The purpose of this article is to propose a value-oriented electrical load forecasting (ELF) approach that aims to minimize load variance by leveraging vehicle-to-grid (V2G) technology. To achieve this, it is critical and urgent to design a loss function that can accurately measure the suboptimality of decisions induced by forecast errors, especially since the commonly used mean squared error (MSE) falls short in this regard. The Lagrange multiplier method and Karush–Kuhn–Tucker conditions are initially used to elucidate the impact of forecast errors on the actual charging power of electric vehicles. Building on this foundation, a differentiable loss function called mean relative magnitude error (MRME) is put forward for value-oriented ELF, which allows parameter updates in the long short-term memory (LSTM) model via the gradient descent method during the training stage. Furthermore, the MRME and MSE loss functions are combined using a weighted sum method to leverage their respective advantages. Numerous case studies have demonstrated that the LSTM model, whether using MRME alone or in combination with MSE, achieves superior and more robust V2G scheduling performance compared to using MSE alone. The weight coefficients for combining MRME and MSE loss functions are also discussed.

With the global proliferation of electric vehicles (EVs), evaluating and quantifying the actual impact of electric vehicles on carbon emissions continues to be a challenge. This paper aims to design low-carbon optimization strategies for the distribution system (DS) and to quantify the value of carbon reduction in the distribution grid under EV and Vehicle-to-Grid (V2G) technology. We propose an optimization method to formulate the charging schedule for EVs based on the carbon emission factors of the distribution grid. By leveraging V2 G technology, EVs are utilized as intermediaries for low-carbon energy dispatch, reducing the base load carbon emissions within the distribution grid and those associated with EV s. The efficacy of our proposed method is validated using the carbon emission factors from the Guangdong provincial power grid and real load data from the Southern University of Science and Technology campus. The results reveal that by dispatching 1000 EVs, the carbon emissions of the distribution network can be reduced 7.2 tons within a charging cycle (24h), marking a decrease of 2.5% compared to before the optimization, and significantly mitigating carbon emissions during the main grid's high-carbon periods. This research provides valuable insights for further advancing the development and application of EVs and V2G technology.