Search for: All records

We have all heard that there is growing need to secure resources to obtain supply-demand balance in a power grid facing increasing volatility from renewable sources of energy. There are mandates for utility scale battery systems in regions all over the world, and there is a growing science of “demand dispatch” to obtain virtual energy storage from flexible electric loads such as water heaters, air conditioning, and pumps for irrigation. The question addressed in this tutorial is how to manage a large number of assets for balancing the grid. The focus is on variants of the economic dispatch problem, which may be regarded as the “feed-forward” component in an overall control architecture. 1) The resource allocation problem is identical to a finite horizon optimal control problem with degenerate cost—so called “cheap control”. This implies a form of state space collapse, whose form is identified: the marginal cost for each load class evolves in a two-dimensional subspace, spanned by a scalar co-state process and its derivative. 2) The implication to distributed control is remarkable. Once the co-state process is synthesized, this common signal may be broadcast to each asset for optimal control. However, the optimal solution is extremely fragile, in a sense made clear through results from numerical studies. 3) Several remedies are proposed to address fragility. One is described through “robust training” in a particular Q-learning architecture (one approach to reinforcement learning). In numerical studies it is found that specialized training leads to more robust control solutions. 

Convex Q-learning is a recent approach to reinforcement learning, motivated by the possibility of a firmer theory for convergence, and the possibility of making use of greater a priori knowledge regarding policy or value function structure. This paper explores algorithm design in the continuous time domain, with a finite-horizon optimal control objective. The main contributions are (i) The new Q-ODE: a model-free characterization of the Hamilton-Jacobi-Bellman equation. (ii) A formulation of Convex Q-learning that avoids approximations appearing in prior work. The Bellman error used in the algorithm is defined by filtered measurements, which is necessary in the presence of measurement noise. (iii) Convex Q-learning with linear function approximation is a convex program. It is shown that the constraint region is bounded, subject to an exploration condition on the training input. (iv) The theory is illustrated in application to resource allocation for distributed energy resources, for which the theory is ideally suited. 

Over the past decade, there has been significant progress on the science of load control for the creation of virtual energy storage. This is an alternative to demand response, and it is termed demand dispatch. Distributed control is used to manage millions of flexible loads to modify the power consumption of the aggregation, which can be ramped up and down, just like discharging and charging a battery. A challenge with distributed control is heterogeneity of the population of loads, which complicates control at the aggregate level. It is shown in this article that additional control at each load in the population can result in a far aggregate model. The local control is designed to flatten resonances and produce approximately all-pass response. Analysis is based on mean-field control for the heterogeneous population; the mean-field model is only justified because of the additional local control introduced in this article. Theory and simulations indicate that the resulting input--output dynamics of the aggregate has a nearly flat input--output response: the behavior of an ideal, multi-GW battery system. 

Demand dispatch is the science of extracting virtual energy storage through the automatic control of deferrable loads to provide balancing or regulation services to the grid, while maintaining consumer-end quality of service.The control of a large collection of heterogeneous loads is in part a resource allocation problem, since different classes of loads are more valuable for different services. The goal of this paper is to unveil the structure of the optimal solution to the resource allocation problem, and investigate short-term market implications. It is found that the marginal cost for each load class evolves in a two-dimensional subspace: spanned by a co-state process and its derivative. The resource allocation problem is recast to construct a dynamic competitive equilibrium model, in which the consumer utility is the negative of the cost of deviation from ideal QoS. It is found that a competitive equilibrium exists with the equilibrium price equal to the negative of an optimal co-state process. Moreover, the equilibrium price is different than what would be obtained based on the standard assumption that the consumer's utility is a function of power consumption.