Abstract
Energy systems worldwide are complex and challenging environments. Multi-agent based simulation platforms are increasing at a high rate, as they show to be a good option to study many issues related to these systems, as well as the involved players at act in this domain. In this scope the authors' research group has developed a multi-agent system: Multi-Agent System for Competitive Electricity Markets (MASCEM), which simulates the electricity markets environment. MASCEM is integrated with Adaptive Learning Strategic Bidding System (ALBidS) that works as a decision support system for market players. The ALBidS system allows MASCEM market negotiating players to take the best possible advantages from the market context. This paper presents the application of a Support Vector Machines (SVM) based approach to provide decision support to electricity market players. This strategy is tested and validated by being included in ALBidS and then compared with the application of an Artificial Neural Network (ANN), originating promising results: an effective electricity market price forecast in a fast execution time. The proposed approach is tested and validated using real electricity markets data from MIBEL - Iberian market operator.

Abstract

Abstract
The use of Decision Support Systems (DSS) in the field of Electricity Markets (EM) is essential to provide strategic support to its players. EM are constantly changing, dynamic environments, with many entities which give them a particularly complex nature. There are several simulators for this purpose, including Bilateral Contracting. However, a gap is noticeable in the pre-negotiation phase of energy transactions, particularly in gathering information on opposing negotiators. This paper presents an overview of existing tools for decision support to the Bilateral Contracting in EM, and proposes a new tool that addresses the identified gap, using concepts related to automated negotiation, game theory and data mining.

Abstract

Abstract
Smart Grid (SG) concept is defined as an electricity network operated intelligently to integrate the behavior and actions of all energy resources connected to the network to ensure efficient, sustainable, economic and secure supply of electricity. This concept emerged in recent decades not only for economic reasons but also ecological and even political. SG have been the subject of major studies and investments and continues to represent an area of enormous challenges. Some of the problems of intelligent systems connected to the managed SG are: the real-time processing optimization algorithms and demand response programs; and more accurate predictions in the management of production and consumption. This paper presents a case study for evaluating the performance and accuracy of energy consumption forecast with use of SVM (Support Vector Machines) in different frameworks. © 2016 IEEE.

Abstract
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. © 2018 IEEE.