In order to reduce the pollution caused by coal-fired generating units during the heating season, and promote the wind power accommodation, an electrical and thermal system dispatch model based on combined heat and power (CHP) with thermal energy storage (TES) and demand response (DR) is proposed. In this model, the emission cost of CO₂, SO₂, NO_x, and the operation cost of desulfurization and denitrification units is considered as environmental cost, which will increase the proportion of the fuel cost in an economic dispatch model. Meanwhile, the fuel cost of generating units, the operation cost and investment cost of thermal energy storage and electrical energy storage, the incentive cost of DR, and the cost of wind curtailment are comprehensively considered in this dispatch model. Then, on the promise of satisfying the load demand, taking the minimum total cost as an objective function, the power of each unit is optimized by a genetic algorithm. Compared with the traditional dispatch model, in which the environmental cost is not considered, the numerical results show that the daily average emissions CO₂, SO₂, NO_x, are decreased by 14,354.35 kg, 55.5 kg, and 47.15 kg, respectively, and the wind power accommodation is increased by an average of 6.56% in a week.

With the increasing capacity of wind power generators (WTGs), the volatility of wind power could significantly challenge the stability and economy of electric and heating networks. To tackle this challenge, this paper proposes an optimal dispatch framework based on controllable load (including controllable electric load and controllable thermostatically load) to reduce wind power curtailment. A forecasting model is developed for the controllable load, which comprehensively considers autocorrelation, weather factor, and consumers’ behavior characteristics. With adjusting controllable load, an optimal dispatch model of power system is then established and resolved by Sequential Least Squares Programming (SLSQP) method. Our method is verified through numerous simulations. The results show that, compared with the state-of-the-art techniques of support vector machine and recurrent neural networks, the root mean square error with the proposed long short-term memory can be reduced by 0.069 and 0.044, respectively. Compared with conventional method, the peak wind power curtailment with dispatching controllable load is reduced by nearly 10% and 5% in two cases, respectively.