Managing construction of decision modules to control target systems

A computer-implemented method comprising:

• generating, by one or more computing systems of a collaborative distributed decision system, an executable decision module for use with a physical system having a plurality of inter-related elements and having one or more outputs whose values vary based at least in part on one or more manipulatable control elements of the plurality, wherein the physical system includes an energy generating facility and the outputs include the energy being provided and the plurality of inter-related elements include at least one energy source within the energy generating facility and at least one energy storage mechanism within the energy generating facility, wherein the manipulatable control elements include one or more controls to determine whether to accept a request to supply a specified amount of energy at a current time and to determine to provide energy to the at least one energy storage mechanism at the current time if not accepted and to provide energy from the at least one energy source at the current time if accepted, the generating including:
• receiving, by the one or more computing systems and from one or more users, system information describing at least a portion of the physical system using multiple rules that each has one or more conditions to evaluate and that specify restrictions involving the plurality of elements;
• converting, by the one or more computing systems and to multiple constraints, the system information and information about a goal to be achieved during controlling of the physical system and information about sensor variables whose values are available during the controlling of the physical system;
• validating, by the one or more computing systems and based on multiple validation rules, the multiple constraints by testing at least one of controllability, observability, stability or goal completeness, wherein testing controllability ensures that each of the manipulatable control elements is specified in the multiple rules to affect one or more other elements of the plurality, wherein testing observability ensures that each of the sensor variables is specified in the multiple rules to relate to at least one element of the plurality, wherein testing stability ensures that solutions determined by the generated decision module during controlling of the at least portion of the physical system will converge with any other solutions determined by any other generated decision modules during controlling of other portions of the physical system, wherein testing goal completeness ensures that each of the manipulatable control elements is reflected in the goal;
• converting, by the one or more computing systems, the validated constraints to coupled differential equations that represent a model for use in describing a state of the target system;
• training, by the one or more computing systems, the model using state information for the plurality of elements for multiple times, to enable the model to determine values of one or more elements that are not directly observable;
• and
• testing, by the one or more computing systems, performance of the trained model in controlling the at least portion of the physical system by simulating manipulations of the manipulatable control elements to affect the outputs in expected manners;
• determining, by the one or more computing systems, that the testing is successful, and providing the generated decision module with the trained model;
• and
• executing, by the one or more computing systems, the generated decision module to perform actual controlling of the at least portion of the energy generating facility of the physical system to modify the energy being provided by the energy generating facility.