Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Publications

Publications by Tiago Manuel Campelos

2019

Fair Remuneration of Energy Consumption Flexibility Using Shapley Value

Authors
Faia, R; Pinto, T; Vale, Z;

Publication
PROGRESS IN ARTIFICIAL INTELLIGENCE, EPIA 2019, PT I

Abstract
This paper proposes a new methodology for fair remuneration of consumers participation in demand response events. With the increasing penetration of renewable energy sources with a high variability; the flexibility from the consumers' side becomes a crucial asset in power and energy systems. However, determining how to effectively remunerate consumers flexibility in a fair way is a challenging task. Current models tend to apply over-simplistic and non-realistic approaches which do not incentivize the participation of the required players. This paper proposes a novel methodology to remunerate consumers flexibility, in a fair way. The proposed model considers different aggregators, which manage the demand response requests within their coalition. After player provide their flexibility, the remuneration is calculated based on the flexibility amount provided by the players, the previous participation in demand response programs, the localization of the players, the type of consumer, the effort put in the provided flexibility amount, and the contribution to the stability of the coalition structure using the Shapley value. Results show that by assigning different weights to the distinct factors that compose the calculation formulation, players remuneration can be adapted to the needs and goals of both the players and the aggregators.

2019

Contextual Simulated Annealing Q-Learning for Pre-negotiation of Agent-Based Bilateral Negotiations

Authors
Pinto, T; Vale, Z;

Publication
PROGRESS IN ARTIFICIAL INTELLIGENCE, EPIA 2019, PT I

Abstract
Electricity markets are complex environments, which have been suffering continuous transformations due to the increase of renewable based generation and the introduction of new players in the system. In this context, players are forced to re-think their behavior and learn how to act in this dynamic environment in order to get as much benefit as possible from market negotiations. This paper introduces a new learning model to enable players identifying the expected prices of future bilateral agreements, as a way to improve the decision-making process in deciding the opponent players to approach for actual negotiations. The proposed model introduces a con-textual dimension in the well-known Q-Learning algorithm, and includes a simulated annealing process to accelerate the convergence process. The proposed model is integrated in a multi-agent decision support system for electricity market players negotiations, enabling the experimentation of results using real data from the Iberian electricity market.

2019

Demonstration of an Energy Consumption Forecasting System for Energy Management in Buildings

Authors
Jozi, A; Ramos, D; Gomes, L; Faria, P; Pinto, T; Vale, Z;

Publication
PROGRESS IN ARTIFICIAL INTELLIGENCE, EPIA 2019, PT I

Abstract
Due to the increment of the energy consumption and dependency of the nowadays lifestyle to the electrical appliances, the essential role of an energy management system in the buildings is realized more than ever. With this motivation, predicting energy consumption is very relevant to support the energy management in buildings. In this paper, the use of an energy management system supported by forecasting models applied to energy consumption prediction is demonstrated. The real-time automatic forecasting system is running separately but integrated with the existing SCADA system. Nine different forecasting approaches to obtain the most reliable estimated energy consumption of the building during the following hours are implemented.

2019

Distributed Constrained Optimization Towards Effective Agent-Based Microgrid Energy Resource Management

Authors
Lezama, F; de Cote, EM; Farinelli, A; Soares, J; Pinto, T; Vale, Z;

Publication
PROGRESS IN ARTIFICIAL INTELLIGENCE, EPIA 2019, PT I

Abstract
The current energy scenario requires actions towards the reduction of energy consumption and the use of renewable resources. In this context, a microgrid is a self-sustained network that can operate connected to the smart grid or in isolation. The long-term scheduling of on/off cycles of devices is a critical problem that has been commonly addressed by centralized approaches. In this work, we propose a novel agent-based method to solve the long-term scheduling problem as a distributed constraint optimization problem (DCOP) by modelling future system configurations rather than reacting to changes. Moreover, with respect to approaches based on decentralised reinforcement learning, we can directly encode system-wide hard constraints (such as for example the Kirchhoff law) which are not easy to represent in a factored representation of the problem. We compare different multi-agent DCOP algorithms showing that the proposed method can find optimal/near-optimal solutions for a specific case study.

2019

Collaborative reinforcement learning of energy contracts negotiation strategies

Authors
Pinto, T; Praça, I; Vale, Z; Santos, C;

Publication
Communications in Computer and Information Science

Abstract
This paper presents the application of collaborative reinforcement learning models to enable the distributed learning of energy contracts negotiation strategies. The learning model combines the learning process on the best negotiation strategies to apply against each opponent, in each context, from multiple learning sources. The diverse learning sources are the learning processes of several agents, which learn the same problem under different perspectives. By combining the different independent learning processes, it is possible to gather the diverse knowledge and reach a final decision on the most suitable negotiation strategy to be applied. The reinforcement learning process is based on the application of the Q-Learning algorithm; and the continuous combination of the different learning results applies and compares several collaborative learning algorithms, namely BEST-Q, Average (AVE)-Q; Particle Swarm Optimization (PSO)-Q, and Weighted Strategy Sharing (WSS)-Q. Results show that the collaborative learning process enables players’ to correctly identify the negotiation strategy to apply in each moment, context and against each opponent. © Springer Nature Switzerland AG 2019.

2020

Energy consumption forecasting using ensemble learning algorithms

Authors
Silva, J; Praça, I; Pinto, T; Vale, Z;

Publication
Advances in Intelligent Systems and Computing

Abstract
The increase of renewable energy sources of intermittent nature has brought several new challenges for power and energy systems. In order to deal with the variability from the generation side, there is the need to balance it by managing consumption appropriately. Forecasting energy consumption becomes, therefore, more relevant than ever. This paper presents and compares three different ensemble learning methods, namely random forests, gradient boosted regression trees and Adaboost. Hour-ahead electricity load forecasts are presented for the building N of GECAD at ISEP campus. The performance of the forecasting models is assessed, and results show that the Adaboost model is superior to the other considered models for the one-hour ahead forecasts. The results of this study compared to previous works indicates that ensemble learning methods are a viable choice for short-term load forecast. © 2020, Springer Nature Switzerland AG.

  • 29
  • 61