The household prosumers’ decentralized cooperation and aggregation in energy communities are essential to increase renewable energy penetration and to ensure a successful energy transition. Despite their potential, the prosumers are not motivated to participate in local energy value chains due to the lack of trust and decentralized cooperation models for meeting community welfare and sustainability preferences, most innovation efforts being focused on financial incentives that are anyway very low. In this paper, we propose a solution for prosumers’ decentralized coordination in self-sufficient energy communities using cooperative games on top of a blockchain overlay that considers their complementary energy features and flexibility mobilization. The proposed model for community-level local energy balance fits well in circumstances in which there is a strong motivation in the community to prioritize sustainability and environmental concerns and reduce dependence on external energy. We define a governance model to support the decentralized self-organization of prosumers in coalitions for balancing the renewable generation and demand while considering via tokenization factors that go beyond purely economic motivations and foster cooperation and collaboration among the prosumers in the community. Self-enforcing contracts are used to implement the cooperative game model enabling the decentralized management of prosumers’ coalitions for optimized tokens-based payoff distribution towards self-sufficiency. The evaluation results show our solution’s effectiveness in facilitating the prosumers cooperation in self-sufficient coalitions achieving a minimal difference between the energy consumption and production in the community of approximately 0.01%, with a low transactional time overhead.

Blockchain and tokens are relatively new research areas insufficiently explored from both technical and economic perspectives. Even though tokens provide benefits such as easier market access, increased liquidity, lower transaction costs, and automated transactional process, their valuation and price determination are still challenging due to factors such as a lack of intrinsic value, volatility, and regulation making trading risky. In this paper, we address this knowledge gap by reviewing the existing literature on token creation and valuation to identify and document the factors affecting their valuation, investment, and founding, as well as the most promising domains of applicability. The study follows the PRISMA methodology and uses the Web of Science database, defining clear research questions and objective inclusion criteria for the articles. We discuss token technical development, including creating, issuing, and managing tokens on an Ethereum blockchain using smart contracts. The study revealed several key factors that significantly impact the field of tokenomics: demand and supply, social incentives, market conditions, macroeconomics, collective behavior, speculation, and inclusion in index funds. The most relevant use cases of blockchain and tokens are related to the digitization of virtual and physical assets, accountability, and traceability usual in smart grids or supply chains management, social governance, and art and gamification including metaverse.

Blockchain technology offers great value in terms of decentralization, data integrity, transparency, and traceability, however the transactional data is public, and accessible raising concerns about violating privacy regulations. For example, in the peer-to-peer energy trading and demand response use cases, the data stored in blockchain may allow a third party to infer the load profiles or even identify the behind the meter assets. In this paper, we employ homomorphic techniques to encrypt the energy transactional data stored on the blockchain allowing the smart contracts functions responsible for implementing the business logic of the energy flexibility trading and settlement to perform computations on encrypted data. As computations on smart contracts and public blockchains can be expensive, we have used the lighter version of the Partial Homomorphic Encryption scheme to obfuscate the energy data. To ensure the validity of the smart contracts' functions executed on encrypted data, we leverage on the consensus mechanism of the blockchain network, thus ensuring computation correctness. The solution was validated considering a micro-grid with 12 prosumers that trade their flexibility peer-to-peer (P2P). The results demonstrate the feasibility of maintaining encrypted energy data on the blockchain, executing smart contract functions on encrypted data, and preserving the privacy of computations. As anticipated, the trade-off for better privacy is the gas consumption overhead of the smart contracts' functions which is higher compared to the non-encrypted case, depending on the length of the public-private keys pair. Nonetheless, our solution exhibits consistent execution times for smart contracts, making it suitable for private networks where gas costs are of minimal concern.

The transition toward decentralized renewable energy transforms the energy grid, with the prosumers playing an active role in the local energy management. Accurate day-ahead prediction of their energy demand is a prerequisite to ensure the stability and efficiency of the power grid by balancing the energy demand with the production, while incorporating renewable energy as much as possible. In this paper, we propose a 24-steps-ahead energy prediction model that integrates clustering and multilayer perceptron classification models used to detect the classes of energy profiles and multilayer perceptron regression models used to fine-tune the energy prediction, considering the energy data streams. We introduce new features derived from the raw energy data collected from prosumers, such as the profile peaks and valleys, concerning the energy baseline and describe a software infrastructure for integrating the real-time energy data streams with the hybrid deep learning models training and prediction. The evaluation tests consider energy datasets that are closer to the real-time energy data streams from prosumers. The results show that, even on energy data streams, the model offers a good prediction accuracy for small- and medium-scale prosumers.

The shift towards renewable energy integration into smart grids has led to complex management processes, which require finer-grained energy and heat generation/ demand forecasting while considering data from monitoring devices and the integration of smaller multi-energy sub-systems at the community, district, or buildings level. However, energy prediction is challenging due to the high variability in the electrical and thermal energy demands of building occupants, the heterogenous characteristics of the energy assets or buildings in a district, and the length of the forecasting horizon. In this paper, we define a data-driven machine-learning pipeline to predict the electricity and thermal consumption of buildings and energy assets from a city district in 24 h intervals. Each pipeline’s step is divided into sensors’ data processing and model integration, data enrichment and features engineering, and multilayer perceptron model training. To address some of the drawbacks of using the multi-layer perceptron model, such as slow convergence rate and risk of overfitting, and to ensure a lower error in the energy prediction process features, an engineering technique was employed. We incorporated weather data features and interaction features derived from fusing the energy data with statistical models to capture the nonlinear patterns of the electrical and heat demands. The proposed approach was successfully validated in a real-world environment, a city district in Gent, Belgium. It featured good prediction results for electricity and heat production and consumption of various assets without considering the physical characteristics, making it viable and easily applicable in broader urban areas. The evaluation of energy prediction accuracy yielded good results, with a Mean Absolute Error (MAE) falling within the range of 0.003 to 3.27, and a Mean Absolute Scaled Error (MASE) ranging from 7 × 10⁻⁵ to 2.57 × 10⁻³.