - perturbed_best/1” strategy and an adaptive control parameter mechanism, is proposed to solve the problem. Results show that DE strategies with fixed parameters, despite very sensitive to the setting, can find better solutions than some adaptive DE versions. Overall, our HyDE algorithm excelled all the other tested algorithms, proving its effectiveness solving a smart grid application under uncertainty.

Smart Grid technologies enable the intelligent integration and management of distributed energy resources. Also, the advanced communication and control capabilities in smart grids facilitate the active participation of aggregators at different levels in the available electricity markets. The portfolio optimization problem consists in finding the optimal bid allocation in the different available markets. In this scenario, the aggregator should be able to provide a solution within a timeframe. Therefore, the application of metaheuristic approaches is justified, since they have proven to be an effective tool to provide near-optimal solutions in acceptable execution times. Among the vast variety of metaheuristics available in the literature, Differential Evolution (DE) is arguably one of the most popular and successful evolutionary algorithms due to its simplicity and effectiveness. In this paper, the use of DE is analyzed for solving the portfolio optimization problem in electricity markets. Moreover, the performance of DE is compared with another powerful metaheuristic, the Particle Swarm optimization (PSO), showing that despite both algorithms provide good results for the problem, DE overcomes PSO in terms of quality of the solutions.

Due to amount of today's electricity consumption, one of the most important tasks of the energy operators is to be able to predict the consumption and be ready to control the energy generation based on the estimated consumption for the future. In this way, having a trustable forecast of the electricity consumption is essential to control the consumption and maintain the balance in energy distribution networks. This study presents a day ahead forecasting approach based on a genetic fuzzy system for fuzzy rule learning based on the MOGUL methodology (GFS.FR.MOGUL). The proposed approach is used to forecast the electricity consumption of an office building in the following 24 hours. The goal of this work is to present a more reliable profile of the electricity consumption comparing to previous works. Therefore, this paper also includes the comparison of the results of day ahead forecasting using GFS.FR.MOGUL method against other fuzzy rule based methods, as well as a set of Artificial Neural Network(ANN) approaches. This comparison shows that using the GFS.FR.MOGUL forecasting method for day-ahead electricity consumption forecasting is able to estimate a more trustable value than the other approaches.

The contemporary adoption of Cyber-Physical Systems and improvements in robotic applications in industrial scenarios demands for horizontal integration mechanisms with already existing automation equipment, controlled by PLCs. This paper aims to shorten the gap between the automation and robotics domain, by proposing an Interprocess Communication method to establish interoperability between robotic systems and automation equipment in a reliable and straightforward manner. In particular, this paper introduces a novel approach for linking ROS and IEC 61131–3 by way of shared memory interfaces, enabling and promoting their interactions. Moreover, this paper addresses the applied synchronization mechanism for handling concurrent accesses to the shared memory location, explores data type mapping between ROS and IEC 61131–3, and identifies some practical industrial applications.

This paper proposes a Building Energy Management System (BEMS) as part of an organization-based Multi-Agent system that models the Smart Home Electricity System (MASHES). The proposed BEMS consists of an Energy Management System (EMS) and a Prediction Engine (PE). The considered Smart Home Electricity System (SHES) consists of different agents, each with different tasks in the system. In this context, smart homes are able to connect to the power grid to sell/buy electrical energy to/from the Local Electricity Market (LEM), and manage electrical energy inside of the smart home. Moreover, a Modified Stochastic Predicted Bands (MSPB) interval optimization method is used to model the uncertainty in the Building Energy Management (BEM) problem. A demand response program (DRP) based on time of use (TOU) rate is also used. The performance of the proposed BEMS is evaluated using a JADE implementation of the proposed organization-based MASHES.

The increase of distributed energy resources, mainly based on renewable sources, requires new solutions that are able to deal with this type of resources' particular characteristics (namely, the renewable energy sources intermittent nature). The smart grid concept is increasing its consensus as the most suitable solution to facilitate the small players' participation in electric power negotiations while improving energy efficiency. The opportunity for players' participation in multiple energy negotiation environments (smart grid negotiation in addition to the already implemented market types, such as day-ahead spot markets, balancing markets, intraday negotiations, bilateral contracts, forward and futures negotiations, and among other) requires players to take suitable decisions on whether to, and how to participate in each market type. This paper proposes a portfolio optimization methodology, which provides the best investment profile for a market player, considering different market opportunities. The amount of power that each supported player should negotiate in each available market type in order to maximize its profits, considers the prices that are expected to be achieved in each market, in different contexts. The price forecasts are performed using artificial neural networks, providing a specific database with the expected prices in the different market types, at each time. This database is then used as input by an evolutionary particle swarm optimization process, which originates the most advantage participation portfolio for the market player. The proposed approach is tested and validated with simulations performed in multiagent simulator of competitive electricity markets, using real electricity markets data from the Iberian operator-MIBEL.

Network coding has the potential to enhance energy efficiency of multicast sessions by providing optimal communication subgraphs for the transmission of the data. However, the coding requirement at intermediate nodes may introduce additional complexity and energy consumption in order to code the data packets. Previous work has shown that in lossless wireline networks, the performance of tree-packing mechanisms is comparable to network coding, albeit with added complexity at the time of computing the trees. This means that most nodes in the network need not code. Thus, mechanisms that identify intermediate nodes that do require coding is instrumental for the efficient operation of coded networks and can have a significant impact in overall energy consumption. We present a distributed, low complexity algorithm that allows every node to identify if it should code and, if so, through what output link should the coded packets be sent. Our algorithm uses as input the optimal subgraph determined by Lun et al's optimization formulation [13]. Numerical results are provided using common Internet Service Provider (ISP) network topologies and also random network deployments. Our results show that the number of coding nodes in the expectation is very low (typically below 1) and that the number of sessions that require coding is limited, e.g., less than 15% for sessions of 4 receivers for the ISP networks and below 0.1% for networks with random node deployments in a square of 1 × 1 km2with of up to 30 nodes and up to 20 receivers.