Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Budget-constrained Collaborative Renewable Energy Forecasting Market

Carla Goncalves, Ricardo J. Bessa, Tiago Teixeira, Joao Vinagre

TL;DR

This work tackles the challenge of improving RES forecasting under decentralized data ownership by designing a data-sharing analytics market with a spline LASSO forecasting model. The market framework enables buyers to bid on accuracy gains and sellers to price individual features, while a Bid-Gain Table guides price setting under budget constraints, ensuring truthfulness and Pareto efficiency. The proposed Spline Bid-Constrained LASSO Regression delivers an interpretable, additive model that selects informative features within budget and yields competitive forecast improvements, as demonstrated on synthetic and wind-power case studies. The approach offers a practical pathway to monetize data sharing in energy systems, balancing incentives, privacy, and forecast performance for real-world, scalable deployment.

Abstract

Accurate power forecasting from renewable energy sources (RES) is crucial for integrating additional RES capacity into the power system and realizing sustainability goals. This work emphasizes the importance of integrating decentralized spatio-temporal data into forecasting models. However, decentralized data ownership presents a critical obstacle to the success of such spatio-temporal models, and incentive mechanisms to foster data-sharing need to be considered. The main contributions are a) a comparative analysis of the forecasting models, advocating for efficient and interpretable spline LASSO regression models, and b) a bidding mechanism within the data/analytics market to ensure fair compensation for data providers and enable both buyers and sellers to express their data price requirements. Furthermore, an incentive mechanism for time series forecasting is proposed, effectively incorporating price constraints and preventing redundant feature allocation. Results show significant accuracy improvements and potential monetary gains for data sellers. For wind power data, an average root mean squared error improvement of over 10% was achieved by comparing forecasts generated by the proposal with locally generated ones.

Budget-constrained Collaborative Renewable Energy Forecasting Market

TL;DR

This work tackles the challenge of improving RES forecasting under decentralized data ownership by designing a data-sharing analytics market with a spline LASSO forecasting model. The market framework enables buyers to bid on accuracy gains and sellers to price individual features, while a Bid-Gain Table guides price setting under budget constraints, ensuring truthfulness and Pareto efficiency. The proposed Spline Bid-Constrained LASSO Regression delivers an interpretable, additive model that selects informative features within budget and yields competitive forecast improvements, as demonstrated on synthetic and wind-power case studies. The approach offers a practical pathway to monetize data sharing in energy systems, balancing incentives, privacy, and forecast performance for real-world, scalable deployment.

Abstract

Accurate power forecasting from renewable energy sources (RES) is crucial for integrating additional RES capacity into the power system and realizing sustainability goals. This work emphasizes the importance of integrating decentralized spatio-temporal data into forecasting models. However, decentralized data ownership presents a critical obstacle to the success of such spatio-temporal models, and incentive mechanisms to foster data-sharing need to be considered. The main contributions are a) a comparative analysis of the forecasting models, advocating for efficient and interpretable spline LASSO regression models, and b) a bidding mechanism within the data/analytics market to ensure fair compensation for data providers and enable both buyers and sellers to express their data price requirements. Furthermore, an incentive mechanism for time series forecasting is proposed, effectively incorporating price constraints and preventing redundant feature allocation. Results show significant accuracy improvements and potential monetary gains for data sellers. For wind power data, an average root mean squared error improvement of over 10% was achieved by comparing forecasts generated by the proposal with locally generated ones.
Paper Structure (28 sections, 3 theorems, 22 equations, 6 figures, 4 tables, 4 algorithms)

This paper contains 28 sections, 3 theorems, 22 equations, 6 figures, 4 tables, 4 algorithms.

Table of Contents

  1. Introduction
  2. Problem Formulation and Related Work
  3. Formulation of the RES Forecasting Problem
  4. RES Forecasting Models
  5. Data Markets
  6. Proposed Analytics Market for Time Series Forecasting
  7. Market Entities
  8. Gain Function and Estimation
  9. Bids and Price Definition
  10. Buyers
  11. Sellers
  12. Market Operator
  13. Spline Bid-Constrained LASSO Regression
  14. Data-sharing Incentive Mechanism
  15. Case Study
  16. ...and 13 more sections

Key Result

Proposition 1

If $\hat{\boldsymbol{\Theta}}_i$ is an optimal solution to eq:min-theta, then where $\hat{\boldsymbol{w}}=\left(\hat{w}_{1,1} \mathbf{1}_{M}, \hat{w}_{1,2} \mathbf{1}_{M}, \ldots, \hat{w}_{j,k} \mathbf{1}_{M}, \ldots\right)^\top$, $\mathbf{1}_{M}$ is the row vector of M 1's, and $\hat{w}_{1,1}, \hat{w}_{1,2}, \ldots, \hat{w}_{j,k}$ is the solution to the following 0-1 knapsac where

Figures (6)

  • Figure 1: Related existing algorithmic solutions for analytics trading.
  • Figure 2: Illustration of price definition.
  • Figure 3: Results for the advanced synthetic setup.
  • Figure 4: Cross-correlation between zones.
  • Figure 5: Comparison of forecasting models regarding RMSE.
  • ...and 1 more figures

Theorems & Definitions (6)

  • Proposition 1
  • proof
  • Proposition 2: Pareto Efficiency
  • proof
  • Proposition 3: Truthfullness
  • proof